diff --git a/Documentation/ABI/testing/sysfs-bus-iio-proximity-as3935 b/Documentation/ABI/testing/sysfs-bus-iio-proximity-as3935 index 6708c5e264aa..33e96f740639 100644 --- a/Documentation/ABI/testing/sysfs-bus-iio-proximity-as3935 +++ b/Documentation/ABI/testing/sysfs-bus-iio-proximity-as3935 @@ -1,4 +1,4 @@ -What /sys/bus/iio/devices/iio:deviceX/in_proximity_raw +What /sys/bus/iio/devices/iio:deviceX/in_proximity_input Date: March 2014 KernelVersion: 3.15 Contact: Matt Ranostay diff --git a/Documentation/ABI/testing/sysfs-bus-usb b/Documentation/ABI/testing/sysfs-bus-usb index 3a4abfc44f5e..136ba17d2da0 100644 --- a/Documentation/ABI/testing/sysfs-bus-usb +++ b/Documentation/ABI/testing/sysfs-bus-usb @@ -134,19 +134,21 @@ Description: enabled for the device. Developer can write y/Y/1 or n/N/0 to the file to enable/disable the feature. -What: /sys/bus/usb/devices/.../power/usb3_hardware_lpm -Date: June 2015 +What: /sys/bus/usb/devices/.../power/usb3_hardware_lpm_u1 + /sys/bus/usb/devices/.../power/usb3_hardware_lpm_u2 +Date: November 2015 Contact: Kevin Strasser + Lu Baolu Description: If CONFIG_PM is set and a USB 3.0 lpm-capable device is plugged in to a xHCI host which supports link PM, it will check if U1 and U2 exit latencies have been set in the BOS descriptor; if - the check is is passed and the host supports USB3 hardware LPM, + the check is passed and the host supports USB3 hardware LPM, USB3 hardware LPM will be enabled for the device and the USB - device directory will contain a file named - power/usb3_hardware_lpm. The file holds a string value (enable - or disable) indicating whether or not USB3 hardware LPM is - enabled for the device. + device directory will contain two files named + power/usb3_hardware_lpm_u1 and power/usb3_hardware_lpm_u2. These + files hold a string value (enable or disable) indicating whether + or not USB3 hardware LPM U1 or U2 is enabled for the device. What: /sys/bus/usb/devices/.../removable Date: February 2012 diff --git a/Documentation/devicetree/bindings/arm/omap/omap.txt b/Documentation/devicetree/bindings/arm/omap/omap.txt index 9f4e5136e568..12af302bca6a 100644 --- a/Documentation/devicetree/bindings/arm/omap/omap.txt +++ b/Documentation/devicetree/bindings/arm/omap/omap.txt @@ -23,6 +23,7 @@ Optional properties: during suspend. - ti,no-reset-on-init: When present, the module should not be reset at init - ti,no-idle-on-init: When present, the module should not be idled at init +- ti,no-idle: When present, the module is never allowed to idle. Example: diff --git a/Documentation/devicetree/bindings/ata/ahci-platform.txt b/Documentation/devicetree/bindings/ata/ahci-platform.txt index c2340eeeb97f..c000832a7fb9 100644 --- a/Documentation/devicetree/bindings/ata/ahci-platform.txt +++ b/Documentation/devicetree/bindings/ata/ahci-platform.txt @@ -30,6 +30,10 @@ Optional properties: - target-supply : regulator for SATA target power - phys : reference to the SATA PHY node - phy-names : must be "sata-phy" +- ports-implemented : Mask that indicates which ports that the HBA supports + are available for software to use. Useful if PORTS_IMPL + is not programmed by the BIOS, which is true with + some embedded SOC's. Required properties when using sub-nodes: - #address-cells : number of cells to encode an address diff --git a/Documentation/devicetree/bindings/clock/imx35-clock.txt b/Documentation/devicetree/bindings/clock/imx35-clock.txt index a70356452a82..f49783213c56 100644 --- a/Documentation/devicetree/bindings/clock/imx35-clock.txt +++ b/Documentation/devicetree/bindings/clock/imx35-clock.txt @@ -94,6 +94,7 @@ clocks and IDs. csi_sel 79 iim_gate 80 gpu2d_gate 81 + ckli_gate 82 Examples: diff --git a/Documentation/devicetree/bindings/pinctrl/img,pistachio-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/img,pistachio-pinctrl.txt index 08a4a32c8eb0..0326154c7925 100644 --- a/Documentation/devicetree/bindings/pinctrl/img,pistachio-pinctrl.txt +++ b/Documentation/devicetree/bindings/pinctrl/img,pistachio-pinctrl.txt @@ -134,12 +134,12 @@ mfio80 ddr_debug, mips_trace_data, mips_debug mfio81 dreq0, mips_trace_data, eth_debug mfio82 dreq1, mips_trace_data, eth_debug mfio83 mips_pll_lock, mips_trace_data, usb_debug -mfio84 sys_pll_lock, mips_trace_data, usb_debug -mfio85 wifi_pll_lock, mips_trace_data, sdhost_debug -mfio86 bt_pll_lock, mips_trace_data, sdhost_debug -mfio87 rpu_v_pll_lock, dreq2, socif_debug -mfio88 rpu_l_pll_lock, dreq3, socif_debug -mfio89 audio_pll_lock, dreq4, dreq5 +mfio84 audio_pll_lock, mips_trace_data, usb_debug +mfio85 rpu_v_pll_lock, mips_trace_data, sdhost_debug +mfio86 rpu_l_pll_lock, mips_trace_data, sdhost_debug +mfio87 sys_pll_lock, dreq2, socif_debug +mfio88 wifi_pll_lock, dreq3, socif_debug +mfio89 bt_pll_lock, dreq4, dreq5 tck trstn tdi diff --git a/Documentation/filesystems/efivarfs.txt b/Documentation/filesystems/efivarfs.txt index c477af086e65..686a64bba775 100644 --- a/Documentation/filesystems/efivarfs.txt +++ b/Documentation/filesystems/efivarfs.txt @@ -14,3 +14,10 @@ filesystem. efivarfs is typically mounted like this, mount -t efivarfs none /sys/firmware/efi/efivars + +Due to the presence of numerous firmware bugs where removing non-standard +UEFI variables causes the system firmware to fail to POST, efivarfs +files that are not well-known standardized variables are created +as immutable files. This doesn't prevent removal - "chattr -i" will work - +but it does prevent this kind of failure from being accomplished +accidentally. diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 742f69d18fc8..0e4102ae1a61 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -3928,6 +3928,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted. sector if the number is odd); i = IGNORE_DEVICE (don't bind to this device); + j = NO_REPORT_LUNS (don't use report luns + command, uas only); l = NOT_LOCKABLE (don't try to lock and unlock ejectable media); m = MAX_SECTORS_64 (don't transfer more diff --git a/Documentation/scsi/scsi_eh.txt b/Documentation/scsi/scsi_eh.txt index 8638f61c8c9d..37eca00796ee 100644 --- a/Documentation/scsi/scsi_eh.txt +++ b/Documentation/scsi/scsi_eh.txt @@ -263,19 +263,23 @@ scmd->allowed. 3. scmd recovered ACTION: scsi_eh_finish_cmd() is invoked to EH-finish scmd - - shost->host_failed-- - clear scmd->eh_eflags - scsi_setup_cmd_retry() - move from local eh_work_q to local eh_done_q LOCKING: none + CONCURRENCY: at most one thread per separate eh_work_q to + keep queue manipulation lockless 4. EH completes ACTION: scsi_eh_flush_done_q() retries scmds or notifies upper - layer of failure. + layer of failure. May be called concurrently but must have + a no more than one thread per separate eh_work_q to + manipulate the queue locklessly - scmd is removed from eh_done_q and scmd->eh_entry is cleared - if retry is necessary, scmd is requeued using scsi_queue_insert() - otherwise, scsi_finish_command() is invoked for scmd + - zero shost->host_failed LOCKING: queue or finish function performs appropriate locking diff --git a/Documentation/serial/tty.txt b/Documentation/serial/tty.txt index bc3842dc323a..e2dea3dc4307 100644 --- a/Documentation/serial/tty.txt +++ b/Documentation/serial/tty.txt @@ -213,9 +213,6 @@ TTY_IO_ERROR If set, causes all subsequent userspace read/write TTY_OTHER_CLOSED Device is a pty and the other side has closed. -TTY_OTHER_DONE Device is a pty and the other side has closed and - all pending input processing has been completed. - TTY_NO_WRITE_SPLIT Prevent driver from splitting up writes into smaller chunks. diff --git a/Documentation/sysctl/fs.txt b/Documentation/sysctl/fs.txt index 88152f214f48..302b5ed616a6 100644 --- a/Documentation/sysctl/fs.txt +++ b/Documentation/sysctl/fs.txt @@ -32,6 +32,8 @@ Currently, these files are in /proc/sys/fs: - nr_open - overflowuid - overflowgid +- pipe-user-pages-hard +- pipe-user-pages-soft - protected_hardlinks - protected_symlinks - suid_dumpable @@ -159,6 +161,27 @@ The default is 65534. ============================================================== +pipe-user-pages-hard: + +Maximum total number of pages a non-privileged user may allocate for pipes. +Once this limit is reached, no new pipes may be allocated until usage goes +below the limit again. When set to 0, no limit is applied, which is the default +setting. + +============================================================== + +pipe-user-pages-soft: + +Maximum total number of pages a non-privileged user may allocate for pipes +before the pipe size gets limited to a single page. Once this limit is reached, +new pipes will be limited to a single page in size for this user in order to +limit total memory usage, and trying to increase them using fcntl() will be +denied until usage goes below the limit again. The default value allows to +allocate up to 1024 pipes at their default size. When set to 0, no limit is +applied. + +============================================================== + protected_hardlinks: A long-standing class of security issues is the hardlink-based diff --git a/Documentation/usb/power-management.txt b/Documentation/usb/power-management.txt index 4a15c90bc11d..0a94ffe17ab6 100644 --- a/Documentation/usb/power-management.txt +++ b/Documentation/usb/power-management.txt @@ -537,17 +537,18 @@ relevant attribute files are usb2_hardware_lpm and usb3_hardware_lpm. can write y/Y/1 or n/N/0 to the file to enable/disable USB2 hardware LPM manually. This is for test purpose mainly. - power/usb3_hardware_lpm + power/usb3_hardware_lpm_u1 + power/usb3_hardware_lpm_u2 When a USB 3.0 lpm-capable device is plugged in to a xHCI host which supports link PM, it will check if U1 and U2 exit latencies have been set in the BOS descriptor; if the check is is passed and the host supports USB3 hardware LPM, USB3 hardware LPM will be - enabled for the device and this file will be created. - The file holds a string value (enable or disable) - indicating whether or not USB3 hardware LPM is - enabled for the device. + enabled for the device and these files will be created. + The files hold a string value (enable or disable) + indicating whether or not USB3 hardware LPM U1 or U2 + is enabled for the device. USB Port Power Control ---------------------- diff --git a/Documentation/virtual/kvm/mmu.txt b/Documentation/virtual/kvm/mmu.txt index 3a4d681c3e98..b653641d4261 100644 --- a/Documentation/virtual/kvm/mmu.txt +++ b/Documentation/virtual/kvm/mmu.txt @@ -358,7 +358,8 @@ In the first case there are two additional complications: - if CR4.SMEP is enabled: since we've turned the page into a kernel page, the kernel may now execute it. We handle this by also setting spte.nx. If we get a user fetch or read fault, we'll change spte.u=1 and - spte.nx=gpte.nx back. + spte.nx=gpte.nx back. For this to work, KVM forces EFER.NX to 1 when + shadow paging is in use. - if CR4.SMAP is disabled: since the page has been changed to a kernel page, it can not be reused when CR4.SMAP is enabled. We set CR4.SMAP && !CR0.WP into shadow page's role to avoid this case. Note, diff --git a/MAINTAINERS b/MAINTAINERS index 233f83464814..ab65bbecb159 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -230,13 +230,13 @@ F: kernel/sys_ni.c ABIT UGURU 1,2 HARDWARE MONITOR DRIVER M: Hans de Goede -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: drivers/hwmon/abituguru.c ABIT UGURU 3 HARDWARE MONITOR DRIVER M: Alistair John Strachan -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: drivers/hwmon/abituguru3.c @@ -373,14 +373,14 @@ S: Maintained ADM1025 HARDWARE MONITOR DRIVER M: Jean Delvare -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/adm1025 F: drivers/hwmon/adm1025.c ADM1029 HARDWARE MONITOR DRIVER M: Corentin Labbe -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: drivers/hwmon/adm1029.c @@ -425,7 +425,7 @@ F: drivers/video/backlight/adp8860_bl.c ADS1015 HARDWARE MONITOR DRIVER M: Dirk Eibach -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/ads1015 F: drivers/hwmon/ads1015.c @@ -438,7 +438,7 @@ F: drivers/macintosh/therm_adt746x.c ADT7475 HARDWARE MONITOR DRIVER M: Jean Delvare -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/adt7475 F: drivers/hwmon/adt7475.c @@ -615,7 +615,7 @@ F: include/linux/ccp.h AMD FAM15H PROCESSOR POWER MONITORING DRIVER M: Andreas Herrmann -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/fam15h_power F: drivers/hwmon/fam15h_power.c @@ -779,7 +779,7 @@ F: drivers/input/mouse/bcm5974.c APPLE SMC DRIVER M: Henrik Rydberg -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Odd fixes F: drivers/hwmon/applesmc.c @@ -1777,7 +1777,7 @@ F: include/media/as3645a.h ASC7621 HARDWARE MONITOR DRIVER M: George Joseph -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/asc7621 F: drivers/hwmon/asc7621.c @@ -1864,7 +1864,7 @@ F: drivers/net/wireless/ath/carl9170/ ATK0110 HWMON DRIVER M: Luca Tettamanti -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: drivers/hwmon/asus_atk0110.c @@ -2984,7 +2984,7 @@ F: mm/swap_cgroup.c CORETEMP HARDWARE MONITORING DRIVER M: Fenghua Yu -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/coretemp F: drivers/hwmon/coretemp.c @@ -3549,7 +3549,7 @@ T: git git://git.infradead.org/users/vkoul/slave-dma.git DME1737 HARDWARE MONITOR DRIVER M: Juerg Haefliger -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/dme1737 F: drivers/hwmon/dme1737.c @@ -4097,8 +4097,8 @@ F: Documentation/efi-stub.txt F: arch/ia64/kernel/efi.c F: arch/x86/boot/compressed/eboot.[ch] F: arch/x86/include/asm/efi.h -F: arch/x86/platform/efi/* -F: drivers/firmware/efi/* +F: arch/x86/platform/efi/ +F: drivers/firmware/efi/ F: include/linux/efi*.h EFI VARIABLE FILESYSTEM @@ -4262,7 +4262,7 @@ F: include/video/exynos_mipi* F71805F HARDWARE MONITORING DRIVER M: Jean Delvare -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/f71805f F: drivers/hwmon/f71805f.c @@ -4341,7 +4341,7 @@ F: fs/* FINTEK F75375S HARDWARE MONITOR AND FAN CONTROLLER DRIVER M: Riku Voipio -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: drivers/hwmon/f75375s.c F: include/linux/f75375s.h @@ -4883,8 +4883,8 @@ F: drivers/media/usb/hackrf/ HARDWARE MONITORING M: Jean Delvare M: Guenter Roeck -L: lm-sensors@lm-sensors.org -W: http://www.lm-sensors.org/ +L: linux-hwmon@vger.kernel.org +W: http://hwmon.wiki.kernel.org/ T: quilt http://jdelvare.nerim.net/devel/linux/jdelvare-hwmon/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/groeck/linux-staging.git S: Maintained @@ -5393,7 +5393,7 @@ F: drivers/usb/atm/ueagle-atm.c INA209 HARDWARE MONITOR DRIVER M: Guenter Roeck -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/ina209 F: Documentation/devicetree/bindings/i2c/ina209.txt @@ -5401,7 +5401,7 @@ F: drivers/hwmon/ina209.c INA2XX HARDWARE MONITOR DRIVER M: Guenter Roeck -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/ina2xx F: drivers/hwmon/ina2xx.c @@ -5884,7 +5884,7 @@ F: drivers/isdn/hardware/eicon/ IT87 HARDWARE MONITORING DRIVER M: Jean Delvare -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/it87 F: drivers/hwmon/it87.c @@ -5920,7 +5920,7 @@ F: drivers/media/dvb-frontends/ix2505v* JC42.4 TEMPERATURE SENSOR DRIVER M: Guenter Roeck -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: drivers/hwmon/jc42.c F: Documentation/hwmon/jc42 @@ -5970,14 +5970,14 @@ F: drivers/tty/serial/jsm/ K10TEMP HARDWARE MONITORING DRIVER M: Clemens Ladisch -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/k10temp F: drivers/hwmon/k10temp.c K8TEMP HARDWARE MONITORING DRIVER M: Rudolf Marek -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/k8temp F: drivers/hwmon/k8temp.c @@ -6485,27 +6485,27 @@ F: net/llc/ LM73 HARDWARE MONITOR DRIVER M: Guillaume Ligneul -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: drivers/hwmon/lm73.c LM78 HARDWARE MONITOR DRIVER M: Jean Delvare -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/lm78 F: drivers/hwmon/lm78.c LM83 HARDWARE MONITOR DRIVER M: Jean Delvare -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/lm83 F: drivers/hwmon/lm83.c LM90 HARDWARE MONITOR DRIVER M: Jean Delvare -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/lm90 F: Documentation/devicetree/bindings/hwmon/lm90.txt @@ -6513,7 +6513,7 @@ F: drivers/hwmon/lm90.c LM95234 HARDWARE MONITOR DRIVER M: Guenter Roeck -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/lm95234 F: drivers/hwmon/lm95234.c @@ -6580,7 +6580,7 @@ F: drivers/scsi/sym53c8xx_2/ LTC4261 HARDWARE MONITOR DRIVER M: Guenter Roeck -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/ltc4261 F: drivers/hwmon/ltc4261.c @@ -6749,28 +6749,28 @@ F: include/uapi/linux/matroxfb.h MAX16065 HARDWARE MONITOR DRIVER M: Guenter Roeck -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/max16065 F: drivers/hwmon/max16065.c MAX20751 HARDWARE MONITOR DRIVER M: Guenter Roeck -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/max20751 F: drivers/hwmon/max20751.c MAX6650 HARDWARE MONITOR AND FAN CONTROLLER DRIVER M: "Hans J. Koch" -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/max6650 F: drivers/hwmon/max6650.c MAX6697 HARDWARE MONITOR DRIVER M: Guenter Roeck -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/max6697 F: Documentation/devicetree/bindings/i2c/max6697.txt @@ -7303,7 +7303,7 @@ F: drivers/scsi/NCR_D700.* NCT6775 HARDWARE MONITOR DRIVER M: Guenter Roeck -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/nct6775 F: drivers/hwmon/nct6775.c @@ -8064,7 +8064,7 @@ F: drivers/video/logo/logo_parisc* PC87360 HARDWARE MONITORING DRIVER M: Jim Cromie -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/pc87360 F: drivers/hwmon/pc87360.c @@ -8076,7 +8076,7 @@ F: drivers/char/pc8736x_gpio.c PC87427 HARDWARE MONITORING DRIVER M: Jean Delvare -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/pc87427 F: drivers/hwmon/pc87427.c @@ -8415,8 +8415,8 @@ F: drivers/rtc/rtc-puv3.c PMBUS HARDWARE MONITORING DRIVERS M: Guenter Roeck -L: lm-sensors@lm-sensors.org -W: http://www.lm-sensors.org/ +L: linux-hwmon@vger.kernel.org +W: http://hwmon.wiki.kernel.org/ W: http://www.roeck-us.net/linux/drivers/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/groeck/linux-staging.git S: Maintained @@ -8610,7 +8610,7 @@ F: drivers/media/usb/pwc/* PWM FAN DRIVER M: Kamil Debski -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Supported F: Documentation/devicetree/bindings/hwmon/pwm-fan.txt F: Documentation/hwmon/pwm-fan @@ -9882,28 +9882,28 @@ F: Documentation/devicetree/bindings/media/i2c/nokia,smia.txt SMM665 HARDWARE MONITOR DRIVER M: Guenter Roeck -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/smm665 F: drivers/hwmon/smm665.c SMSC EMC2103 HARDWARE MONITOR DRIVER M: Steve Glendinning -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/emc2103 F: drivers/hwmon/emc2103.c SMSC SCH5627 HARDWARE MONITOR DRIVER M: Hans de Goede -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Supported F: Documentation/hwmon/sch5627 F: drivers/hwmon/sch5627.c SMSC47B397 HARDWARE MONITOR DRIVER M: Jean Delvare -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/smsc47b397 F: drivers/hwmon/smsc47b397.c @@ -10289,9 +10289,11 @@ S: Maintained F: drivers/net/ethernet/dlink/sundance.c SUPERH +M: Yoshinori Sato +M: Rich Felker L: linux-sh@vger.kernel.org Q: http://patchwork.kernel.org/project/linux-sh/list/ -S: Orphan +S: Maintained F: Documentation/sh/ F: arch/sh/ F: drivers/sh/ @@ -10828,7 +10830,7 @@ F: include/linux/mmc/sh_mobile_sdhi.h TMP401 HARDWARE MONITOR DRIVER M: Guenter Roeck -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/tmp401 F: drivers/hwmon/tmp401.c @@ -11562,14 +11564,14 @@ F: Documentation/networking/vrf.txt VT1211 HARDWARE MONITOR DRIVER M: Juerg Haefliger -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/vt1211 F: drivers/hwmon/vt1211.c VT8231 HARDWARE MONITOR DRIVER M: Roger Lucas -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: drivers/hwmon/vt8231.c @@ -11588,21 +11590,21 @@ F: drivers/w1/ W83791D HARDWARE MONITORING DRIVER M: Marc Hulsman -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/w83791d F: drivers/hwmon/w83791d.c W83793 HARDWARE MONITORING DRIVER M: Rudolf Marek -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: Documentation/hwmon/w83793 F: drivers/hwmon/w83793.c W83795 HARDWARE MONITORING DRIVER M: Jean Delvare -L: lm-sensors@lm-sensors.org +L: linux-hwmon@vger.kernel.org S: Maintained F: drivers/hwmon/w83795.c diff --git a/Makefile b/Makefile index 70dea02f1346..da7621cadc8e 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 4 -SUBLEVEL = 0 +SUBLEVEL = 16 EXTRAVERSION = NAME = Blurry Fish Butt @@ -364,7 +364,7 @@ AFLAGS_MODULE = LDFLAGS_MODULE = CFLAGS_KERNEL = AFLAGS_KERNEL = -CFLAGS_GCOV = -fprofile-arcs -ftest-coverage +CFLAGS_GCOV = -fprofile-arcs -ftest-coverage -fno-tree-loop-im # Use USERINCLUDE when you must reference the UAPI directories only. @@ -682,9 +682,10 @@ KBUILD_CFLAGS += $(call cc-option, -mno-global-merge,) KBUILD_CFLAGS += $(call cc-option, -fcatch-undefined-behavior) else -# This warning generated too much noise in a regular build. -# Use make W=1 to enable this warning (see scripts/Makefile.build) +# These warnings generated too much noise in a regular build. +# Use make W=1 to enable them (see scripts/Makefile.build) KBUILD_CFLAGS += $(call cc-disable-warning, unused-but-set-variable) +KBUILD_CFLAGS += $(call cc-disable-warning, unused-const-variable) endif ifdef CONFIG_FRAME_POINTER diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 6312f607932f..2d785f5a3041 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -387,7 +387,7 @@ config ARC_HAS_LLSC config ARC_STAR_9000923308 bool "Workaround for llock/scond livelock" - default y + default n depends on ISA_ARCV2 && SMP && ARC_HAS_LLSC config ARC_HAS_SWAPE diff --git a/arch/arc/include/asm/bitops.h b/arch/arc/include/asm/bitops.h index 57c1f33844d4..0352fb8d21b9 100644 --- a/arch/arc/include/asm/bitops.h +++ b/arch/arc/include/asm/bitops.h @@ -35,21 +35,6 @@ static inline void op##_bit(unsigned long nr, volatile unsigned long *m)\ \ m += nr >> 5; \ \ - /* \ - * ARC ISA micro-optimization: \ - * \ - * Instructions dealing with bitpos only consider lower 5 bits \ - * e.g (x << 33) is handled like (x << 1) by ASL instruction \ - * (mem pointer still needs adjustment to point to next word) \ - * \ - * Hence the masking to clamp @nr arg can be elided in general. \ - * \ - * However if @nr is a constant (above assumed in a register), \ - * and greater than 31, gcc can optimize away (x << 33) to 0, \ - * as overflow, given the 32-bit ISA. Thus masking needs to be \ - * done for const @nr, but no code is generated due to gcc \ - * const prop. \ - */ \ nr &= 0x1f; \ \ __asm__ __volatile__( \ diff --git a/arch/arc/include/asm/io.h b/arch/arc/include/asm/io.h index 694ece8a0243..cb69299a492e 100644 --- a/arch/arc/include/asm/io.h +++ b/arch/arc/include/asm/io.h @@ -13,6 +13,15 @@ #include #include +#ifdef CONFIG_ISA_ARCV2 +#include +#define __iormb() rmb() +#define __iowmb() wmb() +#else +#define __iormb() do { } while (0) +#define __iowmb() do { } while (0) +#endif + extern void __iomem *ioremap(unsigned long physaddr, unsigned long size); extern void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size, unsigned long flags); @@ -22,6 +31,15 @@ extern void iounmap(const void __iomem *addr); #define ioremap_wc(phy, sz) ioremap(phy, sz) #define ioremap_wt(phy, sz) ioremap(phy, sz) +/* + * io{read,write}{16,32}be() macros + */ +#define ioread16be(p) ({ u16 __v = be16_to_cpu((__force __be16)__raw_readw(p)); __iormb(); __v; }) +#define ioread32be(p) ({ u32 __v = be32_to_cpu((__force __be32)__raw_readl(p)); __iormb(); __v; }) + +#define iowrite16be(v,p) ({ __iowmb(); __raw_writew((__force u16)cpu_to_be16(v), p); }) +#define iowrite32be(v,p) ({ __iowmb(); __raw_writel((__force u32)cpu_to_be32(v), p); }) + /* Change struct page to physical address */ #define page_to_phys(page) (page_to_pfn(page) << PAGE_SHIFT) @@ -99,15 +117,6 @@ static inline void __raw_writel(u32 w, volatile void __iomem *addr) } -#ifdef CONFIG_ISA_ARCV2 -#include -#define __iormb() rmb() -#define __iowmb() wmb() -#else -#define __iormb() do { } while (0) -#define __iowmb() do { } while (0) -#endif - /* * MMIO can also get buffered/optimized in micro-arch, so barriers needed * Based on ARM model for the typical use case @@ -129,15 +138,23 @@ static inline void __raw_writel(u32 w, volatile void __iomem *addr) #define writel(v,c) ({ __iowmb(); writel_relaxed(v,c); }) /* - * Relaxed API for drivers which can handle any ordering themselves + * Relaxed API for drivers which can handle barrier ordering themselves + * + * Also these are defined to perform little endian accesses. + * To provide the typical device register semantics of fixed endian, + * swap the byte order for Big Endian + * + * http://lkml.kernel.org/r/201603100845.30602.arnd@arndb.de */ #define readb_relaxed(c) __raw_readb(c) -#define readw_relaxed(c) __raw_readw(c) -#define readl_relaxed(c) __raw_readl(c) +#define readw_relaxed(c) ({ u16 __r = le16_to_cpu((__force __le16) \ + __raw_readw(c)); __r; }) +#define readl_relaxed(c) ({ u32 __r = le32_to_cpu((__force __le32) \ + __raw_readl(c)); __r; }) #define writeb_relaxed(v,c) __raw_writeb(v,c) -#define writew_relaxed(v,c) __raw_writew(v,c) -#define writel_relaxed(v,c) __raw_writel(v,c) +#define writew_relaxed(v,c) __raw_writew((__force u16) cpu_to_le16(v),c) +#define writel_relaxed(v,c) __raw_writel((__force u32) cpu_to_le32(v),c) #include diff --git a/arch/arc/include/asm/irqflags-arcv2.h b/arch/arc/include/asm/irqflags-arcv2.h index 258b0e5ad332..68b6092349d7 100644 --- a/arch/arc/include/asm/irqflags-arcv2.h +++ b/arch/arc/include/asm/irqflags-arcv2.h @@ -22,6 +22,7 @@ #define AUX_IRQ_CTRL 0x00E #define AUX_IRQ_ACT 0x043 /* Active Intr across all levels */ #define AUX_IRQ_LVL_PEND 0x200 /* Pending Intr across all levels */ +#define AUX_IRQ_HINT 0x201 /* For generating Soft Interrupts */ #define AUX_IRQ_PRIORITY 0x206 #define ICAUSE 0x40a #define AUX_IRQ_SELECT 0x40b @@ -112,6 +113,16 @@ static inline int arch_irqs_disabled(void) return arch_irqs_disabled_flags(arch_local_save_flags()); } +static inline void arc_softirq_trigger(int irq) +{ + write_aux_reg(AUX_IRQ_HINT, irq); +} + +static inline void arc_softirq_clear(int irq) +{ + write_aux_reg(AUX_IRQ_HINT, 0); +} + #else .macro IRQ_DISABLE scratch diff --git a/arch/arc/kernel/entry-arcv2.S b/arch/arc/kernel/entry-arcv2.S index cbfec79137bf..c1264607bbff 100644 --- a/arch/arc/kernel/entry-arcv2.S +++ b/arch/arc/kernel/entry-arcv2.S @@ -45,11 +45,12 @@ VECTOR reserved ; Reserved slots VECTOR handle_interrupt ; (16) Timer0 VECTOR handle_interrupt ; unused (Timer1) VECTOR handle_interrupt ; unused (WDT) -VECTOR handle_interrupt ; (19) ICI (inter core interrupt) -VECTOR handle_interrupt -VECTOR handle_interrupt -VECTOR handle_interrupt -VECTOR handle_interrupt ; (23) End of fixed IRQs +VECTOR handle_interrupt ; (19) Inter core Interrupt (IPI) +VECTOR handle_interrupt ; (20) perf Interrupt +VECTOR handle_interrupt ; (21) Software Triggered Intr (Self IPI) +VECTOR handle_interrupt ; unused +VECTOR handle_interrupt ; (23) unused +# End of fixed IRQs .rept CONFIG_ARC_NUMBER_OF_INTERRUPTS - 8 VECTOR handle_interrupt @@ -211,7 +212,11 @@ debug_marker_syscall: ; (since IRQ NOT allowed in DS in ARCv2, this can only happen if orig ; entry was via Exception in DS which got preempted in kernel). ; -; IRQ RTIE won't reliably restore DE bit and/or BTA, needs handling +; IRQ RTIE won't reliably restore DE bit and/or BTA, needs workaround +; +; Solution is return from Intr w/o any delay slot quirks into a kernel trampoline +; and from pure kernel mode return to delay slot which handles DS bit/BTA correctly + .Lintr_ret_to_delay_slot: debug_marker_ds: @@ -222,18 +227,23 @@ debug_marker_ds: ld r2, [sp, PT_ret] ld r3, [sp, PT_status32] + ; STAT32 for Int return created from scratch + ; (No delay dlot, disable Further intr in trampoline) + bic r0, r3, STATUS_U_MASK|STATUS_DE_MASK|STATUS_IE_MASK|STATUS_L_MASK st r0, [sp, PT_status32] mov r1, .Lintr_ret_to_delay_slot_2 st r1, [sp, PT_ret] + ; Orig exception PC/STAT32 safekept @orig_r0 and @event stack slots st r2, [sp, 0] st r3, [sp, 4] b .Lisr_ret_fast_path .Lintr_ret_to_delay_slot_2: + ; Trampoline to restore orig exception PC/STAT32/BTA/AUX_USER_SP sub sp, sp, SZ_PT_REGS st r9, [sp, -4] @@ -243,11 +253,19 @@ debug_marker_ds: ld r9, [sp, 4] sr r9, [erstatus] + ; restore AUX_USER_SP if returning to U mode + bbit0 r9, STATUS_U_BIT, 1f + ld r9, [sp, PT_sp] + sr r9, [AUX_USER_SP] + +1: ld r9, [sp, 8] sr r9, [erbta] ld r9, [sp, -4] add sp, sp, SZ_PT_REGS + + ; return from pure kernel mode to delay slot rtie END(ret_from_exception) diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c index bd237acdf4f2..30d806ce0c78 100644 --- a/arch/arc/kernel/mcip.c +++ b/arch/arc/kernel/mcip.c @@ -11,9 +11,12 @@ #include #include #include +#include #include #include +#define SOFTIRQ_IRQ 21 + static char smp_cpuinfo_buf[128]; static int idu_detected; @@ -22,6 +25,7 @@ static DEFINE_RAW_SPINLOCK(mcip_lock); static void mcip_setup_per_cpu(int cpu) { smp_ipi_irq_setup(cpu, IPI_IRQ); + smp_ipi_irq_setup(cpu, SOFTIRQ_IRQ); } static void mcip_ipi_send(int cpu) @@ -29,6 +33,12 @@ static void mcip_ipi_send(int cpu) unsigned long flags; int ipi_was_pending; + /* ARConnect can only send IPI to others */ + if (unlikely(cpu == raw_smp_processor_id())) { + arc_softirq_trigger(SOFTIRQ_IRQ); + return; + } + /* * NOTE: We must spin here if the other cpu hasn't yet * serviced a previous message. This can burn lots @@ -63,6 +73,11 @@ static void mcip_ipi_clear(int irq) unsigned long flags; unsigned int __maybe_unused copy; + if (unlikely(irq == SOFTIRQ_IRQ)) { + arc_softirq_clear(irq); + return; + } + raw_spin_lock_irqsave(&mcip_lock, flags); /* Who sent the IPI */ diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index e1b87444ea9a..05131805aa33 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -332,10 +332,6 @@ static void arc_chk_core_config(void) pr_warn("CONFIG_ARC_FPU_SAVE_RESTORE needed for working apps\n"); else if (!cpu->extn.fpu_dp && fpu_enabled) panic("FPU non-existent, disable CONFIG_ARC_FPU_SAVE_RESTORE\n"); - - if (is_isa_arcv2() && IS_ENABLED(CONFIG_SMP) && cpu->isa.atomic && - !IS_ENABLED(CONFIG_ARC_STAR_9000923308)) - panic("llock/scond livelock workaround missing\n"); } /* diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug index 0901c6bd458f..f08e4fd600a3 100644 --- a/arch/arm/Kconfig.debug +++ b/arch/arm/Kconfig.debug @@ -162,10 +162,9 @@ choice mobile SoCs in the Kona family of chips (e.g. bcm28155, bcm11351, etc...) - config DEBUG_BCM63XX + config DEBUG_BCM63XX_UART bool "Kernel low-level debugging on BCM63XX UART" depends on ARCH_BCM_63XX - select DEBUG_UART_BCM63XX config DEBUG_BERLIN_UART bool "Marvell Berlin SoC Debug UART" @@ -1348,7 +1347,7 @@ config DEBUG_LL_INCLUDE default "debug/vf.S" if DEBUG_VF_UART default "debug/vt8500.S" if DEBUG_VT8500_UART0 default "debug/zynq.S" if DEBUG_ZYNQ_UART0 || DEBUG_ZYNQ_UART1 - default "debug/bcm63xx.S" if DEBUG_UART_BCM63XX + default "debug/bcm63xx.S" if DEBUG_BCM63XX_UART default "debug/digicolor.S" if DEBUG_DIGICOLOR_UA0 default "mach/debug-macro.S" @@ -1364,10 +1363,6 @@ config DEBUG_UART_8250 ARCH_IOP33X || ARCH_IXP4XX || \ ARCH_LPC32XX || ARCH_MV78XX0 || ARCH_ORION5X || ARCH_RPC -# Compatibility options for BCM63xx -config DEBUG_UART_BCM63XX - def_bool ARCH_BCM_63XX - config DEBUG_UART_PHYS hex "Physical base address of debug UART" default 0x00100a00 if DEBUG_NETX_UART @@ -1462,7 +1457,7 @@ config DEBUG_UART_PHYS default 0xfffb0000 if DEBUG_OMAP1UART1 || DEBUG_OMAP7XXUART1 default 0xfffb0800 if DEBUG_OMAP1UART2 || DEBUG_OMAP7XXUART2 default 0xfffb9800 if DEBUG_OMAP1UART3 || DEBUG_OMAP7XXUART3 - default 0xfffe8600 if DEBUG_UART_BCM63XX + default 0xfffe8600 if DEBUG_BCM63XX_UART default 0xfffff700 if ARCH_IOP33X depends on ARCH_EP93XX || \ DEBUG_LL_UART_8250 || DEBUG_LL_UART_PL01X || \ @@ -1474,7 +1469,7 @@ config DEBUG_UART_PHYS DEBUG_RCAR_GEN2_SCIF0 || DEBUG_RCAR_GEN2_SCIF2 || \ DEBUG_RMOBILE_SCIFA0 || DEBUG_RMOBILE_SCIFA1 || \ DEBUG_RMOBILE_SCIFA4 || DEBUG_S3C24XX_UART || \ - DEBUG_UART_BCM63XX || DEBUG_ASM9260_UART || \ + DEBUG_BCM63XX_UART || DEBUG_ASM9260_UART || \ DEBUG_SIRFSOC_UART || DEBUG_DIGICOLOR_UA0 || \ DEBUG_AT91_UART @@ -1515,7 +1510,7 @@ config DEBUG_UART_VIRT default 0xfb10c000 if DEBUG_REALVIEW_PB1176_PORT default 0xfc40ab00 if DEBUG_BRCMSTB_UART default 0xfc705000 if DEBUG_ZTE_ZX - default 0xfcfe8600 if DEBUG_UART_BCM63XX + default 0xfcfe8600 if DEBUG_BCM63XX_UART default 0xfd000000 if ARCH_SPEAR3XX || ARCH_SPEAR6XX default 0xfd000000 if ARCH_SPEAR13XX default 0xfd012000 if ARCH_MV78XX0 @@ -1566,7 +1561,7 @@ config DEBUG_UART_VIRT DEBUG_UART_8250 || DEBUG_UART_PL01X || DEBUG_MESON_UARTAO || \ DEBUG_NETX_UART || \ DEBUG_QCOM_UARTDM || DEBUG_S3C24XX_UART || \ - DEBUG_UART_BCM63XX || DEBUG_ASM9260_UART || \ + DEBUG_BCM63XX_UART || DEBUG_ASM9260_UART || \ DEBUG_SIRFSOC_UART || DEBUG_DIGICOLOR_UA0 config DEBUG_UART_8250_SHIFT diff --git a/arch/arm/boot/dts/am43x-epos-evm.dts b/arch/arm/boot/dts/am43x-epos-evm.dts index 47954ed990f8..00707aac72fc 100644 --- a/arch/arm/boot/dts/am43x-epos-evm.dts +++ b/arch/arm/boot/dts/am43x-epos-evm.dts @@ -792,3 +792,8 @@ tx-num-evt = <32>; rx-num-evt = <32>; }; + +&synctimer_32kclk { + assigned-clocks = <&mux_synctimer32k_ck>; + assigned-clock-parents = <&clkdiv32k_ick>; +}; diff --git a/arch/arm/boot/dts/armada-375.dtsi b/arch/arm/boot/dts/armada-375.dtsi index 7ccce7529b0c..cc952cf8ec30 100644 --- a/arch/arm/boot/dts/armada-375.dtsi +++ b/arch/arm/boot/dts/armada-375.dtsi @@ -529,7 +529,7 @@ }; sata@a0000 { - compatible = "marvell,orion-sata"; + compatible = "marvell,armada-370-sata"; reg = <0xa0000 0x5000>; interrupts = ; clocks = <&gateclk 14>, <&gateclk 20>; diff --git a/arch/arm/boot/dts/armada-385-linksys.dtsi b/arch/arm/boot/dts/armada-385-linksys.dtsi index 3710755c6d76..22f7a13e20b4 100644 --- a/arch/arm/boot/dts/armada-385-linksys.dtsi +++ b/arch/arm/boot/dts/armada-385-linksys.dtsi @@ -58,8 +58,8 @@ soc { ranges = ; + MBUS_ID(0x09, 0x19) 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x15) 0 0xf1110000 0x10000>; internal-regs { @@ -117,7 +117,7 @@ }; /* USB part of the eSATA/USB 2.0 port */ - usb@50000 { + usb@58000 { status = "okay"; }; @@ -245,7 +245,7 @@ button@2 { label = "Factory Reset Button"; linux,code = ; - gpios = <&gpio1 15 GPIO_ACTIVE_LOW>; + gpios = <&gpio0 29 GPIO_ACTIVE_LOW>; }; }; @@ -260,7 +260,7 @@ }; sata { - gpios = <&gpio1 22 GPIO_ACTIVE_HIGH>; + gpios = <&gpio1 22 GPIO_ACTIVE_LOW>; default-state = "off"; }; }; @@ -313,7 +313,7 @@ &pinctrl { keys_pin: keys-pin { - marvell,pins = "mpp24", "mpp47"; + marvell,pins = "mpp24", "mpp29"; marvell,function = "gpio"; }; diff --git a/arch/arm/boot/dts/armada-388-gp.dts b/arch/arm/boot/dts/armada-388-gp.dts index a633be3defda..cd316021d6ce 100644 --- a/arch/arm/boot/dts/armada-388-gp.dts +++ b/arch/arm/boot/dts/armada-388-gp.dts @@ -303,16 +303,6 @@ gpio = <&expander0 4 GPIO_ACTIVE_HIGH>; }; - reg_usb2_1_vbus: v5-vbus1 { - compatible = "regulator-fixed"; - regulator-name = "v5.0-vbus1"; - regulator-min-microvolt = <5000000>; - regulator-max-microvolt = <5000000>; - enable-active-high; - regulator-always-on; - gpio = <&expander0 4 GPIO_ACTIVE_HIGH>; - }; - reg_sata0: pwr-sata0 { compatible = "regulator-fixed"; regulator-name = "pwr_en_sata0"; diff --git a/arch/arm/boot/dts/armada-xp-axpwifiap.dts b/arch/arm/boot/dts/armada-xp-axpwifiap.dts index 23fc670c0427..5c21b236721f 100644 --- a/arch/arm/boot/dts/armada-xp-axpwifiap.dts +++ b/arch/arm/boot/dts/armada-xp-axpwifiap.dts @@ -70,8 +70,8 @@ soc { ranges = ; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; pcie-controller { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-db.dts b/arch/arm/boot/dts/armada-xp-db.dts index f774101416a5..ebe1d267406d 100644 --- a/arch/arm/boot/dts/armada-xp-db.dts +++ b/arch/arm/boot/dts/armada-xp-db.dts @@ -76,8 +76,8 @@ ranges = ; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; devbus-bootcs { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-gp.dts b/arch/arm/boot/dts/armada-xp-gp.dts index 4878d7353069..5730b875c4f5 100644 --- a/arch/arm/boot/dts/armada-xp-gp.dts +++ b/arch/arm/boot/dts/armada-xp-gp.dts @@ -95,8 +95,8 @@ ranges = ; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; devbus-bootcs { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-lenovo-ix4-300d.dts b/arch/arm/boot/dts/armada-xp-lenovo-ix4-300d.dts index 58b500873bfd..d960fef77ca1 100644 --- a/arch/arm/boot/dts/armada-xp-lenovo-ix4-300d.dts +++ b/arch/arm/boot/dts/armada-xp-lenovo-ix4-300d.dts @@ -65,8 +65,8 @@ soc { ranges = ; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; pcie-controller { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-linksys-mamba.dts b/arch/arm/boot/dts/armada-xp-linksys-mamba.dts index 6e9820e141f8..7a461541ce50 100644 --- a/arch/arm/boot/dts/armada-xp-linksys-mamba.dts +++ b/arch/arm/boot/dts/armada-xp-linksys-mamba.dts @@ -70,8 +70,8 @@ soc { ranges = ; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; pcie-controller { status = "okay"; @@ -304,13 +304,13 @@ button@1 { label = "WPS"; linux,code = ; - gpios = <&gpio1 0 GPIO_ACTIVE_HIGH>; + gpios = <&gpio1 0 GPIO_ACTIVE_LOW>; }; button@2 { label = "Factory Reset Button"; linux,code = ; - gpios = <&gpio1 1 GPIO_ACTIVE_HIGH>; + gpios = <&gpio1 1 GPIO_ACTIVE_LOW>; }; }; diff --git a/arch/arm/boot/dts/armada-xp-matrix.dts b/arch/arm/boot/dts/armada-xp-matrix.dts index 6ab33837a2b6..6522b04f4a8e 100644 --- a/arch/arm/boot/dts/armada-xp-matrix.dts +++ b/arch/arm/boot/dts/armada-xp-matrix.dts @@ -68,8 +68,8 @@ soc { ranges = ; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; internal-regs { serial@12000 { diff --git a/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts b/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts index 6fe8972de0a2..db54c7158a36 100644 --- a/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts +++ b/arch/arm/boot/dts/armada-xp-netgear-rn2120.dts @@ -64,8 +64,8 @@ soc { ranges = ; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; pcie-controller { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts index a5db17782e08..853bd392a4fe 100644 --- a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts +++ b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts @@ -65,9 +65,9 @@ soc { ranges = ; + MBUS_ID(0x01, 0x2f) 0 0 0xe8000000 0x8000000 + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; devbus-bootcs { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-synology-ds414.dts b/arch/arm/boot/dts/armada-xp-synology-ds414.dts index 2391b11dc546..d17dab0a6f51 100644 --- a/arch/arm/boot/dts/armada-xp-synology-ds414.dts +++ b/arch/arm/boot/dts/armada-xp-synology-ds414.dts @@ -78,8 +78,8 @@ soc { ranges = ; + MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000 + MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>; pcie-controller { status = "okay"; diff --git a/arch/arm/boot/dts/at91-sama5d3_xplained.dts b/arch/arm/boot/dts/at91-sama5d3_xplained.dts index ff888d21c786..f3e2b96c06a3 100644 --- a/arch/arm/boot/dts/at91-sama5d3_xplained.dts +++ b/arch/arm/boot/dts/at91-sama5d3_xplained.dts @@ -303,6 +303,7 @@ regulator-name = "mmc0-card-supply"; regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; + regulator-always-on; }; gpio_keys { diff --git a/arch/arm/boot/dts/at91-sama5d4_xplained.dts b/arch/arm/boot/dts/at91-sama5d4_xplained.dts index 131614f28e75..da84e65b56ef 100644 --- a/arch/arm/boot/dts/at91-sama5d4_xplained.dts +++ b/arch/arm/boot/dts/at91-sama5d4_xplained.dts @@ -86,10 +86,12 @@ macb0: ethernet@f8020000 { phy-mode = "rmii"; status = "okay"; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_macb0_rmii &pinctrl_macb0_phy_irq>; phy0: ethernet-phy@1 { interrupt-parent = <&pioE>; - interrupts = <1 IRQ_TYPE_EDGE_FALLING>; + interrupts = <1 IRQ_TYPE_LEVEL_LOW>; reg = <1>; }; }; @@ -152,6 +154,10 @@ atmel,pins = ; }; + pinctrl_macb0_phy_irq: macb0_phy_irq_0 { + atmel,pins = + ; + }; }; }; }; @@ -262,5 +268,6 @@ regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; vin-supply = <&vcc_3v3_reg>; + regulator-always-on; }; }; diff --git a/arch/arm/boot/dts/at91-sama5d4ek.dts b/arch/arm/boot/dts/at91-sama5d4ek.dts index 2d4a33100af6..4e98cda97403 100644 --- a/arch/arm/boot/dts/at91-sama5d4ek.dts +++ b/arch/arm/boot/dts/at91-sama5d4ek.dts @@ -160,8 +160,15 @@ }; macb0: ethernet@f8020000 { + pinctrl-0 = <&pinctrl_macb0_rmii &pinctrl_macb0_phy_irq>; phy-mode = "rmii"; status = "okay"; + + ethernet-phy@1 { + reg = <0x1>; + interrupt-parent = <&pioE>; + interrupts = <1 IRQ_TYPE_LEVEL_LOW>; + }; }; mmc1: mmc@fc000000 { @@ -193,6 +200,10 @@ pinctrl@fc06a000 { board { + pinctrl_macb0_phy_irq: macb0_phy_irq { + atmel,pins = + ; + }; pinctrl_mmc0_cd: mmc0_cd { atmel,pins = ; diff --git a/arch/arm/boot/dts/at91sam9x5.dtsi b/arch/arm/boot/dts/at91sam9x5.dtsi index 0827d594b1f0..cd0cd5fd09a3 100644 --- a/arch/arm/boot/dts/at91sam9x5.dtsi +++ b/arch/arm/boot/dts/at91sam9x5.dtsi @@ -106,7 +106,7 @@ pmc: pmc@fffffc00 { compatible = "atmel,at91sam9x5-pmc", "syscon"; - reg = <0xfffffc00 0x100>; + reg = <0xfffffc00 0x200>; interrupts = <1 IRQ_TYPE_LEVEL_HIGH 7>; interrupt-controller; #address-cells = <1>; diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi index fe99231cbde5..c2a03c740e79 100644 --- a/arch/arm/boot/dts/dra7.dtsi +++ b/arch/arm/boot/dts/dra7.dtsi @@ -1497,6 +1497,16 @@ 0x48485200 0x2E00>; #address-cells = <1>; #size-cells = <1>; + + /* + * Do not allow gating of cpsw clock as workaround + * for errata i877. Keeping internal clock disabled + * causes the device switching characteristics + * to degrade over time and eventually fail to meet + * the data manual delay time/skew specs. + */ + ti,no-idle; + /* * rx_thresh_pend * rx_pend diff --git a/arch/arm/boot/dts/exynos4210-trats.dts b/arch/arm/boot/dts/exynos4210-trats.dts index a50be640f1b0..59411e447fa0 100644 --- a/arch/arm/boot/dts/exynos4210-trats.dts +++ b/arch/arm/boot/dts/exynos4210-trats.dts @@ -298,6 +298,8 @@ compatible = "maxim,max8997-pmic"; reg = <0x66>; + interrupt-parent = <&gpx0>; + interrupts = <7 0>; max8997,pmic-buck1-uses-gpio-dvs; max8997,pmic-buck2-uses-gpio-dvs; diff --git a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi index 36387b11451d..80f6c786a37e 100644 --- a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi +++ b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi @@ -122,6 +122,7 @@ interrupt-parent = <&gpio5>; interrupts = <24 IRQ_TYPE_LEVEL_HIGH>; /* gpio 152 */ ref-clock-frequency = <26000000>; + tcxo-clock-frequency = <26000000>; }; }; diff --git a/arch/arm/boot/dts/omap5-board-common.dtsi b/arch/arm/boot/dts/omap5-board-common.dtsi index 5cf76a1c5c75..41e80e7f20be 100644 --- a/arch/arm/boot/dts/omap5-board-common.dtsi +++ b/arch/arm/boot/dts/omap5-board-common.dtsi @@ -130,6 +130,16 @@ }; }; +&gpio8 { + /* TI trees use GPIO instead of msecure, see also muxing */ + p234 { + gpio-hog; + gpios = <10 GPIO_ACTIVE_HIGH>; + output-high; + line-name = "gpio8_234/msecure"; + }; +}; + &omap5_pmx_core { pinctrl-names = "default"; pinctrl-0 = < @@ -213,6 +223,13 @@ >; }; + /* TI trees use GPIO mode; msecure mode does not work reliably? */ + palmas_msecure_pins: palmas_msecure_pins { + pinctrl-single,pins = < + OMAP5_IOPAD(0x180, PIN_OUTPUT | MUX_MODE6) /* gpio8_234 */ + >; + }; + usbhost_pins: pinmux_usbhost_pins { pinctrl-single,pins = < 0x84 (PIN_INPUT | MUX_MODE0) /* usbb2_hsic_strobe */ @@ -278,6 +295,12 @@ &usbhost_wkup_pins >; + palmas_sys_nirq_pins: pinmux_palmas_sys_nirq_pins { + pinctrl-single,pins = < + OMAP5_IOPAD(0x068, PIN_INPUT_PULLUP | MUX_MODE0) /* sys_nirq1 */ + >; + }; + usbhost_wkup_pins: pinmux_usbhost_wkup_pins { pinctrl-single,pins = < 0x1A (PIN_OUTPUT | MUX_MODE0) /* fref_clk1_out, USB hub clk */ @@ -345,6 +368,8 @@ interrupt-controller; #interrupt-cells = <2>; ti,system-power-controller; + pinctrl-names = "default"; + pinctrl-0 = <&palmas_sys_nirq_pins &palmas_msecure_pins>; extcon_usb3: palmas_usb { compatible = "ti,palmas-usb-vid"; @@ -358,6 +383,14 @@ #clock-cells = <0>; }; + rtc { + compatible = "ti,palmas-rtc"; + interrupt-parent = <&palmas>; + interrupts = <8 IRQ_TYPE_NONE>; + ti,backup-battery-chargeable; + ti,backup-battery-charge-high-current; + }; + palmas_pmic { compatible = "ti,palmas-pmic"; interrupt-parent = <&palmas>; diff --git a/arch/arm/boot/dts/pxa3xx.dtsi b/arch/arm/boot/dts/pxa3xx.dtsi index cf6998a0804d..564341af7e97 100644 --- a/arch/arm/boot/dts/pxa3xx.dtsi +++ b/arch/arm/boot/dts/pxa3xx.dtsi @@ -30,7 +30,7 @@ reg = <0x43100000 90>; interrupts = <45>; clocks = <&clks CLK_NAND>; - dmas = <&pdma 97>; + dmas = <&pdma 97 3>; dma-names = "data"; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/sama5d2-pinfunc.h b/arch/arm/boot/dts/sama5d2-pinfunc.h index 1afe24629d1f..8a394f336003 100644 --- a/arch/arm/boot/dts/sama5d2-pinfunc.h +++ b/arch/arm/boot/dts/sama5d2-pinfunc.h @@ -90,7 +90,7 @@ #define PIN_PA14__I2SC1_MCK PINMUX_PIN(PIN_PA14, 4, 2) #define PIN_PA14__FLEXCOM3_IO2 PINMUX_PIN(PIN_PA14, 5, 1) #define PIN_PA14__D9 PINMUX_PIN(PIN_PA14, 6, 2) -#define PIN_PA15 14 +#define PIN_PA15 15 #define PIN_PA15__GPIO PINMUX_PIN(PIN_PA15, 0, 0) #define PIN_PA15__SPI0_MOSI PINMUX_PIN(PIN_PA15, 1, 1) #define PIN_PA15__TF1 PINMUX_PIN(PIN_PA15, 2, 1) @@ -837,8 +837,8 @@ #define PIN_PD23__ISC_FIELD PINMUX_PIN(PIN_PD23, 6, 4) #define PIN_PD24 120 #define PIN_PD24__GPIO PINMUX_PIN(PIN_PD24, 0, 0) -#define PIN_PD24__UTXD2 PINMUX_PIN(PIN_PD23, 1, 2) -#define PIN_PD24__FLEXCOM4_IO3 PINMUX_PIN(PIN_PD23, 3, 3) +#define PIN_PD24__UTXD2 PINMUX_PIN(PIN_PD24, 1, 2) +#define PIN_PD24__FLEXCOM4_IO3 PINMUX_PIN(PIN_PD24, 3, 3) #define PIN_PD25 121 #define PIN_PD25__GPIO PINMUX_PIN(PIN_PD25, 0, 0) #define PIN_PD25__SPI1_SPCK PINMUX_PIN(PIN_PD25, 1, 3) diff --git a/arch/arm/boot/dts/sama5d4.dtsi b/arch/arm/boot/dts/sama5d4.dtsi index 2193637b9cd2..3daf8d5d7878 100644 --- a/arch/arm/boot/dts/sama5d4.dtsi +++ b/arch/arm/boot/dts/sama5d4.dtsi @@ -1342,7 +1342,7 @@ dbgu: serial@fc069000 { compatible = "atmel,at91sam9260-dbgu", "atmel,at91sam9260-usart"; reg = <0xfc069000 0x200>; - interrupts = <2 IRQ_TYPE_LEVEL_HIGH 7>; + interrupts = <45 IRQ_TYPE_LEVEL_HIGH 7>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_dbgu>; clocks = <&dbgu_clk>; diff --git a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi index d0c743853318..27a333eb8987 100644 --- a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi +++ b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi @@ -127,22 +127,14 @@ }; mmcsd_default_mode: mmcsd_default { mmcsd_default_cfg1 { - /* MCCLK */ - pins = "GPIO8_B10"; - ste,output = <0>; - }; - mmcsd_default_cfg2 { - /* MCCMDDIR, MCDAT0DIR, MCDAT31DIR, MCDATDIR2 */ - pins = "GPIO10_C11", "GPIO15_A12", - "GPIO16_C13", "GPIO23_D15"; - ste,output = <1>; - }; - mmcsd_default_cfg3 { - /* MCCMD, MCDAT3-0, MCMSFBCLK */ - pins = "GPIO9_A10", "GPIO11_B11", - "GPIO12_A11", "GPIO13_C12", - "GPIO14_B12", "GPIO24_C15"; - ste,input = <1>; + /* + * MCCLK, MCCMDDIR, MCDAT0DIR, MCDAT31DIR, MCDATDIR2 + * MCCMD, MCDAT3-0, MCMSFBCLK + */ + pins = "GPIO8_B10", "GPIO9_A10", "GPIO10_C11", "GPIO11_B11", + "GPIO12_A11", "GPIO13_C12", "GPIO14_B12", "GPIO15_A12", + "GPIO16_C13", "GPIO23_D15", "GPIO24_C15"; + ste,output = <2>; }; }; }; @@ -802,10 +794,21 @@ clock-names = "mclk", "apb_pclk"; interrupt-parent = <&vica>; interrupts = <22>; - max-frequency = <48000000>; + max-frequency = <400000>; bus-width = <4>; cap-mmc-highspeed; cap-sd-highspeed; + full-pwr-cycle; + /* + * The STw4811 circuit used with the Nomadik strictly + * requires that all of these signal direction pins be + * routed and used for its 4-bit levelshifter. + */ + st,sig-dir-dat0; + st,sig-dir-dat2; + st,sig-dir-dat31; + st,sig-dir-cmd; + st,sig-pin-fbclk; pinctrl-names = "default"; pinctrl-0 = <&mmcsd_default_mux>, <&mmcsd_default_mode>; vmmc-supply = <&vmmc_regulator>; diff --git a/arch/arm/boot/dts/sun5i-r8-chip.dts b/arch/arm/boot/dts/sun5i-r8-chip.dts index 530ab28e9ca2..d21f50ba3172 100644 --- a/arch/arm/boot/dts/sun5i-r8-chip.dts +++ b/arch/arm/boot/dts/sun5i-r8-chip.dts @@ -52,7 +52,7 @@ / { model = "NextThing C.H.I.P."; - compatible = "nextthing,chip", "allwinner,sun5i-r8"; + compatible = "nextthing,chip", "allwinner,sun5i-r8", "allwinner,sun5i-a13"; aliases { i2c0 = &i2c0; diff --git a/arch/arm/common/icst.c b/arch/arm/common/icst.c index 2dc6da70ae59..d7ed252708c5 100644 --- a/arch/arm/common/icst.c +++ b/arch/arm/common/icst.c @@ -16,7 +16,7 @@ */ #include #include - +#include #include /* @@ -29,7 +29,11 @@ EXPORT_SYMBOL(icst525_s2div); unsigned long icst_hz(const struct icst_params *p, struct icst_vco vco) { - return p->ref * 2 * (vco.v + 8) / ((vco.r + 2) * p->s2div[vco.s]); + u64 dividend = p->ref * 2 * (u64)(vco.v + 8); + u32 divisor = (vco.r + 2) * p->s2div[vco.s]; + + do_div(dividend, divisor); + return (unsigned long)dividend; } EXPORT_SYMBOL(icst_hz); @@ -58,6 +62,7 @@ icst_hz_to_vco(const struct icst_params *p, unsigned long freq) if (f > p->vco_min && f <= p->vco_max) break; + i++; } while (i < 8); if (i >= 8) diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h index aeddd28b3595..92fd2c8a9af0 100644 --- a/arch/arm/include/asm/pgtable-2level.h +++ b/arch/arm/include/asm/pgtable-2level.h @@ -193,6 +193,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr) #define pmd_large(pmd) (pmd_val(pmd) & 2) #define pmd_bad(pmd) (pmd_val(pmd) & 2) +#define pmd_present(pmd) (pmd_val(pmd)) #define copy_pmd(pmdpd,pmdps) \ do { \ diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h index a745a2a53853..fd929b5ded9e 100644 --- a/arch/arm/include/asm/pgtable-3level.h +++ b/arch/arm/include/asm/pgtable-3level.h @@ -212,6 +212,7 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr) : !!(pmd_val(pmd) & (val))) #define pmd_isclear(pmd, val) (!(pmd_val(pmd) & (val))) +#define pmd_present(pmd) (pmd_isset((pmd), L_PMD_SECT_VALID)) #define pmd_young(pmd) (pmd_isset((pmd), PMD_SECT_AF)) #define pte_special(pte) (pte_isset((pte), L_PTE_SPECIAL)) static inline pte_t pte_mkspecial(pte_t pte) @@ -257,10 +258,10 @@ PMD_BIT_FUNC(mkyoung, |= PMD_SECT_AF); #define pfn_pmd(pfn,prot) (__pmd(((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))) #define mk_pmd(page,prot) pfn_pmd(page_to_pfn(page),prot) -/* represent a notpresent pmd by zero, this is used by pmdp_invalidate */ +/* represent a notpresent pmd by faulting entry, this is used by pmdp_invalidate */ static inline pmd_t pmd_mknotpresent(pmd_t pmd) { - return __pmd(0); + return __pmd(pmd_val(pmd) & ~L_PMD_SECT_VALID); } static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h index 348caabb7625..d62204060cbe 100644 --- a/arch/arm/include/asm/pgtable.h +++ b/arch/arm/include/asm/pgtable.h @@ -182,7 +182,6 @@ extern pgd_t swapper_pg_dir[PTRS_PER_PGD]; #define pgd_offset_k(addr) pgd_offset(&init_mm, addr) #define pmd_none(pmd) (!pmd_val(pmd)) -#define pmd_present(pmd) (pmd_val(pmd)) static inline pte_t *pmd_page_vaddr(pmd_t pmd) { diff --git a/arch/arm/include/asm/xen/page-coherent.h b/arch/arm/include/asm/xen/page-coherent.h index 0375c8caa061..9408a994cc91 100644 --- a/arch/arm/include/asm/xen/page-coherent.h +++ b/arch/arm/include/asm/xen/page-coherent.h @@ -35,14 +35,21 @@ static inline void xen_dma_map_page(struct device *hwdev, struct page *page, dma_addr_t dev_addr, unsigned long offset, size_t size, enum dma_data_direction dir, struct dma_attrs *attrs) { - bool local = XEN_PFN_DOWN(dev_addr) == page_to_xen_pfn(page); + unsigned long page_pfn = page_to_xen_pfn(page); + unsigned long dev_pfn = XEN_PFN_DOWN(dev_addr); + unsigned long compound_pages = + (1<map_page(hwdev, page, offset, size, dir, attrs); diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c index ef9119f7462e..4d9375814b53 100644 --- a/arch/arm/kernel/ptrace.c +++ b/arch/arm/kernel/ptrace.c @@ -733,8 +733,8 @@ static int vfp_set(struct task_struct *target, if (ret) return ret; - vfp_flush_hwstate(thread); thread->vfpstate.hard = new_vfp; + vfp_flush_hwstate(thread); return 0; } diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c index 96e935bbc38c..3705fc2921c2 100644 --- a/arch/arm/kvm/guest.c +++ b/arch/arm/kvm/guest.c @@ -155,7 +155,7 @@ static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) u64 val; val = kvm_arm_timer_get_reg(vcpu, reg->id); - return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)); + return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)) ? -EFAULT : 0; } static unsigned long num_core_regs(void) diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 61d96a645ff3..12d727fae0a7 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -886,11 +886,14 @@ static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache VM_BUG_ON(pmd_present(*pmd) && pmd_pfn(*pmd) != pmd_pfn(*new_pmd)); old_pmd = *pmd; - kvm_set_pmd(pmd, *new_pmd); - if (pmd_present(old_pmd)) + if (pmd_present(old_pmd)) { + pmd_clear(pmd); kvm_tlb_flush_vmid_ipa(kvm, addr); - else + } else { get_page(virt_to_page(pmd)); + } + + kvm_set_pmd(pmd, *new_pmd); return 0; } @@ -939,12 +942,14 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, /* Create 2nd stage page table mapping - Level 3 */ old_pte = *pte; - kvm_set_pte(pte, *new_pte); - if (pte_present(old_pte)) + if (pte_present(old_pte)) { + kvm_set_pte(pte, __pte(0)); kvm_tlb_flush_vmid_ipa(kvm, addr); - else + } else { get_page(virt_to_page(pte)); + } + kvm_set_pte(pte, *new_pte); return 0; } diff --git a/arch/arm/mach-cns3xxx/pcie.c b/arch/arm/mach-cns3xxx/pcie.c index 47905a50e075..318394ed5c7a 100644 --- a/arch/arm/mach-cns3xxx/pcie.c +++ b/arch/arm/mach-cns3xxx/pcie.c @@ -220,13 +220,13 @@ static void cns3xxx_write_config(struct cns3xxx_pcie *cnspci, u32 mask = (0x1ull << (size * 8)) - 1; int shift = (where % 4) * 8; - v = readl_relaxed(base + (where & 0xffc)); + v = readl_relaxed(base); v &= ~(mask << shift); v |= (val & mask) << shift; - writel_relaxed(v, base + (where & 0xffc)); - readl_relaxed(base + (where & 0xffc)); + writel_relaxed(v, base); + readl_relaxed(base); } static void __init cns3xxx_pcie_hw_init(struct cns3xxx_pcie *cnspci) diff --git a/arch/arm/mach-exynos/Kconfig b/arch/arm/mach-exynos/Kconfig index 3a10f1a8317a..bfd8bb371477 100644 --- a/arch/arm/mach-exynos/Kconfig +++ b/arch/arm/mach-exynos/Kconfig @@ -26,6 +26,7 @@ menuconfig ARCH_EXYNOS select S5P_DEV_MFC select SRAM select THERMAL + select THERMAL_OF select MFD_SYSCON help Support for SAMSUNG EXYNOS SoCs (EXYNOS4/5) diff --git a/arch/arm/mach-exynos/pm_domains.c b/arch/arm/mach-exynos/pm_domains.c index 7c21760f590f..875a2bab64f6 100644 --- a/arch/arm/mach-exynos/pm_domains.c +++ b/arch/arm/mach-exynos/pm_domains.c @@ -92,7 +92,7 @@ static int exynos_pd_power(struct generic_pm_domain *domain, bool power_on) if (IS_ERR(pd->clk[i])) break; - if (IS_ERR(pd->clk[i])) + if (IS_ERR(pd->pclk[i])) continue; /* Skip on first power up */ if (clk_set_parent(pd->clk[i], pd->pclk[i])) pr_err("%s: error setting parent to clock%d\n", diff --git a/arch/arm/mach-imx/mach-imx6ul.c b/arch/arm/mach-imx/mach-imx6ul.c index acaf7056efa5..e08d02667c81 100644 --- a/arch/arm/mach-imx/mach-imx6ul.c +++ b/arch/arm/mach-imx/mach-imx6ul.c @@ -46,7 +46,7 @@ static int ksz8081_phy_fixup(struct phy_device *dev) static void __init imx6ul_enet_phy_init(void) { if (IS_BUILTIN(CONFIG_PHYLIB)) - phy_register_fixup_for_uid(PHY_ID_KSZ8081, 0xffffffff, + phy_register_fixup_for_uid(PHY_ID_KSZ8081, MICREL_PHY_ID_MASK, ksz8081_phy_fixup); } diff --git a/arch/arm/mach-mvebu/coherency.c b/arch/arm/mach-mvebu/coherency.c index 55348ee5a352..feed36b32ff6 100644 --- a/arch/arm/mach-mvebu/coherency.c +++ b/arch/arm/mach-mvebu/coherency.c @@ -162,22 +162,16 @@ exit: } /* - * This ioremap hook is used on Armada 375/38x to ensure that PCIe - * memory areas are mapped as MT_UNCACHED instead of MT_DEVICE. This - * is needed as a workaround for a deadlock issue between the PCIe - * interface and the cache controller. + * This ioremap hook is used on Armada 375/38x to ensure that all MMIO + * areas are mapped as MT_UNCACHED instead of MT_DEVICE. This is + * needed for the HW I/O coherency mechanism to work properly without + * deadlock. */ static void __iomem * -armada_pcie_wa_ioremap_caller(phys_addr_t phys_addr, size_t size, - unsigned int mtype, void *caller) +armada_wa_ioremap_caller(phys_addr_t phys_addr, size_t size, + unsigned int mtype, void *caller) { - struct resource pcie_mem; - - mvebu_mbus_get_pcie_mem_aperture(&pcie_mem); - - if (pcie_mem.start <= phys_addr && (phys_addr + size) <= pcie_mem.end) - mtype = MT_UNCACHED; - + mtype = MT_UNCACHED; return __arm_ioremap_caller(phys_addr, size, mtype, caller); } @@ -186,7 +180,7 @@ static void __init armada_375_380_coherency_init(struct device_node *np) struct device_node *cache_dn; coherency_cpu_base = of_iomap(np, 0); - arch_ioremap_caller = armada_pcie_wa_ioremap_caller; + arch_ioremap_caller = armada_wa_ioremap_caller; /* * We should switch the PL310 to I/O coherency mode only if diff --git a/arch/arm/mach-omap2/cpuidle34xx.c b/arch/arm/mach-omap2/cpuidle34xx.c index aa7b379e2661..2a3db0bd9e15 100644 --- a/arch/arm/mach-omap2/cpuidle34xx.c +++ b/arch/arm/mach-omap2/cpuidle34xx.c @@ -34,6 +34,7 @@ #include "pm.h" #include "control.h" #include "common.h" +#include "soc.h" /* Mach specific information to be recorded in the C-state driver_data */ struct omap3_idle_statedata { @@ -315,6 +316,69 @@ static struct cpuidle_driver omap3_idle_driver = { .safe_state_index = 0, }; +/* + * Numbers based on measurements made in October 2009 for PM optimized kernel + * with CPU freq enabled on device Nokia N900. Assumes OPP2 (main idle OPP, + * and worst case latencies). + */ +static struct cpuidle_driver omap3430_idle_driver = { + .name = "omap3430_idle", + .owner = THIS_MODULE, + .states = { + { + .enter = omap3_enter_idle_bm, + .exit_latency = 110 + 162, + .target_residency = 5, + .name = "C1", + .desc = "MPU ON + CORE ON", + }, + { + .enter = omap3_enter_idle_bm, + .exit_latency = 106 + 180, + .target_residency = 309, + .name = "C2", + .desc = "MPU ON + CORE ON", + }, + { + .enter = omap3_enter_idle_bm, + .exit_latency = 107 + 410, + .target_residency = 46057, + .name = "C3", + .desc = "MPU RET + CORE ON", + }, + { + .enter = omap3_enter_idle_bm, + .exit_latency = 121 + 3374, + .target_residency = 46057, + .name = "C4", + .desc = "MPU OFF + CORE ON", + }, + { + .enter = omap3_enter_idle_bm, + .exit_latency = 855 + 1146, + .target_residency = 46057, + .name = "C5", + .desc = "MPU RET + CORE RET", + }, + { + .enter = omap3_enter_idle_bm, + .exit_latency = 7580 + 4134, + .target_residency = 484329, + .name = "C6", + .desc = "MPU OFF + CORE RET", + }, + { + .enter = omap3_enter_idle_bm, + .exit_latency = 7505 + 15274, + .target_residency = 484329, + .name = "C7", + .desc = "MPU OFF + CORE OFF", + }, + }, + .state_count = ARRAY_SIZE(omap3_idle_data), + .safe_state_index = 0, +}; + /* Public functions */ /** @@ -333,5 +397,8 @@ int __init omap3_idle_init(void) if (!mpu_pd || !core_pd || !per_pd || !cam_pd) return -ENODEV; - return cpuidle_register(&omap3_idle_driver, NULL); + if (cpu_is_omap3430()) + return cpuidle_register(&omap3430_idle_driver, NULL); + else + return cpuidle_register(&omap3_idle_driver, NULL); } diff --git a/arch/arm/mach-omap2/gpmc-onenand.c b/arch/arm/mach-omap2/gpmc-onenand.c index 7b76ce01c21d..8633c703546a 100644 --- a/arch/arm/mach-omap2/gpmc-onenand.c +++ b/arch/arm/mach-omap2/gpmc-onenand.c @@ -101,10 +101,8 @@ static void omap2_onenand_set_async_mode(void __iomem *onenand_base) static void set_onenand_cfg(void __iomem *onenand_base) { - u32 reg; + u32 reg = ONENAND_SYS_CFG1_RDY | ONENAND_SYS_CFG1_INT; - reg = readw(onenand_base + ONENAND_REG_SYS_CFG1); - reg &= ~((0x7 << ONENAND_SYS_CFG1_BRL_SHIFT) | (0x7 << 9)); reg |= (latency << ONENAND_SYS_CFG1_BRL_SHIFT) | ONENAND_SYS_CFG1_BL_16; if (onenand_flags & ONENAND_FLAG_SYNCREAD) @@ -123,6 +121,7 @@ static void set_onenand_cfg(void __iomem *onenand_base) reg |= ONENAND_SYS_CFG1_VHF; else reg &= ~ONENAND_SYS_CFG1_VHF; + writew(reg, onenand_base + ONENAND_REG_SYS_CFG1); } @@ -289,6 +288,7 @@ static int omap2_onenand_setup_async(void __iomem *onenand_base) } } + onenand_async.sync_write = true; omap2_onenand_calc_async_timings(&t); ret = gpmc_cs_program_settings(gpmc_onenand_data->cs, &onenand_async); diff --git a/arch/arm/mach-omap2/io.c b/arch/arm/mach-omap2/io.c index 3eaeaca5da05..3a911d8dea8b 100644 --- a/arch/arm/mach-omap2/io.c +++ b/arch/arm/mach-omap2/io.c @@ -368,6 +368,7 @@ void __init omap5_map_io(void) void __init dra7xx_map_io(void) { iotable_init(dra7xx_io_desc, ARRAY_SIZE(dra7xx_io_desc)); + omap_barriers_init(); } #endif /* diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index 48495ad82aba..147c90e70b2e 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -1416,9 +1416,7 @@ static void _enable_sysc(struct omap_hwmod *oh) (sf & SYSC_HAS_CLOCKACTIVITY)) _set_clockactivity(oh, oh->class->sysc->clockact, &v); - /* If the cached value is the same as the new value, skip the write */ - if (oh->_sysc_cache != v) - _write_sysconfig(v, oh); + _write_sysconfig(v, oh); /* * Set the autoidle bit only after setting the smartidle bit @@ -1481,7 +1479,9 @@ static void _idle_sysc(struct omap_hwmod *oh) _set_master_standbymode(oh, idlemode, &v); } - _write_sysconfig(v, oh); + /* If the cached value is the same as the new value, skip the write */ + if (oh->_sysc_cache != v) + _write_sysconfig(v, oh); } /** @@ -2200,6 +2200,11 @@ static int _enable(struct omap_hwmod *oh) */ static int _idle(struct omap_hwmod *oh) { + if (oh->flags & HWMOD_NO_IDLE) { + oh->_int_flags |= _HWMOD_SKIP_ENABLE; + return 0; + } + pr_debug("omap_hwmod: %s: idling\n", oh->name); if (oh->_state != _HWMOD_STATE_ENABLED) { @@ -2504,6 +2509,8 @@ static int __init _init(struct omap_hwmod *oh, void *data) oh->flags |= HWMOD_INIT_NO_RESET; if (of_find_property(np, "ti,no-idle-on-init", NULL)) oh->flags |= HWMOD_INIT_NO_IDLE; + if (of_find_property(np, "ti,no-idle", NULL)) + oh->flags |= HWMOD_NO_IDLE; } oh->_state = _HWMOD_STATE_INITIALIZED; @@ -2630,7 +2637,7 @@ static void __init _setup_postsetup(struct omap_hwmod *oh) * XXX HWMOD_INIT_NO_IDLE does not belong in hwmod data - * it should be set by the core code as a runtime flag during startup */ - if ((oh->flags & HWMOD_INIT_NO_IDLE) && + if ((oh->flags & (HWMOD_INIT_NO_IDLE | HWMOD_NO_IDLE)) && (postsetup_state == _HWMOD_STATE_IDLE)) { oh->_int_flags |= _HWMOD_SKIP_ENABLE; postsetup_state = _HWMOD_STATE_ENABLED; diff --git a/arch/arm/mach-omap2/omap_hwmod.h b/arch/arm/mach-omap2/omap_hwmod.h index 76bce11c85a4..7c7a31169475 100644 --- a/arch/arm/mach-omap2/omap_hwmod.h +++ b/arch/arm/mach-omap2/omap_hwmod.h @@ -525,6 +525,8 @@ struct omap_hwmod_omap4_prcm { * or idled. * HWMOD_OPT_CLKS_NEEDED: The optional clocks are needed for the module to * operate and they need to be handled at the same time as the main_clk. + * HWMOD_NO_IDLE: Do not idle the hwmod at all. Useful to handle certain + * IPs like CPSW on DRA7, where clocks to this module cannot be disabled. */ #define HWMOD_SWSUP_SIDLE (1 << 0) #define HWMOD_SWSUP_MSTANDBY (1 << 1) @@ -541,6 +543,7 @@ struct omap_hwmod_omap4_prcm { #define HWMOD_SWSUP_SIDLE_ACT (1 << 12) #define HWMOD_RECONFIG_IO_CHAIN (1 << 13) #define HWMOD_OPT_CLKS_NEEDED (1 << 14) +#define HWMOD_NO_IDLE (1 << 15) /* * omap_hwmod._int_flags definitions diff --git a/arch/arm/mach-omap2/sleep34xx.S b/arch/arm/mach-omap2/sleep34xx.S index eafd120b53f1..1b9f0520dea9 100644 --- a/arch/arm/mach-omap2/sleep34xx.S +++ b/arch/arm/mach-omap2/sleep34xx.S @@ -86,13 +86,18 @@ ENTRY(enable_omap3630_toggle_l2_on_restore) stmfd sp!, {lr} @ save registers on stack /* Setup so that we will disable and enable l2 */ mov r1, #0x1 - adrl r2, l2dis_3630 @ may be too distant for plain adr - str r1, [r2] + adrl r3, l2dis_3630_offset @ may be too distant for plain adr + ldr r2, [r3] @ value for offset + str r1, [r2, r3] @ write to l2dis_3630 ldmfd sp!, {pc} @ restore regs and return ENDPROC(enable_omap3630_toggle_l2_on_restore) - .text -/* Function to call rom code to save secure ram context */ +/* + * Function to call rom code to save secure ram context. This gets + * relocated to SRAM, so it can be all in .data section. Otherwise + * we need to initialize api_params separately. + */ + .data .align 3 ENTRY(save_secure_ram_context) stmfd sp!, {r4 - r11, lr} @ save registers on stack @@ -126,6 +131,8 @@ ENDPROC(save_secure_ram_context) ENTRY(save_secure_ram_context_sz) .word . - save_secure_ram_context + .text + /* * ====================== * == Idle entry point == @@ -289,12 +296,6 @@ wait_sdrc_ready: bic r5, r5, #0x40 str r5, [r4] -/* - * PC-relative stores lead to undefined behaviour in Thumb-2: use a r7 as a - * base instead. - * Be careful not to clobber r7 when maintaing this code. - */ - is_dll_in_lock_mode: /* Is dll in lock mode? */ ldr r4, sdrc_dlla_ctrl @@ -302,11 +303,7 @@ is_dll_in_lock_mode: tst r5, #0x4 bne exit_nonoff_modes @ Return if locked /* wait till dll locks */ - adr r7, kick_counter wait_dll_lock_timed: - ldr r4, wait_dll_lock_counter - add r4, r4, #1 - str r4, [r7, #wait_dll_lock_counter - kick_counter] ldr r4, sdrc_dlla_status /* Wait 20uS for lock */ mov r6, #8 @@ -330,9 +327,6 @@ kick_dll: orr r6, r6, #(1<<3) @ enable dll str r6, [r4] dsb - ldr r4, kick_counter - add r4, r4, #1 - str r4, [r7] @ kick_counter b wait_dll_lock_timed exit_nonoff_modes: @@ -360,15 +354,6 @@ sdrc_dlla_status: .word SDRC_DLLA_STATUS_V sdrc_dlla_ctrl: .word SDRC_DLLA_CTRL_V - /* - * When exporting to userspace while the counters are in SRAM, - * these 2 words need to be at the end to facilitate retrival! - */ -kick_counter: - .word 0 -wait_dll_lock_counter: - .word 0 - ENTRY(omap3_do_wfi_sz) .word . - omap3_do_wfi @@ -437,7 +422,9 @@ ENTRY(omap3_restore) cmp r2, #0x0 @ Check if target power state was OFF or RET bne logic_l1_restore - ldr r0, l2dis_3630 + adr r1, l2dis_3630_offset @ address for offset + ldr r0, [r1] @ value for offset + ldr r0, [r1, r0] @ value at l2dis_3630 cmp r0, #0x1 @ should we disable L2 on 3630? bne skipl2dis mrc p15, 0, r0, c1, c0, 1 @@ -449,12 +436,14 @@ skipl2dis: and r1, #0x700 cmp r1, #0x300 beq l2_inv_gp + adr r0, l2_inv_api_params_offset + ldr r3, [r0] + add r3, r3, r0 @ r3 points to dummy parameters mov r0, #40 @ set service ID for PPA mov r12, r0 @ copy secure Service ID in r12 mov r1, #0 @ set task id for ROM code in r1 mov r2, #4 @ set some flags in r2, r6 mov r6, #0xff - adr r3, l2_inv_api_params @ r3 points to dummy parameters dsb @ data write barrier dmb @ data memory barrier smc #1 @ call SMI monitor (smi #1) @@ -488,8 +477,8 @@ skipl2dis: b logic_l1_restore .align -l2_inv_api_params: - .word 0x1, 0x00 +l2_inv_api_params_offset: + .long l2_inv_api_params - . l2_inv_gp: /* Execute smi to invalidate L2 cache */ mov r12, #0x1 @ set up to invalidate L2 @@ -506,7 +495,9 @@ l2_inv_gp: mov r12, #0x2 smc #0 @ Call SMI monitor (smieq) logic_l1_restore: - ldr r1, l2dis_3630 + adr r0, l2dis_3630_offset @ adress for offset + ldr r1, [r0] @ value for offset + ldr r1, [r0, r1] @ value at l2dis_3630 cmp r1, #0x1 @ Test if L2 re-enable needed on 3630 bne skipl2reen mrc p15, 0, r1, c1, c0, 1 @@ -535,9 +526,17 @@ control_stat: .word CONTROL_STAT control_mem_rta: .word CONTROL_MEM_RTA_CTRL +l2dis_3630_offset: + .long l2dis_3630 - . + + .data l2dis_3630: .word 0 + .data +l2_inv_api_params: + .word 0x1, 0x00 + /* * Internal functions */ diff --git a/arch/arm/mach-omap2/sleep44xx.S b/arch/arm/mach-omap2/sleep44xx.S index 9b09d85d811a..c7a3b4aab4b5 100644 --- a/arch/arm/mach-omap2/sleep44xx.S +++ b/arch/arm/mach-omap2/sleep44xx.S @@ -29,12 +29,6 @@ dsb .endm -ppa_zero_params: - .word 0x0 - -ppa_por_params: - .word 1, 0 - #ifdef CONFIG_ARCH_OMAP4 /* @@ -266,7 +260,9 @@ ENTRY(omap4_cpu_resume) beq skip_ns_smp_enable ppa_actrl_retry: mov r0, #OMAP4_PPA_CPU_ACTRL_SMP_INDEX - adr r3, ppa_zero_params @ Pointer to parameters + adr r1, ppa_zero_params_offset + ldr r3, [r1] + add r3, r3, r1 @ Pointer to ppa_zero_params mov r1, #0x0 @ Process ID mov r2, #0x4 @ Flag mov r6, #0xff @@ -303,7 +299,9 @@ skip_ns_smp_enable: ldr r0, =OMAP4_PPA_L2_POR_INDEX ldr r1, =OMAP44XX_SAR_RAM_BASE ldr r4, [r1, #L2X0_PREFETCH_CTRL_OFFSET] - adr r3, ppa_por_params + adr r1, ppa_por_params_offset + ldr r3, [r1] + add r3, r3, r1 @ Pointer to ppa_por_params str r4, [r3, #0x04] mov r1, #0x0 @ Process ID mov r2, #0x4 @ Flag @@ -328,6 +326,8 @@ skip_l2en: #endif b cpu_resume @ Jump to generic resume +ppa_por_params_offset: + .long ppa_por_params - . ENDPROC(omap4_cpu_resume) #endif /* CONFIG_ARCH_OMAP4 */ @@ -380,4 +380,13 @@ ENTRY(omap_do_wfi) nop ldmfd sp!, {pc} +ppa_zero_params_offset: + .long ppa_zero_params - . ENDPROC(omap_do_wfi) + + .data +ppa_zero_params: + .word 0 + +ppa_por_params: + .word 1, 0 diff --git a/arch/arm/mach-prima2/Kconfig b/arch/arm/mach-prima2/Kconfig index 9ab8932403e5..56e55fd37d13 100644 --- a/arch/arm/mach-prima2/Kconfig +++ b/arch/arm/mach-prima2/Kconfig @@ -1,6 +1,7 @@ menuconfig ARCH_SIRF bool "CSR SiRF" if ARCH_MULTI_V7 select ARCH_HAS_RESET_CONTROLLER + select RESET_CONTROLLER select ARCH_REQUIRE_GPIOLIB select GENERIC_IRQ_CHIP select NO_IOPORT_MAP diff --git a/arch/arm/mach-s3c64xx/dev-audio.c b/arch/arm/mach-s3c64xx/dev-audio.c index ff780a8d8366..9a42736ef4ac 100644 --- a/arch/arm/mach-s3c64xx/dev-audio.c +++ b/arch/arm/mach-s3c64xx/dev-audio.c @@ -54,12 +54,12 @@ static int s3c64xx_i2s_cfg_gpio(struct platform_device *pdev) static struct resource s3c64xx_iis0_resource[] = { [0] = DEFINE_RES_MEM(S3C64XX_PA_IIS0, SZ_256), - [1] = DEFINE_RES_DMA(DMACH_I2S0_OUT), - [2] = DEFINE_RES_DMA(DMACH_I2S0_IN), }; -static struct s3c_audio_pdata i2sv3_pdata = { +static struct s3c_audio_pdata i2s0_pdata = { .cfg_gpio = s3c64xx_i2s_cfg_gpio, + .dma_playback = DMACH_I2S0_OUT, + .dma_capture = DMACH_I2S0_IN, }; struct platform_device s3c64xx_device_iis0 = { @@ -68,15 +68,19 @@ struct platform_device s3c64xx_device_iis0 = { .num_resources = ARRAY_SIZE(s3c64xx_iis0_resource), .resource = s3c64xx_iis0_resource, .dev = { - .platform_data = &i2sv3_pdata, + .platform_data = &i2s0_pdata, }, }; EXPORT_SYMBOL(s3c64xx_device_iis0); static struct resource s3c64xx_iis1_resource[] = { [0] = DEFINE_RES_MEM(S3C64XX_PA_IIS1, SZ_256), - [1] = DEFINE_RES_DMA(DMACH_I2S1_OUT), - [2] = DEFINE_RES_DMA(DMACH_I2S1_IN), +}; + +static struct s3c_audio_pdata i2s1_pdata = { + .cfg_gpio = s3c64xx_i2s_cfg_gpio, + .dma_playback = DMACH_I2S1_OUT, + .dma_capture = DMACH_I2S1_IN, }; struct platform_device s3c64xx_device_iis1 = { @@ -85,19 +89,19 @@ struct platform_device s3c64xx_device_iis1 = { .num_resources = ARRAY_SIZE(s3c64xx_iis1_resource), .resource = s3c64xx_iis1_resource, .dev = { - .platform_data = &i2sv3_pdata, + .platform_data = &i2s1_pdata, }, }; EXPORT_SYMBOL(s3c64xx_device_iis1); static struct resource s3c64xx_iisv4_resource[] = { [0] = DEFINE_RES_MEM(S3C64XX_PA_IISV4, SZ_256), - [1] = DEFINE_RES_DMA(DMACH_HSI_I2SV40_TX), - [2] = DEFINE_RES_DMA(DMACH_HSI_I2SV40_RX), }; static struct s3c_audio_pdata i2sv4_pdata = { .cfg_gpio = s3c64xx_i2s_cfg_gpio, + .dma_playback = DMACH_HSI_I2SV40_TX, + .dma_capture = DMACH_HSI_I2SV40_RX, .type = { .i2s = { .quirks = QUIRK_PRI_6CHAN, @@ -142,12 +146,12 @@ static int s3c64xx_pcm_cfg_gpio(struct platform_device *pdev) static struct resource s3c64xx_pcm0_resource[] = { [0] = DEFINE_RES_MEM(S3C64XX_PA_PCM0, SZ_256), - [1] = DEFINE_RES_DMA(DMACH_PCM0_TX), - [2] = DEFINE_RES_DMA(DMACH_PCM0_RX), }; static struct s3c_audio_pdata s3c_pcm0_pdata = { .cfg_gpio = s3c64xx_pcm_cfg_gpio, + .dma_capture = DMACH_PCM0_RX, + .dma_playback = DMACH_PCM0_TX, }; struct platform_device s3c64xx_device_pcm0 = { @@ -163,12 +167,12 @@ EXPORT_SYMBOL(s3c64xx_device_pcm0); static struct resource s3c64xx_pcm1_resource[] = { [0] = DEFINE_RES_MEM(S3C64XX_PA_PCM1, SZ_256), - [1] = DEFINE_RES_DMA(DMACH_PCM1_TX), - [2] = DEFINE_RES_DMA(DMACH_PCM1_RX), }; static struct s3c_audio_pdata s3c_pcm1_pdata = { .cfg_gpio = s3c64xx_pcm_cfg_gpio, + .dma_playback = DMACH_PCM1_TX, + .dma_capture = DMACH_PCM1_RX, }; struct platform_device s3c64xx_device_pcm1 = { @@ -196,13 +200,14 @@ static int s3c64xx_ac97_cfg_gpe(struct platform_device *pdev) static struct resource s3c64xx_ac97_resource[] = { [0] = DEFINE_RES_MEM(S3C64XX_PA_AC97, SZ_256), - [1] = DEFINE_RES_DMA(DMACH_AC97_PCMOUT), - [2] = DEFINE_RES_DMA(DMACH_AC97_PCMIN), - [3] = DEFINE_RES_DMA(DMACH_AC97_MICIN), - [4] = DEFINE_RES_IRQ(IRQ_AC97), + [1] = DEFINE_RES_IRQ(IRQ_AC97), }; -static struct s3c_audio_pdata s3c_ac97_pdata; +static struct s3c_audio_pdata s3c_ac97_pdata = { + .dma_playback = DMACH_AC97_PCMOUT, + .dma_capture = DMACH_AC97_PCMIN, + .dma_capture_mic = DMACH_AC97_MICIN, +}; static u64 s3c64xx_ac97_dmamask = DMA_BIT_MASK(32); diff --git a/arch/arm/mach-s3c64xx/include/mach/dma.h b/arch/arm/mach-s3c64xx/include/mach/dma.h index 096e14073bd9..9c739eafe95c 100644 --- a/arch/arm/mach-s3c64xx/include/mach/dma.h +++ b/arch/arm/mach-s3c64xx/include/mach/dma.h @@ -14,38 +14,38 @@ #define S3C64XX_DMA_CHAN(name) ((unsigned long)(name)) /* DMA0/SDMA0 */ -#define DMACH_UART0 S3C64XX_DMA_CHAN("uart0_tx") -#define DMACH_UART0_SRC2 S3C64XX_DMA_CHAN("uart0_rx") -#define DMACH_UART1 S3C64XX_DMA_CHAN("uart1_tx") -#define DMACH_UART1_SRC2 S3C64XX_DMA_CHAN("uart1_rx") -#define DMACH_UART2 S3C64XX_DMA_CHAN("uart2_tx") -#define DMACH_UART2_SRC2 S3C64XX_DMA_CHAN("uart2_rx") -#define DMACH_UART3 S3C64XX_DMA_CHAN("uart3_tx") -#define DMACH_UART3_SRC2 S3C64XX_DMA_CHAN("uart3_rx") -#define DMACH_PCM0_TX S3C64XX_DMA_CHAN("pcm0_tx") -#define DMACH_PCM0_RX S3C64XX_DMA_CHAN("pcm0_rx") -#define DMACH_I2S0_OUT S3C64XX_DMA_CHAN("i2s0_tx") -#define DMACH_I2S0_IN S3C64XX_DMA_CHAN("i2s0_rx") +#define DMACH_UART0 "uart0_tx" +#define DMACH_UART0_SRC2 "uart0_rx" +#define DMACH_UART1 "uart1_tx" +#define DMACH_UART1_SRC2 "uart1_rx" +#define DMACH_UART2 "uart2_tx" +#define DMACH_UART2_SRC2 "uart2_rx" +#define DMACH_UART3 "uart3_tx" +#define DMACH_UART3_SRC2 "uart3_rx" +#define DMACH_PCM0_TX "pcm0_tx" +#define DMACH_PCM0_RX "pcm0_rx" +#define DMACH_I2S0_OUT "i2s0_tx" +#define DMACH_I2S0_IN "i2s0_rx" #define DMACH_SPI0_TX S3C64XX_DMA_CHAN("spi0_tx") #define DMACH_SPI0_RX S3C64XX_DMA_CHAN("spi0_rx") -#define DMACH_HSI_I2SV40_TX S3C64XX_DMA_CHAN("i2s2_tx") -#define DMACH_HSI_I2SV40_RX S3C64XX_DMA_CHAN("i2s2_rx") +#define DMACH_HSI_I2SV40_TX "i2s2_tx" +#define DMACH_HSI_I2SV40_RX "i2s2_rx" /* DMA1/SDMA1 */ -#define DMACH_PCM1_TX S3C64XX_DMA_CHAN("pcm1_tx") -#define DMACH_PCM1_RX S3C64XX_DMA_CHAN("pcm1_rx") -#define DMACH_I2S1_OUT S3C64XX_DMA_CHAN("i2s1_tx") -#define DMACH_I2S1_IN S3C64XX_DMA_CHAN("i2s1_rx") +#define DMACH_PCM1_TX "pcm1_tx" +#define DMACH_PCM1_RX "pcm1_rx" +#define DMACH_I2S1_OUT "i2s1_tx" +#define DMACH_I2S1_IN "i2s1_rx" #define DMACH_SPI1_TX S3C64XX_DMA_CHAN("spi1_tx") #define DMACH_SPI1_RX S3C64XX_DMA_CHAN("spi1_rx") -#define DMACH_AC97_PCMOUT S3C64XX_DMA_CHAN("ac97_out") -#define DMACH_AC97_PCMIN S3C64XX_DMA_CHAN("ac97_in") -#define DMACH_AC97_MICIN S3C64XX_DMA_CHAN("ac97_mic") -#define DMACH_PWM S3C64XX_DMA_CHAN("pwm") -#define DMACH_IRDA S3C64XX_DMA_CHAN("irda") -#define DMACH_EXTERNAL S3C64XX_DMA_CHAN("external") -#define DMACH_SECURITY_RX S3C64XX_DMA_CHAN("sec_rx") -#define DMACH_SECURITY_TX S3C64XX_DMA_CHAN("sec_tx") +#define DMACH_AC97_PCMOUT "ac97_out" +#define DMACH_AC97_PCMIN "ac97_in" +#define DMACH_AC97_MICIN "ac97_mic" +#define DMACH_PWM "pwm" +#define DMACH_IRDA "irda" +#define DMACH_EXTERNAL "external" +#define DMACH_SECURITY_RX "sec_rx" +#define DMACH_SECURITY_TX "sec_tx" enum dma_ch { DMACH_MAX = 32 diff --git a/arch/arm/mach-socfpga/headsmp.S b/arch/arm/mach-socfpga/headsmp.S index 5d94b7a2fb10..c160fa3007e9 100644 --- a/arch/arm/mach-socfpga/headsmp.S +++ b/arch/arm/mach-socfpga/headsmp.S @@ -13,6 +13,7 @@ #include .arch armv7-a + .arm ENTRY(secondary_trampoline) /* CPU1 will always fetch from 0x0 when it is brought out of reset. diff --git a/arch/arm/plat-samsung/devs.c b/arch/arm/plat-samsung/devs.c index 82074625de5c..e212f9d804bd 100644 --- a/arch/arm/plat-samsung/devs.c +++ b/arch/arm/plat-samsung/devs.c @@ -65,6 +65,7 @@ #include #include #include +#include #include static u64 samsung_device_dma_mask = DMA_BIT_MASK(32); @@ -74,9 +75,12 @@ static u64 samsung_device_dma_mask = DMA_BIT_MASK(32); static struct resource s3c_ac97_resource[] = { [0] = DEFINE_RES_MEM(S3C2440_PA_AC97, S3C2440_SZ_AC97), [1] = DEFINE_RES_IRQ(IRQ_S3C244X_AC97), - [2] = DEFINE_RES_DMA_NAMED(DMACH_PCM_OUT, "PCM out"), - [3] = DEFINE_RES_DMA_NAMED(DMACH_PCM_IN, "PCM in"), - [4] = DEFINE_RES_DMA_NAMED(DMACH_MIC_IN, "Mic in"), +}; + +static struct s3c_audio_pdata s3c_ac97_pdata = { + .dma_playback = (void *)DMACH_PCM_OUT, + .dma_capture = (void *)DMACH_PCM_IN, + .dma_capture_mic = (void *)DMACH_MIC_IN, }; struct platform_device s3c_device_ac97 = { @@ -87,6 +91,7 @@ struct platform_device s3c_device_ac97 = { .dev = { .dma_mask = &samsung_device_dma_mask, .coherent_dma_mask = DMA_BIT_MASK(32), + .platform_data = &s3c_ac97_pdata, } }; #endif /* CONFIG_CPU_S3C2440 */ diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 4e77fd165f38..b8509f5304b0 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -28,6 +28,7 @@ endif KBUILD_CFLAGS += -mgeneral-regs-only $(lseinstr) KBUILD_CFLAGS += -fno-pic +KBUILD_CFLAGS += $(call cc-option, -mpc-relative-literal-loads) KBUILD_AFLAGS += $(lseinstr) ifeq ($(CONFIG_CPU_BIG_ENDIAN), y) diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h index faad6df49e5b..bc6492b9a924 100644 --- a/arch/arm64/include/asm/elf.h +++ b/arch/arm64/include/asm/elf.h @@ -156,14 +156,14 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm, #define STACK_RND_MASK (0x3ffff >> (PAGE_SHIFT - 12)) #endif -#ifdef CONFIG_COMPAT - #ifdef __AARCH64EB__ #define COMPAT_ELF_PLATFORM ("v8b") #else #define COMPAT_ELF_PLATFORM ("v8l") #endif +#ifdef CONFIG_COMPAT + #define COMPAT_ELF_ET_DYN_BASE (2 * TASK_SIZE_32 / 3) /* AArch32 registers. */ diff --git a/arch/arm64/include/asm/opcodes.h b/arch/arm64/include/asm/opcodes.h index 4e603ea36ad3..123f45d92cd1 100644 --- a/arch/arm64/include/asm/opcodes.h +++ b/arch/arm64/include/asm/opcodes.h @@ -1 +1,5 @@ +#ifdef CONFIG_CPU_BIG_ENDIAN +#define CONFIG_CPU_ENDIAN_BE8 CONFIG_CPU_BIG_ENDIAN +#endif + #include <../../arm/include/asm/opcodes.h> diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index d6739e836f7b..b9da9545b442 100644 --- a/arch/arm64/include/asm/pgtable-hwdef.h +++ b/arch/arm64/include/asm/pgtable-hwdef.h @@ -117,7 +117,6 @@ * Section */ #define PMD_SECT_VALID (_AT(pmdval_t, 1) << 0) -#define PMD_SECT_PROT_NONE (_AT(pmdval_t, 1) << 58) #define PMD_SECT_USER (_AT(pmdval_t, 1) << 6) /* AP[1] */ #define PMD_SECT_RDONLY (_AT(pmdval_t, 1) << 7) /* AP[2] */ #define PMD_SECT_S (_AT(pmdval_t, 3) << 8) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 63f52b55defe..67c2ad6d33b7 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -34,7 +34,7 @@ /* * VMALLOC and SPARSEMEM_VMEMMAP ranges. * - * VMEMAP_SIZE: allows the whole VA space to be covered by a struct page array + * VMEMAP_SIZE: allows the whole linear region to be covered by a struct page array * (rounded up to PUD_SIZE). * VMALLOC_START: beginning of the kernel VA space * VMALLOC_END: extends to the available space below vmmemmap, PCI I/O space, @@ -51,7 +51,9 @@ #define VMALLOC_END (PAGE_OFFSET - PUD_SIZE - VMEMMAP_SIZE - SZ_64K) -#define vmemmap ((struct page *)(VMALLOC_END + SZ_64K)) +#define VMEMMAP_START (VMALLOC_END + SZ_64K) +#define vmemmap ((struct page *)VMEMMAP_START - \ + SECTION_ALIGN_DOWN(memstart_addr >> PAGE_SHIFT)) #define FIRST_USER_ADDRESS 0UL @@ -67,11 +69,11 @@ extern void __pgd_error(const char *file, int line, unsigned long val); #define PROT_DEFAULT (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED) #define PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S) -#define PROT_DEVICE_nGnRnE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRnE)) -#define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRE)) -#define PROT_NORMAL_NC (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL_NC)) -#define PROT_NORMAL_WT (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL_WT)) -#define PROT_NORMAL (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL)) +#define PROT_DEVICE_nGnRnE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE)) +#define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE)) +#define PROT_NORMAL_NC (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_NC)) +#define PROT_NORMAL_WT (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_WT)) +#define PROT_NORMAL (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL)) #define PROT_SECT_DEVICE_nGnRE (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_DEVICE_nGnRE)) #define PROT_SECT_NORMAL (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL)) @@ -81,7 +83,7 @@ extern void __pgd_error(const char *file, int line, unsigned long val); #define PAGE_KERNEL __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE) #define PAGE_KERNEL_RO __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_RDONLY) -#define PAGE_KERNEL_ROX __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_RDONLY) +#define PAGE_KERNEL_ROX __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_RDONLY) #define PAGE_KERNEL_EXEC __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE) #define PAGE_KERNEL_EXEC_CONT __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_CONT) @@ -153,6 +155,7 @@ extern struct page *empty_zero_page; #define pte_write(pte) (!!(pte_val(pte) & PTE_WRITE)) #define pte_exec(pte) (!(pte_val(pte) & PTE_UXN)) #define pte_cont(pte) (!!(pte_val(pte) & PTE_CONT)) +#define pte_user(pte) (!!(pte_val(pte) & PTE_USER)) #ifdef CONFIG_ARM64_HW_AFDBM #define pte_hw_dirty(pte) (pte_write(pte) && !(pte_val(pte) & PTE_RDONLY)) @@ -163,8 +166,6 @@ extern struct page *empty_zero_page; #define pte_dirty(pte) (pte_sw_dirty(pte) || pte_hw_dirty(pte)) #define pte_valid(pte) (!!(pte_val(pte) & PTE_VALID)) -#define pte_valid_user(pte) \ - ((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER)) #define pte_valid_not_user(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID) @@ -262,13 +263,13 @@ extern void __sync_icache_dcache(pte_t pteval, unsigned long addr); static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { - if (pte_valid_user(pte)) { - if (!pte_special(pte) && pte_exec(pte)) - __sync_icache_dcache(pte, addr); + if (pte_present(pte)) { if (pte_sw_dirty(pte) && pte_write(pte)) pte_val(pte) &= ~PTE_RDONLY; else pte_val(pte) |= PTE_RDONLY; + if (pte_user(pte) && pte_exec(pte) && !pte_special(pte)) + __sync_icache_dcache(pte, addr); } /* @@ -346,6 +347,7 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address, #endif /* CONFIG_HAVE_RCU_TABLE_FREE */ #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#define pmd_present(pmd) pte_present(pmd_pte(pmd)) #define pmd_dirty(pmd) pte_dirty(pmd_pte(pmd)) #define pmd_young(pmd) pte_young(pmd_pte(pmd)) #define pmd_wrprotect(pmd) pte_pmd(pte_wrprotect(pmd_pte(pmd))) @@ -354,7 +356,7 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address, #define pmd_mkwrite(pmd) pte_pmd(pte_mkwrite(pmd_pte(pmd))) #define pmd_mkdirty(pmd) pte_pmd(pte_mkdirty(pmd_pte(pmd))) #define pmd_mkyoung(pmd) pte_pmd(pte_mkyoung(pmd_pte(pmd))) -#define pmd_mknotpresent(pmd) (__pmd(pmd_val(pmd) & ~PMD_TYPE_MASK)) +#define pmd_mknotpresent(pmd) (__pmd(pmd_val(pmd) & ~PMD_SECT_VALID)) #define __HAVE_ARCH_PMD_WRITE #define pmd_write(pmd) pte_write(pmd_pte(pmd)) @@ -393,7 +395,6 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size, pgprot_t vma_prot); #define pmd_none(pmd) (!pmd_val(pmd)) -#define pmd_present(pmd) (pmd_val(pmd)) #define pmd_bad(pmd) (!(pmd_val(pmd) & 2)) @@ -537,6 +538,21 @@ static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) } #ifdef CONFIG_ARM64_HW_AFDBM +#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS +extern int ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep, + pte_t entry, int dirty); + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS +static inline int pmdp_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp, + pmd_t entry, int dirty) +{ + return ptep_set_access_flags(vma, address, (pte_t *)pmdp, pmd_pte(entry), dirty); +} +#endif + /* * Atomic pte/pmd modifications. */ @@ -589,9 +605,9 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, } #ifdef CONFIG_TRANSPARENT_HUGEPAGE -#define __HAVE_ARCH_PMDP_GET_AND_CLEAR -static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm, - unsigned long address, pmd_t *pmdp) +#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR +static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, + unsigned long address, pmd_t *pmdp) { return pte_pmd(ptep_get_and_clear(mm, address, (pte_t *)pmdp)); } @@ -639,6 +655,7 @@ extern pgd_t idmap_pg_dir[PTRS_PER_PGD]; * bits 0-1: present (must be zero) * bits 2-7: swap type * bits 8-57: swap offset + * bit 58: PTE_PROT_NONE (must be zero) */ #define __SWP_TYPE_SHIFT 2 #define __SWP_TYPE_BITS 6 diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h index e9e5467e0bf4..a307eb6e7fa8 100644 --- a/arch/arm64/include/asm/ptrace.h +++ b/arch/arm64/include/asm/ptrace.h @@ -58,6 +58,7 @@ #define COMPAT_PSR_Z_BIT 0x40000000 #define COMPAT_PSR_N_BIT 0x80000000 #define COMPAT_PSR_IT_MASK 0x0600fc00 /* If-Then execution state mask */ +#define COMPAT_PSR_GE_MASK 0x000f0000 #ifdef CONFIG_CPU_BIG_ENDIAN #define COMPAT_PSR_ENDSTATE COMPAT_PSR_E_BIT @@ -151,35 +152,9 @@ static inline unsigned long regs_return_value(struct pt_regs *regs) return regs->regs[0]; } -/* - * Are the current registers suitable for user mode? (used to maintain - * security in signal handlers) - */ -static inline int valid_user_regs(struct user_pt_regs *regs) -{ - if (user_mode(regs) && (regs->pstate & PSR_I_BIT) == 0) { - regs->pstate &= ~(PSR_F_BIT | PSR_A_BIT); - - /* The T bit is reserved for AArch64 */ - if (!(regs->pstate & PSR_MODE32_BIT)) - regs->pstate &= ~COMPAT_PSR_T_BIT; - - return 1; - } - - /* - * Force PSR to something logical... - */ - regs->pstate &= PSR_f | PSR_s | (PSR_x & ~PSR_A_BIT) | \ - COMPAT_PSR_T_BIT | PSR_MODE32_BIT; - - if (!(regs->pstate & PSR_MODE32_BIT)) { - regs->pstate &= ~COMPAT_PSR_T_BIT; - regs->pstate |= PSR_MODE_EL0t; - } - - return 0; -} +/* We must avoid circular header include via sched.h */ +struct task_struct; +int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task); #define instruction_pointer(regs) ((unsigned long)(regs)->pc) diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 212ae6361d8b..0166cfbc866c 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -22,6 +22,8 @@ #include #include +#include +#include #include #include #include @@ -85,7 +87,8 @@ static const char *const compat_hwcap_str[] = { "idivt", "vfpd32", "lpae", - "evtstrm" + "evtstrm", + NULL }; static const char *const compat_hwcap2_str[] = { @@ -101,6 +104,7 @@ static const char *const compat_hwcap2_str[] = { static int c_show(struct seq_file *m, void *v) { int i, j; + bool compat = personality(current->personality) == PER_LINUX32; for_each_online_cpu(i) { struct cpuinfo_arm64 *cpuinfo = &per_cpu(cpu_data, i); @@ -112,6 +116,9 @@ static int c_show(struct seq_file *m, void *v) * "processor". Give glibc what it expects. */ seq_printf(m, "processor\t: %d\n", i); + if (compat) + seq_printf(m, "model name\t: ARMv8 Processor rev %d (%s)\n", + MIDR_REVISION(midr), COMPAT_ELF_PLATFORM); seq_printf(m, "BogoMIPS\t: %lu.%02lu\n", loops_per_jiffy / (500000UL/HZ), @@ -124,7 +131,7 @@ static int c_show(struct seq_file *m, void *v) * software which does already (at least for 32-bit). */ seq_puts(m, "Features\t:"); - if (personality(current->personality) == PER_LINUX32) { + if (compat) { #ifdef CONFIG_COMPAT for (j = 0; compat_hwcap_str[j]; j++) if (compat_elf_hwcap & (1 << j)) diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c index 8aee3aeec3e6..c1492ba1f6d1 100644 --- a/arch/arm64/kernel/debug-monitors.c +++ b/arch/arm64/kernel/debug-monitors.c @@ -186,20 +186,21 @@ static void clear_regs_spsr_ss(struct pt_regs *regs) /* EL1 Single Step Handler hooks */ static LIST_HEAD(step_hook); -static DEFINE_RWLOCK(step_hook_lock); +static DEFINE_SPINLOCK(step_hook_lock); void register_step_hook(struct step_hook *hook) { - write_lock(&step_hook_lock); - list_add(&hook->node, &step_hook); - write_unlock(&step_hook_lock); + spin_lock(&step_hook_lock); + list_add_rcu(&hook->node, &step_hook); + spin_unlock(&step_hook_lock); } void unregister_step_hook(struct step_hook *hook) { - write_lock(&step_hook_lock); - list_del(&hook->node); - write_unlock(&step_hook_lock); + spin_lock(&step_hook_lock); + list_del_rcu(&hook->node); + spin_unlock(&step_hook_lock); + synchronize_rcu(); } /* @@ -213,15 +214,15 @@ static int call_step_hook(struct pt_regs *regs, unsigned int esr) struct step_hook *hook; int retval = DBG_HOOK_ERROR; - read_lock(&step_hook_lock); + rcu_read_lock(); - list_for_each_entry(hook, &step_hook, node) { + list_for_each_entry_rcu(hook, &step_hook, node) { retval = hook->fn(regs, esr); if (retval == DBG_HOOK_HANDLED) break; } - read_unlock(&step_hook_lock); + rcu_read_unlock(); return retval; } diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 23cfc08fc8ba..b685257926f0 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -512,9 +512,14 @@ CPU_LE( movk x0, #0x30d0, lsl #16 ) // Clear EE and E0E on LE systems #endif /* EL2 debug */ + mrs x0, id_aa64dfr0_el1 // Check ID_AA64DFR0_EL1 PMUVer + sbfx x0, x0, #8, #4 + cmp x0, #1 + b.lt 4f // Skip if no PMU present mrs x0, pmcr_el0 // Disable debug access traps ubfx x0, x0, #11, #5 // to EL2 and allow access to msr mdcr_el2, x0 // all PMU counters from EL1 +4: /* Stage-2 translation */ msr vttbr_el2, xzr diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index 5b1897e8ca24..62d3dc60ca09 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -574,9 +574,6 @@ static void armv8pmu_reset(void *info) /* Initialize & Reset PMNC: C and P bits. */ armv8pmu_pmcr_write(ARMV8_PMCR_P | ARMV8_PMCR_C); - - /* Disable access from userspace. */ - asm volatile("msr pmuserenr_el0, %0" :: "r" (0)); } static int armv8_pmuv3_map_event(struct perf_event *event) diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 1971f491bb90..fc779ec6f051 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -39,6 +39,7 @@ #include #include +#include #include #include #include @@ -58,6 +59,12 @@ */ void ptrace_disable(struct task_struct *child) { + /* + * This would be better off in core code, but PTRACE_DETACH has + * grown its fair share of arch-specific worts and changing it + * is likely to cause regressions on obscure architectures. + */ + user_disable_single_step(child); } #ifdef CONFIG_HAVE_HW_BREAKPOINT @@ -494,7 +501,7 @@ static int gpr_set(struct task_struct *target, const struct user_regset *regset, if (ret) return ret; - if (!valid_user_regs(&newregs)) + if (!valid_user_regs(&newregs, target)) return -EINVAL; task_pt_regs(target)->user_regs = newregs; @@ -764,7 +771,7 @@ static int compat_gpr_set(struct task_struct *target, } - if (valid_user_regs(&newregs.user_regs)) + if (valid_user_regs(&newregs.user_regs, target)) *task_pt_regs(target) = newregs; else ret = -EINVAL; @@ -1266,3 +1273,79 @@ asmlinkage void syscall_trace_exit(struct pt_regs *regs) if (test_thread_flag(TIF_SYSCALL_TRACE)) tracehook_report_syscall(regs, PTRACE_SYSCALL_EXIT); } + +/* + * Bits which are always architecturally RES0 per ARM DDI 0487A.h + * Userspace cannot use these until they have an architectural meaning. + * We also reserve IL for the kernel; SS is handled dynamically. + */ +#define SPSR_EL1_AARCH64_RES0_BITS \ + (GENMASK_ULL(63,32) | GENMASK_ULL(27, 22) | GENMASK_ULL(20, 10) | \ + GENMASK_ULL(5, 5)) +#define SPSR_EL1_AARCH32_RES0_BITS \ + (GENMASK_ULL(63,32) | GENMASK_ULL(24, 22) | GENMASK_ULL(20,20)) + +static int valid_compat_regs(struct user_pt_regs *regs) +{ + regs->pstate &= ~SPSR_EL1_AARCH32_RES0_BITS; + + if (!system_supports_mixed_endian_el0()) { + if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) + regs->pstate |= COMPAT_PSR_E_BIT; + else + regs->pstate &= ~COMPAT_PSR_E_BIT; + } + + if (user_mode(regs) && (regs->pstate & PSR_MODE32_BIT) && + (regs->pstate & COMPAT_PSR_A_BIT) == 0 && + (regs->pstate & COMPAT_PSR_I_BIT) == 0 && + (regs->pstate & COMPAT_PSR_F_BIT) == 0) { + return 1; + } + + /* + * Force PSR to a valid 32-bit EL0t, preserving the same bits as + * arch/arm. + */ + regs->pstate &= COMPAT_PSR_N_BIT | COMPAT_PSR_Z_BIT | + COMPAT_PSR_C_BIT | COMPAT_PSR_V_BIT | + COMPAT_PSR_Q_BIT | COMPAT_PSR_IT_MASK | + COMPAT_PSR_GE_MASK | COMPAT_PSR_E_BIT | + COMPAT_PSR_T_BIT; + regs->pstate |= PSR_MODE32_BIT; + + return 0; +} + +static int valid_native_regs(struct user_pt_regs *regs) +{ + regs->pstate &= ~SPSR_EL1_AARCH64_RES0_BITS; + + if (user_mode(regs) && !(regs->pstate & PSR_MODE32_BIT) && + (regs->pstate & PSR_D_BIT) == 0 && + (regs->pstate & PSR_A_BIT) == 0 && + (regs->pstate & PSR_I_BIT) == 0 && + (regs->pstate & PSR_F_BIT) == 0) { + return 1; + } + + /* Force PSR to a valid 64-bit EL0t */ + regs->pstate &= PSR_N_BIT | PSR_Z_BIT | PSR_C_BIT | PSR_V_BIT; + + return 0; +} + +/* + * Are the current registers suitable for user mode? (used to maintain + * security in signal handlers) + */ +int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task) +{ + if (!test_tsk_thread_flag(task, TIF_SINGLESTEP)) + regs->pstate &= ~DBG_SPSR_SS; + + if (is_compat_thread(task_thread_info(task))) + return valid_compat_regs(regs); + else + return valid_native_regs(regs); +} diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index e18c48cb6db1..a8eafdbc7cb8 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -115,7 +115,7 @@ static int restore_sigframe(struct pt_regs *regs, */ regs->syscallno = ~0UL; - err |= !valid_user_regs(®s->user_regs); + err |= !valid_user_regs(®s->user_regs, current); if (err == 0) { struct fpsimd_context *fpsimd_ctx = @@ -307,7 +307,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) /* * Check that the resulting registers are actually sane. */ - ret |= !valid_user_regs(®s->user_regs); + ret |= !valid_user_regs(®s->user_regs, current); /* * Fast forward the stepping logic so we step into the signal diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c index 71ef6dc89ae5..107335637390 100644 --- a/arch/arm64/kernel/signal32.c +++ b/arch/arm64/kernel/signal32.c @@ -356,7 +356,7 @@ static int compat_restore_sigframe(struct pt_regs *regs, */ regs->syscallno = ~0UL; - err |= !valid_user_regs(®s->user_regs); + err |= !valid_user_regs(®s->user_regs, current); aux = (struct compat_aux_sigframe __user *) sf->uc.uc_regspace; if (err == 0) diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index d250160d32bc..3039f080e2d5 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -186,7 +186,7 @@ static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) u64 val; val = kvm_arm_timer_get_reg(vcpu, reg->id); - return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)); + return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)) ? -EFAULT : 0; } /** diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c index 648112e90ed5..3972e65fbd5a 100644 --- a/arch/arm64/kvm/inject_fault.c +++ b/arch/arm64/kvm/inject_fault.c @@ -130,7 +130,7 @@ static void inject_abt64(struct kvm_vcpu *vcpu, bool is_iabt, unsigned long addr esr |= (ESR_ELx_EC_IABT_CUR << ESR_ELx_EC_SHIFT); if (!is_iabt) - esr |= ESR_ELx_EC_DABT_LOW; + esr |= ESR_ELx_EC_DABT_LOW << ESR_ELx_EC_SHIFT; vcpu_sys_reg(vcpu, ESR_EL1) = esr | ESR_ELx_FSC_EXTABT; } diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 6ad554b01e95..ddfb97a299f2 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -933,6 +933,10 @@ static int __init __iommu_dma_init(void) ret = register_iommu_dma_ops_notifier(&platform_bus_type); if (!ret) ret = register_iommu_dma_ops_notifier(&amba_bustype); + + /* handle devices queued before this arch_initcall */ + if (!ret) + __iommu_attach_notifier(NULL, BUS_NOTIFY_ADD_DEVICE, NULL); return ret; } arch_initcall(__iommu_dma_init); diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 92ddac1e8ca2..4c1a118c1d09 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -81,6 +81,56 @@ void show_pte(struct mm_struct *mm, unsigned long addr) printk("\n"); } +#ifdef CONFIG_ARM64_HW_AFDBM +/* + * This function sets the access flags (dirty, accessed), as well as write + * permission, and only to a more permissive setting. + * + * It needs to cope with hardware update of the accessed/dirty state by other + * agents in the system and can safely skip the __sync_icache_dcache() call as, + * like set_pte_at(), the PTE is never changed from no-exec to exec here. + * + * Returns whether or not the PTE actually changed. + */ +int ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep, + pte_t entry, int dirty) +{ + pteval_t old_pteval; + unsigned int tmp; + + if (pte_same(*ptep, entry)) + return 0; + + /* only preserve the access flags and write permission */ + pte_val(entry) &= PTE_AF | PTE_WRITE | PTE_DIRTY; + + /* + * PTE_RDONLY is cleared by default in the asm below, so set it in + * back if necessary (read-only or clean PTE). + */ + if (!pte_write(entry) || !pte_sw_dirty(entry)) + pte_val(entry) |= PTE_RDONLY; + + /* + * Setting the flags must be done atomically to avoid racing with the + * hardware update of the access/dirty state. + */ + asm volatile("// ptep_set_access_flags\n" + " prfm pstl1strm, %2\n" + "1: ldxr %0, %2\n" + " and %0, %0, %3 // clear PTE_RDONLY\n" + " orr %0, %0, %4 // set flags\n" + " stxr %w1, %0, %2\n" + " cbnz %w1, 1b\n" + : "=&r" (old_pteval), "=&r" (tmp), "+Q" (pte_val(*ptep)) + : "L" (~PTE_RDONLY), "r" (pte_val(entry))); + + flush_tlb_fix_spurious_fault(vma, address); + return 1; +} +#endif + /* * The kernel tried to access some page that wasn't present. */ diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 325f89ff897e..224238943aff 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -321,8 +321,8 @@ void __init mem_init(void) #endif MLG(VMALLOC_START, VMALLOC_END), #ifdef CONFIG_SPARSEMEM_VMEMMAP - MLG((unsigned long)vmemmap, - (unsigned long)vmemmap + VMEMMAP_SIZE), + MLG(VMEMMAP_START, + VMEMMAP_START + VMEMMAP_SIZE), MLM((unsigned long)virt_to_page(PAGE_OFFSET), (unsigned long)virt_to_page(high_memory)), #endif diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 873e363048c6..116ad654dd59 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -456,6 +456,9 @@ void __init paging_init(void) empty_zero_page = virt_to_page(zero_page); + /* Ensure the zero page is visible to the page table walker */ + dsb(ishst); + /* * TTBR0 is only used for the identity mapping at this stage. Make it * point to zero page to avoid speculatively fetching new entries. diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index 3571c7309c5e..cf6240741134 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -57,6 +57,9 @@ static int change_memory_common(unsigned long addr, int numpages, if (end < MODULES_VADDR || end >= MODULES_END) return -EINVAL; + if (!numpages) + return 0; + data.set_mask = set_mask; data.clear_mask = clear_mask; diff --git a/arch/arm64/mm/proc-macros.S b/arch/arm64/mm/proc-macros.S index 4c4d93c4bf65..d69dffffaa89 100644 --- a/arch/arm64/mm/proc-macros.S +++ b/arch/arm64/mm/proc-macros.S @@ -62,3 +62,15 @@ bfi \valreg, \tmpreg, #TCR_T0SZ_OFFSET, #TCR_TxSZ_WIDTH #endif .endm + +/* + * reset_pmuserenr_el0 - reset PMUSERENR_EL0 if PMUv3 present + */ + .macro reset_pmuserenr_el0, tmpreg + mrs \tmpreg, id_aa64dfr0_el1 // Check ID_AA64DFR0_EL1 PMUVer + sbfx \tmpreg, \tmpreg, #8, #4 + cmp \tmpreg, #1 // Skip if no PMU present + b.lt 9000f + msr pmuserenr_el0, xzr // Disable PMU access from EL0 +9000: + .endm diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index cacecc4ad3e5..b8f04b3f2786 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -117,6 +117,7 @@ ENTRY(cpu_do_resume) */ ubfx x11, x11, #1, #1 msr oslar_el1, x11 + reset_pmuserenr_el0 x0 // Disable PMU access from EL0 mov x0, x12 dsb nsh // Make sure local tlb invalidation completed isb @@ -155,6 +156,7 @@ ENTRY(__cpu_setup) msr cpacr_el1, x0 // Enable FP/ASIMD mov x0, #1 << 12 // Reset mdscr_el1 and disable msr mdscr_el1, x0 // access to the DCC from EL0 + reset_pmuserenr_el0 x0 // Disable PMU access from EL0 /* * Memory region attributes for LPAE: * diff --git a/arch/ia64/include/asm/io.h b/arch/ia64/include/asm/io.h index 9041bbe2b7b4..8fdb9c7eeb66 100644 --- a/arch/ia64/include/asm/io.h +++ b/arch/ia64/include/asm/io.h @@ -436,6 +436,7 @@ static inline void __iomem * ioremap_cache (unsigned long phys_addr, unsigned lo return ioremap(phys_addr, size); } #define ioremap_cache ioremap_cache +#define ioremap_uc ioremap_nocache /* diff --git a/arch/m32r/kernel/setup.c b/arch/m32r/kernel/setup.c index 0392112a5d70..a5ecef7188ba 100644 --- a/arch/m32r/kernel/setup.c +++ b/arch/m32r/kernel/setup.c @@ -81,7 +81,10 @@ static struct resource code_resource = { }; unsigned long memory_start; +EXPORT_SYMBOL(memory_start); + unsigned long memory_end; +EXPORT_SYMBOL(memory_end); void __init setup_arch(char **); int get_cpuinfo(char *); diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 71683a853372..db459612de44 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -2155,7 +2155,7 @@ config MIPS_MT_SMP select CPU_MIPSR2_IRQ_VI select CPU_MIPSR2_IRQ_EI select SYNC_R4K - select MIPS_GIC_IPI + select MIPS_GIC_IPI if MIPS_GIC select MIPS_MT select SMP select SMP_UP @@ -2253,7 +2253,7 @@ config MIPS_VPE_APSP_API_MT config MIPS_CMP bool "MIPS CMP framework support (DEPRECATED)" depends on SYS_SUPPORTS_MIPS_CMP && !CPU_MIPSR6 - select MIPS_GIC_IPI + select MIPS_GIC_IPI if MIPS_GIC select SMP select SYNC_R4K select SYS_SUPPORTS_SMP @@ -2273,7 +2273,7 @@ config MIPS_CPS select MIPS_CM select MIPS_CPC select MIPS_CPS_PM if HOTPLUG_CPU - select MIPS_GIC_IPI + select MIPS_GIC_IPI if MIPS_GIC select SMP select SYNC_R4K if (CEVT_R4K || CSRC_R4K) select SYS_SUPPORTS_HOTPLUG_CPU @@ -2292,6 +2292,7 @@ config MIPS_CPS_PM bool config MIPS_GIC_IPI + depends on MIPS_GIC bool config MIPS_CM diff --git a/arch/mips/alchemy/devboards/db1000.c b/arch/mips/alchemy/devboards/db1000.c index bdeed9d13c6f..433c4b9a9f0a 100644 --- a/arch/mips/alchemy/devboards/db1000.c +++ b/arch/mips/alchemy/devboards/db1000.c @@ -503,15 +503,15 @@ int __init db1000_dev_setup(void) if (board == BCSR_WHOAMI_DB1500) { c0 = AU1500_GPIO2_INT; c1 = AU1500_GPIO5_INT; - d0 = AU1500_GPIO0_INT; - d1 = AU1500_GPIO3_INT; + d0 = 0; /* GPIO number, NOT irq! */ + d1 = 3; /* GPIO number, NOT irq! */ s0 = AU1500_GPIO1_INT; s1 = AU1500_GPIO4_INT; } else if (board == BCSR_WHOAMI_DB1100) { c0 = AU1100_GPIO2_INT; c1 = AU1100_GPIO5_INT; - d0 = AU1100_GPIO0_INT; - d1 = AU1100_GPIO3_INT; + d0 = 0; /* GPIO number, NOT irq! */ + d1 = 3; /* GPIO number, NOT irq! */ s0 = AU1100_GPIO1_INT; s1 = AU1100_GPIO4_INT; @@ -545,15 +545,15 @@ int __init db1000_dev_setup(void) } else if (board == BCSR_WHOAMI_DB1000) { c0 = AU1000_GPIO2_INT; c1 = AU1000_GPIO5_INT; - d0 = AU1000_GPIO0_INT; - d1 = AU1000_GPIO3_INT; + d0 = 0; /* GPIO number, NOT irq! */ + d1 = 3; /* GPIO number, NOT irq! */ s0 = AU1000_GPIO1_INT; s1 = AU1000_GPIO4_INT; platform_add_devices(db1000_devs, ARRAY_SIZE(db1000_devs)); } else if ((board == BCSR_WHOAMI_PB1500) || (board == BCSR_WHOAMI_PB1500R2)) { c0 = AU1500_GPIO203_INT; - d0 = AU1500_GPIO201_INT; + d0 = 1; /* GPIO number, NOT irq! */ s0 = AU1500_GPIO202_INT; twosocks = 0; flashsize = 64; @@ -566,7 +566,7 @@ int __init db1000_dev_setup(void) */ } else if (board == BCSR_WHOAMI_PB1100) { c0 = AU1100_GPIO11_INT; - d0 = AU1100_GPIO9_INT; + d0 = 9; /* GPIO number, NOT irq! */ s0 = AU1100_GPIO10_INT; twosocks = 0; flashsize = 64; @@ -583,7 +583,6 @@ int __init db1000_dev_setup(void) } else return 0; /* unknown board, no further dev setup to do */ - irq_set_irq_type(d0, IRQ_TYPE_EDGE_BOTH); irq_set_irq_type(c0, IRQ_TYPE_LEVEL_LOW); irq_set_irq_type(s0, IRQ_TYPE_LEVEL_LOW); @@ -597,7 +596,6 @@ int __init db1000_dev_setup(void) c0, d0, /*s0*/0, 0, 0); if (twosocks) { - irq_set_irq_type(d1, IRQ_TYPE_EDGE_BOTH); irq_set_irq_type(c1, IRQ_TYPE_LEVEL_LOW); irq_set_irq_type(s1, IRQ_TYPE_LEVEL_LOW); diff --git a/arch/mips/alchemy/devboards/db1550.c b/arch/mips/alchemy/devboards/db1550.c index 5740bcfdfc7f..6c37b9326f41 100644 --- a/arch/mips/alchemy/devboards/db1550.c +++ b/arch/mips/alchemy/devboards/db1550.c @@ -514,7 +514,7 @@ static void __init db1550_devices(void) AU1000_PCMCIA_MEM_PHYS_ADDR + 0x000400000 - 1, AU1000_PCMCIA_IO_PHYS_ADDR, AU1000_PCMCIA_IO_PHYS_ADDR + 0x000010000 - 1, - AU1550_GPIO3_INT, AU1550_GPIO0_INT, + AU1550_GPIO3_INT, 0, /*AU1550_GPIO21_INT*/0, 0, 0); db1x_register_pcmcia_socket( @@ -524,7 +524,7 @@ static void __init db1550_devices(void) AU1000_PCMCIA_MEM_PHYS_ADDR + 0x004400000 - 1, AU1000_PCMCIA_IO_PHYS_ADDR + 0x004000000, AU1000_PCMCIA_IO_PHYS_ADDR + 0x004010000 - 1, - AU1550_GPIO5_INT, AU1550_GPIO1_INT, + AU1550_GPIO5_INT, 1, /*AU1550_GPIO22_INT*/0, 0, 1); platform_device_register(&db1550_nand_dev); diff --git a/arch/mips/ath79/early_printk.c b/arch/mips/ath79/early_printk.c index b955fafc58ba..d1adc59af5bf 100644 --- a/arch/mips/ath79/early_printk.c +++ b/arch/mips/ath79/early_printk.c @@ -31,13 +31,15 @@ static inline void prom_putchar_wait(void __iomem *reg, u32 mask, u32 val) } while (1); } +#define BOTH_EMPTY (UART_LSR_TEMT | UART_LSR_THRE) + static void prom_putchar_ar71xx(unsigned char ch) { void __iomem *base = (void __iomem *)(KSEG1ADDR(AR71XX_UART_BASE)); - prom_putchar_wait(base + UART_LSR * 4, UART_LSR_THRE, UART_LSR_THRE); + prom_putchar_wait(base + UART_LSR * 4, BOTH_EMPTY, BOTH_EMPTY); __raw_writel(ch, base + UART_TX * 4); - prom_putchar_wait(base + UART_LSR * 4, UART_LSR_THRE, UART_LSR_THRE); + prom_putchar_wait(base + UART_LSR * 4, BOTH_EMPTY, BOTH_EMPTY); } static void prom_putchar_ar933x(unsigned char ch) diff --git a/arch/mips/include/asm/asmmacro.h b/arch/mips/include/asm/asmmacro.h index 867f924b05c7..e689b894353c 100644 --- a/arch/mips/include/asm/asmmacro.h +++ b/arch/mips/include/asm/asmmacro.h @@ -298,21 +298,21 @@ .set pop .endm - .macro copy_u_w ws, n + .macro copy_s_w ws, n .set push .set mips32r2 .set fp=64 .set msa - copy_u.w $1, $w\ws[\n] + copy_s.w $1, $w\ws[\n] .set pop .endm - .macro copy_u_d ws, n + .macro copy_s_d ws, n .set push .set mips64r2 .set fp=64 .set msa - copy_u.d $1, $w\ws[\n] + copy_s.d $1, $w\ws[\n] .set pop .endm @@ -346,8 +346,8 @@ #define STH_MSA_INSN 0x5800081f #define STW_MSA_INSN 0x5800082f #define STD_MSA_INSN 0x5800083f -#define COPY_UW_MSA_INSN 0x58f00056 -#define COPY_UD_MSA_INSN 0x58f80056 +#define COPY_SW_MSA_INSN 0x58b00056 +#define COPY_SD_MSA_INSN 0x58b80056 #define INSERT_W_MSA_INSN 0x59300816 #define INSERT_D_MSA_INSN 0x59380816 #else @@ -361,8 +361,8 @@ #define STH_MSA_INSN 0x78000825 #define STW_MSA_INSN 0x78000826 #define STD_MSA_INSN 0x78000827 -#define COPY_UW_MSA_INSN 0x78f00059 -#define COPY_UD_MSA_INSN 0x78f80059 +#define COPY_SW_MSA_INSN 0x78b00059 +#define COPY_SD_MSA_INSN 0x78b80059 #define INSERT_W_MSA_INSN 0x79300819 #define INSERT_D_MSA_INSN 0x79380819 #endif @@ -393,7 +393,7 @@ .set push .set noat SET_HARDFLOAT - addu $1, \base, \off + PTR_ADDU $1, \base, \off .word LDB_MSA_INSN | (\wd << 6) .set pop .endm @@ -402,7 +402,7 @@ .set push .set noat SET_HARDFLOAT - addu $1, \base, \off + PTR_ADDU $1, \base, \off .word LDH_MSA_INSN | (\wd << 6) .set pop .endm @@ -411,7 +411,7 @@ .set push .set noat SET_HARDFLOAT - addu $1, \base, \off + PTR_ADDU $1, \base, \off .word LDW_MSA_INSN | (\wd << 6) .set pop .endm @@ -420,7 +420,7 @@ .set push .set noat SET_HARDFLOAT - addu $1, \base, \off + PTR_ADDU $1, \base, \off .word LDD_MSA_INSN | (\wd << 6) .set pop .endm @@ -429,7 +429,7 @@ .set push .set noat SET_HARDFLOAT - addu $1, \base, \off + PTR_ADDU $1, \base, \off .word STB_MSA_INSN | (\wd << 6) .set pop .endm @@ -438,7 +438,7 @@ .set push .set noat SET_HARDFLOAT - addu $1, \base, \off + PTR_ADDU $1, \base, \off .word STH_MSA_INSN | (\wd << 6) .set pop .endm @@ -447,7 +447,7 @@ .set push .set noat SET_HARDFLOAT - addu $1, \base, \off + PTR_ADDU $1, \base, \off .word STW_MSA_INSN | (\wd << 6) .set pop .endm @@ -456,26 +456,26 @@ .set push .set noat SET_HARDFLOAT - addu $1, \base, \off + PTR_ADDU $1, \base, \off .word STD_MSA_INSN | (\wd << 6) .set pop .endm - .macro copy_u_w ws, n + .macro copy_s_w ws, n .set push .set noat SET_HARDFLOAT .insn - .word COPY_UW_MSA_INSN | (\n << 16) | (\ws << 11) + .word COPY_SW_MSA_INSN | (\n << 16) | (\ws << 11) .set pop .endm - .macro copy_u_d ws, n + .macro copy_s_d ws, n .set push .set noat SET_HARDFLOAT .insn - .word COPY_UD_MSA_INSN | (\n << 16) | (\ws << 11) + .word COPY_SD_MSA_INSN | (\n << 16) | (\ws << 11) .set pop .endm diff --git a/arch/mips/include/asm/cacheflush.h b/arch/mips/include/asm/cacheflush.h index 723229f4cf27..176de586a71a 100644 --- a/arch/mips/include/asm/cacheflush.h +++ b/arch/mips/include/asm/cacheflush.h @@ -51,7 +51,6 @@ extern void (*flush_cache_range)(struct vm_area_struct *vma, unsigned long start, unsigned long end); extern void (*flush_cache_page)(struct vm_area_struct *vma, unsigned long page, unsigned long pfn); extern void __flush_dcache_page(struct page *page); -extern void __flush_icache_page(struct vm_area_struct *vma, struct page *page); #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 static inline void flush_dcache_page(struct page *page) @@ -77,11 +76,6 @@ static inline void flush_anon_page(struct vm_area_struct *vma, static inline void flush_icache_page(struct vm_area_struct *vma, struct page *page) { - if (!cpu_has_ic_fills_f_dc && (vma->vm_flags & VM_EXEC) && - Page_dcache_dirty(page)) { - __flush_icache_page(vma, page); - ClearPageDcacheDirty(page); - } } extern void (*flush_icache_range)(unsigned long start, unsigned long end); diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index 6ded8d347af9..dd7cee795709 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -372,6 +372,7 @@ struct kvm_mips_tlb { #define KVM_MIPS_GUEST_TLB_SIZE 64 struct kvm_vcpu_arch { void *host_ebase, *guest_ebase; + int (*vcpu_run)(struct kvm_run *run, struct kvm_vcpu *vcpu); unsigned long host_stack; unsigned long host_gp; @@ -784,7 +785,7 @@ extern enum emulation_result kvm_mips_complete_mmio_load(struct kvm_vcpu *vcpu, uint32_t kvm_mips_read_count(struct kvm_vcpu *vcpu); void kvm_mips_write_count(struct kvm_vcpu *vcpu, uint32_t count); -void kvm_mips_write_compare(struct kvm_vcpu *vcpu, uint32_t compare); +void kvm_mips_write_compare(struct kvm_vcpu *vcpu, uint32_t compare, bool ack); void kvm_mips_init_count(struct kvm_vcpu *vcpu); int kvm_mips_set_count_ctl(struct kvm_vcpu *vcpu, s64 count_ctl); int kvm_mips_set_count_resume(struct kvm_vcpu *vcpu, s64 count_resume); diff --git a/arch/mips/include/asm/msa.h b/arch/mips/include/asm/msa.h index bbb85fe21642..6e4effa6f626 100644 --- a/arch/mips/include/asm/msa.h +++ b/arch/mips/include/asm/msa.h @@ -147,6 +147,19 @@ static inline void restore_msa(struct task_struct *t) _restore_msa(t); } +static inline void init_msa_upper(void) +{ + /* + * Check cpu_has_msa only if it's a constant. This will allow the + * compiler to optimise out code for CPUs without MSA without adding + * an extra redundant check for CPUs with MSA. + */ + if (__builtin_constant_p(cpu_has_msa) && !cpu_has_msa) + return; + + _init_msa_upper(); +} + #ifdef TOOLCHAIN_SUPPORTS_MSA #define __BUILD_MSA_CTL_REG(name, cs) \ diff --git a/arch/mips/include/asm/page.h b/arch/mips/include/asm/page.h index 2046c0230224..21ed7150fec3 100644 --- a/arch/mips/include/asm/page.h +++ b/arch/mips/include/asm/page.h @@ -33,7 +33,7 @@ #define PAGE_SHIFT 16 #endif #define PAGE_SIZE (_AC(1,UL) << PAGE_SHIFT) -#define PAGE_MASK (~(PAGE_SIZE - 1)) +#define PAGE_MASK (~((1 << PAGE_SHIFT) - 1)) /* * This is used for calculating the real page sizes diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h index 8957f15e21ec..4e68c644acc5 100644 --- a/arch/mips/include/asm/pgtable.h +++ b/arch/mips/include/asm/pgtable.h @@ -127,10 +127,14 @@ do { \ } \ } while(0) +static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pteval); + #if defined(CONFIG_PHYS_ADDR_T_64BIT) && defined(CONFIG_CPU_MIPS32) #define pte_none(pte) (!(((pte).pte_high) & ~_PAGE_GLOBAL)) #define pte_present(pte) ((pte).pte_low & _PAGE_PRESENT) +#define pte_no_exec(pte) ((pte).pte_low & _PAGE_NO_EXEC) static inline void set_pte(pte_t *ptep, pte_t pte) { @@ -148,7 +152,6 @@ static inline void set_pte(pte_t *ptep, pte_t pte) buddy->pte_high |= _PAGE_GLOBAL; } } -#define set_pte_at(mm, addr, ptep, pteval) set_pte(ptep, pteval) static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { @@ -166,6 +169,7 @@ static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *pt #define pte_none(pte) (!(pte_val(pte) & ~_PAGE_GLOBAL)) #define pte_present(pte) (pte_val(pte) & _PAGE_PRESENT) +#define pte_no_exec(pte) (pte_val(pte) & _PAGE_NO_EXEC) /* * Certain architectures need to do special things when pte's @@ -218,7 +222,6 @@ static inline void set_pte(pte_t *ptep, pte_t pteval) } #endif } -#define set_pte_at(mm, addr, ptep, pteval) set_pte(ptep, pteval) static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { @@ -234,6 +237,22 @@ static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *pt } #endif +static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pteval) +{ + extern void __update_cache(unsigned long address, pte_t pte); + + if (!pte_present(pteval)) + goto cache_sync_done; + + if (pte_present(*ptep) && (pte_pfn(*ptep) == pte_pfn(pteval))) + goto cache_sync_done; + + __update_cache(addr, pteval); +cache_sync_done: + set_pte(ptep, pteval); +} + /* * (pmds are folded into puds so this doesn't get actually called, * but the define is needed for a generic inline function.) @@ -353,7 +372,7 @@ static inline pte_t pte_mkdirty(pte_t pte) static inline pte_t pte_mkyoung(pte_t pte) { pte_val(pte) |= _PAGE_ACCESSED; -#ifdef CONFIG_CPU_MIPSR2 +#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6) if (!(pte_val(pte) & _PAGE_NO_READ)) pte_val(pte) |= _PAGE_SILENT_READ; else @@ -430,15 +449,12 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) extern void __update_tlb(struct vm_area_struct *vma, unsigned long address, pte_t pte); -extern void __update_cache(struct vm_area_struct *vma, unsigned long address, - pte_t pte); static inline void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { pte_t pte = *ptep; __update_tlb(vma, address, pte); - __update_cache(vma, address, pte); } static inline void update_mmu_cache_pmd(struct vm_area_struct *vma, @@ -560,7 +576,7 @@ static inline pmd_t pmd_mkyoung(pmd_t pmd) { pmd_val(pmd) |= _PAGE_ACCESSED; -#ifdef CONFIG_CPU_MIPSR2 +#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6) if (!(pmd_val(pmd) & _PAGE_NO_READ)) pmd_val(pmd) |= _PAGE_SILENT_READ; else diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h index 3f832c3dd8f5..041153f5cf93 100644 --- a/arch/mips/include/asm/processor.h +++ b/arch/mips/include/asm/processor.h @@ -45,7 +45,7 @@ extern unsigned int vced_count, vcei_count; * User space process size: 2GB. This is hardcoded into a few places, * so don't change it unless you know what you are doing. */ -#define TASK_SIZE 0x7fff8000UL +#define TASK_SIZE 0x80000000UL #endif #define STACK_TOP_MAX TASK_SIZE diff --git a/arch/mips/include/asm/switch_to.h b/arch/mips/include/asm/switch_to.h index 28b5d84a5022..ebb5c0f2f90d 100644 --- a/arch/mips/include/asm/switch_to.h +++ b/arch/mips/include/asm/switch_to.h @@ -105,7 +105,7 @@ do { \ __clear_software_ll_bit(); \ if (cpu_has_userlocal) \ write_c0_userlocal(task_thread_info(next)->tp_value); \ - __restore_watch(); \ + __restore_watch(next); \ (last) = resume(prev, next, task_thread_info(next)); \ } while (0) diff --git a/arch/mips/include/asm/syscall.h b/arch/mips/include/asm/syscall.h index 6499d93ae68d..47bc45a67e9b 100644 --- a/arch/mips/include/asm/syscall.h +++ b/arch/mips/include/asm/syscall.h @@ -101,10 +101,8 @@ static inline void syscall_get_arguments(struct task_struct *task, /* O32 ABI syscall() - Either 64-bit with O32 or 32-bit */ if ((config_enabled(CONFIG_32BIT) || test_tsk_thread_flag(task, TIF_32BIT_REGS)) && - (regs->regs[2] == __NR_syscall)) { + (regs->regs[2] == __NR_syscall)) i++; - n++; - } while (n--) ret |= mips_get_syscall_arg(args++, task, regs, i++); diff --git a/arch/mips/include/asm/watch.h b/arch/mips/include/asm/watch.h index 20126ec79359..6ffe3eadf105 100644 --- a/arch/mips/include/asm/watch.h +++ b/arch/mips/include/asm/watch.h @@ -12,21 +12,21 @@ #include -void mips_install_watch_registers(void); +void mips_install_watch_registers(struct task_struct *t); void mips_read_watch_registers(void); void mips_clear_watch_registers(void); void mips_probe_watch_registers(struct cpuinfo_mips *c); #ifdef CONFIG_HARDWARE_WATCHPOINTS -#define __restore_watch() do { \ +#define __restore_watch(task) do { \ if (unlikely(test_bit(TIF_LOAD_WATCH, \ - ¤t_thread_info()->flags))) { \ - mips_install_watch_registers(); \ + &task_thread_info(task)->flags))) { \ + mips_install_watch_registers(task); \ } \ } while (0) #else -#define __restore_watch() do {} while (0) +#define __restore_watch(task) do {} while (0) #endif #endif /* _ASM_WATCH_H */ diff --git a/arch/mips/include/uapi/asm/siginfo.h b/arch/mips/include/uapi/asm/siginfo.h index 2cb7fdead570..e2b5337e840f 100644 --- a/arch/mips/include/uapi/asm/siginfo.h +++ b/arch/mips/include/uapi/asm/siginfo.h @@ -28,7 +28,7 @@ #define __ARCH_SIGSYS -#include +#include /* We can't use generic siginfo_t, because our si_code and si_errno are swapped */ typedef struct siginfo { @@ -42,13 +42,13 @@ typedef struct siginfo { /* kill() */ struct { - pid_t _pid; /* sender's pid */ + __kernel_pid_t _pid; /* sender's pid */ __ARCH_SI_UID_T _uid; /* sender's uid */ } _kill; /* POSIX.1b timers */ struct { - timer_t _tid; /* timer id */ + __kernel_timer_t _tid; /* timer id */ int _overrun; /* overrun count */ char _pad[sizeof( __ARCH_SI_UID_T) - sizeof(int)]; sigval_t _sigval; /* same as below */ @@ -57,26 +57,26 @@ typedef struct siginfo { /* POSIX.1b signals */ struct { - pid_t _pid; /* sender's pid */ + __kernel_pid_t _pid; /* sender's pid */ __ARCH_SI_UID_T _uid; /* sender's uid */ sigval_t _sigval; } _rt; /* SIGCHLD */ struct { - pid_t _pid; /* which child */ + __kernel_pid_t _pid; /* which child */ __ARCH_SI_UID_T _uid; /* sender's uid */ int _status; /* exit code */ - clock_t _utime; - clock_t _stime; + __kernel_clock_t _utime; + __kernel_clock_t _stime; } _sigchld; /* IRIX SIGCHLD */ struct { - pid_t _pid; /* which child */ - clock_t _utime; + __kernel_pid_t _pid; /* which child */ + __kernel_clock_t _utime; int _status; /* exit code */ - clock_t _stime; + __kernel_clock_t _stime; } _irix_sigchld; /* SIGILL, SIGFPE, SIGSEGV, SIGBUS */ @@ -118,6 +118,4 @@ typedef struct siginfo { #define SI_TIMER __SI_CODE(__SI_TIMER, -3) /* sent by timer expiration */ #define SI_MESGQ __SI_CODE(__SI_MESGQ, -4) /* sent by real time mesq state change */ -#include - #endif /* _UAPI_ASM_SIGINFO_H */ diff --git a/arch/mips/kernel/mips-r2-to-r6-emul.c b/arch/mips/kernel/mips-r2-to-r6-emul.c index 1f5aac7f9ec3..4674a74a08b5 100644 --- a/arch/mips/kernel/mips-r2-to-r6-emul.c +++ b/arch/mips/kernel/mips-r2-to-r6-emul.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include @@ -1251,10 +1252,10 @@ fpu_emul: " j 10b\n" " .previous\n" " .section __ex_table,\"a\"\n" - " .word 1b,8b\n" - " .word 2b,8b\n" - " .word 3b,8b\n" - " .word 4b,8b\n" + STR(PTR) " 1b,8b\n" + STR(PTR) " 2b,8b\n" + STR(PTR) " 3b,8b\n" + STR(PTR) " 4b,8b\n" " .previous\n" " .set pop\n" : "+&r"(rt), "=&r"(rs), @@ -1326,10 +1327,10 @@ fpu_emul: " j 10b\n" " .previous\n" " .section __ex_table,\"a\"\n" - " .word 1b,8b\n" - " .word 2b,8b\n" - " .word 3b,8b\n" - " .word 4b,8b\n" + STR(PTR) " 1b,8b\n" + STR(PTR) " 2b,8b\n" + STR(PTR) " 3b,8b\n" + STR(PTR) " 4b,8b\n" " .previous\n" " .set pop\n" : "+&r"(rt), "=&r"(rs), @@ -1397,10 +1398,10 @@ fpu_emul: " j 9b\n" " .previous\n" " .section __ex_table,\"a\"\n" - " .word 1b,8b\n" - " .word 2b,8b\n" - " .word 3b,8b\n" - " .word 4b,8b\n" + STR(PTR) " 1b,8b\n" + STR(PTR) " 2b,8b\n" + STR(PTR) " 3b,8b\n" + STR(PTR) " 4b,8b\n" " .previous\n" " .set pop\n" : "+&r"(rt), "=&r"(rs), @@ -1467,10 +1468,10 @@ fpu_emul: " j 9b\n" " .previous\n" " .section __ex_table,\"a\"\n" - " .word 1b,8b\n" - " .word 2b,8b\n" - " .word 3b,8b\n" - " .word 4b,8b\n" + STR(PTR) " 1b,8b\n" + STR(PTR) " 2b,8b\n" + STR(PTR) " 3b,8b\n" + STR(PTR) " 4b,8b\n" " .previous\n" " .set pop\n" : "+&r"(rt), "=&r"(rs), @@ -1582,14 +1583,14 @@ fpu_emul: " j 9b\n" " .previous\n" " .section __ex_table,\"a\"\n" - " .word 1b,8b\n" - " .word 2b,8b\n" - " .word 3b,8b\n" - " .word 4b,8b\n" - " .word 5b,8b\n" - " .word 6b,8b\n" - " .word 7b,8b\n" - " .word 0b,8b\n" + STR(PTR) " 1b,8b\n" + STR(PTR) " 2b,8b\n" + STR(PTR) " 3b,8b\n" + STR(PTR) " 4b,8b\n" + STR(PTR) " 5b,8b\n" + STR(PTR) " 6b,8b\n" + STR(PTR) " 7b,8b\n" + STR(PTR) " 0b,8b\n" " .previous\n" " .set pop\n" : "+&r"(rt), "=&r"(rs), @@ -1701,14 +1702,14 @@ fpu_emul: " j 9b\n" " .previous\n" " .section __ex_table,\"a\"\n" - " .word 1b,8b\n" - " .word 2b,8b\n" - " .word 3b,8b\n" - " .word 4b,8b\n" - " .word 5b,8b\n" - " .word 6b,8b\n" - " .word 7b,8b\n" - " .word 0b,8b\n" + STR(PTR) " 1b,8b\n" + STR(PTR) " 2b,8b\n" + STR(PTR) " 3b,8b\n" + STR(PTR) " 4b,8b\n" + STR(PTR) " 5b,8b\n" + STR(PTR) " 6b,8b\n" + STR(PTR) " 7b,8b\n" + STR(PTR) " 0b,8b\n" " .previous\n" " .set pop\n" : "+&r"(rt), "=&r"(rs), @@ -1820,14 +1821,14 @@ fpu_emul: " j 9b\n" " .previous\n" " .section __ex_table,\"a\"\n" - " .word 1b,8b\n" - " .word 2b,8b\n" - " .word 3b,8b\n" - " .word 4b,8b\n" - " .word 5b,8b\n" - " .word 6b,8b\n" - " .word 7b,8b\n" - " .word 0b,8b\n" + STR(PTR) " 1b,8b\n" + STR(PTR) " 2b,8b\n" + STR(PTR) " 3b,8b\n" + STR(PTR) " 4b,8b\n" + STR(PTR) " 5b,8b\n" + STR(PTR) " 6b,8b\n" + STR(PTR) " 7b,8b\n" + STR(PTR) " 0b,8b\n" " .previous\n" " .set pop\n" : "+&r"(rt), "=&r"(rs), @@ -1938,14 +1939,14 @@ fpu_emul: " j 9b\n" " .previous\n" " .section __ex_table,\"a\"\n" - " .word 1b,8b\n" - " .word 2b,8b\n" - " .word 3b,8b\n" - " .word 4b,8b\n" - " .word 5b,8b\n" - " .word 6b,8b\n" - " .word 7b,8b\n" - " .word 0b,8b\n" + STR(PTR) " 1b,8b\n" + STR(PTR) " 2b,8b\n" + STR(PTR) " 3b,8b\n" + STR(PTR) " 4b,8b\n" + STR(PTR) " 5b,8b\n" + STR(PTR) " 6b,8b\n" + STR(PTR) " 7b,8b\n" + STR(PTR) " 0b,8b\n" " .previous\n" " .set pop\n" : "+&r"(rt), "=&r"(rs), @@ -2000,7 +2001,7 @@ fpu_emul: "j 2b\n" ".previous\n" ".section __ex_table,\"a\"\n" - ".word 1b, 3b\n" + STR(PTR) " 1b,3b\n" ".previous\n" : "=&r"(res), "+&r"(err) : "r"(vaddr), "i"(SIGSEGV) @@ -2058,7 +2059,7 @@ fpu_emul: "j 2b\n" ".previous\n" ".section __ex_table,\"a\"\n" - ".word 1b, 3b\n" + STR(PTR) " 1b,3b\n" ".previous\n" : "+&r"(res), "+&r"(err) : "r"(vaddr), "i"(SIGSEGV)); @@ -2119,7 +2120,7 @@ fpu_emul: "j 2b\n" ".previous\n" ".section __ex_table,\"a\"\n" - ".word 1b, 3b\n" + STR(PTR) " 1b,3b\n" ".previous\n" : "=&r"(res), "+&r"(err) : "r"(vaddr), "i"(SIGSEGV) @@ -2182,7 +2183,7 @@ fpu_emul: "j 2b\n" ".previous\n" ".section __ex_table,\"a\"\n" - ".word 1b, 3b\n" + STR(PTR) " 1b,3b\n" ".previous\n" : "+&r"(res), "+&r"(err) : "r"(vaddr), "i"(SIGSEGV)); diff --git a/arch/mips/kernel/pm.c b/arch/mips/kernel/pm.c index fefdf39d3df3..dc814892133c 100644 --- a/arch/mips/kernel/pm.c +++ b/arch/mips/kernel/pm.c @@ -56,7 +56,7 @@ static void mips_cpu_restore(void) write_c0_userlocal(current_thread_info()->tp_value); /* Restore watch registers */ - __restore_watch(); + __restore_watch(current); } /** diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index f2975d4d1e44..89847bee2b53 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -457,7 +457,7 @@ unsigned long notrace unwind_stack_by_address(unsigned long stack_page, *sp + sizeof(*regs) <= stack_page + THREAD_SIZE - 32) { regs = (struct pt_regs *)*sp; pc = regs->cp0_epc; - if (__kernel_text_address(pc)) { + if (!user_mode(regs) && __kernel_text_address(pc)) { *sp = regs->regs[29]; *ra = regs->regs[31]; return pc; @@ -603,6 +603,9 @@ int mips_set_process_fp_mode(struct task_struct *task, unsigned int value) if (!(value & PR_FP_MODE_FR) && cpu_has_fpu && cpu_has_mips_r6) return -EOPNOTSUPP; + /* Proceed with the mode switch */ + preempt_disable(); + /* Save FP & vector context, then disable FPU & MSA */ if (task->signal == current->signal) lose_fpu(1); @@ -661,6 +664,7 @@ int mips_set_process_fp_mode(struct task_struct *task, unsigned int value) /* Allow threads to use FP again */ atomic_set(&task->mm->context.fp_mode_switching, 0); + preempt_enable(); return 0; } diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c index 4f0ac78d17f1..74d581569778 100644 --- a/arch/mips/kernel/ptrace.c +++ b/arch/mips/kernel/ptrace.c @@ -57,8 +57,7 @@ static void init_fp_ctx(struct task_struct *target) /* Begin with data registers set to all 1s... */ memset(&target->thread.fpu.fpr, ~0, sizeof(target->thread.fpu.fpr)); - /* ...and FCSR zeroed */ - target->thread.fpu.fcr31 = 0; + /* FCSR has been preset by `mips_set_personality_nan'. */ /* * Record that the target has "used" math, such that the context @@ -79,6 +78,22 @@ void ptrace_disable(struct task_struct *child) clear_tsk_thread_flag(child, TIF_LOAD_WATCH); } +/* + * Poke at FCSR according to its mask. Don't set the cause bits as + * this is currently not handled correctly in FP context restoration + * and will cause an oops if a corresponding enable bit is set. + */ +static void ptrace_setfcr31(struct task_struct *child, u32 value) +{ + u32 fcr31; + u32 mask; + + value &= ~FPU_CSR_ALL_X; + fcr31 = child->thread.fpu.fcr31; + mask = boot_cpu_data.fpu_msk31; + child->thread.fpu.fcr31 = (value & ~mask) | (fcr31 & mask); +} + /* * Read a general register set. We always use the 64-bit format, even * for 32-bit kernels and for 32-bit processes on a 64-bit kernel. @@ -159,9 +174,7 @@ int ptrace_setfpregs(struct task_struct *child, __u32 __user *data) { union fpureg *fregs; u64 fpr_val; - u32 fcr31; u32 value; - u32 mask; int i; if (!access_ok(VERIFY_READ, data, 33 * 8)) @@ -176,9 +189,7 @@ int ptrace_setfpregs(struct task_struct *child, __u32 __user *data) } __get_user(value, data + 64); - fcr31 = child->thread.fpu.fcr31; - mask = boot_cpu_data.fpu_msk31; - child->thread.fpu.fcr31 = (value & ~mask) | (fcr31 & mask); + ptrace_setfcr31(child, value); /* FIR may not be written. */ @@ -808,7 +819,7 @@ long arch_ptrace(struct task_struct *child, long request, break; #endif case FPC_CSR: - child->thread.fpu.fcr31 = data & ~FPU_CSR_ALL_X; + ptrace_setfcr31(child, data); break; case DSP_BASE ... DSP_BASE + 5: { dspreg_t *dregs; diff --git a/arch/mips/kernel/r4k_fpu.S b/arch/mips/kernel/r4k_fpu.S index f09546ee2cdc..bc74485ec805 100644 --- a/arch/mips/kernel/r4k_fpu.S +++ b/arch/mips/kernel/r4k_fpu.S @@ -244,17 +244,17 @@ LEAF(\name) .set push .set noat #ifdef CONFIG_64BIT - copy_u_d \wr, 1 + copy_s_d \wr, 1 EX sd $1, \off(\base) #elif defined(CONFIG_CPU_LITTLE_ENDIAN) - copy_u_w \wr, 2 + copy_s_w \wr, 2 EX sw $1, \off(\base) - copy_u_w \wr, 3 + copy_s_w \wr, 3 EX sw $1, (\off+4)(\base) #else /* CONFIG_CPU_BIG_ENDIAN */ - copy_u_w \wr, 2 + copy_s_w \wr, 2 EX sw $1, (\off+4)(\base) - copy_u_w \wr, 3 + copy_s_w \wr, 3 EX sw $1, \off(\base) #endif .set pop diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 66aac55df349..8acae316f26b 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -706,6 +706,9 @@ static void __init arch_mem_init(char **cmdline_p) for_each_memblock(reserved, reg) if (reg->size != 0) reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT); + + reserve_bootmem_region(__pa_symbol(&__nosave_begin), + __pa_symbol(&__nosave_end)); /* Reserve for hibernation */ } static void __init resource_init(void) diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c index bf792e2839a6..9e35b6b26aa8 100644 --- a/arch/mips/kernel/signal.c +++ b/arch/mips/kernel/signal.c @@ -195,6 +195,9 @@ static int restore_msa_extcontext(void __user *buf, unsigned int size) unsigned int csr; int i, err; + if (!config_enabled(CONFIG_CPU_HAS_MSA)) + return SIGSYS; + if (size != sizeof(*msa)) return -EINVAL; @@ -398,8 +401,8 @@ int protected_restore_fp_context(void __user *sc) } fp_done: - if (used & USED_EXTCONTEXT) - err |= restore_extcontext(sc_to_extcontext(sc)); + if (!err && (used & USED_EXTCONTEXT)) + err = restore_extcontext(sc_to_extcontext(sc)); return err ?: sig; } @@ -767,15 +770,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) sigset_t *oldset = sigmask_to_save(); int ret; struct mips_abi *abi = current->thread.abi; -#ifdef CONFIG_CPU_MICROMIPS - void *vdso; - unsigned long tmp = (unsigned long)current->mm->context.vdso; - - set_isa16_mode(tmp); - vdso = (void *)tmp; -#else void *vdso = current->mm->context.vdso; -#endif if (regs->regs[0]) { switch(regs->regs[2]) { diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index bd4385a8e6e8..2b521e07b860 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -121,6 +121,7 @@ static inline void calculate_cpu_foreign_map(void) cpumask_t temp_foreign_map; /* Re-calculate the mask */ + cpumask_clear(&temp_foreign_map); for_each_online_cpu(i) { core_present = 0; for_each_cpu(k, &temp_foreign_map) diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 886cb1976e90..99a402231f4d 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -144,7 +144,7 @@ static void show_backtrace(struct task_struct *task, const struct pt_regs *regs) if (!task) task = current; - if (raw_show_trace || !__kernel_text_address(pc)) { + if (raw_show_trace || user_mode(regs) || !__kernel_text_address(pc)) { show_raw_backtrace(sp); return; } @@ -690,15 +690,15 @@ static int simulate_sync(struct pt_regs *regs, unsigned int opcode) asmlinkage void do_ov(struct pt_regs *regs) { enum ctx_state prev_state; - siginfo_t info; + siginfo_t info = { + .si_signo = SIGFPE, + .si_code = FPE_INTOVF, + .si_addr = (void __user *)regs->cp0_epc, + }; prev_state = exception_enter(); die_if_kernel("Integer overflow", regs); - info.si_code = FPE_INTOVF; - info.si_signo = SIGFPE; - info.si_errno = 0; - info.si_addr = (void __user *) regs->cp0_epc; force_sig_info(SIGFPE, &info, current); exception_exit(prev_state); } @@ -874,7 +874,7 @@ out: void do_trap_or_bp(struct pt_regs *regs, unsigned int code, const char *str) { - siginfo_t info; + siginfo_t info = { 0 }; char b[40]; #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP @@ -903,7 +903,6 @@ void do_trap_or_bp(struct pt_regs *regs, unsigned int code, else info.si_code = FPE_INTOVF; info.si_signo = SIGFPE; - info.si_errno = 0; info.si_addr = (void __user *) regs->cp0_epc; force_sig_info(SIGFPE, &info, current); break; @@ -1242,7 +1241,7 @@ static int enable_restore_fp_context(int msa) err = init_fpu(); if (msa && !err) { enable_msa(); - _init_msa_upper(); + init_msa_upper(); set_thread_flag(TIF_USEDMSA); set_thread_flag(TIF_MSA_CTX_LIVE); } @@ -1305,7 +1304,7 @@ static int enable_restore_fp_context(int msa) */ prior_msa = test_and_set_thread_flag(TIF_MSA_CTX_LIVE); if (!prior_msa && was_fpu_owner) { - _init_msa_upper(); + init_msa_upper(); goto out; } @@ -1322,7 +1321,7 @@ static int enable_restore_fp_context(int msa) * of each vector register such that it cannot see data left * behind by another task. */ - _init_msa_upper(); + init_msa_upper(); } else { /* We need to restore the vector context. */ restore_msa(current); diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c index 490cea569d57..5c62065cbf22 100644 --- a/arch/mips/kernel/unaligned.c +++ b/arch/mips/kernel/unaligned.c @@ -885,7 +885,7 @@ static void emulate_load_store_insn(struct pt_regs *regs, { union mips_instruction insn; unsigned long value; - unsigned int res; + unsigned int res, preempted; unsigned long origpc; unsigned long orig31; void __user *fault_addr = NULL; @@ -1226,27 +1226,36 @@ static void emulate_load_store_insn(struct pt_regs *regs, if (!access_ok(VERIFY_READ, addr, sizeof(*fpr))) goto sigbus; - /* - * Disable preemption to avoid a race between copying - * state from userland, migrating to another CPU and - * updating the hardware vector register below. - */ - preempt_disable(); + do { + /* + * If we have live MSA context keep track of + * whether we get preempted in order to avoid + * the register context we load being clobbered + * by the live context as it's saved during + * preemption. If we don't have live context + * then it can't be saved to clobber the value + * we load. + */ + preempted = test_thread_flag(TIF_USEDMSA); - res = __copy_from_user_inatomic(fpr, addr, - sizeof(*fpr)); - if (res) - goto fault; + res = __copy_from_user_inatomic(fpr, addr, + sizeof(*fpr)); + if (res) + goto fault; - /* - * Update the hardware register if it is in use by the - * task in this quantum, in order to avoid having to - * save & restore the whole vector context. - */ - if (test_thread_flag(TIF_USEDMSA)) - write_msa_wr(wd, fpr, df); - - preempt_enable(); + /* + * Update the hardware register if it is in use + * by the task in this quantum, in order to + * avoid having to save & restore the whole + * vector context. + */ + preempt_disable(); + if (test_thread_flag(TIF_USEDMSA)) { + write_msa_wr(wd, fpr, df); + preempted = 0; + } + preempt_enable(); + } while (preempted); break; case msa_st_op: diff --git a/arch/mips/kernel/watch.c b/arch/mips/kernel/watch.c index 2a03abb5bd2c..9b78e375118e 100644 --- a/arch/mips/kernel/watch.c +++ b/arch/mips/kernel/watch.c @@ -15,10 +15,9 @@ * Install the watch registers for the current thread. A maximum of * four registers are installed although the machine may have more. */ -void mips_install_watch_registers(void) +void mips_install_watch_registers(struct task_struct *t) { - struct mips3264_watch_reg_state *watches = - ¤t->thread.watch.mips3264; + struct mips3264_watch_reg_state *watches = &t->thread.watch.mips3264; switch (current_cpu_data.watch_reg_use_cnt) { default: BUG(); diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c index 41b1b090f56f..dc10c77b7500 100644 --- a/arch/mips/kvm/emulate.c +++ b/arch/mips/kvm/emulate.c @@ -302,12 +302,31 @@ static inline ktime_t kvm_mips_count_time(struct kvm_vcpu *vcpu) */ static uint32_t kvm_mips_read_count_running(struct kvm_vcpu *vcpu, ktime_t now) { - ktime_t expires; + struct mips_coproc *cop0 = vcpu->arch.cop0; + ktime_t expires, threshold; + uint32_t count, compare; int running; - /* Is the hrtimer pending? */ + /* Calculate the biased and scaled guest CP0_Count */ + count = vcpu->arch.count_bias + kvm_mips_ktime_to_count(vcpu, now); + compare = kvm_read_c0_guest_compare(cop0); + + /* + * Find whether CP0_Count has reached the closest timer interrupt. If + * not, we shouldn't inject it. + */ + if ((int32_t)(count - compare) < 0) + return count; + + /* + * The CP0_Count we're going to return has already reached the closest + * timer interrupt. Quickly check if it really is a new interrupt by + * looking at whether the interval until the hrtimer expiry time is + * less than 1/4 of the timer period. + */ expires = hrtimer_get_expires(&vcpu->arch.comparecount_timer); - if (ktime_compare(now, expires) >= 0) { + threshold = ktime_add_ns(now, vcpu->arch.count_period / 4); + if (ktime_before(expires, threshold)) { /* * Cancel it while we handle it so there's no chance of * interference with the timeout handler. @@ -329,8 +348,7 @@ static uint32_t kvm_mips_read_count_running(struct kvm_vcpu *vcpu, ktime_t now) } } - /* Return the biased and scaled guest CP0_Count */ - return vcpu->arch.count_bias + kvm_mips_ktime_to_count(vcpu, now); + return count; } /** @@ -419,32 +437,6 @@ static void kvm_mips_resume_hrtimer(struct kvm_vcpu *vcpu, hrtimer_start(&vcpu->arch.comparecount_timer, expire, HRTIMER_MODE_ABS); } -/** - * kvm_mips_update_hrtimer() - Update next expiry time of hrtimer. - * @vcpu: Virtual CPU. - * - * Recalculates and updates the expiry time of the hrtimer. This can be used - * after timer parameters have been altered which do not depend on the time that - * the change occurs (in those cases kvm_mips_freeze_hrtimer() and - * kvm_mips_resume_hrtimer() are used directly). - * - * It is guaranteed that no timer interrupts will be lost in the process. - * - * Assumes !kvm_mips_count_disabled(@vcpu) (guest CP0_Count timer is running). - */ -static void kvm_mips_update_hrtimer(struct kvm_vcpu *vcpu) -{ - ktime_t now; - uint32_t count; - - /* - * freeze_hrtimer takes care of a timer interrupts <= count, and - * resume_hrtimer the hrtimer takes care of a timer interrupts > count. - */ - now = kvm_mips_freeze_hrtimer(vcpu, &count); - kvm_mips_resume_hrtimer(vcpu, now, count); -} - /** * kvm_mips_write_count() - Modify the count and update timer. * @vcpu: Virtual CPU. @@ -540,23 +532,42 @@ int kvm_mips_set_count_hz(struct kvm_vcpu *vcpu, s64 count_hz) * kvm_mips_write_compare() - Modify compare and update timer. * @vcpu: Virtual CPU. * @compare: New CP0_Compare value. + * @ack: Whether to acknowledge timer interrupt. * * Update CP0_Compare to a new value and update the timeout. + * If @ack, atomically acknowledge any pending timer interrupt, otherwise ensure + * any pending timer interrupt is preserved. */ -void kvm_mips_write_compare(struct kvm_vcpu *vcpu, uint32_t compare) +void kvm_mips_write_compare(struct kvm_vcpu *vcpu, uint32_t compare, bool ack) { struct mips_coproc *cop0 = vcpu->arch.cop0; + int dc; + u32 old_compare = kvm_read_c0_guest_compare(cop0); + ktime_t now; + uint32_t count; /* if unchanged, must just be an ack */ - if (kvm_read_c0_guest_compare(cop0) == compare) + if (old_compare == compare) { + if (!ack) + return; + kvm_mips_callbacks->dequeue_timer_int(vcpu); + kvm_write_c0_guest_compare(cop0, compare); return; + } + + /* freeze_hrtimer() takes care of timer interrupts <= count */ + dc = kvm_mips_count_disabled(vcpu); + if (!dc) + now = kvm_mips_freeze_hrtimer(vcpu, &count); + + if (ack) + kvm_mips_callbacks->dequeue_timer_int(vcpu); - /* Update compare */ kvm_write_c0_guest_compare(cop0, compare); - /* Update timeout if count enabled */ - if (!kvm_mips_count_disabled(vcpu)) - kvm_mips_update_hrtimer(vcpu); + /* resume_hrtimer() takes care of timer interrupts > count */ + if (!dc) + kvm_mips_resume_hrtimer(vcpu, now, count); } /** @@ -1095,9 +1106,9 @@ enum emulation_result kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc, /* If we are writing to COMPARE */ /* Clear pending timer interrupt, if any */ - kvm_mips_callbacks->dequeue_timer_int(vcpu); kvm_mips_write_compare(vcpu, - vcpu->arch.gprs[rt]); + vcpu->arch.gprs[rt], + true); } else if ((rd == MIPS_CP0_STATUS) && (sel == 0)) { unsigned int old_val, val, change; diff --git a/arch/mips/kvm/interrupt.h b/arch/mips/kvm/interrupt.h index 4ab4bdfad703..2143884709e4 100644 --- a/arch/mips/kvm/interrupt.h +++ b/arch/mips/kvm/interrupt.h @@ -28,6 +28,7 @@ #define MIPS_EXC_MAX 12 /* XXXSL More to follow */ +extern char __kvm_mips_vcpu_run_end[]; extern char mips32_exception[], mips32_exceptionEnd[]; extern char mips32_GuestException[], mips32_GuestExceptionEnd[]; diff --git a/arch/mips/kvm/locore.S b/arch/mips/kvm/locore.S index 7e2210846b8b..77706433651b 100644 --- a/arch/mips/kvm/locore.S +++ b/arch/mips/kvm/locore.S @@ -227,6 +227,7 @@ FEXPORT(__kvm_mips_load_k0k1) /* Jump to guest */ eret +EXPORT(__kvm_mips_vcpu_run_end) VECTOR(MIPSX(exception), unknown) /* Find out what mode we came from and jump to the proper handler. */ diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index b9b803facdbf..e86b7499921a 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -314,6 +314,15 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id) memcpy(gebase + offset, mips32_GuestException, mips32_GuestExceptionEnd - mips32_GuestException); +#ifdef MODULE + offset += mips32_GuestExceptionEnd - mips32_GuestException; + memcpy(gebase + offset, (char *)__kvm_mips_vcpu_run, + __kvm_mips_vcpu_run_end - (char *)__kvm_mips_vcpu_run); + vcpu->arch.vcpu_run = gebase + offset; +#else + vcpu->arch.vcpu_run = __kvm_mips_vcpu_run; +#endif + /* Invalidate the icache for these ranges */ local_flush_icache_range((unsigned long)gebase, (unsigned long)gebase + ALIGN(size, PAGE_SIZE)); @@ -403,7 +412,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) /* Disable hardware page table walking while in guest */ htw_stop(); - r = __kvm_mips_vcpu_run(run, vcpu); + r = vcpu->arch.vcpu_run(run, vcpu); /* Re-enable HTW before enabling interrupts */ htw_start(); @@ -702,7 +711,7 @@ static int kvm_mips_get_reg(struct kvm_vcpu *vcpu, } else if ((reg->id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U128) { void __user *uaddr = (void __user *)(long)reg->addr; - return copy_to_user(uaddr, vs, 16); + return copy_to_user(uaddr, vs, 16) ? -EFAULT : 0; } else { return -EINVAL; } @@ -732,7 +741,7 @@ static int kvm_mips_set_reg(struct kvm_vcpu *vcpu, } else if ((reg->id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U128) { void __user *uaddr = (void __user *)(long)reg->addr; - return copy_from_user(vs, uaddr, 16); + return copy_from_user(vs, uaddr, 16) ? -EFAULT : 0; } else { return -EINVAL; } diff --git a/arch/mips/kvm/trap_emul.c b/arch/mips/kvm/trap_emul.c index d836ed5b0bc7..307cc4c98bdd 100644 --- a/arch/mips/kvm/trap_emul.c +++ b/arch/mips/kvm/trap_emul.c @@ -547,7 +547,7 @@ static int kvm_trap_emul_set_one_reg(struct kvm_vcpu *vcpu, kvm_mips_write_count(vcpu, v); break; case KVM_REG_MIPS_CP0_COMPARE: - kvm_mips_write_compare(vcpu, v); + kvm_mips_write_compare(vcpu, v, false); break; case KVM_REG_MIPS_CP0_CAUSE: /* diff --git a/arch/mips/lib/ashldi3.c b/arch/mips/lib/ashldi3.c index beb80f316095..927dc94a030f 100644 --- a/arch/mips/lib/ashldi3.c +++ b/arch/mips/lib/ashldi3.c @@ -2,7 +2,7 @@ #include "libgcc.h" -long long __ashldi3(long long u, word_type b) +long long notrace __ashldi3(long long u, word_type b) { DWunion uu, w; word_type bm; diff --git a/arch/mips/lib/ashrdi3.c b/arch/mips/lib/ashrdi3.c index c884a912b660..9fdf1a598428 100644 --- a/arch/mips/lib/ashrdi3.c +++ b/arch/mips/lib/ashrdi3.c @@ -2,7 +2,7 @@ #include "libgcc.h" -long long __ashrdi3(long long u, word_type b) +long long notrace __ashrdi3(long long u, word_type b) { DWunion uu, w; word_type bm; diff --git a/arch/mips/lib/bswapdi.c b/arch/mips/lib/bswapdi.c index 77e5f9c1f005..e3e77aa52c95 100644 --- a/arch/mips/lib/bswapdi.c +++ b/arch/mips/lib/bswapdi.c @@ -1,6 +1,6 @@ #include -unsigned long long __bswapdi2(unsigned long long u) +unsigned long long notrace __bswapdi2(unsigned long long u) { return (((u) & 0xff00000000000000ull) >> 56) | (((u) & 0x00ff000000000000ull) >> 40) | diff --git a/arch/mips/lib/bswapsi.c b/arch/mips/lib/bswapsi.c index 2b302ff121d2..530a8afe6fda 100644 --- a/arch/mips/lib/bswapsi.c +++ b/arch/mips/lib/bswapsi.c @@ -1,6 +1,6 @@ #include -unsigned int __bswapsi2(unsigned int u) +unsigned int notrace __bswapsi2(unsigned int u) { return (((u) & 0xff000000) >> 24) | (((u) & 0x00ff0000) >> 8) | diff --git a/arch/mips/lib/cmpdi2.c b/arch/mips/lib/cmpdi2.c index 8c1306437ed1..06857da96993 100644 --- a/arch/mips/lib/cmpdi2.c +++ b/arch/mips/lib/cmpdi2.c @@ -2,7 +2,7 @@ #include "libgcc.h" -word_type __cmpdi2(long long a, long long b) +word_type notrace __cmpdi2(long long a, long long b) { const DWunion au = { .ll = a diff --git a/arch/mips/lib/lshrdi3.c b/arch/mips/lib/lshrdi3.c index dcf8d6810b7c..364547449c65 100644 --- a/arch/mips/lib/lshrdi3.c +++ b/arch/mips/lib/lshrdi3.c @@ -2,7 +2,7 @@ #include "libgcc.h" -long long __lshrdi3(long long u, word_type b) +long long notrace __lshrdi3(long long u, word_type b) { DWunion uu, w; word_type bm; diff --git a/arch/mips/lib/ucmpdi2.c b/arch/mips/lib/ucmpdi2.c index bb4cb2f828ea..bd599f58234c 100644 --- a/arch/mips/lib/ucmpdi2.c +++ b/arch/mips/lib/ucmpdi2.c @@ -2,7 +2,7 @@ #include "libgcc.h" -word_type __ucmpdi2(unsigned long long a, unsigned long long b) +word_type notrace __ucmpdi2(unsigned long long a, unsigned long long b) { const DWunion au = {.ll = a}; const DWunion bu = {.ll = b}; diff --git a/arch/mips/loongson64/loongson-3/hpet.c b/arch/mips/loongson64/loongson-3/hpet.c index bf9f1a77f0e5..a2631a52ca99 100644 --- a/arch/mips/loongson64/loongson-3/hpet.c +++ b/arch/mips/loongson64/loongson-3/hpet.c @@ -13,6 +13,9 @@ #define SMBUS_PCI_REG64 0x64 #define SMBUS_PCI_REGB4 0xb4 +#define HPET_MIN_CYCLES 64 +#define HPET_MIN_PROG_DELTA (HPET_MIN_CYCLES + (HPET_MIN_CYCLES >> 1)) + static DEFINE_SPINLOCK(hpet_lock); DEFINE_PER_CPU(struct clock_event_device, hpet_clockevent_device); @@ -161,8 +164,9 @@ static int hpet_next_event(unsigned long delta, cnt += delta; hpet_write(HPET_T0_CMP, cnt); - res = ((int)(hpet_read(HPET_COUNTER) - cnt) > 0) ? -ETIME : 0; - return res; + res = (int)(cnt - hpet_read(HPET_COUNTER)); + + return res < HPET_MIN_CYCLES ? -ETIME : 0; } static irqreturn_t hpet_irq_handler(int irq, void *data) @@ -237,7 +241,7 @@ void __init setup_hpet_timer(void) cd->cpumask = cpumask_of(cpu); clockevent_set_clock(cd, HPET_FREQ); cd->max_delta_ns = clockevent_delta2ns(0x7fffffff, cd); - cd->min_delta_ns = 5000; + cd->min_delta_ns = clockevent_delta2ns(HPET_MIN_PROG_DELTA, cd); clockevents_register_device(cd); setup_irq(HPET_T0_IRQ, &hpet_irq); diff --git a/arch/mips/loongson64/loongson-3/numa.c b/arch/mips/loongson64/loongson-3/numa.c index 6f9e010cec4d..282c5a8c2fcd 100644 --- a/arch/mips/loongson64/loongson-3/numa.c +++ b/arch/mips/loongson64/loongson-3/numa.c @@ -213,10 +213,10 @@ static void __init node_mem_init(unsigned int node) BOOTMEM_DEFAULT); if (node == 0 && node_end_pfn(0) >= (0xffffffff >> PAGE_SHIFT)) { - /* Reserve 0xff800000~0xffffffff for RS780E integrated GPU */ + /* Reserve 0xfe000000~0xffffffff for RS780E integrated GPU */ reserve_bootmem_node(NODE_DATA(node), - (node_addrspace_offset | 0xff800000), - 8 << 20, BOOTMEM_DEFAULT); + (node_addrspace_offset | 0xfe000000), + 32 << 20, BOOTMEM_DEFAULT); } sparse_memory_present_with_active_regions(node); diff --git a/arch/mips/loongson64/loongson-3/smp.c b/arch/mips/loongson64/loongson-3/smp.c index 1a4738a8f2d3..509832a9836c 100644 --- a/arch/mips/loongson64/loongson-3/smp.c +++ b/arch/mips/loongson64/loongson-3/smp.c @@ -30,13 +30,13 @@ #include "smp.h" DEFINE_PER_CPU(int, cpu_state); -DEFINE_PER_CPU(uint32_t, core0_c0count); static void *ipi_set0_regs[16]; static void *ipi_clear0_regs[16]; static void *ipi_status0_regs[16]; static void *ipi_en0_regs[16]; static void *ipi_mailbox_buf[16]; +static uint32_t core0_c0count[NR_CPUS]; /* read a 32bit value from ipi register */ #define loongson3_ipi_read32(addr) readl(addr) @@ -275,12 +275,14 @@ void loongson3_ipi_interrupt(struct pt_regs *regs) if (action & SMP_ASK_C0COUNT) { BUG_ON(cpu != 0); c0count = read_c0_count(); - for (i = 1; i < num_possible_cpus(); i++) - per_cpu(core0_c0count, i) = c0count; + c0count = c0count ? c0count : 1; + for (i = 1; i < nr_cpu_ids; i++) + core0_c0count[i] = c0count; + __wbflush(); /* Let others see the result ASAP */ } } -#define MAX_LOOPS 1111 +#define MAX_LOOPS 800 /* * SMP init and finish on secondary CPUs */ @@ -305,16 +307,20 @@ static void loongson3_init_secondary(void) cpu_logical_map(cpu) / loongson_sysconf.cores_per_package; i = 0; - __this_cpu_write(core0_c0count, 0); + core0_c0count[cpu] = 0; loongson3_send_ipi_single(0, SMP_ASK_C0COUNT); - while (!__this_cpu_read(core0_c0count)) { + while (!core0_c0count[cpu]) { i++; cpu_relax(); } if (i > MAX_LOOPS) i = MAX_LOOPS; - initcount = __this_cpu_read(core0_c0count) + i; + if (cpu_data[cpu].package) + initcount = core0_c0count[cpu] + i; + else /* Local access is faster for loops */ + initcount = core0_c0count[cpu] + i/2; + write_c0_count(initcount); } diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c index 32f0e19a0d7f..734a2c7665ec 100644 --- a/arch/mips/math-emu/cp1emu.c +++ b/arch/mips/math-emu/cp1emu.c @@ -445,9 +445,11 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, case spec_op: switch (insn.r_format.func) { case jalr_op: - regs->regs[insn.r_format.rd] = - regs->cp0_epc + dec_insn.pc_inc + - dec_insn.next_pc_inc; + if (insn.r_format.rd != 0) { + regs->regs[insn.r_format.rd] = + regs->cp0_epc + dec_insn.pc_inc + + dec_insn.next_pc_inc; + } /* Fall through */ case jr_op: /* For R6, JR already emulated in jalr_op */ diff --git a/arch/mips/mm/cache.c b/arch/mips/mm/cache.c index aab218c36e0d..e87bccd6e0aa 100644 --- a/arch/mips/mm/cache.c +++ b/arch/mips/mm/cache.c @@ -16,6 +16,7 @@ #include #include +#include #include #include #include @@ -83,8 +84,6 @@ void __flush_dcache_page(struct page *page) struct address_space *mapping = page_mapping(page); unsigned long addr; - if (PageHighMem(page)) - return; if (mapping && !mapping_mapped(mapping)) { SetPageDcacheDirty(page); return; @@ -95,8 +94,15 @@ void __flush_dcache_page(struct page *page) * case is for exec env/arg pages and those are %99 certainly going to * get faulted into the tlb (and thus flushed) anyways. */ - addr = (unsigned long) page_address(page); + if (PageHighMem(page)) + addr = (unsigned long)kmap_atomic(page); + else + addr = (unsigned long)page_address(page); + flush_data_cache_page(addr); + + if (PageHighMem(page)) + __kunmap_atomic((void *)addr); } EXPORT_SYMBOL(__flush_dcache_page); @@ -119,33 +125,28 @@ void __flush_anon_page(struct page *page, unsigned long vmaddr) EXPORT_SYMBOL(__flush_anon_page); -void __flush_icache_page(struct vm_area_struct *vma, struct page *page) -{ - unsigned long addr; - - if (PageHighMem(page)) - return; - - addr = (unsigned long) page_address(page); - flush_data_cache_page(addr); -} -EXPORT_SYMBOL_GPL(__flush_icache_page); - -void __update_cache(struct vm_area_struct *vma, unsigned long address, - pte_t pte) +void __update_cache(unsigned long address, pte_t pte) { struct page *page; unsigned long pfn, addr; - int exec = (vma->vm_flags & VM_EXEC) && !cpu_has_ic_fills_f_dc; + int exec = !pte_no_exec(pte) && !cpu_has_ic_fills_f_dc; pfn = pte_pfn(pte); if (unlikely(!pfn_valid(pfn))) return; page = pfn_to_page(pfn); - if (page_mapping(page) && Page_dcache_dirty(page)) { - addr = (unsigned long) page_address(page); + if (Page_dcache_dirty(page)) { + if (PageHighMem(page)) + addr = (unsigned long)kmap_atomic(page); + else + addr = (unsigned long)page_address(page); + if (exec || pages_do_alias(addr, address & PAGE_MASK)) flush_data_cache_page(addr); + + if (PageHighMem(page)) + __kunmap_atomic((void *)addr); + ClearPageDcacheDirty(page); } } diff --git a/arch/mips/mm/sc-mips.c b/arch/mips/mm/sc-mips.c index 3bd0597d9c3d..ddb8154610cc 100644 --- a/arch/mips/mm/sc-mips.c +++ b/arch/mips/mm/sc-mips.c @@ -164,11 +164,13 @@ static int __init mips_sc_probe_cm3(void) sets = cfg & CM_GCR_L2_CONFIG_SET_SIZE_MSK; sets >>= CM_GCR_L2_CONFIG_SET_SIZE_SHF; - c->scache.sets = 64 << sets; + if (sets) + c->scache.sets = 64 << sets; line_sz = cfg & CM_GCR_L2_CONFIG_LINE_SIZE_MSK; line_sz >>= CM_GCR_L2_CONFIG_LINE_SIZE_SHF; - c->scache.linesz = 2 << line_sz; + if (line_sz) + c->scache.linesz = 2 << line_sz; assoc = cfg & CM_GCR_L2_CONFIG_ASSOC_MSK; assoc >>= CM_GCR_L2_CONFIG_ASSOC_SHF; @@ -176,9 +178,12 @@ static int __init mips_sc_probe_cm3(void) c->scache.waysize = c->scache.sets * c->scache.linesz; c->scache.waybit = __ffs(c->scache.waysize); - c->scache.flags &= ~MIPS_CACHE_NOT_PRESENT; + if (c->scache.linesz) { + c->scache.flags &= ~MIPS_CACHE_NOT_PRESENT; + return 1; + } - return 1; + return 0; } void __weak platform_early_l2_init(void) diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index 32e0be27673f..29f73e00253d 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -242,7 +242,7 @@ static void output_pgtable_bits_defines(void) pr_define("_PAGE_HUGE_SHIFT %d\n", _PAGE_HUGE_SHIFT); pr_define("_PAGE_SPLITTING_SHIFT %d\n", _PAGE_SPLITTING_SHIFT); #endif -#ifdef CONFIG_CPU_MIPSR2 +#if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6) if (cpu_has_rixi) { #ifdef _PAGE_NO_EXEC_SHIFT pr_define("_PAGE_NO_EXEC_SHIFT %d\n", _PAGE_NO_EXEC_SHIFT); diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile index 14568900fc1d..090393aa0f20 100644 --- a/arch/mips/vdso/Makefile +++ b/arch/mips/vdso/Makefile @@ -5,10 +5,12 @@ obj-vdso-y := elf.o gettimeofday.o sigreturn.o ccflags-vdso := \ $(filter -I%,$(KBUILD_CFLAGS)) \ $(filter -E%,$(KBUILD_CFLAGS)) \ + $(filter -mmicromips,$(KBUILD_CFLAGS)) \ $(filter -march=%,$(KBUILD_CFLAGS)) cflags-vdso := $(ccflags-vdso) \ $(filter -W%,$(filter-out -Wa$(comma)%,$(KBUILD_CFLAGS))) \ - -O2 -g -fPIC -fno-common -fno-builtin -G 0 -DDISABLE_BRANCH_PROFILING \ + -O2 -g -fPIC -fno-strict-aliasing -fno-common -fno-builtin -G 0 \ + -DDISABLE_BRANCH_PROFILING \ $(call cc-option, -fno-stack-protector) aflags-vdso := $(ccflags-vdso) \ $(filter -I%,$(KBUILD_CFLAGS)) \ diff --git a/arch/parisc/include/asm/hugetlb.h b/arch/parisc/include/asm/hugetlb.h index 7d56a9ccb752..a65d888716c4 100644 --- a/arch/parisc/include/asm/hugetlb.h +++ b/arch/parisc/include/asm/hugetlb.h @@ -54,24 +54,12 @@ static inline pte_t huge_pte_wrprotect(pte_t pte) return pte_wrprotect(pte); } -static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, - unsigned long addr, pte_t *ptep) -{ - pte_t old_pte = *ptep; - set_huge_pte_at(mm, addr, ptep, pte_wrprotect(old_pte)); -} +void huge_ptep_set_wrprotect(struct mm_struct *mm, + unsigned long addr, pte_t *ptep); -static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, +int huge_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, - pte_t pte, int dirty) -{ - int changed = !pte_same(*ptep, pte); - if (changed) { - set_huge_pte_at(vma->vm_mm, addr, ptep, pte); - flush_tlb_page(vma, addr); - } - return changed; -} + pte_t pte, int dirty); static inline pte_t huge_ptep_get(pte_t *ptep) { diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h index 0abdd4c607ed..1960b87c1c8b 100644 --- a/arch/parisc/include/asm/uaccess.h +++ b/arch/parisc/include/asm/uaccess.h @@ -76,6 +76,7 @@ struct exception_table_entry { */ struct exception_data { unsigned long fault_ip; + unsigned long fault_gp; unsigned long fault_space; unsigned long fault_addr; }; diff --git a/arch/parisc/include/uapi/asm/siginfo.h b/arch/parisc/include/uapi/asm/siginfo.h index d7034728f377..1c75565d984b 100644 --- a/arch/parisc/include/uapi/asm/siginfo.h +++ b/arch/parisc/include/uapi/asm/siginfo.h @@ -1,6 +1,10 @@ #ifndef _PARISC_SIGINFO_H #define _PARISC_SIGINFO_H +#if defined(__LP64__) +#define __ARCH_SI_PREAMBLE_SIZE (4 * sizeof(int)) +#endif + #include #undef NSIGTRAP diff --git a/arch/parisc/kernel/asm-offsets.c b/arch/parisc/kernel/asm-offsets.c index d2f62570a7b1..78d30d2ea2d8 100644 --- a/arch/parisc/kernel/asm-offsets.c +++ b/arch/parisc/kernel/asm-offsets.c @@ -299,6 +299,7 @@ int main(void) #endif BLANK(); DEFINE(EXCDATA_IP, offsetof(struct exception_data, fault_ip)); + DEFINE(EXCDATA_GP, offsetof(struct exception_data, fault_gp)); DEFINE(EXCDATA_SPACE, offsetof(struct exception_data, fault_space)); DEFINE(EXCDATA_ADDR, offsetof(struct exception_data, fault_addr)); BLANK(); diff --git a/arch/parisc/kernel/parisc_ksyms.c b/arch/parisc/kernel/parisc_ksyms.c index 568b2c61ea02..3cad8aadc69e 100644 --- a/arch/parisc/kernel/parisc_ksyms.c +++ b/arch/parisc/kernel/parisc_ksyms.c @@ -47,11 +47,11 @@ EXPORT_SYMBOL(__cmpxchg_u64); EXPORT_SYMBOL(lclear_user); EXPORT_SYMBOL(lstrnlen_user); -/* Global fixups */ -extern void fixup_get_user_skip_1(void); -extern void fixup_get_user_skip_2(void); -extern void fixup_put_user_skip_1(void); -extern void fixup_put_user_skip_2(void); +/* Global fixups - defined as int to avoid creation of function pointers */ +extern int fixup_get_user_skip_1; +extern int fixup_get_user_skip_2; +extern int fixup_put_user_skip_1; +extern int fixup_put_user_skip_2; EXPORT_SYMBOL(fixup_get_user_skip_1); EXPORT_SYMBOL(fixup_get_user_skip_2); EXPORT_SYMBOL(fixup_put_user_skip_1); diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c index 9585c81f755f..ce0b2b4075c7 100644 --- a/arch/parisc/kernel/ptrace.c +++ b/arch/parisc/kernel/ptrace.c @@ -269,14 +269,19 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, long do_syscall_trace_enter(struct pt_regs *regs) { - long ret = 0; - /* Do the secure computing check first. */ secure_computing_strict(regs->gr[20]); if (test_thread_flag(TIF_SYSCALL_TRACE) && - tracehook_report_syscall_entry(regs)) - ret = -1L; + tracehook_report_syscall_entry(regs)) { + /* + * Tracing decided this syscall should not happen or the + * debugger stored an invalid system call number. Skip + * the system call and the system call restart handling. + */ + regs->gr[20] = -1UL; + goto out; + } #ifdef CONFIG_64BIT if (!is_compat_task()) @@ -290,7 +295,8 @@ long do_syscall_trace_enter(struct pt_regs *regs) regs->gr[24] & 0xffffffff, regs->gr[23] & 0xffffffff); - return ret ? : regs->gr[20]; +out: + return regs->gr[20]; } void do_syscall_trace_exit(struct pt_regs *regs) diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S index 3fbd7252a4b2..fbafa0d0e2bf 100644 --- a/arch/parisc/kernel/syscall.S +++ b/arch/parisc/kernel/syscall.S @@ -343,7 +343,7 @@ tracesys_next: #endif comiclr,>>= __NR_Linux_syscalls, %r20, %r0 - b,n .Lsyscall_nosys + b,n .Ltracesys_nosys LDREGX %r20(%r19), %r19 @@ -359,6 +359,9 @@ tracesys_next: be 0(%sr7,%r19) ldo R%tracesys_exit(%r2),%r2 +.Ltracesys_nosys: + ldo -ENOSYS(%r0),%r28 /* set errno */ + /* Do *not* call this function on the gateway page, because it makes a direct call to syscall_trace. */ diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c index 553b09855cfd..77e2262c97f6 100644 --- a/arch/parisc/kernel/traps.c +++ b/arch/parisc/kernel/traps.c @@ -798,6 +798,9 @@ void notrace handle_interruption(int code, struct pt_regs *regs) if (fault_space == 0 && !faulthandler_disabled()) { + /* Clean up and return if in exception table. */ + if (fixup_exception(regs)) + return; pdc_chassis_send_status(PDC_CHASSIS_DIRECT_PANIC); parisc_terminate("Kernel Fault", regs, code, fault_address); } diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c index d7c0acb35ec2..8d49614d600d 100644 --- a/arch/parisc/kernel/unaligned.c +++ b/arch/parisc/kernel/unaligned.c @@ -666,7 +666,7 @@ void handle_unaligned(struct pt_regs *regs) break; } - if (modify && R1(regs->iir)) + if (ret == 0 && modify && R1(regs->iir)) regs->gr[R1(regs->iir)] = newbase; @@ -677,6 +677,14 @@ void handle_unaligned(struct pt_regs *regs) if (ret) { + /* + * The unaligned handler failed. + * If we were called by __get_user() or __put_user() jump + * to it's exception fixup handler instead of crashing. + */ + if (!user_mode(regs) && fixup_exception(regs)) + return; + printk(KERN_CRIT "Unaligned handler failed, ret = %d\n", ret); die_if_kernel("Unaligned data reference", regs, 28); diff --git a/arch/parisc/lib/fixup.S b/arch/parisc/lib/fixup.S index 536ef66bb94b..1052b747e011 100644 --- a/arch/parisc/lib/fixup.S +++ b/arch/parisc/lib/fixup.S @@ -26,6 +26,7 @@ #ifdef CONFIG_SMP .macro get_fault_ip t1 t2 + loadgp addil LT%__per_cpu_offset,%r27 LDREG RT%__per_cpu_offset(%r1),\t1 /* t2 = smp_processor_id() */ @@ -40,14 +41,19 @@ LDREG RT%exception_data(%r1),\t1 /* t1 = this_cpu_ptr(&exception_data) */ add,l \t1,\t2,\t1 + /* %r27 = t1->fault_gp - restore gp */ + LDREG EXCDATA_GP(\t1), %r27 /* t1 = t1->fault_ip */ LDREG EXCDATA_IP(\t1), \t1 .endm #else .macro get_fault_ip t1 t2 + loadgp /* t1 = this_cpu_ptr(&exception_data) */ addil LT%exception_data,%r27 LDREG RT%exception_data(%r1),\t2 + /* %r27 = t2->fault_gp - restore gp */ + LDREG EXCDATA_GP(\t2), %r27 /* t1 = t2->fault_ip */ LDREG EXCDATA_IP(\t2), \t1 .endm diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index a762864ec92e..f9064449908a 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -151,6 +151,7 @@ int fixup_exception(struct pt_regs *regs) struct exception_data *d; d = this_cpu_ptr(&exception_data); d->fault_ip = regs->iaoq[0]; + d->fault_gp = regs->gr[27]; d->fault_space = regs->isr; d->fault_addr = regs->ior; diff --git a/arch/parisc/mm/hugetlbpage.c b/arch/parisc/mm/hugetlbpage.c index f6fdc77a72bd..54ba39262b82 100644 --- a/arch/parisc/mm/hugetlbpage.c +++ b/arch/parisc/mm/hugetlbpage.c @@ -105,15 +105,13 @@ static inline void purge_tlb_entries_huge(struct mm_struct *mm, unsigned long ad addr |= _HUGE_PAGE_SIZE_ENCODING_DEFAULT; for (i = 0; i < (1 << (HPAGE_SHIFT-REAL_HPAGE_SHIFT)); i++) { - mtsp(mm->context, 1); - pdtlb(addr); - if (unlikely(split_tlb)) - pitlb(addr); + purge_tlb_entries(mm, addr); addr += (1UL << REAL_HPAGE_SHIFT); } } -void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, +/* __set_huge_pte_at() must be called holding the pa_tlb_lock. */ +static void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t entry) { unsigned long addr_start; @@ -123,14 +121,9 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, addr_start = addr; for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) { - /* Directly write pte entry. We could call set_pte_at(mm, addr, ptep, entry) - * instead, but then we get double locking on pa_tlb_lock. */ - *ptep = entry; + set_pte(ptep, entry); ptep++; - /* Drop the PAGE_SIZE/non-huge tlb entry */ - purge_tlb_entries(mm, addr); - addr += PAGE_SIZE; pte_val(entry) += PAGE_SIZE; } @@ -138,18 +131,61 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, purge_tlb_entries_huge(mm, addr_start); } +void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t entry) +{ + unsigned long flags; + + purge_tlb_start(flags); + __set_huge_pte_at(mm, addr, ptep, entry); + purge_tlb_end(flags); +} + pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { + unsigned long flags; pte_t entry; + purge_tlb_start(flags); entry = *ptep; - set_huge_pte_at(mm, addr, ptep, __pte(0)); + __set_huge_pte_at(mm, addr, ptep, __pte(0)); + purge_tlb_end(flags); return entry; } + +void huge_ptep_set_wrprotect(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + unsigned long flags; + pte_t old_pte; + + purge_tlb_start(flags); + old_pte = *ptep; + __set_huge_pte_at(mm, addr, ptep, pte_wrprotect(old_pte)); + purge_tlb_end(flags); +} + +int huge_ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t pte, int dirty) +{ + unsigned long flags; + int changed; + + purge_tlb_start(flags); + changed = !pte_same(*ptep, pte); + if (changed) { + __set_huge_pte_at(vma->vm_mm, addr, ptep, pte); + } + purge_tlb_end(flags); + return changed; +} + + int pmd_huge(pmd_t pmd) { return 0; diff --git a/arch/powerpc/include/asm/cmpxchg.h b/arch/powerpc/include/asm/cmpxchg.h index ad6263cffb0f..d1a8d93cccfd 100644 --- a/arch/powerpc/include/asm/cmpxchg.h +++ b/arch/powerpc/include/asm/cmpxchg.h @@ -18,12 +18,12 @@ __xchg_u32(volatile void *p, unsigned long val) unsigned long prev; __asm__ __volatile__( - PPC_RELEASE_BARRIER + PPC_ATOMIC_ENTRY_BARRIER "1: lwarx %0,0,%2 \n" PPC405_ERR77(0,%2) " stwcx. %3,0,%2 \n\ bne- 1b" - PPC_ACQUIRE_BARRIER + PPC_ATOMIC_EXIT_BARRIER : "=&r" (prev), "+m" (*(volatile unsigned int *)p) : "r" (p), "r" (val) : "cc", "memory"); @@ -61,12 +61,12 @@ __xchg_u64(volatile void *p, unsigned long val) unsigned long prev; __asm__ __volatile__( - PPC_RELEASE_BARRIER + PPC_ATOMIC_ENTRY_BARRIER "1: ldarx %0,0,%2 \n" PPC405_ERR77(0,%2) " stdcx. %3,0,%2 \n\ bne- 1b" - PPC_ACQUIRE_BARRIER + PPC_ATOMIC_EXIT_BARRIER : "=&r" (prev), "+m" (*(volatile unsigned long *)p) : "r" (p), "r" (val) : "cc", "memory"); @@ -151,14 +151,14 @@ __cmpxchg_u32(volatile unsigned int *p, unsigned long old, unsigned long new) unsigned int prev; __asm__ __volatile__ ( - PPC_RELEASE_BARRIER + PPC_ATOMIC_ENTRY_BARRIER "1: lwarx %0,0,%2 # __cmpxchg_u32\n\ cmpw 0,%0,%3\n\ bne- 2f\n" PPC405_ERR77(0,%2) " stwcx. %4,0,%2\n\ bne- 1b" - PPC_ACQUIRE_BARRIER + PPC_ATOMIC_EXIT_BARRIER "\n\ 2:" : "=&r" (prev), "+m" (*p) @@ -197,13 +197,13 @@ __cmpxchg_u64(volatile unsigned long *p, unsigned long old, unsigned long new) unsigned long prev; __asm__ __volatile__ ( - PPC_RELEASE_BARRIER + PPC_ATOMIC_ENTRY_BARRIER "1: ldarx %0,0,%2 # __cmpxchg_u64\n\ cmpd 0,%0,%3\n\ bne- 2f\n\ stdcx. %4,0,%2\n\ bne- 1b" - PPC_ACQUIRE_BARRIER + PPC_ATOMIC_EXIT_BARRIER "\n\ 2:" : "=&r" (prev), "+m" (*p) diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index c5eb86f3d452..867c39b45df6 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -81,6 +81,7 @@ struct pci_dn; #define EEH_PE_KEEP (1 << 8) /* Keep PE on hotplug */ #define EEH_PE_CFG_RESTRICTED (1 << 9) /* Block config on error */ #define EEH_PE_REMOVED (1 << 10) /* Removed permanently */ +#define EEH_PE_PRI_BUS (1 << 11) /* Cached primary bus */ struct eeh_pe { int type; /* PE type: PHB/Bus/Device */ diff --git a/arch/powerpc/include/asm/opal-api.h b/arch/powerpc/include/asm/opal-api.h index 8374afed9d0a..f8faaaeeca1e 100644 --- a/arch/powerpc/include/asm/opal-api.h +++ b/arch/powerpc/include/asm/opal-api.h @@ -157,7 +157,8 @@ #define OPAL_LEDS_GET_INDICATOR 114 #define OPAL_LEDS_SET_INDICATOR 115 #define OPAL_CEC_REBOOT2 116 -#define OPAL_LAST 116 +#define OPAL_CONSOLE_FLUSH 117 +#define OPAL_LAST 117 /* Device tree flags */ diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h index 800115910e43..07a99e638449 100644 --- a/arch/powerpc/include/asm/opal.h +++ b/arch/powerpc/include/asm/opal.h @@ -35,6 +35,7 @@ int64_t opal_console_read(int64_t term_number, __be64 *length, uint8_t *buffer); int64_t opal_console_write_buffer_space(int64_t term_number, __be64 *length); +int64_t opal_console_flush(int64_t term_number); int64_t opal_rtc_read(__be32 *year_month_day, __be64 *hour_minute_second_millisecond); int64_t opal_rtc_write(uint32_t year_month_day, @@ -262,6 +263,8 @@ extern int opal_resync_timebase(void); extern void opal_lpc_init(void); +extern void opal_kmsg_init(void); + extern int opal_event_request(unsigned int opal_event_nr); struct opal_sg_list *opal_vmalloc_to_sg_list(void *vmalloc_addr, diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 2220f7a60def..070fa8552051 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -707,7 +707,7 @@ #define MMCR0_FCWAIT 0x00000002UL /* freeze counter in WAIT state */ #define MMCR0_FCHV 0x00000001UL /* freeze conditions in hypervisor mode */ #define SPRN_MMCR1 798 -#define SPRN_MMCR2 769 +#define SPRN_MMCR2 785 #define SPRN_MMCRA 0x312 #define MMCRA_SDSYNC 0x80000000UL /* SDAR synced with SIAR */ #define MMCRA_SDAR_DCACHE_MISS 0x40000000UL @@ -744,13 +744,13 @@ #define SPRN_PMC6 792 #define SPRN_PMC7 793 #define SPRN_PMC8 794 -#define SPRN_SIAR 780 -#define SPRN_SDAR 781 #define SPRN_SIER 784 #define SIER_SIPR 0x2000000 /* Sampled MSR_PR */ #define SIER_SIHV 0x1000000 /* Sampled MSR_HV */ #define SIER_SIAR_VALID 0x0400000 /* SIAR contents valid */ #define SIER_SDAR_VALID 0x0200000 /* SDAR contents valid */ +#define SPRN_SIAR 796 +#define SPRN_SDAR 797 #define SPRN_TACR 888 #define SPRN_TCSCR 889 #define SPRN_CSIGR 890 diff --git a/arch/powerpc/include/asm/synch.h b/arch/powerpc/include/asm/synch.h index e682a7143edb..c50868681f9e 100644 --- a/arch/powerpc/include/asm/synch.h +++ b/arch/powerpc/include/asm/synch.h @@ -44,7 +44,7 @@ static inline void isync(void) MAKE_LWSYNC_SECTION_ENTRY(97, __lwsync_fixup); #define PPC_ACQUIRE_BARRIER "\n" stringify_in_c(__PPC_ACQUIRE_BARRIER) #define PPC_RELEASE_BARRIER stringify_in_c(LWSYNC) "\n" -#define PPC_ATOMIC_ENTRY_BARRIER "\n" stringify_in_c(LWSYNC) "\n" +#define PPC_ATOMIC_ENTRY_BARRIER "\n" stringify_in_c(sync) "\n" #define PPC_ATOMIC_EXIT_BARRIER "\n" stringify_in_c(sync) "\n" #else #define PPC_ACQUIRE_BARRIER diff --git a/arch/powerpc/include/asm/word-at-a-time.h b/arch/powerpc/include/asm/word-at-a-time.h index e4396a7d0f7c..4afe66aa1400 100644 --- a/arch/powerpc/include/asm/word-at-a-time.h +++ b/arch/powerpc/include/asm/word-at-a-time.h @@ -82,7 +82,7 @@ static inline unsigned long create_zero_mask(unsigned long bits) "andc %1,%1,%2\n\t" "popcntd %0,%1" : "=r" (leading_zero_bits), "=&r" (trailing_zero_bit_mask) - : "r" (bits)); + : "b" (bits)); return leading_zero_bits; } diff --git a/arch/powerpc/include/uapi/asm/cputable.h b/arch/powerpc/include/uapi/asm/cputable.h index 43686043e297..2734c005da21 100644 --- a/arch/powerpc/include/uapi/asm/cputable.h +++ b/arch/powerpc/include/uapi/asm/cputable.h @@ -31,6 +31,7 @@ #define PPC_FEATURE_PSERIES_PERFMON_COMPAT \ 0x00000040 +/* Reserved - do not use 0x00000004 */ #define PPC_FEATURE_TRUE_LE 0x00000002 #define PPC_FEATURE_PPC_LE 0x00000001 diff --git a/arch/powerpc/include/uapi/asm/elf.h b/arch/powerpc/include/uapi/asm/elf.h index 59dad113897b..c2d21d11c2d2 100644 --- a/arch/powerpc/include/uapi/asm/elf.h +++ b/arch/powerpc/include/uapi/asm/elf.h @@ -295,6 +295,8 @@ do { \ #define R_PPC64_TLSLD 108 #define R_PPC64_TOCSAVE 109 +#define R_PPC64_ENTRY 118 + #define R_PPC64_REL16 249 #define R_PPC64_REL16_LO 250 #define R_PPC64_REL16_HI 251 diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 40e4d4a27663..b34e8a54f7db 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -1072,7 +1072,7 @@ void eeh_add_device_early(struct pci_dn *pdn) struct pci_controller *phb; struct eeh_dev *edev = pdn_to_eeh_dev(pdn); - if (!edev || !eeh_enabled()) + if (!edev) return; if (!eeh_has_flag(EEH_PROBE_MODE_DEVTREE)) diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 8d14feb40f12..247a0dc012f1 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -166,6 +166,16 @@ static void *eeh_dev_save_state(void *data, void *userdata) if (!edev) return NULL; + /* + * We cannot access the config space on some adapters. + * Otherwise, it will cause fenced PHB. We don't save + * the content in their config space and will restore + * from the initial config space saved when the EEH + * device is created. + */ + if (edev->pe && (edev->pe->state & EEH_PE_CFG_RESTRICTED)) + return NULL; + pdev = eeh_dev_to_pci_dev(edev); if (!pdev) return NULL; @@ -305,6 +315,19 @@ static void *eeh_dev_restore_state(void *data, void *userdata) if (!edev) return NULL; + /* + * The content in the config space isn't saved because + * the blocked config space on some adapters. We have + * to restore the initial saved config space when the + * EEH device is created. + */ + if (edev->pe && (edev->pe->state & EEH_PE_CFG_RESTRICTED)) { + if (list_is_last(&edev->list, &edev->pe->edevs)) + eeh_pe_restore_bars(edev->pe); + + return NULL; + } + pdev = eeh_dev_to_pci_dev(edev); if (!pdev) return NULL; @@ -418,8 +441,7 @@ static void *eeh_rmv_device(void *data, void *userdata) eeh_pcid_put(dev); if (driver->err_handler && driver->err_handler->error_detected && - driver->err_handler->slot_reset && - driver->err_handler->resume) + driver->err_handler->slot_reset) return NULL; } @@ -505,9 +527,6 @@ int eeh_pe_reset_and_recover(struct eeh_pe *pe) /* Save states */ eeh_pe_dev_traverse(pe, eeh_dev_save_state, NULL); - /* Report error */ - eeh_pe_dev_traverse(pe, eeh_report_error, &result); - /* Issue reset */ ret = eeh_reset_pe(pe); if (ret) { @@ -564,6 +583,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus) */ eeh_pe_state_mark(pe, EEH_PE_KEEP); if (bus) { + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); pci_lock_rescan_remove(); pcibios_remove_pci_devices(bus); pci_unlock_rescan_remove(); @@ -803,6 +823,7 @@ perm_error: * the their PCI config any more. */ if (frozen_bus) { + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED); pci_lock_rescan_remove(); @@ -886,6 +907,7 @@ static void eeh_handle_special_event(void) continue; /* Notify all devices to be down */ + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); bus = eeh_pe_bus_get(phb_pe); eeh_pe_dev_traverse(pe, eeh_report_failure, NULL); diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index 8654cb166c19..98f81800e00c 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -883,32 +883,29 @@ void eeh_pe_restore_bars(struct eeh_pe *pe) const char *eeh_pe_loc_get(struct eeh_pe *pe) { struct pci_bus *bus = eeh_pe_bus_get(pe); - struct device_node *dn = pci_bus_to_OF_node(bus); + struct device_node *dn; const char *loc = NULL; - if (!dn) - goto out; + while (bus) { + dn = pci_bus_to_OF_node(bus); + if (!dn) { + bus = bus->parent; + continue; + } - /* PHB PE or root PE ? */ - if (pci_is_root_bus(bus)) { - loc = of_get_property(dn, "ibm,loc-code", NULL); - if (!loc) + if (pci_is_root_bus(bus)) loc = of_get_property(dn, "ibm,io-base-loc-code", NULL); - if (loc) - goto out; + else + loc = of_get_property(dn, "ibm,slot-location-code", + NULL); - /* Check the root port */ - dn = dn->child; - if (!dn) - goto out; + if (loc) + return loc; + + bus = bus->parent; } - loc = of_get_property(dn, "ibm,loc-code", NULL); - if (!loc) - loc = of_get_property(dn, "ibm,slot-location-code", NULL); - -out: - return loc ? loc : "N/A"; + return "N/A"; } /** @@ -931,7 +928,7 @@ struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe) bus = pe->phb->bus; } else if (pe->type & EEH_PE_BUS || pe->type & EEH_PE_DEVICE) { - if (pe->bus) { + if (pe->state & EEH_PE_PRI_BUS) { bus = pe->bus; goto out; } diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 0a0399c2af11..b81ccc5fb32d 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -962,11 +962,6 @@ hv_facility_unavailable_relon_trampoline: #endif STD_RELON_EXCEPTION_PSERIES(0x5700, 0x1700, altivec_assist) - /* Other future vectors */ - .align 7 - .globl __end_interrupts -__end_interrupts: - .align 7 system_call_entry: b system_call_common @@ -1253,6 +1248,17 @@ __end_handlers: STD_RELON_EXCEPTION_PSERIES_OOL(0xf60, facility_unavailable) STD_RELON_EXCEPTION_HV_OOL(0xf80, hv_facility_unavailable) + /* + * The __end_interrupts marker must be past the out-of-line (OOL) + * handlers, so that they are copied to real address 0x100 when running + * a relocatable kernel. This ensures they can be reached from the short + * trampoline handlers (like 0x4f00, 0x4f20, etc.) which branch + * directly, without using LOAD_HANDLER(). + */ + .align 7 + .globl __end_interrupts +__end_interrupts: + #if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV) /* * Data area reserved for FWNMI option. diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 68384514506b..e4f7d4eed20c 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -335,7 +335,7 @@ static void dedotify(Elf64_Sym *syms, unsigned int numsyms, char *strtab) if (syms[i].st_shndx == SHN_UNDEF) { char *name = strtab + syms[i].st_name; if (name[0] == '.') - memmove(name, name+1, strlen(name)); + syms[i].st_name++; } } } @@ -635,6 +635,33 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, */ break; + case R_PPC64_ENTRY: + /* + * Optimize ELFv2 large code model entry point if + * the TOC is within 2GB range of current location. + */ + value = my_r2(sechdrs, me) - (unsigned long)location; + if (value + 0x80008000 > 0xffffffff) + break; + /* + * Check for the large code model prolog sequence: + * ld r2, ...(r12) + * add r2, r2, r12 + */ + if ((((uint32_t *)location)[0] & ~0xfffc) + != 0xe84c0000) + break; + if (((uint32_t *)location)[1] != 0x7c426214) + break; + /* + * If found, replace it with: + * addis r2, r12, (.TOC.-func)@ha + * addi r2, r12, (.TOC.-func)@l + */ + ((uint32_t *)location)[0] = 0x3c4c0000 + PPC_HA(value); + ((uint32_t *)location)[1] = 0x38420000 + PPC_LO(value); + break; + case R_PPC64_REL16_HA: /* Subtract location pointer */ value -= (unsigned long)location; diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index a7b91b54c813..b7abf3cd2a67 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1239,6 +1239,16 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) current->thread.regs = regs - 1; } +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + /* + * Clear any transactional state, we're exec()ing. The cause is + * not important as there will never be a recheckpoint so it's not + * user visible. + */ + if (MSR_TM_SUSPENDED(mfmsr())) + tm_reclaim_current(0); +#endif + memset(regs->gpr, 0, sizeof(regs->gpr)); regs->ctr = 0; regs->link = 0; diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 7030b035905d..a15fe1d4e84a 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -148,23 +148,25 @@ static struct ibm_pa_feature { unsigned long cpu_features; /* CPU_FTR_xxx bit */ unsigned long mmu_features; /* MMU_FTR_xxx bit */ unsigned int cpu_user_ftrs; /* PPC_FEATURE_xxx bit */ + unsigned int cpu_user_ftrs2; /* PPC_FEATURE2_xxx bit */ unsigned char pabyte; /* byte number in ibm,pa-features */ unsigned char pabit; /* bit number (big-endian) */ unsigned char invert; /* if 1, pa bit set => clear feature */ } ibm_pa_features[] __initdata = { - {0, 0, PPC_FEATURE_HAS_MMU, 0, 0, 0}, - {0, 0, PPC_FEATURE_HAS_FPU, 0, 1, 0}, - {CPU_FTR_CTRL, 0, 0, 0, 3, 0}, - {CPU_FTR_NOEXECUTE, 0, 0, 0, 6, 0}, - {CPU_FTR_NODSISRALIGN, 0, 0, 1, 1, 1}, - {0, MMU_FTR_CI_LARGE_PAGE, 0, 1, 2, 0}, - {CPU_FTR_REAL_LE, PPC_FEATURE_TRUE_LE, 5, 0, 0}, + {0, 0, PPC_FEATURE_HAS_MMU, 0, 0, 0, 0}, + {0, 0, PPC_FEATURE_HAS_FPU, 0, 0, 1, 0}, + {CPU_FTR_CTRL, 0, 0, 0, 0, 3, 0}, + {CPU_FTR_NOEXECUTE, 0, 0, 0, 0, 6, 0}, + {CPU_FTR_NODSISRALIGN, 0, 0, 0, 1, 1, 1}, + {0, MMU_FTR_CI_LARGE_PAGE, 0, 0, 1, 2, 0}, + {CPU_FTR_REAL_LE, 0, PPC_FEATURE_TRUE_LE, 0, 5, 0, 0}, /* - * If the kernel doesn't support TM (ie. CONFIG_PPC_TRANSACTIONAL_MEM=n), - * we don't want to turn on CPU_FTR_TM here, so we use CPU_FTR_TM_COMP - * which is 0 if the kernel doesn't support TM. + * If the kernel doesn't support TM (ie CONFIG_PPC_TRANSACTIONAL_MEM=n), + * we don't want to turn on TM here, so we use the *_COMP versions + * which are 0 if the kernel doesn't support TM. */ - {CPU_FTR_TM_COMP, 0, 0, 22, 0, 0}, + {CPU_FTR_TM_COMP, 0, 0, + PPC_FEATURE2_HTM_COMP|PPC_FEATURE2_HTM_NOSC_COMP, 22, 0, 0}, }; static void __init scan_features(unsigned long node, const unsigned char *ftrs, @@ -195,10 +197,12 @@ static void __init scan_features(unsigned long node, const unsigned char *ftrs, if (bit ^ fp->invert) { cur_cpu_spec->cpu_features |= fp->cpu_features; cur_cpu_spec->cpu_user_features |= fp->cpu_user_ftrs; + cur_cpu_spec->cpu_user_features2 |= fp->cpu_user_ftrs2; cur_cpu_spec->mmu_features |= fp->mmu_features; } else { cur_cpu_spec->cpu_features &= ~fp->cpu_features; cur_cpu_spec->cpu_user_features &= ~fp->cpu_user_ftrs; + cur_cpu_spec->cpu_user_features2 &= ~fp->cpu_user_ftrs2; cur_cpu_spec->mmu_features &= ~fp->mmu_features; } } diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 92dea8df6b26..b7e86e00048f 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -655,6 +655,7 @@ unsigned char ibm_architecture_vec[] = { W(0xffff0000), W(0x003e0000), /* POWER6 */ W(0xffff0000), W(0x003f0000), /* POWER7 */ W(0xffff0000), W(0x004b0000), /* POWER8E */ + W(0xffff0000), W(0x004c0000), /* POWER8NVL */ W(0xffff0000), W(0x004d0000), /* POWER8 */ W(0xffffffff), W(0x0f000004), /* all 2.07-compliant */ W(0xffffffff), W(0x0f000003), /* all 2.06-compliant */ @@ -717,7 +718,7 @@ unsigned char ibm_architecture_vec[] = { * must match by the macro below. Update the definition if * the structure layout changes. */ -#define IBM_ARCH_VEC_NRCORES_OFFSET 125 +#define IBM_ARCH_VEC_NRCORES_OFFSET 133 W(NR_CPUS), /* number of cores supported */ 0, 0, diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 3c6badcd53ef..463af88c95a2 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -1370,6 +1370,20 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) std r6, VCPU_ACOP(r9) stw r7, VCPU_GUEST_PID(r9) std r8, VCPU_WORT(r9) + /* + * Restore various registers to 0, where non-zero values + * set by the guest could disrupt the host. + */ + li r0, 0 + mtspr SPRN_IAMR, r0 + mtspr SPRN_CIABR, r0 + mtspr SPRN_DAWRX, r0 + mtspr SPRN_TCSCR, r0 + mtspr SPRN_WORT, r0 + /* Set MMCRS to 1<<31 to freeze and disable the SPMC counters */ + li r0, 1 + sldi r0, r0, 31 + mtspr SPRN_MMCRS, r0 8: /* Save and reset AMR and UAMOR before turning on the MMU */ @@ -2153,7 +2167,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) /* Emulate H_SET_DABR/X on P8 for the sake of compat mode guests */ 2: rlwimi r5, r4, 5, DAWRX_DR | DAWRX_DW - rlwimi r5, r4, 1, DAWRX_WT + rlwimi r5, r4, 2, DAWRX_WT clrrdi r4, r4, 3 std r4, VCPU_DAWR(r3) std r5, VCPU_DAWRX(r3) diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 6fd2405c7f4a..a3b182dcb823 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -919,21 +919,17 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) r = -ENXIO; break; } - vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0] = val.vval; + val.vval = vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0]; break; case KVM_REG_PPC_VSCR: if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { r = -ENXIO; break; } - vcpu->arch.vr.vscr.u[3] = set_reg_val(reg->id, val); + val = get_reg_val(reg->id, vcpu->arch.vr.vscr.u[3]); break; case KVM_REG_PPC_VRSAVE: - if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { - r = -ENXIO; - break; - } - vcpu->arch.vrsave = set_reg_val(reg->id, val); + val = get_reg_val(reg->id, vcpu->arch.vrsave); break; #endif /* CONFIG_ALTIVEC */ default: @@ -974,17 +970,21 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg) r = -ENXIO; break; } - val.vval = vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0]; + vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0] = val.vval; break; case KVM_REG_PPC_VSCR: if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { r = -ENXIO; break; } - val = get_reg_val(reg->id, vcpu->arch.vr.vscr.u[3]); + vcpu->arch.vr.vscr.u[3] = set_reg_val(reg->id, val); break; case KVM_REG_PPC_VRSAVE: - val = get_reg_val(reg->id, vcpu->arch.vrsave); + if (!cpu_has_feature(CPU_FTR_ALTIVEC)) { + r = -ENXIO; + break; + } + vcpu->arch.vrsave = set_reg_val(reg->id, val); break; #endif /* CONFIG_ALTIVEC */ default: diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 9833fee493ec..807f1594701d 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -486,13 +486,13 @@ static void hugepd_free(struct mmu_gather *tlb, void *hugepte) { struct hugepd_freelist **batchp; - batchp = this_cpu_ptr(&hugepd_freelist_cur); + batchp = &get_cpu_var(hugepd_freelist_cur); if (atomic_read(&tlb->mm->mm_users) < 2 || cpumask_equal(mm_cpumask(tlb->mm), cpumask_of(smp_processor_id()))) { kmem_cache_free(hugepte_cache, hugepte); - put_cpu_var(hugepd_freelist_cur); + put_cpu_var(hugepd_freelist_cur); return; } diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile index 1c8cdb6250e7..b9de7ef48849 100644 --- a/arch/powerpc/platforms/powernv/Makefile +++ b/arch/powerpc/platforms/powernv/Makefile @@ -2,6 +2,7 @@ obj-y += setup.o opal-wrappers.o opal.o opal-async.o idle.o obj-y += opal-rtc.o opal-nvram.o opal-lpc.o opal-flash.o obj-y += rng.o opal-elog.o opal-dump.o opal-sysparam.o opal-sensor.o obj-y += opal-msglog.o opal-hmi.o opal-power.o opal-irqchip.o +obj-y += opal-kmsg.o obj-$(CONFIG_SMP) += smp.o subcore.o subcore-asm.o obj-$(CONFIG_PCI) += pci.o pci-p5ioc2.o pci-ioda.o diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index e1c90725522a..2ba602591a20 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -444,9 +444,12 @@ static void *pnv_eeh_probe(struct pci_dn *pdn, void *data) * PCI devices of the PE are expected to be removed prior * to PE reset. */ - if (!edev->pe->bus) + if (!(edev->pe->state & EEH_PE_PRI_BUS)) { edev->pe->bus = pci_find_bus(hose->global_number, pdn->busno); + if (edev->pe->bus) + edev->pe->state |= EEH_PE_PRI_BUS; + } /* * Enable EEH explicitly so that we will do EEH check diff --git a/arch/powerpc/platforms/powernv/opal-kmsg.c b/arch/powerpc/platforms/powernv/opal-kmsg.c new file mode 100644 index 000000000000..6f1214d4de92 --- /dev/null +++ b/arch/powerpc/platforms/powernv/opal-kmsg.c @@ -0,0 +1,75 @@ +/* + * kmsg dumper that ensures the OPAL console fully flushes panic messages + * + * Author: Russell Currey + * + * Copyright 2015 IBM Corporation. + * + * 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. + */ + +#include + +#include +#include + +/* + * Console output is controlled by OPAL firmware. The kernel regularly calls + * OPAL_POLL_EVENTS, which flushes some console output. In a panic state, + * however, the kernel no longer calls OPAL_POLL_EVENTS and the panic message + * may not be completely printed. This function does not actually dump the + * message, it just ensures that OPAL completely flushes the console buffer. + */ +static void force_opal_console_flush(struct kmsg_dumper *dumper, + enum kmsg_dump_reason reason) +{ + int i; + int64_t ret; + + /* + * Outside of a panic context the pollers will continue to run, + * so we don't need to do any special flushing. + */ + if (reason != KMSG_DUMP_PANIC) + return; + + if (opal_check_token(OPAL_CONSOLE_FLUSH)) { + ret = opal_console_flush(0); + + if (ret == OPAL_UNSUPPORTED || ret == OPAL_PARAMETER) + return; + + /* Incrementally flush until there's nothing left */ + while (opal_console_flush(0) != OPAL_SUCCESS); + } else { + /* + * If OPAL_CONSOLE_FLUSH is not implemented in the firmware, + * the console can still be flushed by calling the polling + * function enough times to flush the buffer. We don't know + * how much output still needs to be flushed, but we can be + * generous since the kernel is in panic and doesn't need + * to do much else. + */ + printk(KERN_NOTICE "opal: OPAL_CONSOLE_FLUSH missing.\n"); + for (i = 0; i < 1024; i++) { + opal_poll_events(NULL); + } + } +} + +static struct kmsg_dumper opal_kmsg_dumper = { + .dump = force_opal_console_flush +}; + +void __init opal_kmsg_init(void) +{ + int rc; + + /* Add our dumper to the list */ + rc = kmsg_dump_register(&opal_kmsg_dumper); + if (rc != 0) + pr_err("opal: kmsg_dump_register failed; returned %d\n", rc); +} diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S index b7a464fef7a7..e45b88a5d7e0 100644 --- a/arch/powerpc/platforms/powernv/opal-wrappers.S +++ b/arch/powerpc/platforms/powernv/opal-wrappers.S @@ -301,3 +301,4 @@ OPAL_CALL(opal_flash_erase, OPAL_FLASH_ERASE); OPAL_CALL(opal_prd_msg, OPAL_PRD_MSG); OPAL_CALL(opal_leds_get_ind, OPAL_LEDS_GET_INDICATOR); OPAL_CALL(opal_leds_set_ind, OPAL_LEDS_SET_INDICATOR); +OPAL_CALL(opal_console_flush, OPAL_CONSOLE_FLUSH); diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 57cffb80bc36..ae29eaf85e9e 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -758,6 +758,9 @@ static int __init opal_init(void) opal_pdev_init(opal_node, "ibm,opal-flash"); opal_pdev_init(opal_node, "ibm,opal-prd"); + /* Initialise OPAL kmsg dumper for flushing console on panic */ + opal_kmsg_init(); + return 0; } machine_subsys_initcall(powernv, opal_init); diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 414fd1a00fda..e40d0714679e 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -3034,6 +3034,7 @@ static void pnv_pci_ioda_shutdown(struct pci_controller *hose) static const struct pci_controller_ops pnv_pci_ioda_controller_ops = { .dma_dev_setup = pnv_pci_dma_dev_setup, + .dma_bus_setup = pnv_pci_dma_bus_setup, #ifdef CONFIG_PCI_MSI .setup_msi_irqs = pnv_setup_msi_irqs, .teardown_msi_irqs = pnv_teardown_msi_irqs, diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index f2dd77234240..ad8c3f4a5e0b 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -601,6 +601,9 @@ int pnv_tce_build(struct iommu_table *tbl, long index, long npages, u64 rpn = __pa(uaddr) >> tbl->it_page_shift; long i; + if (proto_tce & TCE_PCI_WRITE) + proto_tce |= TCE_PCI_READ; + for (i = 0; i < npages; i++) { unsigned long newtce = proto_tce | ((rpn + i) << tbl->it_page_shift); @@ -622,6 +625,9 @@ int pnv_tce_xchg(struct iommu_table *tbl, long index, BUG_ON(*hpa & ~IOMMU_PAGE_MASK(tbl)); + if (newtce & TCE_PCI_WRITE) + newtce |= TCE_PCI_READ; + oldtce = xchg(pnv_tce(tbl, idx), cpu_to_be64(newtce)); *hpa = be64_to_cpu(oldtce) & ~(TCE_PCI_READ | TCE_PCI_WRITE); *direction = iommu_tce_direction(oldtce); @@ -762,6 +768,26 @@ void pnv_pci_dma_dev_setup(struct pci_dev *pdev) phb->dma_dev_setup(phb, pdev); } +void pnv_pci_dma_bus_setup(struct pci_bus *bus) +{ + struct pci_controller *hose = bus->sysdata; + struct pnv_phb *phb = hose->private_data; + struct pnv_ioda_pe *pe; + + list_for_each_entry(pe, &phb->ioda.pe_list, list) { + if (!(pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL))) + continue; + + if (!pe->pbus) + continue; + + if (bus->number == ((pe->rid >> 8) & 0xFF)) { + pe->pbus = bus; + break; + } + } +} + void pnv_pci_shutdown(void) { struct pci_controller *hose; diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h index c8ff50e90766..36a99feab7d8 100644 --- a/arch/powerpc/platforms/powernv/pci.h +++ b/arch/powerpc/platforms/powernv/pci.h @@ -235,6 +235,7 @@ extern void pnv_pci_reset_secondary_bus(struct pci_dev *dev); extern int pnv_eeh_phb_reset(struct pci_controller *hose, int option); extern void pnv_pci_dma_dev_setup(struct pci_dev *pdev); +extern void pnv_pci_dma_bus_setup(struct pci_bus *bus); extern int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type); extern void pnv_teardown_msi_irqs(struct pci_dev *pdev); diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index ac3ffd97e059..405baaf96864 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -615,29 +615,50 @@ static int pseries_eeh_configure_bridge(struct eeh_pe *pe) { int config_addr; int ret; + /* Waiting 0.2s maximum before skipping configuration */ + int max_wait = 200; /* Figure out the PE address */ config_addr = pe->config_addr; if (pe->addr) config_addr = pe->addr; - /* Use new configure-pe function, if supported */ - if (ibm_configure_pe != RTAS_UNKNOWN_SERVICE) { - ret = rtas_call(ibm_configure_pe, 3, 1, NULL, - config_addr, BUID_HI(pe->phb->buid), - BUID_LO(pe->phb->buid)); - } else if (ibm_configure_bridge != RTAS_UNKNOWN_SERVICE) { - ret = rtas_call(ibm_configure_bridge, 3, 1, NULL, - config_addr, BUID_HI(pe->phb->buid), - BUID_LO(pe->phb->buid)); - } else { - return -EFAULT; + while (max_wait > 0) { + /* Use new configure-pe function, if supported */ + if (ibm_configure_pe != RTAS_UNKNOWN_SERVICE) { + ret = rtas_call(ibm_configure_pe, 3, 1, NULL, + config_addr, BUID_HI(pe->phb->buid), + BUID_LO(pe->phb->buid)); + } else if (ibm_configure_bridge != RTAS_UNKNOWN_SERVICE) { + ret = rtas_call(ibm_configure_bridge, 3, 1, NULL, + config_addr, BUID_HI(pe->phb->buid), + BUID_LO(pe->phb->buid)); + } else { + return -EFAULT; + } + + if (!ret) + return ret; + + /* + * If RTAS returns a delay value that's above 100ms, cut it + * down to 100ms in case firmware made a mistake. For more + * on how these delay values work see rtas_busy_delay_time + */ + if (ret > RTAS_EXTENDED_DELAY_MIN+2 && + ret <= RTAS_EXTENDED_DELAY_MAX) + ret = RTAS_EXTENDED_DELAY_MIN+2; + + max_wait -= rtas_busy_delay_time(ret); + + if (max_wait < 0) + break; + + rtas_busy_delay(ret); } - if (ret) - pr_warn("%s: Unable to configure bridge PHB#%d-PE#%x (%d)\n", - __func__, pe->phb->global_number, pe->addr, ret); - + pr_warn("%s: Unable to configure bridge PHB#%d-PE#%x (%d)\n", + __func__, pe->phb->global_number, pe->addr, ret); return ret; } diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index bd98ce2be17b..3e8865b187de 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -912,7 +912,8 @@ machine_arch_initcall(pseries, find_existing_ddw_windows); static int query_ddw(struct pci_dev *dev, const u32 *ddw_avail, struct ddw_query_response *query) { - struct eeh_dev *edev; + struct device_node *dn; + struct pci_dn *pdn; u32 cfg_addr; u64 buid; int ret; @@ -923,11 +924,10 @@ static int query_ddw(struct pci_dev *dev, const u32 *ddw_avail, * Retrieve them from the pci device, not the node with the * dma-window property */ - edev = pci_dev_to_eeh_dev(dev); - cfg_addr = edev->config_addr; - if (edev->pe_config_addr) - cfg_addr = edev->pe_config_addr; - buid = edev->phb->buid; + dn = pci_device_to_OF_node(dev); + pdn = PCI_DN(dn); + buid = pdn->phb->buid; + cfg_addr = ((pdn->busno << 16) | (pdn->devfn << 8)); ret = rtas_call(ddw_avail[0], 3, 5, (u32 *)query, cfg_addr, BUID_HI(buid), BUID_LO(buid)); @@ -941,7 +941,8 @@ static int create_ddw(struct pci_dev *dev, const u32 *ddw_avail, struct ddw_create_response *create, int page_shift, int window_shift) { - struct eeh_dev *edev; + struct device_node *dn; + struct pci_dn *pdn; u32 cfg_addr; u64 buid; int ret; @@ -952,11 +953,10 @@ static int create_ddw(struct pci_dev *dev, const u32 *ddw_avail, * Retrieve them from the pci device, not the node with the * dma-window property */ - edev = pci_dev_to_eeh_dev(dev); - cfg_addr = edev->config_addr; - if (edev->pe_config_addr) - cfg_addr = edev->pe_config_addr; - buid = edev->phb->buid; + dn = pci_device_to_OF_node(dev); + pdn = PCI_DN(dn); + buid = pdn->phb->buid; + cfg_addr = ((pdn->busno << 16) | (pdn->devfn << 8)); do { /* extra outputs are LIOBN and dma-addr (hi, lo) */ diff --git a/arch/s390/include/asm/fpu/api.h b/arch/s390/include/asm/fpu/api.h index 5e04f3cbd320..8ae236b0f80b 100644 --- a/arch/s390/include/asm/fpu/api.h +++ b/arch/s390/include/asm/fpu/api.h @@ -22,7 +22,7 @@ static inline int test_fp_ctl(u32 fpc) " la %0,0\n" "1:\n" EX_TABLE(0b,1b) - : "=d" (rc), "=d" (orig_fpc) + : "=d" (rc), "=&d" (orig_fpc) : "d" (fpc), "0" (-EINVAL)); return rc; } diff --git a/arch/s390/include/asm/fpu/internal.h b/arch/s390/include/asm/fpu/internal.h index 2559b16da525..17d9dcd29d45 100644 --- a/arch/s390/include/asm/fpu/internal.h +++ b/arch/s390/include/asm/fpu/internal.h @@ -48,6 +48,7 @@ static inline void convert_fp_to_vx(__vector128 *vxrs, freg_t *fprs) static inline void fpregs_store(_s390_fp_regs *fpregs, struct fpu *fpu) { fpregs->pad = 0; + fpregs->fpc = fpu->fpc; if (MACHINE_HAS_VX) convert_vx_to_fp((freg_t *)&fpregs->fprs, fpu->vxrs); else @@ -57,6 +58,7 @@ static inline void fpregs_store(_s390_fp_regs *fpregs, struct fpu *fpu) static inline void fpregs_load(_s390_fp_regs *fpregs, struct fpu *fpu) { + fpu->fpc = fpregs->fpc; if (MACHINE_HAS_VX) convert_fp_to_vx(fpu->vxrs, (freg_t *)&fpregs->fprs); else diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index efaac2c3bb77..e9a983f40a24 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -506,7 +506,6 @@ struct kvm_vcpu_arch { struct kvm_s390_sie_block *sie_block; unsigned int host_acrs[NUM_ACRS]; struct fpu host_fpregs; - struct fpu guest_fpregs; struct kvm_s390_local_interrupt local_int; struct hrtimer ckc_timer; struct kvm_s390_pgm_info pgm; diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h index d29ad9545b41..081b2ad99d73 100644 --- a/arch/s390/include/asm/mmu.h +++ b/arch/s390/include/asm/mmu.h @@ -11,7 +11,7 @@ typedef struct { spinlock_t list_lock; struct list_head pgtable_list; struct list_head gmap_list; - unsigned long asce_bits; + unsigned long asce; unsigned long asce_limit; unsigned long vdso_base; /* The mmu context allocates 4K page tables. */ diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index fb1b93ea3e3f..22877c9440ea 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -15,17 +15,41 @@ static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { + spin_lock_init(&mm->context.list_lock); + INIT_LIST_HEAD(&mm->context.pgtable_list); + INIT_LIST_HEAD(&mm->context.gmap_list); cpumask_clear(&mm->context.cpu_attach_mask); atomic_set(&mm->context.attach_count, 0); mm->context.flush_mm = 0; - mm->context.asce_bits = _ASCE_TABLE_LENGTH | _ASCE_USER_BITS; - mm->context.asce_bits |= _ASCE_TYPE_REGION3; #ifdef CONFIG_PGSTE mm->context.alloc_pgste = page_table_allocate_pgste; mm->context.has_pgste = 0; mm->context.use_skey = 0; #endif - mm->context.asce_limit = STACK_TOP_MAX; + switch (mm->context.asce_limit) { + case 1UL << 42: + /* + * forked 3-level task, fall through to set new asce with new + * mm->pgd + */ + case 0: + /* context created by exec, set asce limit to 4TB */ + mm->context.asce_limit = STACK_TOP_MAX; + mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | + _ASCE_USER_BITS | _ASCE_TYPE_REGION3; + break; + case 1UL << 53: + /* forked 4-level task, set new asce with new mm->pgd */ + mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | + _ASCE_USER_BITS | _ASCE_TYPE_REGION2; + break; + case 1UL << 31: + /* forked 2-level compat task, set new asce with new mm->pgd */ + mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | + _ASCE_USER_BITS | _ASCE_TYPE_SEGMENT; + /* pgd_alloc() did not increase mm->nr_pmds */ + mm_inc_nr_pmds(mm); + } crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm)); return 0; } @@ -34,7 +58,7 @@ static inline int init_new_context(struct task_struct *tsk, static inline void set_user_asce(struct mm_struct *mm) { - S390_lowcore.user_asce = mm->context.asce_bits | __pa(mm->pgd); + S390_lowcore.user_asce = mm->context.asce; if (current->thread.mm_segment.ar4) __ctl_load(S390_lowcore.user_asce, 7, 7); set_cpu_flag(CIF_ASCE); @@ -63,7 +87,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, { int cpu = smp_processor_id(); - S390_lowcore.user_asce = next->context.asce_bits | __pa(next->pgd); + S390_lowcore.user_asce = next->context.asce; if (prev == next) return; if (MACHINE_HAS_TLB_LC) @@ -111,8 +135,6 @@ static inline void activate_mm(struct mm_struct *prev, static inline void arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) { - if (oldmm->context.asce_limit < mm->context.asce_limit) - crst_table_downgrade(mm, oldmm->context.asce_limit); } static inline void arch_exit_mmap(struct mm_struct *mm) diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index c873e682b67f..6dafabb6ae1a 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -45,7 +45,8 @@ struct zpci_fmb { u64 rpcit_ops; u64 dma_rbytes; u64 dma_wbytes; -} __packed __aligned(16); + u64 pad[2]; +} __packed __aligned(128); enum zpci_state { ZPCI_FN_STATE_RESERVED, diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h index 7b7858f158b4..5991cdcb5b40 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -56,8 +56,8 @@ static inline unsigned long pgd_entry_type(struct mm_struct *mm) return _REGION2_ENTRY_EMPTY; } -int crst_table_upgrade(struct mm_struct *, unsigned long limit); -void crst_table_downgrade(struct mm_struct *, unsigned long limit); +int crst_table_upgrade(struct mm_struct *); +void crst_table_downgrade(struct mm_struct *); static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address) { @@ -100,12 +100,26 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) static inline pgd_t *pgd_alloc(struct mm_struct *mm) { - spin_lock_init(&mm->context.list_lock); - INIT_LIST_HEAD(&mm->context.pgtable_list); - INIT_LIST_HEAD(&mm->context.gmap_list); - return (pgd_t *) crst_table_alloc(mm); + unsigned long *table = crst_table_alloc(mm); + + if (!table) + return NULL; + if (mm->context.asce_limit == (1UL << 31)) { + /* Forking a compat process with 2 page table levels */ + if (!pgtable_pmd_page_ctor(virt_to_page(table))) { + crst_table_free(mm, table); + return NULL; + } + } + return (pgd_t *) table; +} + +static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) +{ + if (mm->context.asce_limit == (1UL << 31)) + pgtable_pmd_page_dtor(virt_to_page(pgd)); + crst_table_free(mm, (unsigned long *) pgd); } -#define pgd_free(mm, pgd) crst_table_free(mm, (unsigned long *) pgd) static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, pgtable_t pte) diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index b16c3d0a1b9f..c1ea67db8404 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -163,7 +163,7 @@ extern __vector128 init_task_fpu_regs[__NUM_VXRS]; regs->psw.mask = PSW_USER_BITS | PSW_MASK_BA; \ regs->psw.addr = new_psw | PSW_ADDR_AMODE; \ regs->gprs[15] = new_stackp; \ - crst_table_downgrade(current->mm, 1UL << 31); \ + crst_table_downgrade(current->mm); \ execve_tail(); \ } while (0) diff --git a/arch/s390/include/asm/tlbflush.h b/arch/s390/include/asm/tlbflush.h index ca148f7c3eaa..a2e6ef32e054 100644 --- a/arch/s390/include/asm/tlbflush.h +++ b/arch/s390/include/asm/tlbflush.h @@ -110,8 +110,7 @@ static inline void __tlb_flush_asce(struct mm_struct *mm, unsigned long asce) static inline void __tlb_flush_kernel(void) { if (MACHINE_HAS_IDTE) - __tlb_flush_idte((unsigned long) init_mm.pgd | - init_mm.context.asce_bits); + __tlb_flush_idte(init_mm.context.asce); else __tlb_flush_global(); } @@ -133,8 +132,7 @@ static inline void __tlb_flush_asce(struct mm_struct *mm, unsigned long asce) static inline void __tlb_flush_kernel(void) { if (MACHINE_HAS_TLB_LC) - __tlb_flush_idte_local((unsigned long) init_mm.pgd | - init_mm.context.asce_bits); + __tlb_flush_idte_local(init_mm.context.asce); else __tlb_flush_local(); } @@ -148,8 +146,7 @@ static inline void __tlb_flush_mm(struct mm_struct * mm) * only ran on the local cpu. */ if (MACHINE_HAS_IDTE && list_empty(&mm->context.gmap_list)) - __tlb_flush_asce(mm, (unsigned long) mm->pgd | - mm->context.asce_bits); + __tlb_flush_asce(mm, mm->context.asce); else __tlb_flush_full(mm); } diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index 9cd248f637c7..dc6c9c604543 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -181,6 +181,7 @@ int main(void) OFFSET(__LC_PSW_SAVE_AREA, _lowcore, psw_save_area); OFFSET(__LC_PREFIX_SAVE_AREA, _lowcore, prefixreg_save_area); OFFSET(__LC_FP_CREG_SAVE_AREA, _lowcore, fpt_creg_save_area); + OFFSET(__LC_TOD_PROGREG_SAVE_AREA, _lowcore, tod_progreg_save_area); OFFSET(__LC_CPU_TIMER_SAVE_AREA, _lowcore, cpu_timer_save_area); OFFSET(__LC_CLOCK_COMP_SAVE_AREA, _lowcore, clock_comp_save_area); OFFSET(__LC_AREGS_SAVE_AREA, _lowcore, access_regs_save_area); diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c index 66c94417c0ba..4af60374eba0 100644 --- a/arch/s390/kernel/compat_signal.c +++ b/arch/s390/kernel/compat_signal.c @@ -271,7 +271,7 @@ static int restore_sigregs_ext32(struct pt_regs *regs, /* Restore high gprs from signal stack */ if (__copy_from_user(&gprs_high, &sregs_ext->gprs_high, - sizeof(&sregs_ext->gprs_high))) + sizeof(sregs_ext->gprs_high))) return -EFAULT; for (i = 0; i < NUM_GPRS; i++) *(__u32 *)®s->gprs[i] = gprs_high[i]; diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 857b6526d298..424e6809ad07 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -1197,114 +1197,12 @@ cleanup_critical: .quad .Lpsw_idle_lpsw .Lcleanup_save_fpu_regs: - TSTMSK __LC_CPU_FLAGS,_CIF_FPU - bor %r14 - clg %r9,BASED(.Lcleanup_save_fpu_regs_done) - jhe 5f - clg %r9,BASED(.Lcleanup_save_fpu_regs_fp) - jhe 4f - clg %r9,BASED(.Lcleanup_save_fpu_regs_vx_high) - jhe 3f - clg %r9,BASED(.Lcleanup_save_fpu_regs_vx_low) - jhe 2f - clg %r9,BASED(.Lcleanup_save_fpu_fpc_end) - jhe 1f - lg %r2,__LC_CURRENT - aghi %r2,__TASK_thread -0: # Store floating-point controls - stfpc __THREAD_FPU_fpc(%r2) -1: # Load register save area and check if VX is active - lg %r3,__THREAD_FPU_regs(%r2) - TSTMSK __LC_MACHINE_FLAGS,MACHINE_FLAG_VX - jz 4f # no VX -> store FP regs -2: # Store vector registers (V0-V15) - VSTM %v0,%v15,0,%r3 # vstm 0,15,0(3) -3: # Store vector registers (V16-V31) - VSTM %v16,%v31,256,%r3 # vstm 16,31,256(3) - j 5f # -> done, set CIF_FPU flag -4: # Store floating-point registers - std 0,0(%r3) - std 1,8(%r3) - std 2,16(%r3) - std 3,24(%r3) - std 4,32(%r3) - std 5,40(%r3) - std 6,48(%r3) - std 7,56(%r3) - std 8,64(%r3) - std 9,72(%r3) - std 10,80(%r3) - std 11,88(%r3) - std 12,96(%r3) - std 13,104(%r3) - std 14,112(%r3) - std 15,120(%r3) -5: # Set CIF_FPU flag - oi __LC_CPU_FLAGS+7,_CIF_FPU - lg %r9,48(%r11) # return from save_fpu_regs + larl %r9,save_fpu_regs br %r14 -.Lcleanup_save_fpu_fpc_end: - .quad .Lsave_fpu_regs_fpc_end -.Lcleanup_save_fpu_regs_vx_low: - .quad .Lsave_fpu_regs_vx_low -.Lcleanup_save_fpu_regs_vx_high: - .quad .Lsave_fpu_regs_vx_high -.Lcleanup_save_fpu_regs_fp: - .quad .Lsave_fpu_regs_fp -.Lcleanup_save_fpu_regs_done: - .quad .Lsave_fpu_regs_done .Lcleanup_load_fpu_regs: - TSTMSK __LC_CPU_FLAGS,_CIF_FPU - bnor %r14 - clg %r9,BASED(.Lcleanup_load_fpu_regs_done) - jhe 1f - clg %r9,BASED(.Lcleanup_load_fpu_regs_fp) - jhe 2f - clg %r9,BASED(.Lcleanup_load_fpu_regs_vx_high) - jhe 3f - clg %r9,BASED(.Lcleanup_load_fpu_regs_vx) - jhe 4f - lg %r4,__LC_CURRENT - aghi %r4,__TASK_thread - lfpc __THREAD_FPU_fpc(%r4) - TSTMSK __LC_MACHINE_FLAGS,MACHINE_FLAG_VX - lg %r4,__THREAD_FPU_regs(%r4) # %r4 <- reg save area - jz 2f # -> no VX, load FP regs -4: # Load V0 ..V15 registers - VLM %v0,%v15,0,%r4 -3: # Load V16..V31 registers - VLM %v16,%v31,256,%r4 - j 1f -2: # Load floating-point registers - ld 0,0(%r4) - ld 1,8(%r4) - ld 2,16(%r4) - ld 3,24(%r4) - ld 4,32(%r4) - ld 5,40(%r4) - ld 6,48(%r4) - ld 7,56(%r4) - ld 8,64(%r4) - ld 9,72(%r4) - ld 10,80(%r4) - ld 11,88(%r4) - ld 12,96(%r4) - ld 13,104(%r4) - ld 14,112(%r4) - ld 15,120(%r4) -1: # Clear CIF_FPU bit - ni __LC_CPU_FLAGS+7,255-_CIF_FPU - lg %r9,48(%r11) # return from load_fpu_regs + larl %r9,load_fpu_regs br %r14 -.Lcleanup_load_fpu_regs_vx: - .quad .Lload_fpu_regs_vx -.Lcleanup_load_fpu_regs_vx_high: - .quad .Lload_fpu_regs_vx_high -.Lcleanup_load_fpu_regs_fp: - .quad .Lload_fpu_regs_fp -.Lcleanup_load_fpu_regs_done: - .quad .Lload_fpu_regs_done /* * Integer constants diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S index 58b719fa8067..1ad2407c7f75 100644 --- a/arch/s390/kernel/head64.S +++ b/arch/s390/kernel/head64.S @@ -16,7 +16,7 @@ __HEAD ENTRY(startup_continue) - tm __LC_STFL_FAC_LIST+6,0x80 # LPP available ? + tm __LC_STFL_FAC_LIST+5,0x80 # LPP available ? jz 0f xc __LC_LPP+1(7,0),__LC_LPP+1 # clear lpp and current_pid mvi __LC_LPP,0x80 # and set LPP_MAGIC diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index c837bcacf218..1f581eb61bc2 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -329,6 +329,7 @@ static void __init setup_lowcore(void) + PAGE_SIZE - STACK_FRAME_OVERHEAD - sizeof(struct pt_regs); lc->current_task = (unsigned long) init_thread_union.thread_info.task; lc->thread_info = (unsigned long) &init_thread_union; + lc->lpp = LPP_MAGIC; lc->machine_flags = S390_lowcore.machine_flags; lc->stfl_fac_list = S390_lowcore.stfl_fac_list; memcpy(lc->stfle_fac_list, S390_lowcore.stfle_fac_list, diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 846589281b04..575dc123bda2 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -1268,44 +1268,18 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) return 0; } -/* - * Backs up the current FP/VX register save area on a particular - * destination. Used to switch between different register save - * areas. - */ -static inline void save_fpu_to(struct fpu *dst) -{ - dst->fpc = current->thread.fpu.fpc; - dst->regs = current->thread.fpu.regs; -} - -/* - * Switches the FP/VX register save area from which to lazy - * restore register contents. - */ -static inline void load_fpu_from(struct fpu *from) -{ - current->thread.fpu.fpc = from->fpc; - current->thread.fpu.regs = from->regs; -} - void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { /* Save host register state */ save_fpu_regs(); - save_fpu_to(&vcpu->arch.host_fpregs); - - if (test_kvm_facility(vcpu->kvm, 129)) { - current->thread.fpu.fpc = vcpu->run->s.regs.fpc; - /* - * Use the register save area in the SIE-control block - * for register restore and save in kvm_arch_vcpu_put() - */ - current->thread.fpu.vxrs = - (__vector128 *)&vcpu->run->s.regs.vrs; - } else - load_fpu_from(&vcpu->arch.guest_fpregs); + vcpu->arch.host_fpregs.fpc = current->thread.fpu.fpc; + vcpu->arch.host_fpregs.regs = current->thread.fpu.regs; + /* Depending on MACHINE_HAS_VX, data stored to vrs either + * has vector register or floating point register format. + */ + current->thread.fpu.regs = vcpu->run->s.regs.vrs; + current->thread.fpu.fpc = vcpu->run->s.regs.fpc; if (test_fp_ctl(current->thread.fpu.fpc)) /* User space provided an invalid FPC, let's clear it */ current->thread.fpu.fpc = 0; @@ -1321,19 +1295,13 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) atomic_andnot(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags); gmap_disable(vcpu->arch.gmap); + /* Save guest register state */ save_fpu_regs(); + vcpu->run->s.regs.fpc = current->thread.fpu.fpc; - if (test_kvm_facility(vcpu->kvm, 129)) - /* - * kvm_arch_vcpu_load() set up the register save area to - * the &vcpu->run->s.regs.vrs and, thus, the vector registers - * are already saved. Only the floating-point control must be - * copied. - */ - vcpu->run->s.regs.fpc = current->thread.fpu.fpc; - else - save_fpu_to(&vcpu->arch.guest_fpregs); - load_fpu_from(&vcpu->arch.host_fpregs); + /* Restore host register state */ + current->thread.fpu.fpc = vcpu->arch.host_fpregs.fpc; + current->thread.fpu.regs = vcpu->arch.host_fpregs.regs; save_access_regs(vcpu->run->s.regs.acrs); restore_access_regs(vcpu->arch.host_acrs); @@ -1351,8 +1319,9 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu) memset(vcpu->arch.sie_block->gcr, 0, 16 * sizeof(__u64)); vcpu->arch.sie_block->gcr[0] = 0xE0UL; vcpu->arch.sie_block->gcr[14] = 0xC2000000UL; - vcpu->arch.guest_fpregs.fpc = 0; - asm volatile("lfpc %0" : : "Q" (vcpu->arch.guest_fpregs.fpc)); + /* make sure the new fpc will be lazily loaded */ + save_fpu_regs(); + current->thread.fpu.fpc = 0; vcpu->arch.sie_block->gbea = 1; vcpu->arch.sie_block->pp = 0; vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID; @@ -1501,19 +1470,6 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, vcpu->arch.local_int.wq = &vcpu->wq; vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags; - /* - * Allocate a save area for floating-point registers. If the vector - * extension is available, register contents are saved in the SIE - * control block. The allocated save area is still required in - * particular places, for example, in kvm_s390_vcpu_store_status(). - */ - vcpu->arch.guest_fpregs.fprs = kzalloc(sizeof(freg_t) * __NUM_FPRS, - GFP_KERNEL); - if (!vcpu->arch.guest_fpregs.fprs) { - rc = -ENOMEM; - goto out_free_sie_block; - } - rc = kvm_vcpu_init(vcpu, kvm, id); if (rc) goto out_free_sie_block; @@ -1734,19 +1690,27 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { + /* make sure the new values will be lazily loaded */ + save_fpu_regs(); if (test_fp_ctl(fpu->fpc)) return -EINVAL; - memcpy(vcpu->arch.guest_fpregs.fprs, &fpu->fprs, sizeof(fpu->fprs)); - vcpu->arch.guest_fpregs.fpc = fpu->fpc; - save_fpu_regs(); - load_fpu_from(&vcpu->arch.guest_fpregs); + current->thread.fpu.fpc = fpu->fpc; + if (MACHINE_HAS_VX) + convert_fp_to_vx(current->thread.fpu.vxrs, (freg_t *)fpu->fprs); + else + memcpy(current->thread.fpu.fprs, &fpu->fprs, sizeof(fpu->fprs)); return 0; } int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { - memcpy(&fpu->fprs, vcpu->arch.guest_fpregs.fprs, sizeof(fpu->fprs)); - fpu->fpc = vcpu->arch.guest_fpregs.fpc; + /* make sure we have the latest values */ + save_fpu_regs(); + if (MACHINE_HAS_VX) + convert_vx_to_fp((freg_t *)fpu->fprs, current->thread.fpu.vxrs); + else + memcpy(fpu->fprs, current->thread.fpu.fprs, sizeof(fpu->fprs)); + fpu->fpc = current->thread.fpu.fpc; return 0; } @@ -2266,41 +2230,50 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa) { unsigned char archmode = 1; + freg_t fprs[NUM_FPRS]; unsigned int px; u64 clkcomp; int rc; + px = kvm_s390_get_prefix(vcpu); if (gpa == KVM_S390_STORE_STATUS_NOADDR) { if (write_guest_abs(vcpu, 163, &archmode, 1)) return -EFAULT; - gpa = SAVE_AREA_BASE; + gpa = 0; } else if (gpa == KVM_S390_STORE_STATUS_PREFIXED) { if (write_guest_real(vcpu, 163, &archmode, 1)) return -EFAULT; - gpa = kvm_s390_real_to_abs(vcpu, SAVE_AREA_BASE); + gpa = px; + } else + gpa -= __LC_FPREGS_SAVE_AREA; + + /* manually convert vector registers if necessary */ + if (MACHINE_HAS_VX) { + convert_vx_to_fp(fprs, (__vector128 *) vcpu->run->s.regs.vrs); + rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA, + fprs, 128); + } else { + rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA, + vcpu->run->s.regs.vrs, 128); } - rc = write_guest_abs(vcpu, gpa + offsetof(struct save_area, fp_regs), - vcpu->arch.guest_fpregs.fprs, 128); - rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, gp_regs), + rc |= write_guest_abs(vcpu, gpa + __LC_GPREGS_SAVE_AREA, vcpu->run->s.regs.gprs, 128); - rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, psw), + rc |= write_guest_abs(vcpu, gpa + __LC_PSW_SAVE_AREA, &vcpu->arch.sie_block->gpsw, 16); - px = kvm_s390_get_prefix(vcpu); - rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, pref_reg), + rc |= write_guest_abs(vcpu, gpa + __LC_PREFIX_SAVE_AREA, &px, 4); - rc |= write_guest_abs(vcpu, - gpa + offsetof(struct save_area, fp_ctrl_reg), - &vcpu->arch.guest_fpregs.fpc, 4); - rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, tod_reg), + rc |= write_guest_abs(vcpu, gpa + __LC_FP_CREG_SAVE_AREA, + &vcpu->run->s.regs.fpc, 4); + rc |= write_guest_abs(vcpu, gpa + __LC_TOD_PROGREG_SAVE_AREA, &vcpu->arch.sie_block->todpr, 4); - rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, timer), + rc |= write_guest_abs(vcpu, gpa + __LC_CPU_TIMER_SAVE_AREA, &vcpu->arch.sie_block->cputm, 8); clkcomp = vcpu->arch.sie_block->ckc >> 8; - rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, clk_cmp), + rc |= write_guest_abs(vcpu, gpa + __LC_CLOCK_COMP_SAVE_AREA, &clkcomp, 8); - rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, acc_regs), + rc |= write_guest_abs(vcpu, gpa + __LC_AREGS_SAVE_AREA, &vcpu->run->s.regs.acrs, 64); - rc |= write_guest_abs(vcpu, gpa + offsetof(struct save_area, ctrl_regs), + rc |= write_guest_abs(vcpu, gpa + __LC_CREGS_SAVE_AREA, &vcpu->arch.sie_block->gcr, 128); return rc ? -EFAULT : 0; } @@ -2313,19 +2286,7 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr) * it into the save area */ save_fpu_regs(); - if (test_kvm_facility(vcpu->kvm, 129)) { - /* - * If the vector extension is available, the vector registers - * which overlaps with floating-point registers are saved in - * the SIE-control block. Hence, extract the floating-point - * registers and the FPC value and store them in the - * guest_fpregs structure. - */ - vcpu->arch.guest_fpregs.fpc = current->thread.fpu.fpc; - convert_vx_to_fp(vcpu->arch.guest_fpregs.fprs, - current->thread.fpu.vxrs); - } else - save_fpu_to(&vcpu->arch.guest_fpregs); + vcpu->run->s.regs.fpc = current->thread.fpu.fpc; save_access_regs(vcpu->run->s.regs.acrs); return kvm_s390_store_status_unloaded(vcpu, addr); diff --git a/arch/s390/mm/extable.c b/arch/s390/mm/extable.c index 4d1ee88864e8..18c8b819b0aa 100644 --- a/arch/s390/mm/extable.c +++ b/arch/s390/mm/extable.c @@ -52,12 +52,16 @@ void sort_extable(struct exception_table_entry *start, int i; /* Normalize entries to being relative to the start of the section */ - for (p = start, i = 0; p < finish; p++, i += 8) + for (p = start, i = 0; p < finish; p++, i += 8) { p->insn += i; + p->fixup += i + 4; + } sort(start, finish - start, sizeof(*start), cmp_ex, NULL); /* Denormalize all entries */ - for (p = start, i = 0; p < finish; p++, i += 8) + for (p = start, i = 0; p < finish; p++, i += 8) { p->insn -= i; + p->fixup -= i + 4; + } } #ifdef CONFIG_MODULES diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index c722400c7697..feff9caf89b5 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -89,7 +89,8 @@ void __init paging_init(void) asce_bits = _ASCE_TYPE_REGION3 | _ASCE_TABLE_LENGTH; pgd_type = _REGION3_ENTRY_EMPTY; } - S390_lowcore.kernel_asce = (__pa(init_mm.pgd) & PAGE_MASK) | asce_bits; + init_mm.context.asce = (__pa(init_mm.pgd) & PAGE_MASK) | asce_bits; + S390_lowcore.kernel_asce = init_mm.context.asce; clear_table((unsigned long *) init_mm.pgd, pgd_type, sizeof(unsigned long)*2048); vmem_map_init(); diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index ea01477b4aa6..f2b6b1d9c804 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -174,7 +174,7 @@ int s390_mmap_check(unsigned long addr, unsigned long len, unsigned long flags) if (!(flags & MAP_FIXED)) addr = 0; if ((addr + len) >= TASK_SIZE) - return crst_table_upgrade(current->mm, 1UL << 53); + return crst_table_upgrade(current->mm); return 0; } @@ -191,7 +191,7 @@ s390_get_unmapped_area(struct file *filp, unsigned long addr, return area; if (area == -ENOMEM && !is_compat_task() && TASK_SIZE < (1UL << 53)) { /* Upgrade the page table to 4 levels and retry. */ - rc = crst_table_upgrade(mm, 1UL << 53); + rc = crst_table_upgrade(mm); if (rc) return (unsigned long) rc; area = arch_get_unmapped_area(filp, addr, len, pgoff, flags); @@ -213,7 +213,7 @@ s390_get_unmapped_area_topdown(struct file *filp, const unsigned long addr, return area; if (area == -ENOMEM && !is_compat_task() && TASK_SIZE < (1UL << 53)) { /* Upgrade the page table to 4 levels and retry. */ - rc = crst_table_upgrade(mm, 1UL << 53); + rc = crst_table_upgrade(mm); if (rc) return (unsigned long) rc; area = arch_get_unmapped_area_topdown(filp, addr, len, diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 54ef3bc01b43..471a370a527b 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -49,81 +49,52 @@ static void __crst_table_upgrade(void *arg) __tlb_flush_local(); } -int crst_table_upgrade(struct mm_struct *mm, unsigned long limit) +int crst_table_upgrade(struct mm_struct *mm) { unsigned long *table, *pgd; - unsigned long entry; - int flush; - BUG_ON(limit > (1UL << 53)); - flush = 0; -repeat: + /* upgrade should only happen from 3 to 4 levels */ + BUG_ON(mm->context.asce_limit != (1UL << 42)); + table = crst_table_alloc(mm); if (!table) return -ENOMEM; + spin_lock_bh(&mm->page_table_lock); - if (mm->context.asce_limit < limit) { - pgd = (unsigned long *) mm->pgd; - if (mm->context.asce_limit <= (1UL << 31)) { - entry = _REGION3_ENTRY_EMPTY; - mm->context.asce_limit = 1UL << 42; - mm->context.asce_bits = _ASCE_TABLE_LENGTH | - _ASCE_USER_BITS | - _ASCE_TYPE_REGION3; - } else { - entry = _REGION2_ENTRY_EMPTY; - mm->context.asce_limit = 1UL << 53; - mm->context.asce_bits = _ASCE_TABLE_LENGTH | - _ASCE_USER_BITS | - _ASCE_TYPE_REGION2; - } - crst_table_init(table, entry); - pgd_populate(mm, (pgd_t *) table, (pud_t *) pgd); - mm->pgd = (pgd_t *) table; - mm->task_size = mm->context.asce_limit; - table = NULL; - flush = 1; - } + pgd = (unsigned long *) mm->pgd; + crst_table_init(table, _REGION2_ENTRY_EMPTY); + pgd_populate(mm, (pgd_t *) table, (pud_t *) pgd); + mm->pgd = (pgd_t *) table; + mm->context.asce_limit = 1UL << 53; + mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | + _ASCE_USER_BITS | _ASCE_TYPE_REGION2; + mm->task_size = mm->context.asce_limit; spin_unlock_bh(&mm->page_table_lock); - if (table) - crst_table_free(mm, table); - if (mm->context.asce_limit < limit) - goto repeat; - if (flush) - on_each_cpu(__crst_table_upgrade, mm, 0); + + on_each_cpu(__crst_table_upgrade, mm, 0); return 0; } -void crst_table_downgrade(struct mm_struct *mm, unsigned long limit) +void crst_table_downgrade(struct mm_struct *mm) { pgd_t *pgd; + /* downgrade should only happen from 3 to 2 levels (compat only) */ + BUG_ON(mm->context.asce_limit != (1UL << 42)); + if (current->active_mm == mm) { clear_user_asce(); __tlb_flush_mm(mm); } - while (mm->context.asce_limit > limit) { - pgd = mm->pgd; - switch (pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) { - case _REGION_ENTRY_TYPE_R2: - mm->context.asce_limit = 1UL << 42; - mm->context.asce_bits = _ASCE_TABLE_LENGTH | - _ASCE_USER_BITS | - _ASCE_TYPE_REGION3; - break; - case _REGION_ENTRY_TYPE_R3: - mm->context.asce_limit = 1UL << 31; - mm->context.asce_bits = _ASCE_TABLE_LENGTH | - _ASCE_USER_BITS | - _ASCE_TYPE_SEGMENT; - break; - default: - BUG(); - } - mm->pgd = (pgd_t *) (pgd_val(*pgd) & _REGION_ENTRY_ORIGIN); - mm->task_size = mm->context.asce_limit; - crst_table_free(mm, (unsigned long *) pgd); - } + + pgd = mm->pgd; + mm->pgd = (pgd_t *) (pgd_val(*pgd) & _REGION_ENTRY_ORIGIN); + mm->context.asce_limit = 1UL << 31; + mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | + _ASCE_USER_BITS | _ASCE_TYPE_SEGMENT; + mm->task_size = mm->context.asce_limit; + crst_table_free(mm, (unsigned long *) pgd); + if (current->active_mm == mm) set_user_asce(mm); } diff --git a/arch/s390/net/bpf_jit.h b/arch/s390/net/bpf_jit.h index f010c93a88b1..fda605dbc1b4 100644 --- a/arch/s390/net/bpf_jit.h +++ b/arch/s390/net/bpf_jit.h @@ -37,7 +37,7 @@ extern u8 sk_load_word[], sk_load_half[], sk_load_byte[]; * | | | * +---------------+ | * | 8 byte skbp | | - * R15+170 -> +---------------+ | + * R15+176 -> +---------------+ | * | 8 byte hlen | | * R15+168 -> +---------------+ | * | 4 byte align | | @@ -58,7 +58,7 @@ extern u8 sk_load_word[], sk_load_half[], sk_load_byte[]; #define STK_OFF (STK_SPACE - STK_160_UNUSED) #define STK_OFF_TMP 160 /* Offset of tmp buffer on stack */ #define STK_OFF_HLEN 168 /* Offset of SKB header length on stack */ -#define STK_OFF_SKBP 170 /* Offset of SKB pointer on stack */ +#define STK_OFF_SKBP 176 /* Offset of SKB pointer on stack */ #define STK_OFF_R6 (160 - 11 * 8) /* Offset of r6 on stack */ #define STK_OFF_TCCNT (160 - 12 * 8) /* Offset of tail_call_cnt on stack */ diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 9a0c4c22e536..0e2919dd8df3 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -45,7 +45,7 @@ struct bpf_jit { int labels[1]; /* Labels for local jumps */ }; -#define BPF_SIZE_MAX 0x7ffff /* Max size for program (20 bit signed displ) */ +#define BPF_SIZE_MAX 0xffff /* Max size for program (16 bit branches) */ #define SEEN_SKB 1 /* skb access */ #define SEEN_MEM 2 /* use mem[] for temporary storage */ @@ -446,7 +446,7 @@ static void bpf_jit_prologue(struct bpf_jit *jit, bool is_classic) emit_load_skb_data_hlen(jit); if (jit->seen & SEEN_SKB_CHANGE) /* stg %b1,ST_OFF_SKBP(%r0,%r15) */ - EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0, REG_15, + EMIT6_DISP_LH(0xe3000000, 0x0024, BPF_REG_1, REG_0, REG_15, STK_OFF_SKBP); /* Clear A (%b0) and X (%b7) registers for converted BPF programs */ if (is_classic) { diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 7ef12a3ace3a..19442395f413 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -871,8 +871,11 @@ static inline int barsize(u8 size) static int zpci_mem_init(void) { + BUILD_BUG_ON(!is_power_of_2(__alignof__(struct zpci_fmb)) || + __alignof__(struct zpci_fmb) < sizeof(struct zpci_fmb)); + zdev_fmb_cache = kmem_cache_create("PCI_FMB_cache", sizeof(struct zpci_fmb), - 16, 0, NULL); + __alignof__(struct zpci_fmb), 0, NULL); if (!zdev_fmb_cache) goto error_zdev; diff --git a/arch/sh/mm/kmap.c b/arch/sh/mm/kmap.c index ec29e14ec5a8..bf25d7c79a2d 100644 --- a/arch/sh/mm/kmap.c +++ b/arch/sh/mm/kmap.c @@ -36,6 +36,7 @@ void *kmap_coherent(struct page *page, unsigned long addr) BUG_ON(!test_bit(PG_dcache_clean, &page->flags)); + preempt_disable(); pagefault_disable(); idx = FIX_CMAP_END - @@ -64,4 +65,5 @@ void kunmap_coherent(void *kvaddr) } pagefault_enable(); + preempt_enable(); } diff --git a/arch/sparc/include/asm/head_64.h b/arch/sparc/include/asm/head_64.h index 10e9dabc4c41..f0700cfeedd7 100644 --- a/arch/sparc/include/asm/head_64.h +++ b/arch/sparc/include/asm/head_64.h @@ -15,6 +15,10 @@ #define PTREGS_OFF (STACK_BIAS + STACKFRAME_SZ) +#define RTRAP_PSTATE (PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_IE) +#define RTRAP_PSTATE_IRQOFF (PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV) +#define RTRAP_PSTATE_AG_IRQOFF (PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_AG) + #define __CHEETAH_ID 0x003e0014 #define __JALAPENO_ID 0x003e0016 #define __SERRANO_ID 0x003e0022 diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 131d36fcd07a..408b715c95a5 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -375,7 +375,7 @@ static inline pgprot_t pgprot_noncached(pgprot_t prot) #define pgprot_noncached pgprot_noncached #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) -static inline pte_t pte_mkhuge(pte_t pte) +static inline unsigned long __pte_huge_mask(void) { unsigned long mask; @@ -390,8 +390,19 @@ static inline pte_t pte_mkhuge(pte_t pte) : "=r" (mask) : "i" (_PAGE_SZHUGE_4U), "i" (_PAGE_SZHUGE_4V)); - return __pte(pte_val(pte) | mask); + return mask; } + +static inline pte_t pte_mkhuge(pte_t pte) +{ + return __pte(pte_val(pte) | __pte_huge_mask()); +} + +static inline bool is_hugetlb_pte(pte_t pte) +{ + return !!(pte_val(pte) & __pte_huge_mask()); +} + #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline pmd_t pmd_mkhuge(pmd_t pmd) { @@ -403,6 +414,11 @@ static inline pmd_t pmd_mkhuge(pmd_t pmd) return __pmd(pte_val(pte)); } #endif +#else +static inline bool is_hugetlb_pte(pte_t pte) +{ + return false; +} #endif static inline pte_t pte_mkdirty(pte_t pte) @@ -865,6 +881,19 @@ static inline unsigned long pud_pfn(pud_t pud) void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr, pte_t *ptep, pte_t orig, int fullmm); +static void maybe_tlb_batch_add(struct mm_struct *mm, unsigned long vaddr, + pte_t *ptep, pte_t orig, int fullmm) +{ + /* It is more efficient to let flush_tlb_kernel_range() + * handle init_mm tlb flushes. + * + * SUN4V NOTE: _PAGE_VALID is the same value in both the SUN4U + * and SUN4V pte layout, so this inline test is fine. + */ + if (likely(mm != &init_mm) && pte_accessible(mm, orig)) + tlb_batch_add(mm, vaddr, ptep, orig, fullmm); +} + #define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr, @@ -881,15 +910,7 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t orig = *ptep; *ptep = pte; - - /* It is more efficient to let flush_tlb_kernel_range() - * handle init_mm tlb flushes. - * - * SUN4V NOTE: _PAGE_VALID is the same value in both the SUN4U - * and SUN4V pte layout, so this inline test is fine. - */ - if (likely(mm != &init_mm) && pte_accessible(mm, orig)) - tlb_batch_add(mm, addr, ptep, orig, fullmm); + maybe_tlb_batch_add(mm, addr, ptep, orig, fullmm); } #define set_pte_at(mm,addr,ptep,pte) \ diff --git a/arch/sparc/include/asm/tlbflush_64.h b/arch/sparc/include/asm/tlbflush_64.h index dea1cfa2122b..a8e192e90700 100644 --- a/arch/sparc/include/asm/tlbflush_64.h +++ b/arch/sparc/include/asm/tlbflush_64.h @@ -8,6 +8,7 @@ #define TLB_BATCH_NR 192 struct tlb_batch { + bool huge; struct mm_struct *mm; unsigned long tlb_nr; unsigned long active; @@ -16,7 +17,7 @@ struct tlb_batch { void flush_tsb_kernel_range(unsigned long start, unsigned long end); void flush_tsb_user(struct tlb_batch *tb); -void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr); +void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr, bool huge); /* TLB flush operations. */ diff --git a/arch/sparc/include/asm/ttable.h b/arch/sparc/include/asm/ttable.h index 71b5a67522ab..781b9f1dbdc2 100644 --- a/arch/sparc/include/asm/ttable.h +++ b/arch/sparc/include/asm/ttable.h @@ -589,8 +589,8 @@ user_rtt_fill_64bit: \ restored; \ nop; nop; nop; nop; nop; nop; \ nop; nop; nop; nop; nop; \ - ba,a,pt %xcc, user_rtt_fill_fixup; \ - ba,a,pt %xcc, user_rtt_fill_fixup; \ + ba,a,pt %xcc, user_rtt_fill_fixup_dax; \ + ba,a,pt %xcc, user_rtt_fill_fixup_mna; \ ba,a,pt %xcc, user_rtt_fill_fixup; @@ -652,8 +652,8 @@ user_rtt_fill_32bit: \ restored; \ nop; nop; nop; nop; nop; \ nop; nop; nop; \ - ba,a,pt %xcc, user_rtt_fill_fixup; \ - ba,a,pt %xcc, user_rtt_fill_fixup; \ + ba,a,pt %xcc, user_rtt_fill_fixup_dax; \ + ba,a,pt %xcc, user_rtt_fill_fixup_mna; \ ba,a,pt %xcc, user_rtt_fill_fixup; diff --git a/arch/sparc/kernel/Makefile b/arch/sparc/kernel/Makefile index 7cf9c6ea3f1f..fdb13327fded 100644 --- a/arch/sparc/kernel/Makefile +++ b/arch/sparc/kernel/Makefile @@ -21,6 +21,7 @@ CFLAGS_REMOVE_perf_event.o := -pg CFLAGS_REMOVE_pcr.o := -pg endif +obj-$(CONFIG_SPARC64) += urtt_fill.o obj-$(CONFIG_SPARC32) += entry.o wof.o wuf.o obj-$(CONFIG_SPARC32) += etrap_32.o obj-$(CONFIG_SPARC32) += rtrap_32.o diff --git a/arch/sparc/kernel/cherrs.S b/arch/sparc/kernel/cherrs.S index 4ee1ad420862..655628def68e 100644 --- a/arch/sparc/kernel/cherrs.S +++ b/arch/sparc/kernel/cherrs.S @@ -214,8 +214,7 @@ do_dcpe_tl1_nonfatal: /* Ok we may use interrupt globals safely. */ subcc %g1, %g2, %g1 ! Next cacheline bge,pt %icc, 1b nop - ba,pt %xcc, dcpe_icpe_tl1_common - nop + ba,a,pt %xcc, dcpe_icpe_tl1_common do_dcpe_tl1_fatal: sethi %hi(1f), %g7 @@ -224,8 +223,7 @@ do_dcpe_tl1_fatal: mov 0x2, %o0 call cheetah_plus_parity_error add %sp, PTREGS_OFF, %o1 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap .size do_dcpe_tl1,.-do_dcpe_tl1 .globl do_icpe_tl1 @@ -259,8 +257,7 @@ do_icpe_tl1_nonfatal: /* Ok we may use interrupt globals safely. */ subcc %g1, %g2, %g1 bge,pt %icc, 1b nop - ba,pt %xcc, dcpe_icpe_tl1_common - nop + ba,a,pt %xcc, dcpe_icpe_tl1_common do_icpe_tl1_fatal: sethi %hi(1f), %g7 @@ -269,8 +266,7 @@ do_icpe_tl1_fatal: mov 0x3, %o0 call cheetah_plus_parity_error add %sp, PTREGS_OFF, %o1 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap .size do_icpe_tl1,.-do_icpe_tl1 .type dcpe_icpe_tl1_common,#function @@ -456,7 +452,7 @@ __cheetah_log_error: cmp %g2, 0x63 be c_cee nop - ba,pt %xcc, c_deferred + ba,a,pt %xcc, c_deferred .size __cheetah_log_error,.-__cheetah_log_error /* Cheetah FECC trap handling, we get here from tl{0,1}_fecc diff --git a/arch/sparc/kernel/entry.S b/arch/sparc/kernel/entry.S index 33c02b15f478..a83707c83be8 100644 --- a/arch/sparc/kernel/entry.S +++ b/arch/sparc/kernel/entry.S @@ -948,7 +948,24 @@ linux_syscall_trace: cmp %o0, 0 bne 3f mov -ENOSYS, %o0 + + /* Syscall tracing can modify the registers. */ + ld [%sp + STACKFRAME_SZ + PT_G1], %g1 + sethi %hi(sys_call_table), %l7 + ld [%sp + STACKFRAME_SZ + PT_I0], %i0 + or %l7, %lo(sys_call_table), %l7 + ld [%sp + STACKFRAME_SZ + PT_I1], %i1 + ld [%sp + STACKFRAME_SZ + PT_I2], %i2 + ld [%sp + STACKFRAME_SZ + PT_I3], %i3 + ld [%sp + STACKFRAME_SZ + PT_I4], %i4 + ld [%sp + STACKFRAME_SZ + PT_I5], %i5 + cmp %g1, NR_syscalls + bgeu 3f + mov -ENOSYS, %o0 + + sll %g1, 2, %l4 mov %i0, %o0 + ld [%l7 + %l4], %l7 mov %i1, %o1 mov %i2, %o2 mov %i3, %o3 diff --git a/arch/sparc/kernel/fpu_traps.S b/arch/sparc/kernel/fpu_traps.S index a6864826a4bd..336d2750fe78 100644 --- a/arch/sparc/kernel/fpu_traps.S +++ b/arch/sparc/kernel/fpu_traps.S @@ -100,8 +100,8 @@ do_fpdis: fmuld %f0, %f2, %f26 faddd %f0, %f2, %f28 fmuld %f0, %f2, %f30 - b,pt %xcc, fpdis_exit - nop + ba,a,pt %xcc, fpdis_exit + 2: andcc %g5, FPRS_DU, %g0 bne,pt %icc, 3f fzero %f32 @@ -144,8 +144,8 @@ do_fpdis: fmuld %f32, %f34, %f58 faddd %f32, %f34, %f60 fmuld %f32, %f34, %f62 - ba,pt %xcc, fpdis_exit - nop + ba,a,pt %xcc, fpdis_exit + 3: mov SECONDARY_CONTEXT, %g3 add %g6, TI_FPREGS, %g1 @@ -197,8 +197,7 @@ fpdis_exit2: fp_other_bounce: call do_fpother add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap .size fp_other_bounce,.-fp_other_bounce .align 32 diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S index f2d30cab5b3f..51faf92ace00 100644 --- a/arch/sparc/kernel/head_64.S +++ b/arch/sparc/kernel/head_64.S @@ -461,9 +461,8 @@ sun4v_chip_type: subcc %g3, 1, %g3 bne,pt %xcc, 41b add %g1, 1, %g1 - mov SUN4V_CHIP_SPARC64X, %g4 ba,pt %xcc, 5f - nop + mov SUN4V_CHIP_SPARC64X, %g4 49: mov SUN4V_CHIP_UNKNOWN, %g4 @@ -548,8 +547,7 @@ sun4u_init: stxa %g0, [%g7] ASI_DMMU membar #Sync - ba,pt %xcc, sun4u_continue - nop + ba,a,pt %xcc, sun4u_continue sun4v_init: /* Set ctx 0 */ @@ -560,14 +558,12 @@ sun4v_init: mov SECONDARY_CONTEXT, %g7 stxa %g0, [%g7] ASI_MMU membar #Sync - ba,pt %xcc, niagara_tlb_fixup - nop + ba,a,pt %xcc, niagara_tlb_fixup sun4u_continue: BRANCH_IF_ANY_CHEETAH(g1, g7, cheetah_tlb_fixup) - ba,pt %xcc, spitfire_tlb_fixup - nop + ba,a,pt %xcc, spitfire_tlb_fixup niagara_tlb_fixup: mov 3, %g2 /* Set TLB type to hypervisor. */ @@ -639,8 +635,7 @@ niagara_patch: call hypervisor_patch_cachetlbops nop - ba,pt %xcc, tlb_fixup_done - nop + ba,a,pt %xcc, tlb_fixup_done cheetah_tlb_fixup: mov 2, %g2 /* Set TLB type to cheetah+. */ @@ -659,8 +654,7 @@ cheetah_tlb_fixup: call cheetah_patch_cachetlbops nop - ba,pt %xcc, tlb_fixup_done - nop + ba,a,pt %xcc, tlb_fixup_done spitfire_tlb_fixup: /* Set TLB type to spitfire. */ @@ -782,8 +776,7 @@ setup_trap_table: call %o1 add %sp, (2047 + 128), %o0 - ba,pt %xcc, 2f - nop + ba,a,pt %xcc, 2f 1: sethi %hi(sparc64_ttable_tl0), %o0 set prom_set_trap_table_name, %g2 @@ -822,8 +815,7 @@ setup_trap_table: BRANCH_IF_ANY_CHEETAH(o2, o3, 1f) - ba,pt %xcc, 2f - nop + ba,a,pt %xcc, 2f /* Disable STICK_INT interrupts. */ 1: diff --git a/arch/sparc/kernel/misctrap.S b/arch/sparc/kernel/misctrap.S index 753b4f031bfb..34b4933900bf 100644 --- a/arch/sparc/kernel/misctrap.S +++ b/arch/sparc/kernel/misctrap.S @@ -18,8 +18,7 @@ __do_privact: 109: or %g7, %lo(109b), %g7 call do_privact add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap .size __do_privact,.-__do_privact .type do_mna,#function @@ -46,8 +45,7 @@ do_mna: mov %l5, %o2 call mem_address_unaligned add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap .size do_mna,.-do_mna .type do_lddfmna,#function @@ -65,8 +63,7 @@ do_lddfmna: mov %l5, %o2 call handle_lddfmna add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap .size do_lddfmna,.-do_lddfmna .type do_stdfmna,#function @@ -84,8 +81,7 @@ do_stdfmna: mov %l5, %o2 call handle_stdfmna add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap .size do_stdfmna,.-do_stdfmna .type breakpoint_trap,#function diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c index badf0951d73c..9f9614df9e1e 100644 --- a/arch/sparc/kernel/pci.c +++ b/arch/sparc/kernel/pci.c @@ -994,6 +994,23 @@ void pcibios_set_master(struct pci_dev *dev) /* No special bus mastering setup handling */ } +#ifdef CONFIG_PCI_IOV +int pcibios_add_device(struct pci_dev *dev) +{ + struct pci_dev *pdev; + + /* Add sriov arch specific initialization here. + * Copy dev_archdata from PF to VF + */ + if (dev->is_virtfn) { + pdev = dev->physfn; + memcpy(&dev->dev.archdata, &pdev->dev.archdata, + sizeof(struct dev_archdata)); + } + return 0; +} +#endif /* CONFIG_PCI_IOV */ + static int __init pcibios_init(void) { pci_dfl_cache_line_size = 64 >> 2; diff --git a/arch/sparc/kernel/rtrap_64.S b/arch/sparc/kernel/rtrap_64.S index d08bdaffdbfc..216948ca4382 100644 --- a/arch/sparc/kernel/rtrap_64.S +++ b/arch/sparc/kernel/rtrap_64.S @@ -14,10 +14,6 @@ #include #include -#define RTRAP_PSTATE (PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_IE) -#define RTRAP_PSTATE_IRQOFF (PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV) -#define RTRAP_PSTATE_AG_IRQOFF (PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_AG) - #ifdef CONFIG_CONTEXT_TRACKING # define SCHEDULE_USER schedule_user #else @@ -242,52 +238,17 @@ rt_continue: ldx [%sp + PTREGS_OFF + PT_V9_G1], %g1 wrpr %g1, %cwp ba,a,pt %xcc, user_rtt_fill_64bit +user_rtt_fill_fixup_dax: + ba,pt %xcc, user_rtt_fill_fixup_common + mov 1, %g3 + +user_rtt_fill_fixup_mna: + ba,pt %xcc, user_rtt_fill_fixup_common + mov 2, %g3 + user_rtt_fill_fixup: - rdpr %cwp, %g1 - add %g1, 1, %g1 - wrpr %g1, 0x0, %cwp - - rdpr %wstate, %g2 - sll %g2, 3, %g2 - wrpr %g2, 0x0, %wstate - - /* We know %canrestore and %otherwin are both zero. */ - - sethi %hi(sparc64_kern_pri_context), %g2 - ldx [%g2 + %lo(sparc64_kern_pri_context)], %g2 - mov PRIMARY_CONTEXT, %g1 - -661: stxa %g2, [%g1] ASI_DMMU - .section .sun4v_1insn_patch, "ax" - .word 661b - stxa %g2, [%g1] ASI_MMU - .previous - - sethi %hi(KERNBASE), %g1 - flush %g1 - - or %g4, FAULT_CODE_WINFIXUP, %g4 - stb %g4, [%g6 + TI_FAULT_CODE] - stx %g5, [%g6 + TI_FAULT_ADDR] - - mov %g6, %l1 - wrpr %g0, 0x0, %tl - -661: nop - .section .sun4v_1insn_patch, "ax" - .word 661b - SET_GL(0) - .previous - - wrpr %g0, RTRAP_PSTATE, %pstate - - mov %l1, %g6 - ldx [%g6 + TI_TASK], %g4 - LOAD_PER_CPU_BASE(%g5, %g6, %g1, %g2, %g3) - call do_sparc64_fault - add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop + ba,pt %xcc, user_rtt_fill_fixup_common + clr %g3 user_rtt_pre_restore: add %g1, 1, %g1 diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c index 4eed773a7735..77655f0f0fc7 100644 --- a/arch/sparc/kernel/signal32.c +++ b/arch/sparc/kernel/signal32.c @@ -138,12 +138,24 @@ int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) return 0; } +/* Checks if the fp is valid. We always build signal frames which are + * 16-byte aligned, therefore we can always enforce that the restore + * frame has that property as well. + */ +static bool invalid_frame_pointer(void __user *fp, int fplen) +{ + if ((((unsigned long) fp) & 15) || + ((unsigned long)fp) > 0x100000000ULL - fplen) + return true; + return false; +} + void do_sigreturn32(struct pt_regs *regs) { struct signal_frame32 __user *sf; compat_uptr_t fpu_save; compat_uptr_t rwin_save; - unsigned int psr; + unsigned int psr, ufp; unsigned pc, npc; sigset_t set; compat_sigset_t seta; @@ -158,11 +170,16 @@ void do_sigreturn32(struct pt_regs *regs) sf = (struct signal_frame32 __user *) regs->u_regs[UREG_FP]; /* 1. Make sure we are not getting garbage from the user */ - if (!access_ok(VERIFY_READ, sf, sizeof(*sf)) || - (((unsigned long) sf) & 3)) + if (invalid_frame_pointer(sf, sizeof(*sf))) goto segv; - if (get_user(pc, &sf->info.si_regs.pc) || + if (get_user(ufp, &sf->info.si_regs.u_regs[UREG_FP])) + goto segv; + + if (ufp & 0x7) + goto segv; + + if (__get_user(pc, &sf->info.si_regs.pc) || __get_user(npc, &sf->info.si_regs.npc)) goto segv; @@ -227,7 +244,7 @@ segv: asmlinkage void do_rt_sigreturn32(struct pt_regs *regs) { struct rt_signal_frame32 __user *sf; - unsigned int psr, pc, npc; + unsigned int psr, pc, npc, ufp; compat_uptr_t fpu_save; compat_uptr_t rwin_save; sigset_t set; @@ -242,11 +259,16 @@ asmlinkage void do_rt_sigreturn32(struct pt_regs *regs) sf = (struct rt_signal_frame32 __user *) regs->u_regs[UREG_FP]; /* 1. Make sure we are not getting garbage from the user */ - if (!access_ok(VERIFY_READ, sf, sizeof(*sf)) || - (((unsigned long) sf) & 3)) + if (invalid_frame_pointer(sf, sizeof(*sf))) goto segv; - if (get_user(pc, &sf->regs.pc) || + if (get_user(ufp, &sf->regs.u_regs[UREG_FP])) + goto segv; + + if (ufp & 0x7) + goto segv; + + if (__get_user(pc, &sf->regs.pc) || __get_user(npc, &sf->regs.npc)) goto segv; @@ -307,14 +329,6 @@ segv: force_sig(SIGSEGV, current); } -/* Checks if the fp is valid */ -static int invalid_frame_pointer(void __user *fp, int fplen) -{ - if ((((unsigned long) fp) & 7) || ((unsigned long)fp) > 0x100000000ULL - fplen) - return 1; - return 0; -} - static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, unsigned long framesize) { unsigned long sp; diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c index 52aa5e4ce5e7..c3c12efe0bc0 100644 --- a/arch/sparc/kernel/signal_32.c +++ b/arch/sparc/kernel/signal_32.c @@ -60,10 +60,22 @@ struct rt_signal_frame { #define SF_ALIGNEDSZ (((sizeof(struct signal_frame) + 7) & (~7))) #define RT_ALIGNEDSZ (((sizeof(struct rt_signal_frame) + 7) & (~7))) +/* Checks if the fp is valid. We always build signal frames which are + * 16-byte aligned, therefore we can always enforce that the restore + * frame has that property as well. + */ +static inline bool invalid_frame_pointer(void __user *fp, int fplen) +{ + if ((((unsigned long) fp) & 15) || !__access_ok((unsigned long)fp, fplen)) + return true; + + return false; +} + asmlinkage void do_sigreturn(struct pt_regs *regs) { + unsigned long up_psr, pc, npc, ufp; struct signal_frame __user *sf; - unsigned long up_psr, pc, npc; sigset_t set; __siginfo_fpu_t __user *fpu_save; __siginfo_rwin_t __user *rwin_save; @@ -77,10 +89,13 @@ asmlinkage void do_sigreturn(struct pt_regs *regs) sf = (struct signal_frame __user *) regs->u_regs[UREG_FP]; /* 1. Make sure we are not getting garbage from the user */ - if (!access_ok(VERIFY_READ, sf, sizeof(*sf))) + if (!invalid_frame_pointer(sf, sizeof(*sf))) goto segv_and_exit; - if (((unsigned long) sf) & 3) + if (get_user(ufp, &sf->info.si_regs.u_regs[UREG_FP])) + goto segv_and_exit; + + if (ufp & 0x7) goto segv_and_exit; err = __get_user(pc, &sf->info.si_regs.pc); @@ -127,7 +142,7 @@ segv_and_exit: asmlinkage void do_rt_sigreturn(struct pt_regs *regs) { struct rt_signal_frame __user *sf; - unsigned int psr, pc, npc; + unsigned int psr, pc, npc, ufp; __siginfo_fpu_t __user *fpu_save; __siginfo_rwin_t __user *rwin_save; sigset_t set; @@ -135,8 +150,13 @@ asmlinkage void do_rt_sigreturn(struct pt_regs *regs) synchronize_user_stack(); sf = (struct rt_signal_frame __user *) regs->u_regs[UREG_FP]; - if (!access_ok(VERIFY_READ, sf, sizeof(*sf)) || - (((unsigned long) sf) & 0x03)) + if (!invalid_frame_pointer(sf, sizeof(*sf))) + goto segv; + + if (get_user(ufp, &sf->regs.u_regs[UREG_FP])) + goto segv; + + if (ufp & 0x7) goto segv; err = __get_user(pc, &sf->regs.pc); @@ -178,15 +198,6 @@ segv: force_sig(SIGSEGV, current); } -/* Checks if the fp is valid */ -static inline int invalid_frame_pointer(void __user *fp, int fplen) -{ - if ((((unsigned long) fp) & 7) || !__access_ok((unsigned long)fp, fplen)) - return 1; - - return 0; -} - static inline void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, unsigned long framesize) { unsigned long sp = regs->u_regs[UREG_FP]; diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c index d88beff47bab..5ee930c48f4c 100644 --- a/arch/sparc/kernel/signal_64.c +++ b/arch/sparc/kernel/signal_64.c @@ -52,7 +52,7 @@ asmlinkage void sparc64_set_context(struct pt_regs *regs) unsigned char fenab; int err; - flush_user_windows(); + synchronize_user_stack(); if (get_thread_wsaved() || (((unsigned long)ucp) & (sizeof(unsigned long)-1)) || (!__access_ok(ucp, sizeof(*ucp)))) @@ -234,6 +234,17 @@ do_sigsegv: goto out; } +/* Checks if the fp is valid. We always build rt signal frames which + * are 16-byte aligned, therefore we can always enforce that the + * restore frame has that property as well. + */ +static bool invalid_frame_pointer(void __user *fp) +{ + if (((unsigned long) fp) & 15) + return true; + return false; +} + struct rt_signal_frame { struct sparc_stackf ss; siginfo_t info; @@ -246,8 +257,8 @@ struct rt_signal_frame { void do_rt_sigreturn(struct pt_regs *regs) { + unsigned long tpc, tnpc, tstate, ufp; struct rt_signal_frame __user *sf; - unsigned long tpc, tnpc, tstate; __siginfo_fpu_t __user *fpu_save; __siginfo_rwin_t __user *rwin_save; sigset_t set; @@ -261,10 +272,16 @@ void do_rt_sigreturn(struct pt_regs *regs) (regs->u_regs [UREG_FP] + STACK_BIAS); /* 1. Make sure we are not getting garbage from the user */ - if (((unsigned long) sf) & 3) + if (invalid_frame_pointer(sf)) goto segv; - err = get_user(tpc, &sf->regs.tpc); + if (get_user(ufp, &sf->regs.u_regs[UREG_FP])) + goto segv; + + if ((ufp + STACK_BIAS) & 0x7) + goto segv; + + err = __get_user(tpc, &sf->regs.tpc); err |= __get_user(tnpc, &sf->regs.tnpc); if (test_thread_flag(TIF_32BIT)) { tpc &= 0xffffffff; @@ -308,14 +325,6 @@ segv: force_sig(SIGSEGV, current); } -/* Checks if the fp is valid */ -static int invalid_frame_pointer(void __user *fp) -{ - if (((unsigned long) fp) & 15) - return 1; - return 0; -} - static inline void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, unsigned long framesize) { unsigned long sp = regs->u_regs[UREG_FP] + STACK_BIAS; diff --git a/arch/sparc/kernel/sigutil_32.c b/arch/sparc/kernel/sigutil_32.c index 0f6eebe71e6c..e5fe8cef9a69 100644 --- a/arch/sparc/kernel/sigutil_32.c +++ b/arch/sparc/kernel/sigutil_32.c @@ -48,6 +48,10 @@ int save_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu) int restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu) { int err; + + if (((unsigned long) fpu) & 3) + return -EFAULT; + #ifdef CONFIG_SMP if (test_tsk_thread_flag(current, TIF_USEDFPU)) regs->psr &= ~PSR_EF; @@ -97,7 +101,10 @@ int restore_rwin_state(__siginfo_rwin_t __user *rp) struct thread_info *t = current_thread_info(); int i, wsaved, err; - __get_user(wsaved, &rp->wsaved); + if (((unsigned long) rp) & 3) + return -EFAULT; + + get_user(wsaved, &rp->wsaved); if (wsaved > NSWINS) return -EFAULT; diff --git a/arch/sparc/kernel/sigutil_64.c b/arch/sparc/kernel/sigutil_64.c index 387834a9c56a..36aadcbeac69 100644 --- a/arch/sparc/kernel/sigutil_64.c +++ b/arch/sparc/kernel/sigutil_64.c @@ -37,7 +37,10 @@ int restore_fpu_state(struct pt_regs *regs, __siginfo_fpu_t __user *fpu) unsigned long fprs; int err; - err = __get_user(fprs, &fpu->si_fprs); + if (((unsigned long) fpu) & 7) + return -EFAULT; + + err = get_user(fprs, &fpu->si_fprs); fprs_write(0); regs->tstate &= ~TSTATE_PEF; if (fprs & FPRS_DL) @@ -72,7 +75,10 @@ int restore_rwin_state(__siginfo_rwin_t __user *rp) struct thread_info *t = current_thread_info(); int i, wsaved, err; - __get_user(wsaved, &rp->wsaved); + if (((unsigned long) rp) & 7) + return -EFAULT; + + get_user(wsaved, &rp->wsaved); if (wsaved > NSWINS) return -EFAULT; diff --git a/arch/sparc/kernel/spiterrs.S b/arch/sparc/kernel/spiterrs.S index c357e40ffd01..4a73009f66a5 100644 --- a/arch/sparc/kernel/spiterrs.S +++ b/arch/sparc/kernel/spiterrs.S @@ -85,8 +85,7 @@ __spitfire_cee_trap_continue: ba,pt %xcc, etraptl1 rd %pc, %g7 - ba,pt %xcc, 2f - nop + ba,a,pt %xcc, 2f 1: ba,pt %xcc, etrap_irq rd %pc, %g7 @@ -100,8 +99,7 @@ __spitfire_cee_trap_continue: mov %l5, %o2 call spitfire_access_error add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap .size __spitfire_access_error,.-__spitfire_access_error /* This is the trap handler entry point for ECC correctable @@ -179,8 +177,7 @@ __spitfire_data_access_exception_tl1: mov %l5, %o2 call spitfire_data_access_exception_tl1 add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap .size __spitfire_data_access_exception_tl1,.-__spitfire_data_access_exception_tl1 .type __spitfire_data_access_exception,#function @@ -200,8 +197,7 @@ __spitfire_data_access_exception: mov %l5, %o2 call spitfire_data_access_exception add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap .size __spitfire_data_access_exception,.-__spitfire_data_access_exception .type __spitfire_insn_access_exception_tl1,#function @@ -220,8 +216,7 @@ __spitfire_insn_access_exception_tl1: mov %l5, %o2 call spitfire_insn_access_exception_tl1 add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap .size __spitfire_insn_access_exception_tl1,.-__spitfire_insn_access_exception_tl1 .type __spitfire_insn_access_exception,#function @@ -240,6 +235,5 @@ __spitfire_insn_access_exception: mov %l5, %o2 call spitfire_insn_access_exception add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap .size __spitfire_insn_access_exception,.-__spitfire_insn_access_exception diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c index c48d93b60afe..b489e9759518 100644 --- a/arch/sparc/kernel/sys_sparc_64.c +++ b/arch/sparc/kernel/sys_sparc_64.c @@ -413,7 +413,7 @@ out: SYSCALL_DEFINE1(sparc64_personality, unsigned long, personality) { - int ret; + long ret; if (personality(current->personality) == PER_LINUX32 && personality(personality) == PER_LINUX) diff --git a/arch/sparc/kernel/syscalls.S b/arch/sparc/kernel/syscalls.S index bb0008927598..c4a1b5c40e4e 100644 --- a/arch/sparc/kernel/syscalls.S +++ b/arch/sparc/kernel/syscalls.S @@ -158,7 +158,25 @@ linux_syscall_trace32: add %sp, PTREGS_OFF, %o0 brnz,pn %o0, 3f mov -ENOSYS, %o0 + + /* Syscall tracing can modify the registers. */ + ldx [%sp + PTREGS_OFF + PT_V9_G1], %g1 + sethi %hi(sys_call_table32), %l7 + ldx [%sp + PTREGS_OFF + PT_V9_I0], %i0 + or %l7, %lo(sys_call_table32), %l7 + ldx [%sp + PTREGS_OFF + PT_V9_I1], %i1 + ldx [%sp + PTREGS_OFF + PT_V9_I2], %i2 + ldx [%sp + PTREGS_OFF + PT_V9_I3], %i3 + ldx [%sp + PTREGS_OFF + PT_V9_I4], %i4 + ldx [%sp + PTREGS_OFF + PT_V9_I5], %i5 + + cmp %g1, NR_syscalls + bgeu,pn %xcc, 3f + mov -ENOSYS, %o0 + + sll %g1, 2, %l4 srl %i0, 0, %o0 + lduw [%l7 + %l4], %l7 srl %i4, 0, %o4 srl %i1, 0, %o1 srl %i2, 0, %o2 @@ -170,7 +188,25 @@ linux_syscall_trace: add %sp, PTREGS_OFF, %o0 brnz,pn %o0, 3f mov -ENOSYS, %o0 + + /* Syscall tracing can modify the registers. */ + ldx [%sp + PTREGS_OFF + PT_V9_G1], %g1 + sethi %hi(sys_call_table64), %l7 + ldx [%sp + PTREGS_OFF + PT_V9_I0], %i0 + or %l7, %lo(sys_call_table64), %l7 + ldx [%sp + PTREGS_OFF + PT_V9_I1], %i1 + ldx [%sp + PTREGS_OFF + PT_V9_I2], %i2 + ldx [%sp + PTREGS_OFF + PT_V9_I3], %i3 + ldx [%sp + PTREGS_OFF + PT_V9_I4], %i4 + ldx [%sp + PTREGS_OFF + PT_V9_I5], %i5 + + cmp %g1, NR_syscalls + bgeu,pn %xcc, 3f + mov -ENOSYS, %o0 + + sll %g1, 2, %l4 mov %i0, %o0 + lduw [%l7 + %l4], %l7 mov %i1, %o1 mov %i2, %o2 mov %i3, %o3 diff --git a/arch/sparc/kernel/urtt_fill.S b/arch/sparc/kernel/urtt_fill.S new file mode 100644 index 000000000000..5604a2b051d4 --- /dev/null +++ b/arch/sparc/kernel/urtt_fill.S @@ -0,0 +1,98 @@ +#include +#include +#include +#include +#include + + .text + .align 8 + .globl user_rtt_fill_fixup_common +user_rtt_fill_fixup_common: + rdpr %cwp, %g1 + add %g1, 1, %g1 + wrpr %g1, 0x0, %cwp + + rdpr %wstate, %g2 + sll %g2, 3, %g2 + wrpr %g2, 0x0, %wstate + + /* We know %canrestore and %otherwin are both zero. */ + + sethi %hi(sparc64_kern_pri_context), %g2 + ldx [%g2 + %lo(sparc64_kern_pri_context)], %g2 + mov PRIMARY_CONTEXT, %g1 + +661: stxa %g2, [%g1] ASI_DMMU + .section .sun4v_1insn_patch, "ax" + .word 661b + stxa %g2, [%g1] ASI_MMU + .previous + + sethi %hi(KERNBASE), %g1 + flush %g1 + + mov %g4, %l4 + mov %g5, %l5 + brnz,pn %g3, 1f + mov %g3, %l3 + + or %g4, FAULT_CODE_WINFIXUP, %g4 + stb %g4, [%g6 + TI_FAULT_CODE] + stx %g5, [%g6 + TI_FAULT_ADDR] +1: + mov %g6, %l1 + wrpr %g0, 0x0, %tl + +661: nop + .section .sun4v_1insn_patch, "ax" + .word 661b + SET_GL(0) + .previous + + wrpr %g0, RTRAP_PSTATE, %pstate + + mov %l1, %g6 + ldx [%g6 + TI_TASK], %g4 + LOAD_PER_CPU_BASE(%g5, %g6, %g1, %g2, %g3) + + brnz,pn %l3, 1f + nop + + call do_sparc64_fault + add %sp, PTREGS_OFF, %o0 + ba,pt %xcc, rtrap + nop + +1: cmp %g3, 2 + bne,pn %xcc, 2f + nop + + sethi %hi(tlb_type), %g1 + lduw [%g1 + %lo(tlb_type)], %g1 + cmp %g1, 3 + bne,pt %icc, 1f + add %sp, PTREGS_OFF, %o0 + mov %l4, %o2 + call sun4v_do_mna + mov %l5, %o1 + ba,a,pt %xcc, rtrap +1: mov %l4, %o1 + mov %l5, %o2 + call mem_address_unaligned + nop + ba,a,pt %xcc, rtrap + +2: sethi %hi(tlb_type), %g1 + mov %l4, %o1 + lduw [%g1 + %lo(tlb_type)], %g1 + mov %l5, %o2 + cmp %g1, 3 + bne,pt %icc, 1f + add %sp, PTREGS_OFF, %o0 + call sun4v_data_access_exception + nop + ba,a,pt %xcc, rtrap + +1: call spitfire_data_access_exception + nop + ba,a,pt %xcc, rtrap diff --git a/arch/sparc/kernel/utrap.S b/arch/sparc/kernel/utrap.S index b7f0f3f3a909..c731e8023d3e 100644 --- a/arch/sparc/kernel/utrap.S +++ b/arch/sparc/kernel/utrap.S @@ -11,8 +11,7 @@ utrap_trap: /* %g3=handler,%g4=level */ mov %l4, %o1 call bad_trap add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap invoke_utrap: sllx %g3, 3, %g3 diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S index f1a2f688b28a..4a41d412dd3d 100644 --- a/arch/sparc/kernel/vmlinux.lds.S +++ b/arch/sparc/kernel/vmlinux.lds.S @@ -33,6 +33,10 @@ ENTRY(_start) jiffies = jiffies_64; #endif +#ifdef CONFIG_SPARC64 +ASSERT((swapper_tsb == 0x0000000000408000), "Error: sparc64 early assembler too large") +#endif + SECTIONS { #ifdef CONFIG_SPARC64 diff --git a/arch/sparc/kernel/winfixup.S b/arch/sparc/kernel/winfixup.S index 1e67ce958369..855019a8590e 100644 --- a/arch/sparc/kernel/winfixup.S +++ b/arch/sparc/kernel/winfixup.S @@ -32,8 +32,7 @@ fill_fixup: rd %pc, %g7 call do_sparc64_fault add %sp, PTREGS_OFF, %o0 - ba,pt %xcc, rtrap - nop + ba,a,pt %xcc, rtrap /* Be very careful about usage of the trap globals here. * You cannot touch %g5 as that has the fault information. diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c index 131eaf4ad7f5..364d093f46c6 100644 --- a/arch/sparc/mm/hugetlbpage.c +++ b/arch/sparc/mm/hugetlbpage.c @@ -176,17 +176,31 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t entry) { int i; + pte_t orig[2]; + unsigned long nptes; if (!pte_present(*ptep) && pte_present(entry)) mm->context.huge_pte_count++; addr &= HPAGE_MASK; - for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) { - set_pte_at(mm, addr, ptep, entry); + + nptes = 1 << HUGETLB_PAGE_ORDER; + orig[0] = *ptep; + orig[1] = *(ptep + nptes / 2); + for (i = 0; i < nptes; i++) { + *ptep = entry; ptep++; addr += PAGE_SIZE; pte_val(entry) += PAGE_SIZE; } + + /* Issue TLB flush at REAL_HPAGE_SIZE boundaries */ + addr -= REAL_HPAGE_SIZE; + ptep -= nptes / 2; + maybe_tlb_batch_add(mm, addr, ptep, orig[1], 0); + addr -= REAL_HPAGE_SIZE; + ptep -= nptes / 2; + maybe_tlb_batch_add(mm, addr, ptep, orig[0], 0); } pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, @@ -194,19 +208,28 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, { pte_t entry; int i; + unsigned long nptes; entry = *ptep; if (pte_present(entry)) mm->context.huge_pte_count--; addr &= HPAGE_MASK; - - for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) { - pte_clear(mm, addr, ptep); + nptes = 1 << HUGETLB_PAGE_ORDER; + for (i = 0; i < nptes; i++) { + *ptep = __pte(0UL); addr += PAGE_SIZE; ptep++; } + /* Issue TLB flush at REAL_HPAGE_SIZE boundaries */ + addr -= REAL_HPAGE_SIZE; + ptep -= nptes / 2; + maybe_tlb_batch_add(mm, addr, ptep, entry, 0); + addr -= REAL_HPAGE_SIZE; + ptep -= nptes / 2; + maybe_tlb_batch_add(mm, addr, ptep, entry, 0); + return entry; } diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 3025bd57f7ab..3c4b8975fa76 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -324,18 +324,6 @@ static void __update_mmu_tsb_insert(struct mm_struct *mm, unsigned long tsb_inde tsb_insert(tsb, tag, tte); } -#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) -static inline bool is_hugetlb_pte(pte_t pte) -{ - if ((tlb_type == hypervisor && - (pte_val(pte) & _PAGE_SZALL_4V) == _PAGE_SZHUGE_4V) || - (tlb_type != hypervisor && - (pte_val(pte) & _PAGE_SZALL_4U) == _PAGE_SZHUGE_4U)) - return true; - return false; -} -#endif - void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { struct mm_struct *mm; @@ -1267,13 +1255,6 @@ static int __init numa_parse_mdesc(void) int i, j, err, count; u64 node; - /* Some sane defaults for numa latency values */ - for (i = 0; i < MAX_NUMNODES; i++) { - for (j = 0; j < MAX_NUMNODES; j++) - numa_latency[i][j] = (i == j) ? - LOCAL_DISTANCE : REMOTE_DISTANCE; - } - node = mdesc_node_by_name(md, MDESC_NODE_NULL, "latency-groups"); if (node == MDESC_NODE_NULL) { mdesc_release(md); @@ -1369,10 +1350,18 @@ static int __init numa_parse_sun4u(void) static int __init bootmem_init_numa(void) { + int i, j; int err = -1; numadbg("bootmem_init_numa()\n"); + /* Some sane defaults for numa latency values */ + for (i = 0; i < MAX_NUMNODES; i++) { + for (j = 0; j < MAX_NUMNODES; j++) + numa_latency[i][j] = (i == j) ? + LOCAL_DISTANCE : REMOTE_DISTANCE; + } + if (numa_enabled) { if (tlb_type == hypervisor) err = numa_parse_mdesc(); @@ -2832,9 +2821,10 @@ void hugetlb_setup(struct pt_regs *regs) * the Data-TLB for huge pages. */ if (tlb_type == cheetah_plus) { + bool need_context_reload = false; unsigned long ctx; - spin_lock(&ctx_alloc_lock); + spin_lock_irq(&ctx_alloc_lock); ctx = mm->context.sparc64_ctx_val; ctx &= ~CTX_PGSZ_MASK; ctx |= CTX_PGSZ_BASE << CTX_PGSZ0_SHIFT; @@ -2853,9 +2843,12 @@ void hugetlb_setup(struct pt_regs *regs) * also executing in this address space. */ mm->context.sparc64_ctx_val = ctx; - on_each_cpu(context_reload, mm, 0); + need_context_reload = true; } - spin_unlock(&ctx_alloc_lock); + spin_unlock_irq(&ctx_alloc_lock); + + if (need_context_reload) + on_each_cpu(context_reload, mm, 0); } } #endif diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c index 9df2190c097e..f81cd9736700 100644 --- a/arch/sparc/mm/tlb.c +++ b/arch/sparc/mm/tlb.c @@ -67,7 +67,7 @@ void arch_leave_lazy_mmu_mode(void) } static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr, - bool exec) + bool exec, bool huge) { struct tlb_batch *tb = &get_cpu_var(tlb_batch); unsigned long nr; @@ -84,13 +84,21 @@ static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr, } if (!tb->active) { - flush_tsb_user_page(mm, vaddr); + flush_tsb_user_page(mm, vaddr, huge); global_flush_tlb_page(mm, vaddr); goto out; } - if (nr == 0) + if (nr == 0) { tb->mm = mm; + tb->huge = huge; + } + + if (tb->huge != huge) { + flush_tlb_pending(); + tb->huge = huge; + nr = 0; + } tb->vaddrs[nr] = vaddr; tb->tlb_nr = ++nr; @@ -104,6 +112,8 @@ out: void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr, pte_t *ptep, pte_t orig, int fullmm) { + bool huge = is_hugetlb_pte(orig); + if (tlb_type != hypervisor && pte_dirty(orig)) { unsigned long paddr, pfn = pte_pfn(orig); @@ -129,7 +139,7 @@ void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr, no_cache_flush: if (!fullmm) - tlb_batch_add_one(mm, vaddr, pte_exec(orig)); + tlb_batch_add_one(mm, vaddr, pte_exec(orig), huge); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -145,7 +155,7 @@ static void tlb_batch_pmd_scan(struct mm_struct *mm, unsigned long vaddr, if (pte_val(*pte) & _PAGE_VALID) { bool exec = pte_exec(*pte); - tlb_batch_add_one(mm, vaddr, exec); + tlb_batch_add_one(mm, vaddr, exec, false); } pte++; vaddr += PAGE_SIZE; @@ -185,8 +195,9 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr, pte_t orig_pte = __pte(pmd_val(orig)); bool exec = pte_exec(orig_pte); - tlb_batch_add_one(mm, addr, exec); - tlb_batch_add_one(mm, addr + REAL_HPAGE_SIZE, exec); + tlb_batch_add_one(mm, addr, exec, true); + tlb_batch_add_one(mm, addr + REAL_HPAGE_SIZE, exec, + true); } else { tlb_batch_pmd_scan(mm, addr, orig); } diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c index a06576683c38..a0604a493a36 100644 --- a/arch/sparc/mm/tsb.c +++ b/arch/sparc/mm/tsb.c @@ -76,14 +76,15 @@ void flush_tsb_user(struct tlb_batch *tb) spin_lock_irqsave(&mm->context.lock, flags); - base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb; - nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries; - if (tlb_type == cheetah_plus || tlb_type == hypervisor) - base = __pa(base); - __flush_tsb_one(tb, PAGE_SHIFT, base, nentries); - + if (!tb->huge) { + base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb; + nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries; + if (tlb_type == cheetah_plus || tlb_type == hypervisor) + base = __pa(base); + __flush_tsb_one(tb, PAGE_SHIFT, base, nentries); + } #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) - if (mm->context.tsb_block[MM_TSB_HUGE].tsb) { + if (tb->huge && mm->context.tsb_block[MM_TSB_HUGE].tsb) { base = (unsigned long) mm->context.tsb_block[MM_TSB_HUGE].tsb; nentries = mm->context.tsb_block[MM_TSB_HUGE].tsb_nentries; if (tlb_type == cheetah_plus || tlb_type == hypervisor) @@ -94,20 +95,21 @@ void flush_tsb_user(struct tlb_batch *tb) spin_unlock_irqrestore(&mm->context.lock, flags); } -void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr) +void flush_tsb_user_page(struct mm_struct *mm, unsigned long vaddr, bool huge) { unsigned long nentries, base, flags; spin_lock_irqsave(&mm->context.lock, flags); - base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb; - nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries; - if (tlb_type == cheetah_plus || tlb_type == hypervisor) - base = __pa(base); - __flush_tsb_one_entry(base, vaddr, PAGE_SHIFT, nentries); - + if (!huge) { + base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb; + nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries; + if (tlb_type == cheetah_plus || tlb_type == hypervisor) + base = __pa(base); + __flush_tsb_one_entry(base, vaddr, PAGE_SHIFT, nentries); + } #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) - if (mm->context.tsb_block[MM_TSB_HUGE].tsb) { + if (huge && mm->context.tsb_block[MM_TSB_HUGE].tsb) { base = (unsigned long) mm->context.tsb_block[MM_TSB_HUGE].tsb; nentries = mm->context.tsb_block[MM_TSB_HUGE].tsb_nentries; if (tlb_type == cheetah_plus || tlb_type == hypervisor) diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c index 29880c9b324e..e22e57298522 100644 --- a/arch/um/drivers/mconsole_kern.c +++ b/arch/um/drivers/mconsole_kern.c @@ -133,7 +133,7 @@ void mconsole_proc(struct mc_request *req) ptr += strlen("proc"); ptr = skip_spaces(ptr); - file = file_open_root(mnt->mnt_root, mnt, ptr, O_RDONLY); + file = file_open_root(mnt->mnt_root, mnt, ptr, O_RDONLY, 0); if (IS_ERR(file)) { mconsole_reply(req, "Failed to open file", 1, 0); printk(KERN_ERR "open /proc/%s: %ld\n", ptr, PTR_ERR(file)); diff --git a/arch/um/os-Linux/start_up.c b/arch/um/os-Linux/start_up.c index 47f1ff056a54..22a358ef1b0c 100644 --- a/arch/um/os-Linux/start_up.c +++ b/arch/um/os-Linux/start_up.c @@ -94,6 +94,8 @@ static int start_ptraced_child(void) { int pid, n, status; + fflush(stdout); + pid = fork(); if (pid == 0) ptrace_child(); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index ae3c83e8bde8..be2395bc2172 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1142,22 +1142,23 @@ config MICROCODE bool "CPU microcode loading support" default y depends on CPU_SUP_AMD || CPU_SUP_INTEL - depends on BLK_DEV_INITRD select FW_LOADER ---help--- - If you say Y here, you will be able to update the microcode on - certain Intel and AMD processors. The Intel support is for the - IA32 family, e.g. Pentium Pro, Pentium II, Pentium III, Pentium 4, - Xeon etc. The AMD support is for families 0x10 and later. You will - obviously need the actual microcode binary data itself which is not - shipped with the Linux kernel. + Intel and AMD processors. The Intel support is for the IA32 family, + e.g. Pentium Pro, Pentium II, Pentium III, Pentium 4, Xeon etc. The + AMD support is for families 0x10 and later. You will obviously need + the actual microcode binary data itself which is not shipped with + the Linux kernel. - This option selects the general module only, you need to select - at least one vendor specific module as well. + The preferred method to load microcode from a detached initrd is described + in Documentation/x86/early-microcode.txt. For that you need to enable + CONFIG_BLK_DEV_INITRD in order for the loader to be able to scan the + initrd for microcode blobs. - To compile this driver as a module, choose M here: the module - will be called microcode. + In addition, you can build-in the microcode into the kernel. For that you + need to enable FIRMWARE_IN_KERNEL and add the vendor-supplied microcode + to the CONFIG_EXTRA_FIRMWARE config option. config MICROCODE_INTEL bool "Intel microcode loading support" diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index 2ee62dba0373..c0cc2a6be0bf 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -162,6 +162,9 @@ isoimage: $(obj)/bzImage for i in lib lib64 share end ; do \ if [ -f /usr/$$i/syslinux/isolinux.bin ] ; then \ cp /usr/$$i/syslinux/isolinux.bin $(obj)/isoimage ; \ + if [ -f /usr/$$i/syslinux/ldlinux.c32 ]; then \ + cp /usr/$$i/syslinux/ldlinux.c32 $(obj)/isoimage ; \ + fi ; \ break ; \ fi ; \ if [ $$i = end ] ; then exit 1 ; fi ; \ diff --git a/arch/x86/crypto/chacha20-ssse3-x86_64.S b/arch/x86/crypto/chacha20-ssse3-x86_64.S index 712b13047b41..3a33124e9112 100644 --- a/arch/x86/crypto/chacha20-ssse3-x86_64.S +++ b/arch/x86/crypto/chacha20-ssse3-x86_64.S @@ -157,7 +157,9 @@ ENTRY(chacha20_4block_xor_ssse3) # done with the slightly better performing SSSE3 byte shuffling, # 7/12-bit word rotation uses traditional shift+OR. - sub $0x40,%rsp + mov %rsp,%r11 + sub $0x80,%rsp + and $~63,%rsp # x0..15[0-3] = s0..3[0..3] movq 0x00(%rdi),%xmm1 @@ -620,6 +622,6 @@ ENTRY(chacha20_4block_xor_ssse3) pxor %xmm1,%xmm15 movdqu %xmm15,0xf0(%rsi) - add $0x40,%rsp + mov %r11,%rsp ret ENDPROC(chacha20_4block_xor_ssse3) diff --git a/arch/x86/crypto/sha-mb/sha1_mb.c b/arch/x86/crypto/sha-mb/sha1_mb.c index a841e9765bd6..8381c09d2870 100644 --- a/arch/x86/crypto/sha-mb/sha1_mb.c +++ b/arch/x86/crypto/sha-mb/sha1_mb.c @@ -453,10 +453,10 @@ static int sha_complete_job(struct mcryptd_hash_request_ctx *rctx, req = cast_mcryptd_ctx_to_req(req_ctx); if (irqs_disabled()) - rctx->complete(&req->base, ret); + req_ctx->complete(&req->base, ret); else { local_bh_disable(); - rctx->complete(&req->base, ret); + req_ctx->complete(&req->base, ret); local_bh_enable(); } } diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 03663740c866..1a4477cedc49 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -268,6 +268,7 @@ static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags) /* Called with IRQs disabled. */ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs) { + struct thread_info *ti = pt_regs_to_thread_info(regs); u32 cached_flags; if (IS_ENABLED(CONFIG_PROVE_LOCKING) && WARN_ON(!irqs_disabled())) @@ -275,12 +276,22 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs) lockdep_sys_exit(); - cached_flags = - READ_ONCE(pt_regs_to_thread_info(regs)->flags); + cached_flags = READ_ONCE(ti->flags); if (unlikely(cached_flags & EXIT_TO_USERMODE_LOOP_FLAGS)) exit_to_usermode_loop(regs, cached_flags); +#ifdef CONFIG_COMPAT + /* + * Compat syscalls set TS_COMPAT. Make sure we clear it before + * returning to user mode. We need to clear it *after* signal + * handling, because syscall restart has a fixup for compat + * syscalls. The fixup is exercised by the ptrace_syscall_32 + * selftest. + */ + ti->status &= ~TS_COMPAT; +#endif + user_enter(); } @@ -332,14 +343,6 @@ __visible inline void syscall_return_slowpath(struct pt_regs *regs) if (unlikely(cached_flags & SYSCALL_EXIT_WORK_FLAGS)) syscall_slow_exit_work(regs, cached_flags); -#ifdef CONFIG_COMPAT - /* - * Compat syscalls set TS_COMPAT. Make sure we clear it before - * returning to user mode. - */ - ti->status &= ~TS_COMPAT; -#endif - local_irq_disable(); prepare_exit_to_usermode(regs); } diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 6a1ae3751e82..15cfebaa7688 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -267,6 +267,7 @@ ENTRY(entry_INT80_compat) * Interrupts are off on entry. */ PARAVIRT_ADJUST_EXCEPTION_FRAME + ASM_CLAC /* Do this early to minimize exposure */ SWAPGS /* diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index a30316bf801a..163769d82475 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -638,8 +638,8 @@ static inline void entering_irq(void) static inline void entering_ack_irq(void) { - ack_APIC_irq(); entering_irq(); + ack_APIC_irq(); } static inline void ipi_entering_ack_irq(void) diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h index 4fa687a47a62..6b8d6e8cd449 100644 --- a/arch/x86/include/asm/boot.h +++ b/arch/x86/include/asm/boot.h @@ -27,7 +27,7 @@ #define BOOT_HEAP_SIZE 0x400000 #else /* !CONFIG_KERNEL_BZIP2 */ -#define BOOT_HEAP_SIZE 0x8000 +#define BOOT_HEAP_SIZE 0x10000 #endif /* !CONFIG_KERNEL_BZIP2 */ diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h index f8a29d2c97b0..e6a8613fbfb0 100644 --- a/arch/x86/include/asm/hugetlb.h +++ b/arch/x86/include/asm/hugetlb.h @@ -4,6 +4,7 @@ #include #include +#define hugepages_supported() cpu_has_pse static inline int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index 1e3408e88604..59caa55fb9b5 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -136,6 +136,7 @@ struct irq_alloc_info { struct irq_cfg { unsigned int dest_apicid; u8 vector; + u8 old_vector; }; extern struct irq_cfg *irq_cfg(unsigned int irq); diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h index 881b4768644a..e7de5c9a4fbd 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -23,11 +23,13 @@ extern void irq_ctx_init(int cpu); #define __ARCH_HAS_DO_SOFTIRQ +struct irq_desc; + #ifdef CONFIG_HOTPLUG_CPU #include extern int check_irq_vectors_for_cpu_disable(void); extern void fixup_irqs(void); -extern void irq_force_complete_move(int); +extern void irq_force_complete_move(struct irq_desc *desc); #endif #ifdef CONFIG_HAVE_KVM @@ -37,7 +39,6 @@ extern void kvm_set_posted_intr_wakeup_handler(void (*handler)(void)); extern void (*x86_platform_ipi_callback)(void); extern void native_init_IRQ(void); -struct irq_desc; extern bool handle_irq(struct irq_desc *desc, struct pt_regs *regs); extern __visible unsigned int do_IRQ(struct pt_regs *regs); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 30cfd64295a0..9d2abb2a41d2 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -41,7 +41,7 @@ #define KVM_PIO_PAGE_OFFSET 1 #define KVM_COALESCED_MMIO_PAGE_OFFSET 2 -#define KVM_HALT_POLL_NS_DEFAULT 500000 +#define KVM_HALT_POLL_NS_DEFAULT 400000 #define KVM_IRQCHIP_NUM_PINS KVM_IOAPIC_NUM_PINS diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index 34e62b1dcfce..712b24ed3a64 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -2,6 +2,7 @@ #define _ASM_X86_MICROCODE_H #include +#include #define native_rdmsr(msr, val1, val2) \ do { \ @@ -168,4 +169,29 @@ static inline void reload_early_microcode(void) { } static inline bool get_builtin_firmware(struct cpio_data *cd, const char *name) { return false; } #endif + +static inline unsigned long get_initrd_start(void) +{ +#ifdef CONFIG_BLK_DEV_INITRD + return initrd_start; +#else + return 0; +#endif +} + +static inline unsigned long get_initrd_start_addr(void) +{ +#ifdef CONFIG_BLK_DEV_INITRD +#ifdef CONFIG_X86_32 + unsigned long *initrd_start_p = (unsigned long *)__pa_nodebug(&initrd_start); + + return (unsigned long)__pa_nodebug(*initrd_start_p); +#else + return get_initrd_start(); +#endif +#else /* CONFIG_BLK_DEV_INITRD */ + return 0; +#endif +} + #endif /* _ASM_X86_MICROCODE_H */ diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 379cd3658799..bfd9b2a35a0b 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -116,8 +116,36 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, #endif cpumask_set_cpu(cpu, mm_cpumask(next)); - /* Re-load page tables */ + /* + * Re-load page tables. + * + * This logic has an ordering constraint: + * + * CPU 0: Write to a PTE for 'next' + * CPU 0: load bit 1 in mm_cpumask. if nonzero, send IPI. + * CPU 1: set bit 1 in next's mm_cpumask + * CPU 1: load from the PTE that CPU 0 writes (implicit) + * + * We need to prevent an outcome in which CPU 1 observes + * the new PTE value and CPU 0 observes bit 1 clear in + * mm_cpumask. (If that occurs, then the IPI will never + * be sent, and CPU 0's TLB will contain a stale entry.) + * + * The bad outcome can occur if either CPU's load is + * reordered before that CPU's store, so both CPUs must + * execute full barriers to prevent this from happening. + * + * Thus, switch_mm needs a full barrier between the + * store to mm_cpumask and any operation that could load + * from next->pgd. TLB fills are special and can happen + * due to instruction fetches or for no reason at all, + * and neither LOCK nor MFENCE orders them. + * Fortunately, load_cr3() is serializing and gives the + * ordering guarantee we need. + * + */ load_cr3(next->pgd); + trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); /* Stop flush ipis for the previous mm */ @@ -156,10 +184,14 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, * schedule, protecting us from simultaneous changes. */ cpumask_set_cpu(cpu, mm_cpumask(next)); + /* * We were in lazy tlb mode and leave_mm disabled * tlb flush IPI delivery. We must reload CR3 * to make sure to use no freed page tables. + * + * As above, load_cr3() is serializing and orders TLB + * fills with respect to the mm_cpumask write. */ load_cr3(next->pgd); trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h index fa1195dae425..164e3f8d3c3d 100644 --- a/arch/x86/include/asm/pci_x86.h +++ b/arch/x86/include/asm/pci_x86.h @@ -93,6 +93,8 @@ extern raw_spinlock_t pci_config_lock; extern int (*pcibios_enable_irq)(struct pci_dev *dev); extern void (*pcibios_disable_irq)(struct pci_dev *dev); +extern bool mp_should_keep_irq(struct device *dev); + struct pci_raw_ops { int (*read)(unsigned int domain, unsigned int bus, unsigned int devfn, int reg, int len, u32 *val); diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 7bcb861a04e5..5a2ed3ed2f26 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -165,6 +165,7 @@ struct x86_pmu_capability { #define GLOBAL_STATUS_ASIF BIT_ULL(60) #define GLOBAL_STATUS_COUNTERS_FROZEN BIT_ULL(59) #define GLOBAL_STATUS_LBRS_FROZEN BIT_ULL(58) +#define GLOBAL_STATUS_TRACE_TOPAPMI BIT_ULL(55) /* * IBS cpuid feature detection diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index a471cadb9630..79c91853e50e 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -363,20 +363,18 @@ static inline enum page_cache_mode pgprot2cachemode(pgprot_t pgprot) } static inline pgprot_t pgprot_4k_2_large(pgprot_t pgprot) { + pgprotval_t val = pgprot_val(pgprot); pgprot_t new; - unsigned long val; - val = pgprot_val(pgprot); pgprot_val(new) = (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) | ((val & _PAGE_PAT) << (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT)); return new; } static inline pgprot_t pgprot_large_2_4k(pgprot_t pgprot) { + pgprotval_t val = pgprot_val(pgprot); pgprot_t new; - unsigned long val; - val = pgprot_val(pgprot); pgprot_val(new) = (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) | ((val & _PAGE_PAT_LARGE) >> (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT)); diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h index 8b2d4bea9962..39171b3646bb 100644 --- a/arch/x86/include/asm/xen/hypervisor.h +++ b/arch/x86/include/asm/xen/hypervisor.h @@ -62,4 +62,6 @@ void xen_arch_register_cpu(int num); void xen_arch_unregister_cpu(int num); #endif +extern void xen_set_iopl_mask(unsigned mask); + #endif /* _ASM_X86_XEN_HYPERVISOR_H */ diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index d1daead5fcdd..adb3eaf8fe2a 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -16,6 +16,7 @@ #include #include +#include #include "../../realmode/rm/wakeup.h" #include "sleep.h" @@ -107,7 +108,13 @@ int x86_acpi_suspend_lowlevel(void) saved_magic = 0x123456789abcdef0L; #endif /* CONFIG_64BIT */ + /* + * Pause/unpause graph tracing around do_suspend_lowlevel as it has + * inconsistent call/return info after it jumps to the wakeup vector. + */ + pause_graph_tracing(); do_suspend_lowlevel(); + unpause_graph_tracing(); return 0; } diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 29fa475ec518..c986d0b3bc35 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -71,8 +71,8 @@ int amd_cache_northbridges(void) while ((misc = next_northbridge(misc, amd_nb_misc_ids)) != NULL) i++; - if (i == 0) - return 0; + if (!i) + return -ENODEV; nb = kzalloc(i * sizeof(struct amd_northbridge), GFP_KERNEL); if (!nb) diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index f25321894ad2..fdb0fbfb1197 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2521,6 +2521,7 @@ void __init setup_ioapic_dest(void) { int pin, ioapic, irq, irq_entry; const struct cpumask *mask; + struct irq_desc *desc; struct irq_data *idata; struct irq_chip *chip; @@ -2536,7 +2537,9 @@ void __init setup_ioapic_dest(void) if (irq < 0 || !mp_init_irq_at_boot(ioapic, irq)) continue; - idata = irq_get_irq_data(irq); + desc = irq_to_desc(irq); + raw_spin_lock_irq(&desc->lock); + idata = irq_desc_get_irq_data(desc); /* * Honour affinities which have been set in early boot @@ -2550,6 +2553,7 @@ void __init setup_ioapic_dest(void) /* Might be lapic_chip for irq 0 */ if (chip->irq_set_affinity) chip->irq_set_affinity(idata, mask, false); + raw_spin_unlock_irq(&desc->lock); } } #endif diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 861bc59c8f25..df6b4eeac0bd 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -30,7 +30,7 @@ struct apic_chip_data { struct irq_domain *x86_vector_domain; static DEFINE_RAW_SPINLOCK(vector_lock); -static cpumask_var_t vector_cpumask; +static cpumask_var_t vector_cpumask, vector_searchmask, searched_cpumask; static struct irq_chip lapic_controller; #ifdef CONFIG_X86_IO_APIC static struct apic_chip_data *legacy_irq_data[NR_IRQS_LEGACY]; @@ -116,35 +116,47 @@ static int __assign_irq_vector(int irq, struct apic_chip_data *d, */ static int current_vector = FIRST_EXTERNAL_VECTOR + VECTOR_OFFSET_START; static int current_offset = VECTOR_OFFSET_START % 16; - int cpu, err; + int cpu, vector; - if (d->move_in_progress) + /* + * If there is still a move in progress or the previous move has not + * been cleaned up completely, tell the caller to come back later. + */ + if (d->move_in_progress || + cpumask_intersects(d->old_domain, cpu_online_mask)) return -EBUSY; /* Only try and allocate irqs on cpus that are present */ - err = -ENOSPC; cpumask_clear(d->old_domain); + cpumask_clear(searched_cpumask); cpu = cpumask_first_and(mask, cpu_online_mask); while (cpu < nr_cpu_ids) { - int new_cpu, vector, offset; + int new_cpu, offset; + /* Get the possible target cpus for @mask/@cpu from the apic */ apic->vector_allocation_domain(cpu, vector_cpumask, mask); + /* + * Clear the offline cpus from @vector_cpumask for searching + * and verify whether the result overlaps with @mask. If true, + * then the call to apic->cpu_mask_to_apicid_and() will + * succeed as well. If not, no point in trying to find a + * vector in this mask. + */ + cpumask_and(vector_searchmask, vector_cpumask, cpu_online_mask); + if (!cpumask_intersects(vector_searchmask, mask)) + goto next_cpu; + if (cpumask_subset(vector_cpumask, d->domain)) { - err = 0; if (cpumask_equal(vector_cpumask, d->domain)) - break; + goto success; /* - * New cpumask using the vector is a proper subset of - * the current in use mask. So cleanup the vector - * allocation for the members that are not used anymore. + * Mark the cpus which are not longer in the mask for + * cleanup. */ - cpumask_andnot(d->old_domain, d->domain, - vector_cpumask); - d->move_in_progress = - cpumask_intersects(d->old_domain, cpu_online_mask); - cpumask_and(d->domain, d->domain, vector_cpumask); - break; + cpumask_andnot(d->old_domain, d->domain, vector_cpumask); + vector = d->cfg.vector; + goto update; } vector = current_vector; @@ -156,45 +168,61 @@ next: vector = FIRST_EXTERNAL_VECTOR + offset; } - if (unlikely(current_vector == vector)) { - cpumask_or(d->old_domain, d->old_domain, - vector_cpumask); - cpumask_andnot(vector_cpumask, mask, d->old_domain); - cpu = cpumask_first_and(vector_cpumask, - cpu_online_mask); - continue; - } + /* If the search wrapped around, try the next cpu */ + if (unlikely(current_vector == vector)) + goto next_cpu; if (test_bit(vector, used_vectors)) goto next; - for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask) { + for_each_cpu(new_cpu, vector_searchmask) { if (!IS_ERR_OR_NULL(per_cpu(vector_irq, new_cpu)[vector])) goto next; } /* Found one! */ current_vector = vector; current_offset = offset; - if (d->cfg.vector) { + /* Schedule the old vector for cleanup on all cpus */ + if (d->cfg.vector) cpumask_copy(d->old_domain, d->domain); - d->move_in_progress = - cpumask_intersects(d->old_domain, cpu_online_mask); - } - for_each_cpu_and(new_cpu, vector_cpumask, cpu_online_mask) + for_each_cpu(new_cpu, vector_searchmask) per_cpu(vector_irq, new_cpu)[vector] = irq_to_desc(irq); - d->cfg.vector = vector; - cpumask_copy(d->domain, vector_cpumask); - err = 0; - break; - } + goto update; - if (!err) { - /* cache destination APIC IDs into cfg->dest_apicid */ - err = apic->cpu_mask_to_apicid_and(mask, d->domain, - &d->cfg.dest_apicid); +next_cpu: + /* + * We exclude the current @vector_cpumask from the requested + * @mask and try again with the next online cpu in the + * result. We cannot modify @mask, so we use @vector_cpumask + * as a temporary buffer here as it will be reassigned when + * calling apic->vector_allocation_domain() above. + */ + cpumask_or(searched_cpumask, searched_cpumask, vector_cpumask); + cpumask_andnot(vector_cpumask, mask, searched_cpumask); + cpu = cpumask_first_and(vector_cpumask, cpu_online_mask); + continue; } + return -ENOSPC; - return err; +update: + /* + * Exclude offline cpus from the cleanup mask and set the + * move_in_progress flag when the result is not empty. + */ + cpumask_and(d->old_domain, d->old_domain, cpu_online_mask); + d->move_in_progress = !cpumask_empty(d->old_domain); + d->cfg.old_vector = d->move_in_progress ? d->cfg.vector : 0; + d->cfg.vector = vector; + cpumask_copy(d->domain, vector_cpumask); +success: + /* + * Cache destination APIC IDs into cfg->dest_apicid. This cannot fail + * as we already established, that mask & d->domain & cpu_online_mask + * is not empty. + */ + BUG_ON(apic->cpu_mask_to_apicid_and(mask, d->domain, + &d->cfg.dest_apicid)); + return 0; } static int assign_irq_vector(int irq, struct apic_chip_data *data, @@ -224,11 +252,10 @@ static int assign_irq_vector_policy(int irq, int node, static void clear_irq_vector(int irq, struct apic_chip_data *data) { struct irq_desc *desc; - unsigned long flags; int cpu, vector; - raw_spin_lock_irqsave(&vector_lock, flags); - BUG_ON(!data->cfg.vector); + if (!data->cfg.vector) + return; vector = data->cfg.vector; for_each_cpu_and(cpu, data->domain, cpu_online_mask) @@ -237,10 +264,13 @@ static void clear_irq_vector(int irq, struct apic_chip_data *data) data->cfg.vector = 0; cpumask_clear(data->domain); - if (likely(!data->move_in_progress)) { - raw_spin_unlock_irqrestore(&vector_lock, flags); + /* + * If move is in progress or the old_domain mask is not empty, + * i.e. the cleanup IPI has not been processed yet, we need to remove + * the old references to desc from all cpus vector tables. + */ + if (!data->move_in_progress && cpumask_empty(data->old_domain)) return; - } desc = irq_to_desc(irq); for_each_cpu_and(cpu, data->old_domain, cpu_online_mask) { @@ -253,7 +283,6 @@ static void clear_irq_vector(int irq, struct apic_chip_data *data) } } data->move_in_progress = 0; - raw_spin_unlock_irqrestore(&vector_lock, flags); } void init_irq_alloc_info(struct irq_alloc_info *info, @@ -274,19 +303,24 @@ void copy_irq_alloc_info(struct irq_alloc_info *dst, struct irq_alloc_info *src) static void x86_vector_free_irqs(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs) { + struct apic_chip_data *apic_data; struct irq_data *irq_data; + unsigned long flags; int i; for (i = 0; i < nr_irqs; i++) { irq_data = irq_domain_get_irq_data(x86_vector_domain, virq + i); if (irq_data && irq_data->chip_data) { + raw_spin_lock_irqsave(&vector_lock, flags); clear_irq_vector(virq + i, irq_data->chip_data); - free_apic_chip_data(irq_data->chip_data); + apic_data = irq_data->chip_data; + irq_domain_reset_irq_data(irq_data); + raw_spin_unlock_irqrestore(&vector_lock, flags); + free_apic_chip_data(apic_data); #ifdef CONFIG_X86_IO_APIC if (virq + i < nr_legacy_irqs()) legacy_irq_data[virq + i] = NULL; #endif - irq_domain_reset_irq_data(irq_data); } } } @@ -404,6 +438,8 @@ int __init arch_early_irq_init(void) arch_init_htirq_domain(x86_vector_domain); BUG_ON(!alloc_cpumask_var(&vector_cpumask, GFP_KERNEL)); + BUG_ON(!alloc_cpumask_var(&vector_searchmask, GFP_KERNEL)); + BUG_ON(!alloc_cpumask_var(&searched_cpumask, GFP_KERNEL)); return arch_early_ioapic_init(); } @@ -492,14 +528,7 @@ static int apic_set_affinity(struct irq_data *irq_data, return -EINVAL; err = assign_irq_vector(irq, data, dest); - if (err) { - if (assign_irq_vector(irq, data, - irq_data_get_affinity_mask(irq_data))) - pr_err("Failed to recover vector for irq %d\n", irq); - return err; - } - - return IRQ_SET_MASK_OK; + return err ? err : IRQ_SET_MASK_OK; } static struct irq_chip lapic_controller = { @@ -511,20 +540,12 @@ static struct irq_chip lapic_controller = { #ifdef CONFIG_SMP static void __send_cleanup_vector(struct apic_chip_data *data) { - cpumask_var_t cleanup_mask; - - if (unlikely(!alloc_cpumask_var(&cleanup_mask, GFP_ATOMIC))) { - unsigned int i; - - for_each_cpu_and(i, data->old_domain, cpu_online_mask) - apic->send_IPI_mask(cpumask_of(i), - IRQ_MOVE_CLEANUP_VECTOR); - } else { - cpumask_and(cleanup_mask, data->old_domain, cpu_online_mask); - apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR); - free_cpumask_var(cleanup_mask); - } + raw_spin_lock(&vector_lock); + cpumask_and(data->old_domain, data->old_domain, cpu_online_mask); data->move_in_progress = 0; + if (!cpumask_empty(data->old_domain)) + apic->send_IPI_mask(data->old_domain, IRQ_MOVE_CLEANUP_VECTOR); + raw_spin_unlock(&vector_lock); } void send_cleanup_vector(struct irq_cfg *cfg) @@ -568,12 +589,25 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void) goto unlock; /* - * Check if the irq migration is in progress. If so, we - * haven't received the cleanup request yet for this irq. + * Nothing to cleanup if irq migration is in progress + * or this cpu is not set in the cleanup mask. */ - if (data->move_in_progress) + if (data->move_in_progress || + !cpumask_test_cpu(me, data->old_domain)) goto unlock; + /* + * We have two cases to handle here: + * 1) vector is unchanged but the target mask got reduced + * 2) vector and the target mask has changed + * + * #1 is obvious, but in #2 we have two vectors with the same + * irq descriptor: the old and the new vector. So we need to + * make sure that we only cleanup the old vector. The new + * vector has the current @vector number in the config and + * this cpu is part of the target mask. We better leave that + * one alone. + */ if (vector == data->cfg.vector && cpumask_test_cpu(me, data->domain)) goto unlock; @@ -591,6 +625,7 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void) goto unlock; } __this_cpu_write(vector_irq[vector], VECTOR_UNUSED); + cpumask_clear_cpu(me, data->old_domain); unlock: raw_spin_unlock(&desc->lock); } @@ -619,12 +654,99 @@ void irq_complete_move(struct irq_cfg *cfg) __irq_complete_move(cfg, ~get_irq_regs()->orig_ax); } -void irq_force_complete_move(int irq) +/* + * Called from fixup_irqs() with @desc->lock held and interrupts disabled. + */ +void irq_force_complete_move(struct irq_desc *desc) { - struct irq_cfg *cfg = irq_cfg(irq); + struct irq_data *irqdata = irq_desc_get_irq_data(desc); + struct apic_chip_data *data = apic_chip_data(irqdata); + struct irq_cfg *cfg = data ? &data->cfg : NULL; + unsigned int cpu; - if (cfg) - __irq_complete_move(cfg, cfg->vector); + if (!cfg) + return; + + /* + * This is tricky. If the cleanup of @data->old_domain has not been + * done yet, then the following setaffinity call will fail with + * -EBUSY. This can leave the interrupt in a stale state. + * + * All CPUs are stuck in stop machine with interrupts disabled so + * calling __irq_complete_move() would be completely pointless. + */ + raw_spin_lock(&vector_lock); + /* + * Clean out all offline cpus (including the outgoing one) from the + * old_domain mask. + */ + cpumask_and(data->old_domain, data->old_domain, cpu_online_mask); + + /* + * If move_in_progress is cleared and the old_domain mask is empty, + * then there is nothing to cleanup. fixup_irqs() will take care of + * the stale vectors on the outgoing cpu. + */ + if (!data->move_in_progress && cpumask_empty(data->old_domain)) { + raw_spin_unlock(&vector_lock); + return; + } + + /* + * 1) The interrupt is in move_in_progress state. That means that we + * have not seen an interrupt since the io_apic was reprogrammed to + * the new vector. + * + * 2) The interrupt has fired on the new vector, but the cleanup IPIs + * have not been processed yet. + */ + if (data->move_in_progress) { + /* + * In theory there is a race: + * + * set_ioapic(new_vector) <-- Interrupt is raised before update + * is effective, i.e. it's raised on + * the old vector. + * + * So if the target cpu cannot handle that interrupt before + * the old vector is cleaned up, we get a spurious interrupt + * and in the worst case the ioapic irq line becomes stale. + * + * But in case of cpu hotplug this should be a non issue + * because if the affinity update happens right before all + * cpus rendevouz in stop machine, there is no way that the + * interrupt can be blocked on the target cpu because all cpus + * loops first with interrupts enabled in stop machine, so the + * old vector is not yet cleaned up when the interrupt fires. + * + * So the only way to run into this issue is if the delivery + * of the interrupt on the apic/system bus would be delayed + * beyond the point where the target cpu disables interrupts + * in stop machine. I doubt that it can happen, but at least + * there is a theroretical chance. Virtualization might be + * able to expose this, but AFAICT the IOAPIC emulation is not + * as stupid as the real hardware. + * + * Anyway, there is nothing we can do about that at this point + * w/o refactoring the whole fixup_irq() business completely. + * We print at least the irq number and the old vector number, + * so we have the necessary information when a problem in that + * area arises. + */ + pr_warn("IRQ fixup: irq %d move in progress, old vector %d\n", + irqdata->irq, cfg->old_vector); + } + /* + * If old_domain is not empty, then other cpus still have the irq + * descriptor set in their vector array. Clean it up. + */ + for_each_cpu(cpu, data->old_domain) + per_cpu(vector_irq, cpu)[cfg->old_vector] = VECTOR_UNUSED; + + /* Cleanup the left overs of the (half finished) move */ + cpumask_clear(data->old_domain); + data->move_in_progress = 0; + raw_spin_unlock(&vector_lock); } #endif diff --git a/arch/x86/kernel/cpu/mcheck/mce-genpool.c b/arch/x86/kernel/cpu/mcheck/mce-genpool.c index 0a850100c594..2658e2af74ec 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-genpool.c +++ b/arch/x86/kernel/cpu/mcheck/mce-genpool.c @@ -29,7 +29,7 @@ static char gen_pool_buf[MCE_POOLSZ]; void mce_gen_pool_process(void) { struct llist_node *head; - struct mce_evt_llist *node; + struct mce_evt_llist *node, *tmp; struct mce *mce; head = llist_del_all(&mce_event_llist); @@ -37,7 +37,7 @@ void mce_gen_pool_process(void) return; head = llist_reverse_order(head); - llist_for_each_entry(node, head, llnode) { + llist_for_each_entry_safe(node, tmp, head, llnode) { mce = &node->mce; atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, mce); gen_pool_free(mce_evt_pool, (unsigned long)node, sizeof(*node)); diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index 2c5aaf8c2e2f..05538582a809 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -385,6 +385,9 @@ static void intel_thermal_interrupt(void) { __u64 msr_val; + if (static_cpu_has(X86_FEATURE_HWP)) + wrmsrl_safe(MSR_HWP_STATUS, 0); + rdmsrl(MSR_IA32_THERM_STATUS, msr_val); /* Check for violation of core thermal thresholds*/ diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index ce47402eb2f9..ac8975a65280 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -555,10 +555,14 @@ scan_microcode(struct mc_saved_data *mc_saved_data, unsigned long *initrd, cd.data = NULL; cd.size = 0; - cd = find_cpio_data(p, (void *)start, size, &offset); - if (!cd.data) { + /* try built-in microcode if no initrd */ + if (!size) { if (!load_builtin_intel_microcode(&cd)) return UCODE_ERROR; + } else { + cd = find_cpio_data(p, (void *)start, size, &offset); + if (!cd.data) + return UCODE_ERROR; } return get_matching_model_microcode(0, start, cd.data, cd.size, @@ -694,7 +698,7 @@ int __init save_microcode_in_initrd_intel(void) if (count == 0) return ret; - copy_initrd_ptrs(mc_saved, mc_saved_in_initrd, initrd_start, count); + copy_initrd_ptrs(mc_saved, mc_saved_in_initrd, get_initrd_start(), count); ret = save_microcode(&mc_saved_data, mc_saved, count); if (ret) pr_err("Cannot save microcode patches from initrd.\n"); @@ -732,16 +736,20 @@ void __init load_ucode_intel_bsp(void) struct boot_params *p; p = (struct boot_params *)__pa_nodebug(&boot_params); - start = p->hdr.ramdisk_image; size = p->hdr.ramdisk_size; - _load_ucode_intel_bsp( - (struct mc_saved_data *)__pa_nodebug(&mc_saved_data), - (unsigned long *)__pa_nodebug(&mc_saved_in_initrd), - start, size); + /* + * Set start only if we have an initrd image. We cannot use initrd_start + * because it is not set that early yet. + */ + start = (size ? p->hdr.ramdisk_image : 0); + + _load_ucode_intel_bsp((struct mc_saved_data *)__pa_nodebug(&mc_saved_data), + (unsigned long *)__pa_nodebug(&mc_saved_in_initrd), + start, size); #else - start = boot_params.hdr.ramdisk_image + PAGE_OFFSET; size = boot_params.hdr.ramdisk_size; + start = (size ? boot_params.hdr.ramdisk_image + PAGE_OFFSET : 0); _load_ucode_intel_bsp(&mc_saved_data, mc_saved_in_initrd, start, size); #endif @@ -752,20 +760,14 @@ void load_ucode_intel_ap(void) struct mc_saved_data *mc_saved_data_p; struct ucode_cpu_info uci; unsigned long *mc_saved_in_initrd_p; - unsigned long initrd_start_addr; enum ucode_state ret; #ifdef CONFIG_X86_32 - unsigned long *initrd_start_p; - mc_saved_in_initrd_p = - (unsigned long *)__pa_nodebug(mc_saved_in_initrd); + mc_saved_in_initrd_p = (unsigned long *)__pa_nodebug(mc_saved_in_initrd); mc_saved_data_p = (struct mc_saved_data *)__pa_nodebug(&mc_saved_data); - initrd_start_p = (unsigned long *)__pa_nodebug(&initrd_start); - initrd_start_addr = (unsigned long)__pa_nodebug(*initrd_start_p); #else - mc_saved_data_p = &mc_saved_data; mc_saved_in_initrd_p = mc_saved_in_initrd; - initrd_start_addr = initrd_start; + mc_saved_data_p = &mc_saved_data; #endif /* @@ -777,7 +779,7 @@ void load_ucode_intel_ap(void) collect_cpu_info_early(&uci); ret = load_microcode(mc_saved_data_p, mc_saved_in_initrd_p, - initrd_start_addr, &uci); + get_initrd_start_addr(), &uci); if (ret != UCODE_OK) return; diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 2bf79d7c97df..a3aeb2cc361e 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -593,6 +593,19 @@ void x86_pmu_disable_all(void) } } +/* + * There may be PMI landing after enabled=0. The PMI hitting could be before or + * after disable_all. + * + * If PMI hits before disable_all, the PMU will be disabled in the NMI handler. + * It will not be re-enabled in the NMI handler again, because enabled=0. After + * handling the NMI, disable_all will be called, which will not change the + * state either. If PMI hits after disable_all, the PMU is already disabled + * before entering NMI handler. The NMI handler will not change the state + * either. + * + * So either situation is harmless. + */ static void x86_pmu_disable(struct pmu *pmu) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index d0e35ebb2adb..ee70445fbb1f 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -591,6 +591,7 @@ struct x86_pmu { pebs_active :1, pebs_broken :1; int pebs_record_size; + int pebs_buffer_size; void (*drain_pebs)(struct pt_regs *regs); struct event_constraint *pebs_constraints; void (*pebs_aliases)(struct perf_event *event); @@ -907,6 +908,8 @@ void intel_pmu_lbr_init_hsw(void); void intel_pmu_lbr_init_skl(void); +void intel_pmu_pebs_data_source_nhm(void); + int intel_pmu_setup_lbr_filter(struct perf_event *event); void intel_pt_interrupt(void); diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index e2a430021e46..5f82cd59f0e5 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1458,7 +1458,15 @@ static __initconst const u64 slm_hw_cache_event_ids }; /* - * Use from PMIs where the LBRs are already disabled. + * Used from PMIs where the LBRs are already disabled. + * + * This function could be called consecutively. It is required to remain in + * disabled state if called consecutively. + * + * During consecutive calls, the same disable value will be written to related + * registers, so the PMU state remains unchanged. hw.state in + * intel_bts_disable_local will remain PERF_HES_STOPPED too in consecutive + * calls. */ static void __intel_pmu_disable_all(void) { @@ -1840,6 +1848,16 @@ again: if (__test_and_clear_bit(62, (unsigned long *)&status)) { handled++; x86_pmu.drain_pebs(regs); + /* + * There are cases where, even though, the PEBS ovfl bit is set + * in GLOBAL_OVF_STATUS, the PEBS events may also have their + * overflow bits set for their counters. We must clear them + * here because they have been processed as exact samples in + * the drain_pebs() routine. They must not be processed again + * in the for_each_bit_set() loop for regular samples below. + */ + status &= ~cpuc->pebs_enabled; + status &= x86_pmu.intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI; } /* @@ -1885,7 +1903,10 @@ again: goto again; done: - __intel_pmu_enable_all(0, true); + /* Only restore PMU state when it's active. See x86_pmu_disable(). */ + if (cpuc->enabled) + __intel_pmu_enable_all(0, true); + /* * Only unmask the NMI after the overflow counters * have been reset. This avoids spurious NMIs on @@ -3315,6 +3336,7 @@ __init int intel_pmu_init(void) intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = X86_CONFIG(.event=0xb1, .umask=0x3f, .inv=1, .cmask=1); + intel_pmu_pebs_data_source_nhm(); x86_add_quirk(intel_nehalem_quirk); pr_cont("Nehalem events, "); @@ -3377,6 +3399,7 @@ __init int intel_pmu_init(void) intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = X86_CONFIG(.event=0xb1, .umask=0x3f, .inv=1, .cmask=1); + intel_pmu_pebs_data_source_nhm(); pr_cont("Westmere events, "); break; @@ -3578,7 +3601,7 @@ __init int intel_pmu_init(void) c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1; } c->idxmsk64 &= - ~(~0UL << (INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed)); + ~(~0ULL << (INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed)); c->weight = hweight64(c->idxmsk64); } } diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 5db1c7755548..7abb2b88572e 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -51,7 +51,8 @@ union intel_x86_pebs_dse { #define OP_LH (P(OP, LOAD) | P(LVL, HIT)) #define SNOOP_NONE_MISS (P(SNOOP, NONE) | P(SNOOP, MISS)) -static const u64 pebs_data_source[] = { +/* Version for Sandy Bridge and later */ +static u64 pebs_data_source[] = { P(OP, LOAD) | P(LVL, MISS) | P(LVL, L3) | P(SNOOP, NA),/* 0x00:ukn L3 */ OP_LH | P(LVL, L1) | P(SNOOP, NONE), /* 0x01: L1 local */ OP_LH | P(LVL, LFB) | P(SNOOP, NONE), /* 0x02: LFB hit */ @@ -70,6 +71,14 @@ static const u64 pebs_data_source[] = { OP_LH | P(LVL, UNC) | P(SNOOP, NONE), /* 0x0f: uncached */ }; +/* Patch up minor differences in the bits */ +void __init intel_pmu_pebs_data_source_nhm(void) +{ + pebs_data_source[0x05] = OP_LH | P(LVL, L3) | P(SNOOP, HIT); + pebs_data_source[0x06] = OP_LH | P(LVL, L3) | P(SNOOP, HITM); + pebs_data_source[0x07] = OP_LH | P(LVL, L3) | P(SNOOP, HITM); +} + static u64 precise_store_data(u64 status) { union intel_x86_pebs_dse dse; @@ -269,7 +278,7 @@ static int alloc_pebs_buffer(int cpu) if (!x86_pmu.pebs) return 0; - buffer = kzalloc_node(PEBS_BUFFER_SIZE, GFP_KERNEL, node); + buffer = kzalloc_node(x86_pmu.pebs_buffer_size, GFP_KERNEL, node); if (unlikely(!buffer)) return -ENOMEM; @@ -286,7 +295,7 @@ static int alloc_pebs_buffer(int cpu) per_cpu(insn_buffer, cpu) = ibuffer; } - max = PEBS_BUFFER_SIZE / x86_pmu.pebs_record_size; + max = x86_pmu.pebs_buffer_size / x86_pmu.pebs_record_size; ds->pebs_buffer_base = (u64)(unsigned long)buffer; ds->pebs_index = ds->pebs_buffer_base; @@ -1296,6 +1305,7 @@ void __init intel_ds_init(void) x86_pmu.bts = boot_cpu_has(X86_FEATURE_BTS); x86_pmu.pebs = boot_cpu_has(X86_FEATURE_PEBS); + x86_pmu.pebs_buffer_size = PEBS_BUFFER_SIZE; if (x86_pmu.pebs) { char pebs_type = x86_pmu.intel_cap.pebs_trap ? '+' : '-'; int format = x86_pmu.intel_cap.pebs_format; @@ -1304,6 +1314,14 @@ void __init intel_ds_init(void) case 0: printk(KERN_CONT "PEBS fmt0%c, ", pebs_type); x86_pmu.pebs_record_size = sizeof(struct pebs_record_core); + /* + * Using >PAGE_SIZE buffers makes the WRMSR to + * PERF_GLOBAL_CTRL in intel_pmu_enable_all() + * mysteriously hang on Core2. + * + * As a workaround, we don't do this. + */ + x86_pmu.pebs_buffer_size = PAGE_SIZE; x86_pmu.drain_pebs = intel_pmu_drain_pebs_core; break; diff --git a/arch/x86/kernel/cpu/perf_event_intel_pt.c b/arch/x86/kernel/cpu/perf_event_intel_pt.c index 868e1194337f..49e35d003b74 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_pt.c +++ b/arch/x86/kernel/cpu/perf_event_intel_pt.c @@ -694,6 +694,7 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf, /* clear STOP and INT from current entry */ buf->topa_index[buf->stop_pos]->stop = 0; + buf->topa_index[buf->stop_pos]->intr = 0; buf->topa_index[buf->intr_pos]->intr = 0; /* how many pages till the STOP marker */ @@ -718,6 +719,7 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf, buf->intr_pos = idx; buf->topa_index[buf->stop_pos]->stop = 1; + buf->topa_index[buf->stop_pos]->intr = 1; buf->topa_index[buf->intr_pos]->intr = 1; return 0; diff --git a/arch/x86/kernel/cpu/perf_event_knc.c b/arch/x86/kernel/cpu/perf_event_knc.c index 5b0c232d1ee6..b931095e86d4 100644 --- a/arch/x86/kernel/cpu/perf_event_knc.c +++ b/arch/x86/kernel/cpu/perf_event_knc.c @@ -263,7 +263,9 @@ again: goto again; done: - knc_pmu_enable_all(0); + /* Only restore PMU state when it's active. See x86_pmu_disable(). */ + if (cpuc->enabled) + knc_pmu_enable_all(0); return handled; } diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c index 37dae792dbbe..589b3193f102 100644 --- a/arch/x86/kernel/ioport.c +++ b/arch/x86/kernel/ioport.c @@ -96,9 +96,14 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on) SYSCALL_DEFINE1(iopl, unsigned int, level) { struct pt_regs *regs = current_pt_regs(); - unsigned int old = (regs->flags >> 12) & 3; struct thread_struct *t = ¤t->thread; + /* + * Careful: the IOPL bits in regs->flags are undefined under Xen PV + * and changing them has no effect. + */ + unsigned int old = t->iopl >> X86_EFLAGS_IOPL_BIT; + if (level > 3) return -EINVAL; /* Trying to gain more privileges? */ @@ -106,8 +111,9 @@ SYSCALL_DEFINE1(iopl, unsigned int, level) if (!capable(CAP_SYS_RAWIO)) return -EPERM; } - regs->flags = (regs->flags & ~X86_EFLAGS_IOPL) | (level << 12); - t->iopl = level << 12; + regs->flags = (regs->flags & ~X86_EFLAGS_IOPL) | + (level << X86_EFLAGS_IOPL_BIT); + t->iopl = level << X86_EFLAGS_IOPL_BIT; set_iopl_mask(t->iopl); return 0; diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index f8062aaf5df9..61521dc19c10 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -462,7 +462,7 @@ void fixup_irqs(void) * non intr-remapping case, we can't wait till this interrupt * arrives at this cpu before completing the irq move. */ - irq_force_complete_move(irq); + irq_force_complete_move(desc); if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) { break_affinity = 1; @@ -470,6 +470,15 @@ void fixup_irqs(void) } chip = irq_data_get_irq_chip(data); + /* + * The interrupt descriptor might have been cleaned up + * already, but it is not yet removed from the radix tree + */ + if (!chip) { + raw_spin_unlock(&desc->lock); + continue; + } + if (!irqd_can_move_in_process_context(data) && chip->irq_mask) chip->irq_mask(data); diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 1deffe6cc873..023c442c33bb 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -959,7 +959,19 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr) * normal page fault. */ regs->ip = (unsigned long)cur->addr; + /* + * Trap flag (TF) has been set here because this fault + * happened where the single stepping will be done. + * So clear it by resetting the current kprobe: + */ + regs->flags &= ~X86_EFLAGS_TF; + + /* + * If the TF flag was set before the kprobe hit, + * don't touch it: + */ regs->flags |= kcb->kprobe_old_flags; + if (kcb->kprobe_status == KPROBE_REENTER) restore_previous_kprobe(kcb); else diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index e835d263a33b..4cbb60fbff3e 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -48,6 +48,7 @@ #include #include #include +#include asmlinkage extern void ret_from_fork(void); @@ -411,6 +412,17 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV)) __switch_to_xtra(prev_p, next_p, tss); +#ifdef CONFIG_XEN + /* + * On Xen PV, IOPL bits in pt_regs->flags have no effect, and + * current_pt_regs()->flags may not match the current task's + * intended IOPL. We need to switch it manually. + */ + if (unlikely(static_cpu_has(X86_FEATURE_XENPV) && + prev->iopl != next->iopl)) + xen_set_iopl_mask(next->iopl); +#endif + if (static_cpu_has_bug(X86_BUG_SYSRET_SS_ATTRS)) { /* * AMD CPUs have a misfeature: SYSRET sets the SS selector but diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 02693dd9a079..f660d63f40fe 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -182,6 +182,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "iMac9,1"), }, }, + { /* Handle problems with rebooting on the iMac10,1. */ + .callback = set_pci_reboot, + .ident = "Apple iMac10,1", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "iMac10,1"), + }, + }, /* ASRock */ { /* Handle problems with rebooting on ASRock Q1900DC-ITX */ diff --git a/arch/x86/kernel/sysfb_efi.c b/arch/x86/kernel/sysfb_efi.c index b285d4e8c68e..5da924bbf0a0 100644 --- a/arch/x86/kernel/sysfb_efi.c +++ b/arch/x86/kernel/sysfb_efi.c @@ -106,14 +106,24 @@ static int __init efifb_set_system(const struct dmi_system_id *id) continue; for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) { resource_size_t start, end; + unsigned long flags; + + flags = pci_resource_flags(dev, i); + if (!(flags & IORESOURCE_MEM)) + continue; + + if (flags & IORESOURCE_UNSET) + continue; + + if (pci_resource_len(dev, i) == 0) + continue; start = pci_resource_start(dev, i); - if (start == 0) - break; end = pci_resource_end(dev, i); if (screen_info.lfb_base >= start && screen_info.lfb_base < end) { found_bar = 1; + break; } } } diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index ade185a46b1d..679302c312f8 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -109,6 +109,12 @@ static inline void preempt_conditional_cli(struct pt_regs *regs) preempt_count_dec(); } +/* + * In IST context, we explicitly disable preemption. This serves two + * purposes: it makes it much less likely that we would accidentally + * schedule in IST context and it will force a warning if we somehow + * manage to schedule by accident. + */ void ist_enter(struct pt_regs *regs) { if (user_mode(regs)) { @@ -123,13 +129,7 @@ void ist_enter(struct pt_regs *regs) rcu_nmi_enter(); } - /* - * We are atomic because we're on the IST stack; or we're on - * x86_32, in which case we still shouldn't schedule; or we're - * on x86_64 and entered from user mode, in which case we're - * still atomic unless ist_begin_non_atomic is called. - */ - preempt_count_add(HARDIRQ_OFFSET); + preempt_disable(); /* This code is a bit fragile. Test it. */ RCU_LOCKDEP_WARN(!rcu_is_watching(), "ist_enter didn't work"); @@ -137,7 +137,7 @@ void ist_enter(struct pt_regs *regs) void ist_exit(struct pt_regs *regs) { - preempt_count_sub(HARDIRQ_OFFSET); + preempt_enable_no_resched(); if (!user_mode(regs)) rcu_nmi_exit(); @@ -168,7 +168,7 @@ void ist_begin_non_atomic(struct pt_regs *regs) BUG_ON((unsigned long)(current_top_of_stack() - current_stack_pointer()) >= THREAD_SIZE); - preempt_count_sub(HARDIRQ_OFFSET); + preempt_enable_no_resched(); } /** @@ -178,7 +178,7 @@ void ist_begin_non_atomic(struct pt_regs *regs) */ void ist_end_non_atomic(void) { - preempt_count_add(HARDIRQ_OFFSET); + preempt_disable(); } static nokprobe_inline int diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c index 92ae6acac8a7..6aa0f4d9eea6 100644 --- a/arch/x86/kernel/tsc_msr.c +++ b/arch/x86/kernel/tsc_msr.c @@ -92,7 +92,7 @@ unsigned long try_msr_calibrate_tsc(void) if (freq_desc_tables[cpu_index].msr_plat) { rdmsr(MSR_PLATFORM_INFO, lo, hi); - ratio = (lo >> 8) & 0x1f; + ratio = (lo >> 8) & 0xff; } else { rdmsr(MSR_IA32_PERF_STATUS, lo, hi); ratio = (hi >> 8) & 0x1f; diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 6525e926f566..2e1fd586b895 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -509,6 +509,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, do_cpuid_1_ent(&entry[i], function, idx); if (idx == 1) { entry[i].eax &= kvm_supported_word10_x86_features; + cpuid_mask(&entry[i].eax, 10); entry[i].ebx = 0; if (entry[i].eax & (F(XSAVES)|F(XSAVEC))) entry[i].ebx = diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 1505587d06e9..b9b09fec173b 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -650,10 +650,10 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt, u16 sel; la = seg_base(ctxt, addr.seg) + addr.ea; - *linear = la; *max_size = 0; switch (mode) { case X86EMUL_MODE_PROT64: + *linear = la; if (is_noncanonical_address(la)) goto bad; @@ -662,6 +662,7 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt, goto bad; break; default: + *linear = la = (u32)la; usable = ctxt->ops->get_segment(ctxt, &sel, &desc, NULL, addr.seg); if (!usable) @@ -689,7 +690,6 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt, if (size > *max_size) goto bad; } - la &= (u32)-1; break; } if (insn_aligned(ctxt, size) && ((la & (size - 1)) != 0)) diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index b0ea42b78ccd..ab5318727579 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -245,7 +245,7 @@ static void kvm_pit_ack_irq(struct kvm_irq_ack_notifier *kian) * PIC is being reset. Handle it gracefully here */ atomic_inc(&ps->pending); - else if (value > 0) + else if (value > 0 && ps->reinject) /* in this case, we had multiple outstanding pit interrupts * that we needed to inject. Reinject */ @@ -288,7 +288,9 @@ static void pit_do_work(struct kthread_work *work) * last one has been acked. */ spin_lock(&ps->inject_lock); - if (ps->irq_ack) { + if (!ps->reinject) + inject = 1; + else if (ps->irq_ack) { ps->irq_ack = 0; inject = 1; } @@ -317,10 +319,10 @@ static enum hrtimer_restart pit_timer_fn(struct hrtimer *data) struct kvm_kpit_state *ps = container_of(data, struct kvm_kpit_state, timer); struct kvm_pit *pt = ps->kvm->arch.vpit; - if (ps->reinject || !atomic_read(&ps->pending)) { + if (ps->reinject) atomic_inc(&ps->pending); - queue_kthread_work(&pt->worker, &pt->expired); - } + + queue_kthread_work(&pt->worker, &pt->expired); if (ps->is_periodic) { hrtimer_add_expires_ns(&ps->timer, ps->period); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index e7c2c1428a69..8eb8a934b531 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3754,13 +3754,15 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu, void reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context) { + bool uses_nx = context->nx || context->base_role.smep_andnot_wp; + /* * Passing "true" to the last argument is okay; it adds a check * on bit 8 of the SPTEs which KVM doesn't use anyway. */ __reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check, boot_cpu_data.x86_phys_bits, - context->shadow_root_level, context->nx, + context->shadow_root_level, uses_nx, guest_cpuid_has_gbpages(vcpu), is_pse(vcpu), true); } diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index 3f8c732117ec..c146f3c262c3 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -44,8 +44,6 @@ static bool msr_mtrr_valid(unsigned msr) case MSR_MTRRdefType: case MSR_IA32_CR_PAT: return true; - case 0x2f8: - return true; } return false; } diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 3058a22a658d..7be8a251363e 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -249,7 +249,7 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu, return ret; kvm_vcpu_mark_page_dirty(vcpu, table_gfn); - walker->ptes[level] = pte; + walker->ptes[level - 1] = pte; } return 0; } diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 120302511802..ab9ae67a80e4 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -268,7 +268,7 @@ TRACE_EVENT(kvm_inj_virq, #define kvm_trace_sym_exc \ EXS(DE), EXS(DB), EXS(BP), EXS(OF), EXS(BR), EXS(UD), EXS(NM), \ EXS(DF), EXS(TS), EXS(NP), EXS(SS), EXS(GP), EXS(PF), \ - EXS(MF), EXS(MC) + EXS(MF), EXS(AC), EXS(MC) /* * Tracepoint for kvm interrupt injection: diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 44976a596fa6..41e7943004fe 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -595,6 +595,8 @@ struct vcpu_vmx { /* Support for PML */ #define PML_ENTITY_NUM 512 struct page *pml_pg; + + u64 current_tsc_ratio; }; enum segment_cache_field { @@ -1746,6 +1748,13 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr, return; } break; + case MSR_IA32_PEBS_ENABLE: + /* PEBS needs a quiescent period after being disabled (to write + * a record). Disabling PEBS through VMX MSR swapping doesn't + * provide that period, so a CPU could write host's record into + * guest's memory. + */ + wrmsrl(MSR_IA32_PEBS_ENABLE, 0); } for (i = 0; i < m->nr; ++i) @@ -1783,26 +1792,31 @@ static void reload_tss(void) static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) { - u64 guest_efer; - u64 ignore_bits; + u64 guest_efer = vmx->vcpu.arch.efer; + u64 ignore_bits = 0; - guest_efer = vmx->vcpu.arch.efer; + if (!enable_ept) { + /* + * NX is needed to handle CR0.WP=1, CR4.SMEP=1. Testing + * host CPUID is more efficient than testing guest CPUID + * or CR4. Host SMEP is anyway a requirement for guest SMEP. + */ + if (boot_cpu_has(X86_FEATURE_SMEP)) + guest_efer |= EFER_NX; + else if (!(guest_efer & EFER_NX)) + ignore_bits |= EFER_NX; + } /* - * NX is emulated; LMA and LME handled by hardware; SCE meaningless - * outside long mode + * LMA and LME handled by hardware; SCE meaningless outside long mode. */ - ignore_bits = EFER_NX | EFER_SCE; + ignore_bits |= EFER_SCE; #ifdef CONFIG_X86_64 ignore_bits |= EFER_LMA | EFER_LME; /* SCE is meaningful only in long mode on Intel */ if (guest_efer & EFER_LMA) ignore_bits &= ~(u64)EFER_SCE; #endif - guest_efer &= ~ignore_bits; - guest_efer |= host_efer & ignore_bits; - vmx->guest_msrs[efer_offset].data = guest_efer; - vmx->guest_msrs[efer_offset].mask = ~ignore_bits; clear_atomic_switch_msr(vmx, MSR_EFER); @@ -1813,16 +1827,21 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) */ if (cpu_has_load_ia32_efer || (enable_ept && ((vmx->vcpu.arch.efer ^ host_efer) & EFER_NX))) { - guest_efer = vmx->vcpu.arch.efer; if (!(guest_efer & EFER_LMA)) guest_efer &= ~EFER_LME; if (guest_efer != host_efer) add_atomic_switch_msr(vmx, MSR_EFER, guest_efer, host_efer); return false; - } + } else { + guest_efer &= ~ignore_bits; + guest_efer |= host_efer & ignore_bits; - return true; + vmx->guest_msrs[efer_offset].data = guest_efer; + vmx->guest_msrs[efer_offset].mask = ~ignore_bits; + + return true; + } } static unsigned long segment_base(u16 selector) @@ -2062,14 +2081,16 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp); vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */ - /* Setup TSC multiplier */ - if (cpu_has_vmx_tsc_scaling()) - vmcs_write64(TSC_MULTIPLIER, - vcpu->arch.tsc_scaling_ratio); - vmx->loaded_vmcs->cpu = cpu; } + /* Setup TSC multiplier */ + if (kvm_has_tsc_control && + vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio) { + vmx->current_tsc_ratio = vcpu->arch.tsc_scaling_ratio; + vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio); + } + vmx_vcpu_pi_load(vcpu, cpu); } @@ -2616,8 +2637,15 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) } else vmx->nested.nested_vmx_ept_caps = 0; + /* + * Old versions of KVM use the single-context version without + * checking for support, so declare that it is supported even + * though it is treated as global context. The alternative is + * not failing the single-context invvpid, and it is worse. + */ if (enable_vpid) vmx->nested.nested_vmx_vpid_caps = VMX_VPID_INVVPID_BIT | + VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT | VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT; else vmx->nested.nested_vmx_vpid_caps = 0; @@ -4926,8 +4954,8 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET; - vmx_set_cr0(vcpu, cr0); /* enter rmode */ vmx->vcpu.arch.cr0 = cr0; + vmx_set_cr0(vcpu, cr0); /* enter rmode */ vmx_set_cr4(vcpu, 0); vmx_set_efer(vcpu, 0); vmx_fpu_activate(vcpu); @@ -6551,7 +6579,13 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu, /* Checks for #GP/#SS exceptions. */ exn = false; - if (is_protmode(vcpu)) { + if (is_long_mode(vcpu)) { + /* Long mode: #GP(0)/#SS(0) if the memory address is in a + * non-canonical form. This is the only check on the memory + * destination for long mode! + */ + exn = is_noncanonical_address(*ret); + } else if (is_protmode(vcpu)) { /* Protected mode: apply checks for segment validity in the * following order: * - segment type check (#GP(0) may be thrown) @@ -6568,17 +6602,10 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu, * execute-only code segment */ exn = ((s.type & 0xa) == 8); - } - if (exn) { - kvm_queue_exception_e(vcpu, GP_VECTOR, 0); - return 1; - } - if (is_long_mode(vcpu)) { - /* Long mode: #GP(0)/#SS(0) if the memory address is in a - * non-canonical form. This is an only check for long mode. - */ - exn = is_noncanonical_address(*ret); - } else if (is_protmode(vcpu)) { + if (exn) { + kvm_queue_exception_e(vcpu, GP_VECTOR, 0); + return 1; + } /* Protected mode: #GP(0)/#SS(0) if the segment is unusable. */ exn = (s.unusable != 0); @@ -7319,6 +7346,7 @@ static int handle_invept(struct kvm_vcpu *vcpu) if (!(types & (1UL << type))) { nested_vmx_failValid(vcpu, VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); + skip_emulated_instruction(vcpu); return 1; } @@ -7377,6 +7405,7 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) if (!(types & (1UL << type))) { nested_vmx_failValid(vcpu, VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); + skip_emulated_instruction(vcpu); return 1; } @@ -7393,12 +7422,17 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) } switch (type) { + case VMX_VPID_EXTENT_SINGLE_CONTEXT: + /* + * Old versions of KVM use the single-context version so we + * have to support it; just treat it the same as all-context. + */ case VMX_VPID_EXTENT_ALL_CONTEXT: __vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02); nested_vmx_succeed(vcpu); break; default: - /* Trap single context invalidation invvpid calls */ + /* Trap individual address invalidation invvpid calls */ BUG_ON(1); break; } @@ -8932,7 +8966,8 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) best->ebx &= ~bit(X86_FEATURE_INVPCID); } - vmcs_set_secondary_exec_control(secondary_exec_ctl); + if (cpu_has_secondary_exec_ctrls()) + vmcs_set_secondary_exec_control(secondary_exec_ctl); if (static_cpu_has(X86_FEATURE_PCOMMIT) && nested) { if (guest_cpuid_has_pcommit(vcpu)) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 97592e190413..be222666b1c2 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -697,7 +697,6 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) if ((xcr0 & XFEATURE_MASK_AVX512) != XFEATURE_MASK_AVX512) return 1; } - kvm_put_guest_xcr0(vcpu); vcpu->arch.xcr0 = xcr0; if ((xcr0 ^ old_xcr0) & XFEATURE_MASK_EXTEND) @@ -951,7 +950,7 @@ static u32 msrs_to_save[] = { MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR, #endif MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA, - MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS + MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS, MSR_TSC_AUX, }; static unsigned num_msrs_to_save; @@ -2736,6 +2735,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) } kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); + vcpu->arch.switch_db_regs |= KVM_DEBUGREG_RELOAD; } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) @@ -3014,6 +3014,11 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, if (dbgregs->flags) return -EINVAL; + if (dbgregs->dr6 & ~0xffffffffull) + return -EINVAL; + if (dbgregs->dr7 & ~0xffffffffull) + return -EINVAL; + memcpy(vcpu->arch.db, dbgregs->db, sizeof(vcpu->arch.db)); kvm_update_dr0123(vcpu); vcpu->arch.dr6 = dbgregs->dr6; @@ -4006,16 +4011,17 @@ static void kvm_init_msr_list(void) /* * Even MSRs that are valid in the host may not be exposed - * to the guests in some cases. We could work around this - * in VMX with the generic MSR save/load machinery, but it - * is not really worthwhile since it will really only - * happen with nested virtualization. + * to the guests in some cases. */ switch (msrs_to_save[i]) { case MSR_IA32_BNDCFGS: if (!kvm_x86_ops->mpx_supported()) continue; break; + case MSR_TSC_AUX: + if (!kvm_x86_ops->rdtscp_supported()) + continue; + break; default: break; } @@ -6022,12 +6028,10 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win) } /* try to inject new event if pending */ - if (vcpu->arch.nmi_pending) { - if (kvm_x86_ops->nmi_allowed(vcpu)) { - --vcpu->arch.nmi_pending; - vcpu->arch.nmi_injected = true; - kvm_x86_ops->set_nmi(vcpu); - } + if (vcpu->arch.nmi_pending && kvm_x86_ops->nmi_allowed(vcpu)) { + --vcpu->arch.nmi_pending; + vcpu->arch.nmi_injected = true; + kvm_x86_ops->set_nmi(vcpu); } else if (kvm_cpu_has_injectable_intr(vcpu)) { /* * Because interrupts can be injected asynchronously, we are @@ -6472,10 +6476,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (inject_pending_event(vcpu, req_int_win) != 0) req_immediate_exit = true; /* enable NMI/IRQ window open exits if needed */ - else if (vcpu->arch.nmi_pending) - kvm_x86_ops->enable_nmi_window(vcpu); - else if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win) - kvm_x86_ops->enable_irq_window(vcpu); + else { + if (vcpu->arch.nmi_pending) + kvm_x86_ops->enable_nmi_window(vcpu); + if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win) + kvm_x86_ops->enable_irq_window(vcpu); + } if (kvm_lapic_enabled(vcpu)) { update_cr8_intercept(vcpu); @@ -6493,8 +6499,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_x86_ops->prepare_guest_switch(vcpu); if (vcpu->fpu_active) kvm_load_guest_fpu(vcpu); - kvm_load_guest_xcr0(vcpu); - vcpu->mode = IN_GUEST_MODE; srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); @@ -6517,6 +6521,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) goto cancel_injection; } + kvm_load_guest_xcr0(vcpu); + if (req_immediate_exit) smp_send_reschedule(vcpu->cpu); @@ -6543,12 +6549,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) * KVM_DEBUGREG_WONT_EXIT again. */ if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) { - int i; - WARN_ON(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP); kvm_x86_ops->sync_dirty_debug_regs(vcpu); - for (i = 0; i < KVM_NR_DB_REGS; i++) - vcpu->arch.eff_db[i] = vcpu->arch.db[i]; + kvm_update_dr0123(vcpu); + kvm_update_dr6(vcpu); + kvm_update_dr7(vcpu); + vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD; } /* @@ -6566,6 +6572,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); + kvm_put_guest_xcr0(vcpu); + /* Interrupt is enabled by handle_external_intr() */ kvm_x86_ops->handle_external_intr(vcpu); @@ -7213,7 +7221,6 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) * and assume host would use all available bits. * Guest xcr0 would be loaded later. */ - kvm_put_guest_xcr0(vcpu); vcpu->guest_fpu_loaded = 1; __kernel_fpu_begin(); __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state); @@ -7222,8 +7229,6 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) { - kvm_put_guest_xcr0(vcpu); - if (!vcpu->guest_fpu_loaded) { vcpu->fpu_counter = 0; return; diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index 982ce34f4a9b..27f89c79a44b 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -232,17 +232,31 @@ ENDPROC(copy_user_enhanced_fast_string) /* * copy_user_nocache - Uncached memory copy with exception handling - * This will force destination/source out of cache for more performance. + * This will force destination out of cache for more performance. + * + * Note: Cached memory copy is used when destination or size is not + * naturally aligned. That is: + * - Require 8-byte alignment when size is 8 bytes or larger. + * - Require 4-byte alignment when size is 4 bytes. */ ENTRY(__copy_user_nocache) ASM_STAC + + /* If size is less than 8 bytes, go to 4-byte copy */ cmpl $8,%edx - jb 20f /* less then 8 bytes, go to byte copy loop */ + jb .L_4b_nocache_copy_entry + + /* If destination is not 8-byte aligned, "cache" copy to align it */ ALIGN_DESTINATION + + /* Set 4x8-byte copy count and remainder */ movl %edx,%ecx andl $63,%edx shrl $6,%ecx - jz 17f + jz .L_8b_nocache_copy_entry /* jump if count is 0 */ + + /* Perform 4x8-byte nocache loop-copy */ +.L_4x8b_nocache_copy_loop: 1: movq (%rsi),%r8 2: movq 1*8(%rsi),%r9 3: movq 2*8(%rsi),%r10 @@ -262,60 +276,106 @@ ENTRY(__copy_user_nocache) leaq 64(%rsi),%rsi leaq 64(%rdi),%rdi decl %ecx - jnz 1b -17: movl %edx,%ecx + jnz .L_4x8b_nocache_copy_loop + + /* Set 8-byte copy count and remainder */ +.L_8b_nocache_copy_entry: + movl %edx,%ecx andl $7,%edx shrl $3,%ecx - jz 20f -18: movq (%rsi),%r8 -19: movnti %r8,(%rdi) + jz .L_4b_nocache_copy_entry /* jump if count is 0 */ + + /* Perform 8-byte nocache loop-copy */ +.L_8b_nocache_copy_loop: +20: movq (%rsi),%r8 +21: movnti %r8,(%rdi) leaq 8(%rsi),%rsi leaq 8(%rdi),%rdi decl %ecx - jnz 18b -20: andl %edx,%edx - jz 23f + jnz .L_8b_nocache_copy_loop + + /* If no byte left, we're done */ +.L_4b_nocache_copy_entry: + andl %edx,%edx + jz .L_finish_copy + + /* If destination is not 4-byte aligned, go to byte copy: */ + movl %edi,%ecx + andl $3,%ecx + jnz .L_1b_cache_copy_entry + + /* Set 4-byte copy count (1 or 0) and remainder */ movl %edx,%ecx -21: movb (%rsi),%al -22: movb %al,(%rdi) + andl $3,%edx + shrl $2,%ecx + jz .L_1b_cache_copy_entry /* jump if count is 0 */ + + /* Perform 4-byte nocache copy: */ +30: movl (%rsi),%r8d +31: movnti %r8d,(%rdi) + leaq 4(%rsi),%rsi + leaq 4(%rdi),%rdi + + /* If no bytes left, we're done: */ + andl %edx,%edx + jz .L_finish_copy + + /* Perform byte "cache" loop-copy for the remainder */ +.L_1b_cache_copy_entry: + movl %edx,%ecx +.L_1b_cache_copy_loop: +40: movb (%rsi),%al +41: movb %al,(%rdi) incq %rsi incq %rdi decl %ecx - jnz 21b -23: xorl %eax,%eax + jnz .L_1b_cache_copy_loop + + /* Finished copying; fence the prior stores */ +.L_finish_copy: + xorl %eax,%eax ASM_CLAC sfence ret .section .fixup,"ax" -30: shll $6,%ecx +.L_fixup_4x8b_copy: + shll $6,%ecx addl %ecx,%edx - jmp 60f -40: lea (%rdx,%rcx,8),%rdx - jmp 60f -50: movl %ecx,%edx -60: sfence + jmp .L_fixup_handle_tail +.L_fixup_8b_copy: + lea (%rdx,%rcx,8),%rdx + jmp .L_fixup_handle_tail +.L_fixup_4b_copy: + lea (%rdx,%rcx,4),%rdx + jmp .L_fixup_handle_tail +.L_fixup_1b_copy: + movl %ecx,%edx +.L_fixup_handle_tail: + sfence jmp copy_user_handle_tail .previous - _ASM_EXTABLE(1b,30b) - _ASM_EXTABLE(2b,30b) - _ASM_EXTABLE(3b,30b) - _ASM_EXTABLE(4b,30b) - _ASM_EXTABLE(5b,30b) - _ASM_EXTABLE(6b,30b) - _ASM_EXTABLE(7b,30b) - _ASM_EXTABLE(8b,30b) - _ASM_EXTABLE(9b,30b) - _ASM_EXTABLE(10b,30b) - _ASM_EXTABLE(11b,30b) - _ASM_EXTABLE(12b,30b) - _ASM_EXTABLE(13b,30b) - _ASM_EXTABLE(14b,30b) - _ASM_EXTABLE(15b,30b) - _ASM_EXTABLE(16b,30b) - _ASM_EXTABLE(18b,40b) - _ASM_EXTABLE(19b,40b) - _ASM_EXTABLE(21b,50b) - _ASM_EXTABLE(22b,50b) + _ASM_EXTABLE(1b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(2b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(3b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(4b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(5b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(6b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(7b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(8b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(9b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(10b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(11b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(12b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(13b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(14b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(15b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(16b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(20b,.L_fixup_8b_copy) + _ASM_EXTABLE(21b,.L_fixup_8b_copy) + _ASM_EXTABLE(30b,.L_fixup_4b_copy) + _ASM_EXTABLE(31b,.L_fixup_4b_copy) + _ASM_EXTABLE(40b,.L_fixup_1b_copy) + _ASM_EXTABLE(41b,.L_fixup_1b_copy) ENDPROC(__copy_user_nocache) diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index eef44d9a3f77..e830c71a1323 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -287,6 +287,9 @@ static noinline int vmalloc_fault(unsigned long address) if (!pmd_k) return -1; + if (pmd_huge(*pmd_k)) + return 0; + pte_k = pte_offset_kernel(pmd_k, address); if (!pte_present(*pte_k)) return -1; @@ -360,8 +363,6 @@ void vmalloc_sync_all(void) * 64-bit: * * Handle a fault on the vmalloc area - * - * This assumes no large pages in there. */ static noinline int vmalloc_fault(unsigned long address) { @@ -403,17 +404,23 @@ static noinline int vmalloc_fault(unsigned long address) if (pud_none(*pud_ref)) return -1; - if (pud_none(*pud) || pud_page_vaddr(*pud) != pud_page_vaddr(*pud_ref)) + if (pud_none(*pud) || pud_pfn(*pud) != pud_pfn(*pud_ref)) BUG(); + if (pud_huge(*pud)) + return 0; + pmd = pmd_offset(pud, address); pmd_ref = pmd_offset(pud_ref, address); if (pmd_none(*pmd_ref)) return -1; - if (pmd_none(*pmd) || pmd_page(*pmd) != pmd_page(*pmd_ref)) + if (pmd_none(*pmd) || pmd_pfn(*pmd) != pmd_pfn(*pmd_ref)) BUG(); + if (pmd_huge(*pmd)) + return 0; + pte_ref = pte_offset_kernel(pmd_ref, address); if (!pte_present(*pte_ref)) return -1; diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c index 637ab34ed632..ddb2244b06a1 100644 --- a/arch/x86/mm/kmmio.c +++ b/arch/x86/mm/kmmio.c @@ -33,7 +33,7 @@ struct kmmio_fault_page { struct list_head list; struct kmmio_fault_page *release_next; - unsigned long page; /* location of the fault page */ + unsigned long addr; /* the requested address */ pteval_t old_presence; /* page presence prior to arming */ bool armed; @@ -70,9 +70,16 @@ unsigned int kmmio_count; static struct list_head kmmio_page_table[KMMIO_PAGE_TABLE_SIZE]; static LIST_HEAD(kmmio_probes); -static struct list_head *kmmio_page_list(unsigned long page) +static struct list_head *kmmio_page_list(unsigned long addr) { - return &kmmio_page_table[hash_long(page, KMMIO_PAGE_HASH_BITS)]; + unsigned int l; + pte_t *pte = lookup_address(addr, &l); + + if (!pte) + return NULL; + addr &= page_level_mask(l); + + return &kmmio_page_table[hash_long(addr, KMMIO_PAGE_HASH_BITS)]; } /* Accessed per-cpu */ @@ -98,15 +105,19 @@ static struct kmmio_probe *get_kmmio_probe(unsigned long addr) } /* You must be holding RCU read lock. */ -static struct kmmio_fault_page *get_kmmio_fault_page(unsigned long page) +static struct kmmio_fault_page *get_kmmio_fault_page(unsigned long addr) { struct list_head *head; struct kmmio_fault_page *f; + unsigned int l; + pte_t *pte = lookup_address(addr, &l); - page &= PAGE_MASK; - head = kmmio_page_list(page); + if (!pte) + return NULL; + addr &= page_level_mask(l); + head = kmmio_page_list(addr); list_for_each_entry_rcu(f, head, list) { - if (f->page == page) + if (f->addr == addr) return f; } return NULL; @@ -137,10 +148,10 @@ static void clear_pte_presence(pte_t *pte, bool clear, pteval_t *old) static int clear_page_presence(struct kmmio_fault_page *f, bool clear) { unsigned int level; - pte_t *pte = lookup_address(f->page, &level); + pte_t *pte = lookup_address(f->addr, &level); if (!pte) { - pr_err("no pte for page 0x%08lx\n", f->page); + pr_err("no pte for addr 0x%08lx\n", f->addr); return -1; } @@ -156,7 +167,7 @@ static int clear_page_presence(struct kmmio_fault_page *f, bool clear) return -1; } - __flush_tlb_one(f->page); + __flush_tlb_one(f->addr); return 0; } @@ -176,12 +187,12 @@ static int arm_kmmio_fault_page(struct kmmio_fault_page *f) int ret; WARN_ONCE(f->armed, KERN_ERR pr_fmt("kmmio page already armed.\n")); if (f->armed) { - pr_warning("double-arm: page 0x%08lx, ref %d, old %d\n", - f->page, f->count, !!f->old_presence); + pr_warning("double-arm: addr 0x%08lx, ref %d, old %d\n", + f->addr, f->count, !!f->old_presence); } ret = clear_page_presence(f, true); - WARN_ONCE(ret < 0, KERN_ERR pr_fmt("arming 0x%08lx failed.\n"), - f->page); + WARN_ONCE(ret < 0, KERN_ERR pr_fmt("arming at 0x%08lx failed.\n"), + f->addr); f->armed = true; return ret; } @@ -191,7 +202,7 @@ static void disarm_kmmio_fault_page(struct kmmio_fault_page *f) { int ret = clear_page_presence(f, false); WARN_ONCE(ret < 0, - KERN_ERR "kmmio disarming 0x%08lx failed.\n", f->page); + KERN_ERR "kmmio disarming at 0x%08lx failed.\n", f->addr); f->armed = false; } @@ -215,6 +226,12 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr) struct kmmio_context *ctx; struct kmmio_fault_page *faultpage; int ret = 0; /* default to fault not handled */ + unsigned long page_base = addr; + unsigned int l; + pte_t *pte = lookup_address(addr, &l); + if (!pte) + return -EINVAL; + page_base &= page_level_mask(l); /* * Preemption is now disabled to prevent process switch during @@ -227,7 +244,7 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr) preempt_disable(); rcu_read_lock(); - faultpage = get_kmmio_fault_page(addr); + faultpage = get_kmmio_fault_page(page_base); if (!faultpage) { /* * Either this page fault is not caused by kmmio, or @@ -239,7 +256,7 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr) ctx = &get_cpu_var(kmmio_ctx); if (ctx->active) { - if (addr == ctx->addr) { + if (page_base == ctx->addr) { /* * A second fault on the same page means some other * condition needs handling by do_page_fault(), the @@ -267,9 +284,9 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr) ctx->active++; ctx->fpage = faultpage; - ctx->probe = get_kmmio_probe(addr); + ctx->probe = get_kmmio_probe(page_base); ctx->saved_flags = (regs->flags & (X86_EFLAGS_TF | X86_EFLAGS_IF)); - ctx->addr = addr; + ctx->addr = page_base; if (ctx->probe && ctx->probe->pre_handler) ctx->probe->pre_handler(ctx->probe, regs, addr); @@ -354,12 +371,11 @@ out: } /* You must be holding kmmio_lock. */ -static int add_kmmio_fault_page(unsigned long page) +static int add_kmmio_fault_page(unsigned long addr) { struct kmmio_fault_page *f; - page &= PAGE_MASK; - f = get_kmmio_fault_page(page); + f = get_kmmio_fault_page(addr); if (f) { if (!f->count) arm_kmmio_fault_page(f); @@ -372,26 +388,25 @@ static int add_kmmio_fault_page(unsigned long page) return -1; f->count = 1; - f->page = page; + f->addr = addr; if (arm_kmmio_fault_page(f)) { kfree(f); return -1; } - list_add_rcu(&f->list, kmmio_page_list(f->page)); + list_add_rcu(&f->list, kmmio_page_list(f->addr)); return 0; } /* You must be holding kmmio_lock. */ -static void release_kmmio_fault_page(unsigned long page, +static void release_kmmio_fault_page(unsigned long addr, struct kmmio_fault_page **release_list) { struct kmmio_fault_page *f; - page &= PAGE_MASK; - f = get_kmmio_fault_page(page); + f = get_kmmio_fault_page(addr); if (!f) return; @@ -420,18 +435,27 @@ int register_kmmio_probe(struct kmmio_probe *p) int ret = 0; unsigned long size = 0; const unsigned long size_lim = p->len + (p->addr & ~PAGE_MASK); + unsigned int l; + pte_t *pte; spin_lock_irqsave(&kmmio_lock, flags); if (get_kmmio_probe(p->addr)) { ret = -EEXIST; goto out; } + + pte = lookup_address(p->addr, &l); + if (!pte) { + ret = -EINVAL; + goto out; + } + kmmio_count++; list_add_rcu(&p->list, &kmmio_probes); while (size < size_lim) { if (add_kmmio_fault_page(p->addr + size)) pr_err("Unable to set page fault.\n"); - size += PAGE_SIZE; + size += page_level_size(l); } out: spin_unlock_irqrestore(&kmmio_lock, flags); @@ -506,11 +530,17 @@ void unregister_kmmio_probe(struct kmmio_probe *p) const unsigned long size_lim = p->len + (p->addr & ~PAGE_MASK); struct kmmio_fault_page *release_list = NULL; struct kmmio_delayed_release *drelease; + unsigned int l; + pte_t *pte; + + pte = lookup_address(p->addr, &l); + if (!pte) + return; spin_lock_irqsave(&kmmio_lock, flags); while (size < size_lim) { release_kmmio_fault_page(p->addr + size, &release_list); - size += PAGE_SIZE; + size += page_level_size(l); } list_del_rcu(&p->list); kmmio_count--; diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c index b2fd67da1701..ef05755a1900 100644 --- a/arch/x86/mm/mpx.c +++ b/arch/x86/mm/mpx.c @@ -123,7 +123,7 @@ static int get_reg_offset(struct insn *insn, struct pt_regs *regs, break; } - if (regno > nr_registers) { + if (regno >= nr_registers) { WARN_ONCE(1, "decoded an instruction with an invalid register"); return -EINVAL; } diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index a3137a4feed1..b599a780a5a9 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -33,7 +33,7 @@ struct cpa_data { pgd_t *pgd; pgprot_t mask_set; pgprot_t mask_clr; - int numpages; + unsigned long numpages; int flags; unsigned long pfn; unsigned force_split : 1; @@ -414,24 +414,30 @@ pmd_t *lookup_pmd_address(unsigned long address) phys_addr_t slow_virt_to_phys(void *__virt_addr) { unsigned long virt_addr = (unsigned long)__virt_addr; - unsigned long phys_addr, offset; + phys_addr_t phys_addr; + unsigned long offset; enum pg_level level; pte_t *pte; pte = lookup_address(virt_addr, &level); BUG_ON(!pte); + /* + * pXX_pfn() returns unsigned long, which must be cast to phys_addr_t + * before being left-shifted PAGE_SHIFT bits -- this trick is to + * make 32-PAE kernel work correctly. + */ switch (level) { case PG_LEVEL_1G: - phys_addr = pud_pfn(*(pud_t *)pte) << PAGE_SHIFT; + phys_addr = (phys_addr_t)pud_pfn(*(pud_t *)pte) << PAGE_SHIFT; offset = virt_addr & ~PUD_PAGE_MASK; break; case PG_LEVEL_2M: - phys_addr = pmd_pfn(*(pmd_t *)pte) << PAGE_SHIFT; + phys_addr = (phys_addr_t)pmd_pfn(*(pmd_t *)pte) << PAGE_SHIFT; offset = virt_addr & ~PMD_PAGE_MASK; break; default: - phys_addr = pte_pfn(*pte) << PAGE_SHIFT; + phys_addr = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT; offset = virt_addr & ~PAGE_MASK; } @@ -1345,7 +1351,7 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias) * CPA operation. Either a large page has been * preserved or a single page update happened. */ - BUG_ON(cpa->numpages > numpages); + BUG_ON(cpa->numpages > numpages || !cpa->numpages); numpages -= cpa->numpages; if (cpa->flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) cpa->curpage++; diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 8ddb5d0d66fb..5fb6adaaa796 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -106,8 +106,6 @@ static void flush_tlb_func(void *info) if (f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm)) return; - if (!f->flush_end) - f->flush_end = f->flush_start + PAGE_SIZE; count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) { @@ -135,12 +133,20 @@ void native_flush_tlb_others(const struct cpumask *cpumask, unsigned long end) { struct flush_tlb_info info; + + if (end == 0) + end = start + PAGE_SIZE; info.flush_mm = mm; info.flush_start = start; info.flush_end = end; count_vm_tlb_event(NR_TLB_REMOTE_FLUSH); - trace_tlb_flush(TLB_REMOTE_SEND_IPI, end - start); + if (end == TLB_FLUSH_ALL) + trace_tlb_flush(TLB_REMOTE_SEND_IPI, TLB_FLUSH_ALL); + else + trace_tlb_flush(TLB_REMOTE_SEND_IPI, + (end - start) >> PAGE_SHIFT); + if (is_uv_system()) { unsigned int cpu; @@ -161,7 +167,10 @@ void flush_tlb_current_task(void) preempt_disable(); count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); + + /* This is an implicit full barrier that synchronizes with switch_mm. */ local_flush_tlb(); + trace_tlb_flush(TLB_LOCAL_SHOOTDOWN, TLB_FLUSH_ALL); if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL); @@ -188,17 +197,29 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, unsigned long base_pages_to_flush = TLB_FLUSH_ALL; preempt_disable(); - if (current->active_mm != mm) + if (current->active_mm != mm) { + /* Synchronize with switch_mm. */ + smp_mb(); + goto out; + } if (!current->mm) { leave_mm(smp_processor_id()); + + /* Synchronize with switch_mm. */ + smp_mb(); + goto out; } if ((end != TLB_FLUSH_ALL) && !(vmflag & VM_HUGETLB)) base_pages_to_flush = (end - start) >> PAGE_SHIFT; + /* + * Both branches below are implicit full barriers (MOV to CR or + * INVLPG) that synchronize with switch_mm. + */ if (base_pages_to_flush > tlb_single_page_flush_ceiling) { base_pages_to_flush = TLB_FLUSH_ALL; count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); @@ -228,10 +249,18 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long start) preempt_disable(); if (current->active_mm == mm) { - if (current->mm) + if (current->mm) { + /* + * Implicit full barrier (INVLPG) that synchronizes + * with switch_mm. + */ __flush_tlb_one(start); - else + } else { leave_mm(smp_processor_id()); + + /* Synchronize with switch_mm. */ + smp_mb(); + } } if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index eccd4d99e6a4..8fd6f44aee83 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -673,28 +673,22 @@ int pcibios_add_device(struct pci_dev *dev) return 0; } -int pcibios_alloc_irq(struct pci_dev *dev) -{ - /* - * If the PCI device was already claimed by core code and has - * MSI enabled, probing of the pcibios IRQ will overwrite - * dev->irq. So bail out if MSI is already enabled. - */ - if (pci_dev_msi_enabled(dev)) - return -EBUSY; - - return pcibios_enable_irq(dev); -} - -void pcibios_free_irq(struct pci_dev *dev) -{ - if (pcibios_disable_irq) - pcibios_disable_irq(dev); -} - int pcibios_enable_device(struct pci_dev *dev, int mask) { - return pci_enable_resources(dev, mask); + int err; + + if ((err = pci_enable_resources(dev, mask)) < 0) + return err; + + if (!pci_dev_msi_enabled(dev)) + return pcibios_enable_irq(dev); + return 0; +} + +void pcibios_disable_device (struct pci_dev *dev) +{ + if (!pci_dev_msi_enabled(dev) && pcibios_disable_irq) + pcibios_disable_irq(dev); } int pci_ext_cfg_avail(void) diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index e58565556703..0ae7e9fa348d 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -540,3 +540,10 @@ static void twinhead_reserve_killing_zone(struct pci_dev *dev) } } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x27B9, twinhead_reserve_killing_zone); + +static void pci_bdwep_bar(struct pci_dev *dev) +{ + dev->non_compliant_bars = 1; +} +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fa0, pci_bdwep_bar); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, pci_bdwep_bar); diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c index 0d24e7c10145..8b93e634af84 100644 --- a/arch/x86/pci/intel_mid_pci.c +++ b/arch/x86/pci/intel_mid_pci.c @@ -215,7 +215,7 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev) int polarity; int ret; - if (pci_has_managed_irq(dev)) + if (dev->irq_managed && dev->irq > 0) return 0; switch (intel_mid_identify_cpu()) { @@ -256,13 +256,10 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev) static void intel_mid_pci_irq_disable(struct pci_dev *dev) { - if (pci_has_managed_irq(dev)) { + if (!mp_should_keep_irq(&dev->dev) && dev->irq_managed && + dev->irq > 0) { mp_unmap_irq(dev->irq); dev->irq_managed = 0; - /* - * Don't reset dev->irq here, otherwise - * intel_mid_pci_irq_enable() will fail on next call. - */ } } diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index 32e70343e6fd..9bd115484745 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -1202,7 +1202,7 @@ static int pirq_enable_irq(struct pci_dev *dev) struct pci_dev *temp_dev; int irq; - if (pci_has_managed_irq(dev)) + if (dev->irq_managed && dev->irq > 0) return 0; irq = IO_APIC_get_PCI_irq_vector(dev->bus->number, @@ -1230,7 +1230,8 @@ static int pirq_enable_irq(struct pci_dev *dev) } dev = temp_dev; if (irq >= 0) { - pci_set_managed_irq(dev, irq); + dev->irq_managed = 1; + dev->irq = irq; dev_info(&dev->dev, "PCI->APIC IRQ transform: " "INT %c -> IRQ %d\n", 'A' + pin - 1, irq); return 0; @@ -1256,10 +1257,24 @@ static int pirq_enable_irq(struct pci_dev *dev) return 0; } +bool mp_should_keep_irq(struct device *dev) +{ + if (dev->power.is_prepared) + return true; +#ifdef CONFIG_PM + if (dev->power.runtime_status == RPM_SUSPENDING) + return true; +#endif + + return false; +} + static void pirq_disable_irq(struct pci_dev *dev) { - if (io_apic_assign_pci_irqs && pci_has_managed_irq(dev)) { + if (io_apic_assign_pci_irqs && !mp_should_keep_irq(&dev->dev) && + dev->irq_managed && dev->irq) { mp_unmap_irq(dev->irq); - pci_reset_managed_irq(dev); + dev->irq = 0; + dev->irq_managed = 0; } } diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index ff31ab464213..c6d6efed392a 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -488,8 +488,11 @@ int __init pci_xen_initial_domain(void) #endif __acpi_register_gsi = acpi_register_gsi_xen; __acpi_unregister_gsi = NULL; - /* Pre-allocate legacy irqs */ - for (irq = 0; irq < nr_legacy_irqs(); irq++) { + /* + * Pre-allocate the legacy IRQs. Use NR_LEGACY_IRQS here + * because we don't have a PIC and thus nr_legacy_irqs() is zero. + */ + for (irq = 0; irq < NR_IRQS_LEGACY; irq++) { int trigger, polarity; if (acpi_get_override_irq(irq, &trigger, &polarity) == -1) diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index b7de78bdc09c..beab8c706ac9 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -961,7 +961,7 @@ static void xen_load_sp0(struct tss_struct *tss, tss->x86_tss.sp0 = thread->sp0; } -static void xen_set_iopl_mask(unsigned mask) +void xen_set_iopl_mask(unsigned mask) { struct physdev_set_iopl set_iopl; diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 7ab29518a3b9..e345891450c3 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -393,6 +393,9 @@ static unsigned long __init xen_set_identity_and_remap_chunk( unsigned long i = 0; unsigned long n = end_pfn - start_pfn; + if (remap_pfn == 0) + remap_pfn = nr_pages; + while (i < n) { unsigned long cur_pfn = start_pfn + i; unsigned long left = n - i; @@ -438,17 +441,29 @@ static unsigned long __init xen_set_identity_and_remap_chunk( return remap_pfn; } -static void __init xen_set_identity_and_remap(unsigned long nr_pages) +static unsigned long __init xen_count_remap_pages( + unsigned long start_pfn, unsigned long end_pfn, unsigned long nr_pages, + unsigned long remap_pages) +{ + if (start_pfn >= nr_pages) + return remap_pages; + + return remap_pages + min(end_pfn, nr_pages) - start_pfn; +} + +static unsigned long __init xen_foreach_remap_area(unsigned long nr_pages, + unsigned long (*func)(unsigned long start_pfn, unsigned long end_pfn, + unsigned long nr_pages, unsigned long last_val)) { phys_addr_t start = 0; - unsigned long last_pfn = nr_pages; + unsigned long ret_val = 0; const struct e820entry *entry = xen_e820_map; int i; /* * Combine non-RAM regions and gaps until a RAM region (or the - * end of the map) is reached, then set the 1:1 map and - * remap the memory in those non-RAM regions. + * end of the map) is reached, then call the provided function + * to perform its duty on the non-RAM region. * * The combined non-RAM regions are rounded to a whole number * of pages so any partial pages are accessible via the 1:1 @@ -466,14 +481,13 @@ static void __init xen_set_identity_and_remap(unsigned long nr_pages) end_pfn = PFN_UP(entry->addr); if (start_pfn < end_pfn) - last_pfn = xen_set_identity_and_remap_chunk( - start_pfn, end_pfn, nr_pages, - last_pfn); + ret_val = func(start_pfn, end_pfn, nr_pages, + ret_val); start = end; } } - pr_info("Released %ld page(s)\n", xen_released_pages); + return ret_val; } /* @@ -596,35 +610,6 @@ static void __init xen_ignore_unusable(void) } } -static unsigned long __init xen_count_remap_pages(unsigned long max_pfn) -{ - unsigned long extra = 0; - unsigned long start_pfn, end_pfn; - const struct e820entry *entry = xen_e820_map; - int i; - - end_pfn = 0; - for (i = 0; i < xen_e820_map_entries; i++, entry++) { - start_pfn = PFN_DOWN(entry->addr); - /* Adjacent regions on non-page boundaries handling! */ - end_pfn = min(end_pfn, start_pfn); - - if (start_pfn >= max_pfn) - return extra + max_pfn - end_pfn; - - /* Add any holes in map to result. */ - extra += start_pfn - end_pfn; - - end_pfn = PFN_UP(entry->addr + entry->size); - end_pfn = min(end_pfn, max_pfn); - - if (entry->type != E820_RAM) - extra += end_pfn - start_pfn; - } - - return extra; -} - bool __init xen_is_e820_reserved(phys_addr_t start, phys_addr_t size) { struct e820entry *entry; @@ -804,7 +789,7 @@ char * __init xen_memory_setup(void) max_pages = xen_get_max_pages(); /* How many extra pages do we need due to remapping? */ - max_pages += xen_count_remap_pages(max_pfn); + max_pages += xen_foreach_remap_area(max_pfn, xen_count_remap_pages); if (max_pages > max_pfn) extra_pages += max_pages - max_pfn; @@ -922,7 +907,9 @@ char * __init xen_memory_setup(void) * Set identity map on non-RAM pages and prepare remapping the * underlying RAM. */ - xen_set_identity_and_remap(max_pfn); + xen_foreach_remap_area(max_pfn, xen_set_identity_and_remap_chunk); + + pr_info("Released %ld page(s)\n", xen_released_pages); return "Xen"; } diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index df0c40559583..7f664c416faf 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -34,7 +34,8 @@ static void xen_hvm_post_suspend(int suspend_cancelled) { #ifdef CONFIG_XEN_PVHVM int cpu; - xen_hvm_init_shared_info(); + if (!suspend_cancelled) + xen_hvm_init_shared_info(); xen_callback_vector(); xen_unplug_emulated_devices(); if (xen_feature(XENFEAT_hvm_safe_pvclock)) { diff --git a/arch/xtensa/kernel/head.S b/arch/xtensa/kernel/head.S index 9ed55649ac8e..05e1df943856 100644 --- a/arch/xtensa/kernel/head.S +++ b/arch/xtensa/kernel/head.S @@ -128,7 +128,7 @@ ENTRY(_startup) wsr a0, icountlevel .set _index, 0 - .rept XCHAL_NUM_DBREAK - 1 + .rept XCHAL_NUM_DBREAK wsr a0, SREG_DBREAKC + _index .set _index, _index + 1 .endr diff --git a/arch/xtensa/mm/cache.c b/arch/xtensa/mm/cache.c index d75aa1476da7..1a804a2f9a5b 100644 --- a/arch/xtensa/mm/cache.c +++ b/arch/xtensa/mm/cache.c @@ -97,11 +97,11 @@ void clear_user_highpage(struct page *page, unsigned long vaddr) unsigned long paddr; void *kvaddr = coherent_kvaddr(page, TLBTEMP_BASE_1, vaddr, &paddr); - pagefault_disable(); + preempt_disable(); kmap_invalidate_coherent(page, vaddr); set_bit(PG_arch_1, &page->flags); clear_page_alias(kvaddr, paddr); - pagefault_enable(); + preempt_enable(); } void copy_user_highpage(struct page *dst, struct page *src, @@ -113,11 +113,11 @@ void copy_user_highpage(struct page *dst, struct page *src, void *src_vaddr = coherent_kvaddr(src, TLBTEMP_BASE_2, vaddr, &src_paddr); - pagefault_disable(); + preempt_disable(); kmap_invalidate_coherent(dst, vaddr); set_bit(PG_arch_1, &dst->flags); copy_page_alias(dst_vaddr, src_vaddr, dst_paddr, src_paddr); - pagefault_enable(); + preempt_enable(); } #endif /* DCACHE_WAY_SIZE > PAGE_SIZE */ diff --git a/arch/xtensa/platforms/iss/console.c b/arch/xtensa/platforms/iss/console.c index 70cb408bc20d..92d785fefb6d 100644 --- a/arch/xtensa/platforms/iss/console.c +++ b/arch/xtensa/platforms/iss/console.c @@ -100,21 +100,23 @@ static void rs_poll(unsigned long priv) { struct tty_port *port = (struct tty_port *)priv; int i = 0; + int rd = 1; unsigned char c; spin_lock(&timer_lock); while (simc_poll(0)) { - simc_read(0, &c, 1); + rd = simc_read(0, &c, 1); + if (rd <= 0) + break; tty_insert_flip_char(port, c, TTY_NORMAL); i++; } if (i) tty_flip_buffer_push(port); - - - mod_timer(&serial_timer, jiffies + SERIAL_TIMER_VALUE); + if (rd) + mod_timer(&serial_timer, jiffies + SERIAL_TIMER_VALUE); spin_unlock(&timer_lock); } diff --git a/block/bio.c b/block/bio.c index 4f184d938942..d4d144363250 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1090,9 +1090,12 @@ int bio_uncopy_user(struct bio *bio) if (!bio_flagged(bio, BIO_NULL_MAPPED)) { /* * if we're in a workqueue, the request is orphaned, so - * don't copy into a random user address space, just free. + * don't copy into a random user address space, just free + * and return -EINTR so user space doesn't expect any data. */ - if (current->mm && bio_data_dir(bio) == READ) + if (!current->mm) + ret = -EINTR; + else if (bio_data_dir(bio) == READ) ret = bio_copy_to_iter(bio, bmd->iter); if (bmd->is_our_pages) bio_free_pages(bio); diff --git a/block/blk-core.c b/block/blk-core.c index 33e2f62d5062..f8e64cac981a 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -2189,7 +2189,7 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq) if (q->mq_ops) { if (blk_queue_io_stat(q)) blk_account_io_start(rq, true); - blk_mq_insert_request(rq, false, true, true); + blk_mq_insert_request(rq, false, true, false); return 0; } diff --git a/block/blk-merge.c b/block/blk-merge.c index e01405a3e8b3..b966db8f3556 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -68,6 +68,18 @@ static struct bio *blk_bio_write_same_split(struct request_queue *q, return bio_split(bio, q->limits.max_write_same_sectors, GFP_NOIO, bs); } +static inline unsigned get_max_io_size(struct request_queue *q, + struct bio *bio) +{ + unsigned sectors = blk_max_size_offset(q, bio->bi_iter.bi_sector); + unsigned mask = queue_logical_block_size(q) - 1; + + /* aligned to logical block size */ + sectors &= ~(mask >> 9); + + return sectors; +} + static struct bio *blk_bio_segment_split(struct request_queue *q, struct bio *bio, struct bio_set *bs, @@ -79,11 +91,9 @@ static struct bio *blk_bio_segment_split(struct request_queue *q, unsigned front_seg_size = bio->bi_seg_front_size; bool do_split = true; struct bio *new = NULL; + const unsigned max_sectors = get_max_io_size(q, bio); bio_for_each_segment(bv, bio, iter) { - if (sectors + (bv.bv_len >> 9) > queue_max_sectors(q)) - goto split; - /* * If the queue doesn't support SG gaps and adding this * offset would create a gap, disallow it. @@ -91,6 +101,21 @@ static struct bio *blk_bio_segment_split(struct request_queue *q, if (bvprvp && bvec_gap_to_prev(q, bvprvp, bv.bv_offset)) goto split; + if (sectors + (bv.bv_len >> 9) > max_sectors) { + /* + * Consider this a new segment if we're splitting in + * the middle of this vector. + */ + if (nsegs < queue_max_segments(q) && + sectors < max_sectors) { + nsegs++; + sectors = max_sectors; + } + if (sectors) + goto split; + /* Make this single bvec as the 1st segment */ + } + if (bvprvp && blk_queue_cluster(q)) { if (seg_size + bv.bv_len > queue_max_segment_size(q)) goto new_segment; diff --git a/block/blk-settings.c b/block/blk-settings.c index dd4973583978..c7bb666aafd1 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -91,8 +91,8 @@ void blk_set_default_limits(struct queue_limits *lim) lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK; lim->virt_boundary_mask = 0; lim->max_segment_size = BLK_MAX_SEGMENT_SIZE; - lim->max_sectors = lim->max_dev_sectors = lim->max_hw_sectors = - BLK_SAFE_MAX_SECTORS; + lim->max_sectors = lim->max_hw_sectors = BLK_SAFE_MAX_SECTORS; + lim->max_dev_sectors = 0; lim->chunk_sectors = 0; lim->max_write_same_sectors = 0; lim->max_discard_sectors = 0; diff --git a/block/partition-generic.c b/block/partition-generic.c index ae95e963c5bb..91327dbfbb1d 100644 --- a/block/partition-generic.c +++ b/block/partition-generic.c @@ -360,15 +360,20 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno, goto out_del; } + err = hd_ref_init(p); + if (err) { + if (flags & ADDPART_FLAG_WHOLEDISK) + goto out_remove_file; + goto out_del; + } + /* everything is up and running, commence */ rcu_assign_pointer(ptbl->part[partno], p); /* suppress uevent if the disk suppresses it */ if (!dev_get_uevent_suppress(ddev)) kobject_uevent(&pdev->kobj, KOBJ_ADD); - - if (!hd_ref_init(p)) - return p; + return p; out_free_info: free_part_info(p); @@ -377,6 +382,8 @@ out_free_stats: out_free: kfree(p); return ERR_PTR(err); +out_remove_file: + device_remove_file(pdev, &dev_attr_whole_disk); out_del: kobject_put(p->holder_dir); device_del(pdev); diff --git a/crypto/af_alg.c b/crypto/af_alg.c index a8e7aa3e257b..f5e18c2a4852 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -76,6 +76,8 @@ int af_alg_register_type(const struct af_alg_type *type) goto unlock; type->ops->owner = THIS_MODULE; + if (type->ops_nokey) + type->ops_nokey->owner = THIS_MODULE; node->type = type; list_add(&node->list, &alg_types); err = 0; @@ -125,6 +127,26 @@ int af_alg_release(struct socket *sock) } EXPORT_SYMBOL_GPL(af_alg_release); +void af_alg_release_parent(struct sock *sk) +{ + struct alg_sock *ask = alg_sk(sk); + unsigned int nokey = ask->nokey_refcnt; + bool last = nokey && !ask->refcnt; + + sk = ask->parent; + ask = alg_sk(sk); + + lock_sock(sk); + ask->nokey_refcnt -= nokey; + if (!last) + last = !--ask->refcnt; + release_sock(sk); + + if (last) + sock_put(sk); +} +EXPORT_SYMBOL_GPL(af_alg_release_parent); + static int alg_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { const u32 forbidden = CRYPTO_ALG_INTERNAL; @@ -133,6 +155,7 @@ static int alg_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) struct sockaddr_alg *sa = (void *)uaddr; const struct af_alg_type *type; void *private; + int err; if (sock->state == SS_CONNECTED) return -EINVAL; @@ -160,16 +183,22 @@ static int alg_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) return PTR_ERR(private); } + err = -EBUSY; lock_sock(sk); + if (ask->refcnt | ask->nokey_refcnt) + goto unlock; swap(ask->type, type); swap(ask->private, private); + err = 0; + +unlock: release_sock(sk); alg_do_release(type, private); - return 0; + return err; } static int alg_setkey(struct sock *sk, char __user *ukey, @@ -202,11 +231,15 @@ static int alg_setsockopt(struct socket *sock, int level, int optname, struct sock *sk = sock->sk; struct alg_sock *ask = alg_sk(sk); const struct af_alg_type *type; - int err = -ENOPROTOOPT; + int err = -EBUSY; lock_sock(sk); + if (ask->refcnt) + goto unlock; + type = ask->type; + err = -ENOPROTOOPT; if (level != SOL_ALG || !type) goto unlock; @@ -238,6 +271,7 @@ int af_alg_accept(struct sock *sk, struct socket *newsock) struct alg_sock *ask = alg_sk(sk); const struct af_alg_type *type; struct sock *sk2; + unsigned int nokey; int err; lock_sock(sk); @@ -257,20 +291,29 @@ int af_alg_accept(struct sock *sk, struct socket *newsock) security_sk_clone(sk, sk2); err = type->accept(ask->private, sk2); - if (err) { - sk_free(sk2); + + nokey = err == -ENOKEY; + if (nokey && type->accept_nokey) + err = type->accept_nokey(ask->private, sk2); + + if (err) goto unlock; - } sk2->sk_family = PF_ALG; - sock_hold(sk); + if (nokey || !ask->refcnt++) + sock_hold(sk); + ask->nokey_refcnt += nokey; alg_sk(sk2)->parent = sk; alg_sk(sk2)->type = type; + alg_sk(sk2)->nokey_refcnt = nokey; newsock->ops = type->ops; newsock->state = SS_CONNECTED; + if (nokey) + newsock->ops = type->ops_nokey; + err = 0; unlock: diff --git a/crypto/ahash.c b/crypto/ahash.c index 9c1dc8d6106a..dac1c24e9c3e 100644 --- a/crypto/ahash.c +++ b/crypto/ahash.c @@ -69,8 +69,9 @@ static int hash_walk_new_entry(struct crypto_hash_walk *walk) struct scatterlist *sg; sg = walk->sg; - walk->pg = sg_page(sg); walk->offset = sg->offset; + walk->pg = sg_page(walk->sg) + (walk->offset >> PAGE_SHIFT); + walk->offset = offset_in_page(walk->offset); walk->entrylen = sg->length; if (walk->entrylen > walk->total) @@ -451,6 +452,7 @@ static int crypto_ahash_init_tfm(struct crypto_tfm *tfm) struct ahash_alg *alg = crypto_ahash_alg(hash); hash->setkey = ahash_nosetkey; + hash->has_setkey = false; hash->export = ahash_no_export; hash->import = ahash_no_import; @@ -463,8 +465,10 @@ static int crypto_ahash_init_tfm(struct crypto_tfm *tfm) hash->finup = alg->finup ?: ahash_def_finup; hash->digest = alg->digest; - if (alg->setkey) + if (alg->setkey) { hash->setkey = alg->setkey; + hash->has_setkey = true; + } if (alg->export) hash->export = alg->export; if (alg->import) diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c index b4c24fe3dcfb..68a5ceaa04c8 100644 --- a/crypto/algif_hash.c +++ b/crypto/algif_hash.c @@ -34,6 +34,11 @@ struct hash_ctx { struct ahash_request req; }; +struct algif_hash_tfm { + struct crypto_ahash *hash; + bool has_key; +}; + static int hash_sendmsg(struct socket *sock, struct msghdr *msg, size_t ignored) { @@ -49,7 +54,8 @@ static int hash_sendmsg(struct socket *sock, struct msghdr *msg, lock_sock(sk); if (!ctx->more) { - err = crypto_ahash_init(&ctx->req); + err = af_alg_wait_for_completion(crypto_ahash_init(&ctx->req), + &ctx->completion); if (err) goto unlock; } @@ -120,6 +126,7 @@ static ssize_t hash_sendpage(struct socket *sock, struct page *page, } else { if (!ctx->more) { err = crypto_ahash_init(&ctx->req); + err = af_alg_wait_for_completion(err, &ctx->completion); if (err) goto unlock; } @@ -235,19 +242,151 @@ static struct proto_ops algif_hash_ops = { .accept = hash_accept, }; +static int hash_check_key(struct socket *sock) +{ + int err = 0; + struct sock *psk; + struct alg_sock *pask; + struct algif_hash_tfm *tfm; + struct sock *sk = sock->sk; + struct alg_sock *ask = alg_sk(sk); + + lock_sock(sk); + if (ask->refcnt) + goto unlock_child; + + psk = ask->parent; + pask = alg_sk(ask->parent); + tfm = pask->private; + + err = -ENOKEY; + lock_sock_nested(psk, SINGLE_DEPTH_NESTING); + if (!tfm->has_key) + goto unlock; + + if (!pask->refcnt++) + sock_hold(psk); + + ask->refcnt = 1; + sock_put(psk); + + err = 0; + +unlock: + release_sock(psk); +unlock_child: + release_sock(sk); + + return err; +} + +static int hash_sendmsg_nokey(struct socket *sock, struct msghdr *msg, + size_t size) +{ + int err; + + err = hash_check_key(sock); + if (err) + return err; + + return hash_sendmsg(sock, msg, size); +} + +static ssize_t hash_sendpage_nokey(struct socket *sock, struct page *page, + int offset, size_t size, int flags) +{ + int err; + + err = hash_check_key(sock); + if (err) + return err; + + return hash_sendpage(sock, page, offset, size, flags); +} + +static int hash_recvmsg_nokey(struct socket *sock, struct msghdr *msg, + size_t ignored, int flags) +{ + int err; + + err = hash_check_key(sock); + if (err) + return err; + + return hash_recvmsg(sock, msg, ignored, flags); +} + +static int hash_accept_nokey(struct socket *sock, struct socket *newsock, + int flags) +{ + int err; + + err = hash_check_key(sock); + if (err) + return err; + + return hash_accept(sock, newsock, flags); +} + +static struct proto_ops algif_hash_ops_nokey = { + .family = PF_ALG, + + .connect = sock_no_connect, + .socketpair = sock_no_socketpair, + .getname = sock_no_getname, + .ioctl = sock_no_ioctl, + .listen = sock_no_listen, + .shutdown = sock_no_shutdown, + .getsockopt = sock_no_getsockopt, + .mmap = sock_no_mmap, + .bind = sock_no_bind, + .setsockopt = sock_no_setsockopt, + .poll = sock_no_poll, + + .release = af_alg_release, + .sendmsg = hash_sendmsg_nokey, + .sendpage = hash_sendpage_nokey, + .recvmsg = hash_recvmsg_nokey, + .accept = hash_accept_nokey, +}; + static void *hash_bind(const char *name, u32 type, u32 mask) { - return crypto_alloc_ahash(name, type, mask); + struct algif_hash_tfm *tfm; + struct crypto_ahash *hash; + + tfm = kzalloc(sizeof(*tfm), GFP_KERNEL); + if (!tfm) + return ERR_PTR(-ENOMEM); + + hash = crypto_alloc_ahash(name, type, mask); + if (IS_ERR(hash)) { + kfree(tfm); + return ERR_CAST(hash); + } + + tfm->hash = hash; + + return tfm; } static void hash_release(void *private) { - crypto_free_ahash(private); + struct algif_hash_tfm *tfm = private; + + crypto_free_ahash(tfm->hash); + kfree(tfm); } static int hash_setkey(void *private, const u8 *key, unsigned int keylen) { - return crypto_ahash_setkey(private, key, keylen); + struct algif_hash_tfm *tfm = private; + int err; + + err = crypto_ahash_setkey(tfm->hash, key, keylen); + tfm->has_key = !err; + + return err; } static void hash_sock_destruct(struct sock *sk) @@ -261,12 +400,14 @@ static void hash_sock_destruct(struct sock *sk) af_alg_release_parent(sk); } -static int hash_accept_parent(void *private, struct sock *sk) +static int hash_accept_parent_nokey(void *private, struct sock *sk) { struct hash_ctx *ctx; struct alg_sock *ask = alg_sk(sk); - unsigned len = sizeof(*ctx) + crypto_ahash_reqsize(private); - unsigned ds = crypto_ahash_digestsize(private); + struct algif_hash_tfm *tfm = private; + struct crypto_ahash *hash = tfm->hash; + unsigned len = sizeof(*ctx) + crypto_ahash_reqsize(hash); + unsigned ds = crypto_ahash_digestsize(hash); ctx = sock_kmalloc(sk, len, GFP_KERNEL); if (!ctx) @@ -286,7 +427,7 @@ static int hash_accept_parent(void *private, struct sock *sk) ask->private = ctx; - ahash_request_set_tfm(&ctx->req, private); + ahash_request_set_tfm(&ctx->req, hash); ahash_request_set_callback(&ctx->req, CRYPTO_TFM_REQ_MAY_BACKLOG, af_alg_complete, &ctx->completion); @@ -295,12 +436,24 @@ static int hash_accept_parent(void *private, struct sock *sk) return 0; } +static int hash_accept_parent(void *private, struct sock *sk) +{ + struct algif_hash_tfm *tfm = private; + + if (!tfm->has_key && crypto_ahash_has_setkey(tfm->hash)) + return -ENOKEY; + + return hash_accept_parent_nokey(private, sk); +} + static const struct af_alg_type algif_type_hash = { .bind = hash_bind, .release = hash_release, .setkey = hash_setkey, .accept = hash_accept_parent, + .accept_nokey = hash_accept_parent_nokey, .ops = &algif_hash_ops, + .ops_nokey = &algif_hash_ops_nokey, .name = "hash", .owner = THIS_MODULE }; diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c index 634b4d1ab681..f5e9f9310b48 100644 --- a/crypto/algif_skcipher.c +++ b/crypto/algif_skcipher.c @@ -31,6 +31,11 @@ struct skcipher_sg_list { struct scatterlist sg[0]; }; +struct skcipher_tfm { + struct crypto_skcipher *skcipher; + bool has_key; +}; + struct skcipher_ctx { struct list_head tsgl; struct af_alg_sgl rsgl; @@ -60,18 +65,10 @@ struct skcipher_async_req { struct skcipher_async_rsgl first_sgl; struct list_head list; struct scatterlist *tsg; - char iv[]; + atomic_t *inflight; + struct skcipher_request req; }; -#define GET_SREQ(areq, ctx) (struct skcipher_async_req *)((char *)areq + \ - crypto_skcipher_reqsize(crypto_skcipher_reqtfm(&ctx->req))) - -#define GET_REQ_SIZE(ctx) \ - crypto_skcipher_reqsize(crypto_skcipher_reqtfm(&ctx->req)) - -#define GET_IV_SIZE(ctx) \ - crypto_skcipher_ivsize(crypto_skcipher_reqtfm(&ctx->req)) - #define MAX_SGL_ENTS ((4096 - sizeof(struct skcipher_sg_list)) / \ sizeof(struct scatterlist) - 1) @@ -97,15 +94,12 @@ static void skcipher_free_async_sgls(struct skcipher_async_req *sreq) static void skcipher_async_cb(struct crypto_async_request *req, int err) { - struct sock *sk = req->data; - struct alg_sock *ask = alg_sk(sk); - struct skcipher_ctx *ctx = ask->private; - struct skcipher_async_req *sreq = GET_SREQ(req, ctx); + struct skcipher_async_req *sreq = req->data; struct kiocb *iocb = sreq->iocb; - atomic_dec(&ctx->inflight); + atomic_dec(sreq->inflight); skcipher_free_async_sgls(sreq); - kfree(req); + kzfree(sreq); iocb->ki_complete(iocb, err, err); } @@ -301,8 +295,11 @@ static int skcipher_sendmsg(struct socket *sock, struct msghdr *msg, { struct sock *sk = sock->sk; struct alg_sock *ask = alg_sk(sk); + struct sock *psk = ask->parent; + struct alg_sock *pask = alg_sk(psk); struct skcipher_ctx *ctx = ask->private; - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(&ctx->req); + struct skcipher_tfm *skc = pask->private; + struct crypto_skcipher *tfm = skc->skcipher; unsigned ivsize = crypto_skcipher_ivsize(tfm); struct skcipher_sg_list *sgl; struct af_alg_control con = {}; @@ -387,7 +384,8 @@ static int skcipher_sendmsg(struct socket *sock, struct msghdr *msg, sgl = list_entry(ctx->tsgl.prev, struct skcipher_sg_list, list); sg = sgl->sg; - sg_unmark_end(sg + sgl->cur); + if (sgl->cur) + sg_unmark_end(sg + sgl->cur - 1); do { i = sgl->cur; plen = min_t(int, len, PAGE_SIZE); @@ -503,37 +501,43 @@ static int skcipher_recvmsg_async(struct socket *sock, struct msghdr *msg, { struct sock *sk = sock->sk; struct alg_sock *ask = alg_sk(sk); + struct sock *psk = ask->parent; + struct alg_sock *pask = alg_sk(psk); struct skcipher_ctx *ctx = ask->private; + struct skcipher_tfm *skc = pask->private; + struct crypto_skcipher *tfm = skc->skcipher; struct skcipher_sg_list *sgl; struct scatterlist *sg; struct skcipher_async_req *sreq; struct skcipher_request *req; struct skcipher_async_rsgl *last_rsgl = NULL; - unsigned int txbufs = 0, len = 0, tx_nents = skcipher_all_sg_nents(ctx); - unsigned int reqlen = sizeof(struct skcipher_async_req) + - GET_REQ_SIZE(ctx) + GET_IV_SIZE(ctx); + unsigned int txbufs = 0, len = 0, tx_nents; + unsigned int reqsize = crypto_skcipher_reqsize(tfm); + unsigned int ivsize = crypto_skcipher_ivsize(tfm); int err = -ENOMEM; bool mark = false; + char *iv; + + sreq = kzalloc(sizeof(*sreq) + reqsize + ivsize, GFP_KERNEL); + if (unlikely(!sreq)) + goto out; + + req = &sreq->req; + iv = (char *)(req + 1) + reqsize; + sreq->iocb = msg->msg_iocb; + INIT_LIST_HEAD(&sreq->list); + sreq->inflight = &ctx->inflight; lock_sock(sk); - req = kmalloc(reqlen, GFP_KERNEL); - if (unlikely(!req)) - goto unlock; - - sreq = GET_SREQ(req, ctx); - sreq->iocb = msg->msg_iocb; - memset(&sreq->first_sgl, '\0', sizeof(struct skcipher_async_rsgl)); - INIT_LIST_HEAD(&sreq->list); + tx_nents = skcipher_all_sg_nents(ctx); sreq->tsg = kcalloc(tx_nents, sizeof(*sg), GFP_KERNEL); - if (unlikely(!sreq->tsg)) { - kfree(req); + if (unlikely(!sreq->tsg)) goto unlock; - } sg_init_table(sreq->tsg, tx_nents); - memcpy(sreq->iv, ctx->iv, GET_IV_SIZE(ctx)); - skcipher_request_set_tfm(req, crypto_skcipher_reqtfm(&ctx->req)); - skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, - skcipher_async_cb, sk); + memcpy(iv, ctx->iv, ivsize); + skcipher_request_set_tfm(req, tfm); + skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, + skcipher_async_cb, sreq); while (iov_iter_count(&msg->msg_iter)) { struct skcipher_async_rsgl *rsgl; @@ -609,20 +613,22 @@ static int skcipher_recvmsg_async(struct socket *sock, struct msghdr *msg, sg_mark_end(sreq->tsg + txbufs - 1); skcipher_request_set_crypt(req, sreq->tsg, sreq->first_sgl.sgl.sg, - len, sreq->iv); + len, iv); err = ctx->enc ? crypto_skcipher_encrypt(req) : crypto_skcipher_decrypt(req); if (err == -EINPROGRESS) { atomic_inc(&ctx->inflight); err = -EIOCBQUEUED; + sreq = NULL; goto unlock; } free: skcipher_free_async_sgls(sreq); - kfree(req); unlock: skcipher_wmem_wakeup(sk); release_sock(sk); + kzfree(sreq); +out: return err; } @@ -631,9 +637,12 @@ static int skcipher_recvmsg_sync(struct socket *sock, struct msghdr *msg, { struct sock *sk = sock->sk; struct alg_sock *ask = alg_sk(sk); + struct sock *psk = ask->parent; + struct alg_sock *pask = alg_sk(psk); struct skcipher_ctx *ctx = ask->private; - unsigned bs = crypto_skcipher_blocksize(crypto_skcipher_reqtfm( - &ctx->req)); + struct skcipher_tfm *skc = pask->private; + struct crypto_skcipher *tfm = skc->skcipher; + unsigned bs = crypto_skcipher_blocksize(tfm); struct skcipher_sg_list *sgl; struct scatterlist *sg; int err = -EAGAIN; @@ -642,13 +651,6 @@ static int skcipher_recvmsg_sync(struct socket *sock, struct msghdr *msg, lock_sock(sk); while (msg_data_left(msg)) { - sgl = list_first_entry(&ctx->tsgl, - struct skcipher_sg_list, list); - sg = sgl->sg; - - while (!sg->length) - sg++; - if (!ctx->used) { err = skcipher_wait_for_data(sk, flags); if (err) @@ -669,6 +671,13 @@ static int skcipher_recvmsg_sync(struct socket *sock, struct msghdr *msg, if (!used) goto free; + sgl = list_first_entry(&ctx->tsgl, + struct skcipher_sg_list, list); + sg = sgl->sg; + + while (!sg->length) + sg++; + skcipher_request_set_crypt(&ctx->req, sg, ctx->rsgl.sg, used, ctx->iv); @@ -748,19 +757,139 @@ static struct proto_ops algif_skcipher_ops = { .poll = skcipher_poll, }; +static int skcipher_check_key(struct socket *sock) +{ + int err = 0; + struct sock *psk; + struct alg_sock *pask; + struct skcipher_tfm *tfm; + struct sock *sk = sock->sk; + struct alg_sock *ask = alg_sk(sk); + + lock_sock(sk); + if (ask->refcnt) + goto unlock_child; + + psk = ask->parent; + pask = alg_sk(ask->parent); + tfm = pask->private; + + err = -ENOKEY; + lock_sock_nested(psk, SINGLE_DEPTH_NESTING); + if (!tfm->has_key) + goto unlock; + + if (!pask->refcnt++) + sock_hold(psk); + + ask->refcnt = 1; + sock_put(psk); + + err = 0; + +unlock: + release_sock(psk); +unlock_child: + release_sock(sk); + + return err; +} + +static int skcipher_sendmsg_nokey(struct socket *sock, struct msghdr *msg, + size_t size) +{ + int err; + + err = skcipher_check_key(sock); + if (err) + return err; + + return skcipher_sendmsg(sock, msg, size); +} + +static ssize_t skcipher_sendpage_nokey(struct socket *sock, struct page *page, + int offset, size_t size, int flags) +{ + int err; + + err = skcipher_check_key(sock); + if (err) + return err; + + return skcipher_sendpage(sock, page, offset, size, flags); +} + +static int skcipher_recvmsg_nokey(struct socket *sock, struct msghdr *msg, + size_t ignored, int flags) +{ + int err; + + err = skcipher_check_key(sock); + if (err) + return err; + + return skcipher_recvmsg(sock, msg, ignored, flags); +} + +static struct proto_ops algif_skcipher_ops_nokey = { + .family = PF_ALG, + + .connect = sock_no_connect, + .socketpair = sock_no_socketpair, + .getname = sock_no_getname, + .ioctl = sock_no_ioctl, + .listen = sock_no_listen, + .shutdown = sock_no_shutdown, + .getsockopt = sock_no_getsockopt, + .mmap = sock_no_mmap, + .bind = sock_no_bind, + .accept = sock_no_accept, + .setsockopt = sock_no_setsockopt, + + .release = af_alg_release, + .sendmsg = skcipher_sendmsg_nokey, + .sendpage = skcipher_sendpage_nokey, + .recvmsg = skcipher_recvmsg_nokey, + .poll = skcipher_poll, +}; + static void *skcipher_bind(const char *name, u32 type, u32 mask) { - return crypto_alloc_skcipher(name, type, mask); + struct skcipher_tfm *tfm; + struct crypto_skcipher *skcipher; + + tfm = kzalloc(sizeof(*tfm), GFP_KERNEL); + if (!tfm) + return ERR_PTR(-ENOMEM); + + skcipher = crypto_alloc_skcipher(name, type, mask); + if (IS_ERR(skcipher)) { + kfree(tfm); + return ERR_CAST(skcipher); + } + + tfm->skcipher = skcipher; + + return tfm; } static void skcipher_release(void *private) { - crypto_free_skcipher(private); + struct skcipher_tfm *tfm = private; + + crypto_free_skcipher(tfm->skcipher); + kfree(tfm); } static int skcipher_setkey(void *private, const u8 *key, unsigned int keylen) { - return crypto_skcipher_setkey(private, key, keylen); + struct skcipher_tfm *tfm = private; + int err; + + err = crypto_skcipher_setkey(tfm->skcipher, key, keylen); + tfm->has_key = !err; + + return err; } static void skcipher_wait(struct sock *sk) @@ -788,24 +917,26 @@ static void skcipher_sock_destruct(struct sock *sk) af_alg_release_parent(sk); } -static int skcipher_accept_parent(void *private, struct sock *sk) +static int skcipher_accept_parent_nokey(void *private, struct sock *sk) { struct skcipher_ctx *ctx; struct alg_sock *ask = alg_sk(sk); - unsigned int len = sizeof(*ctx) + crypto_skcipher_reqsize(private); + struct skcipher_tfm *tfm = private; + struct crypto_skcipher *skcipher = tfm->skcipher; + unsigned int len = sizeof(*ctx) + crypto_skcipher_reqsize(skcipher); ctx = sock_kmalloc(sk, len, GFP_KERNEL); if (!ctx) return -ENOMEM; - ctx->iv = sock_kmalloc(sk, crypto_skcipher_ivsize(private), + ctx->iv = sock_kmalloc(sk, crypto_skcipher_ivsize(skcipher), GFP_KERNEL); if (!ctx->iv) { sock_kfree_s(sk, ctx, len); return -ENOMEM; } - memset(ctx->iv, 0, crypto_skcipher_ivsize(private)); + memset(ctx->iv, 0, crypto_skcipher_ivsize(skcipher)); INIT_LIST_HEAD(&ctx->tsgl); ctx->len = len; @@ -818,8 +949,9 @@ static int skcipher_accept_parent(void *private, struct sock *sk) ask->private = ctx; - skcipher_request_set_tfm(&ctx->req, private); - skcipher_request_set_callback(&ctx->req, CRYPTO_TFM_REQ_MAY_BACKLOG, + skcipher_request_set_tfm(&ctx->req, skcipher); + skcipher_request_set_callback(&ctx->req, CRYPTO_TFM_REQ_MAY_SLEEP | + CRYPTO_TFM_REQ_MAY_BACKLOG, af_alg_complete, &ctx->completion); sk->sk_destruct = skcipher_sock_destruct; @@ -827,12 +959,24 @@ static int skcipher_accept_parent(void *private, struct sock *sk) return 0; } +static int skcipher_accept_parent(void *private, struct sock *sk) +{ + struct skcipher_tfm *tfm = private; + + if (!tfm->has_key && crypto_skcipher_has_setkey(tfm->skcipher)) + return -ENOKEY; + + return skcipher_accept_parent_nokey(private, sk); +} + static const struct af_alg_type algif_type_skcipher = { .bind = skcipher_bind, .release = skcipher_release, .setkey = skcipher_setkey, .accept = skcipher_accept_parent, + .accept_nokey = skcipher_accept_parent_nokey, .ops = &algif_skcipher_ops, + .ops_nokey = &algif_skcipher_ops_nokey, .name = "skcipher", .owner = THIS_MODULE }; diff --git a/crypto/asymmetric_keys/Kconfig b/crypto/asymmetric_keys/Kconfig index 4870f28403f5..05bfe568cd30 100644 --- a/crypto/asymmetric_keys/Kconfig +++ b/crypto/asymmetric_keys/Kconfig @@ -14,6 +14,7 @@ config ASYMMETRIC_PUBLIC_KEY_SUBTYPE select MPILIB select PUBLIC_KEY_ALGO_RSA select CRYPTO_HASH_INFO + select CRYPTO_AKCIPHER help This option provides support for asymmetric public key type handling. If signature generation and/or verification are to be used, diff --git a/crypto/asymmetric_keys/pkcs7_trust.c b/crypto/asymmetric_keys/pkcs7_trust.c index 90d6d47965b0..ecdb5a2ce085 100644 --- a/crypto/asymmetric_keys/pkcs7_trust.c +++ b/crypto/asymmetric_keys/pkcs7_trust.c @@ -178,6 +178,8 @@ int pkcs7_validate_trust(struct pkcs7_message *pkcs7, int cached_ret = -ENOKEY; int ret; + *_trusted = false; + for (p = pkcs7->certs; p; p = p->next) p->seen = false; diff --git a/crypto/asymmetric_keys/x509_cert_parser.c b/crypto/asymmetric_keys/x509_cert_parser.c index 021d39c0ba75..13c4e5a5fe8c 100644 --- a/crypto/asymmetric_keys/x509_cert_parser.c +++ b/crypto/asymmetric_keys/x509_cert_parser.c @@ -494,7 +494,7 @@ int x509_decode_time(time64_t *_t, size_t hdrlen, unsigned char tag, const unsigned char *value, size_t vlen) { - static const unsigned char month_lengths[] = { 31, 29, 31, 30, 31, 30, + static const unsigned char month_lengths[] = { 31, 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31 }; const unsigned char *p = value; unsigned year, mon, day, hour, min, sec, mon_len; @@ -540,9 +540,9 @@ int x509_decode_time(time64_t *_t, size_t hdrlen, if (year % 4 == 0) { mon_len = 29; if (year % 100 == 0) { - year /= 100; - if (year % 4 != 0) - mon_len = 28; + mon_len = 28; + if (year % 400 == 0) + mon_len = 29; } } } diff --git a/crypto/crc32c_generic.c b/crypto/crc32c_generic.c index 06f1b60f02b2..4c0a0e271876 100644 --- a/crypto/crc32c_generic.c +++ b/crypto/crc32c_generic.c @@ -172,4 +172,3 @@ MODULE_DESCRIPTION("CRC32c (Castagnoli) calculations wrapper for lib/crc32c"); MODULE_LICENSE("GPL"); MODULE_ALIAS_CRYPTO("crc32c"); MODULE_ALIAS_CRYPTO("crc32c-generic"); -MODULE_SOFTDEP("pre: crc32c"); diff --git a/crypto/crypto_user.c b/crypto/crypto_user.c index 237f3795cfaa..7097a3395b25 100644 --- a/crypto/crypto_user.c +++ b/crypto/crypto_user.c @@ -455,6 +455,7 @@ static const int crypto_msg_min[CRYPTO_NR_MSGTYPES] = { [CRYPTO_MSG_NEWALG - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg), [CRYPTO_MSG_DELALG - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg), [CRYPTO_MSG_UPDATEALG - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg), + [CRYPTO_MSG_GETALG - CRYPTO_MSG_BASE] = MSGSIZE(crypto_user_alg), [CRYPTO_MSG_DELRNG - CRYPTO_MSG_BASE] = 0, }; @@ -499,6 +500,7 @@ static int crypto_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) if (link->dump == NULL) return -EINVAL; + down_read(&crypto_alg_sem); list_for_each_entry(alg, &crypto_alg_list, cra_list) dump_alloc += CRYPTO_REPORT_MAXSIZE; @@ -508,8 +510,11 @@ static int crypto_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) .done = link->done, .min_dump_alloc = dump_alloc, }; - return netlink_dump_start(crypto_nlsk, skb, nlh, &c); + err = netlink_dump_start(crypto_nlsk, skb, nlh, &c); } + up_read(&crypto_alg_sem); + + return err; } err = nlmsg_parse(nlh, crypto_msg_min[type], attrs, CRYPTOCFGA_MAX, diff --git a/crypto/keywrap.c b/crypto/keywrap.c index b1d106ce55f3..72014f963ba7 100644 --- a/crypto/keywrap.c +++ b/crypto/keywrap.c @@ -212,7 +212,7 @@ static int crypto_kw_decrypt(struct blkcipher_desc *desc, SEMIBSIZE)) ret = -EBADMSG; - memzero_explicit(&block, sizeof(struct crypto_kw_block)); + memzero_explicit(block, sizeof(struct crypto_kw_block)); return ret; } @@ -297,7 +297,7 @@ static int crypto_kw_encrypt(struct blkcipher_desc *desc, /* establish the IV for the caller to pick up */ memcpy(desc->info, block->A, SEMIBSIZE); - memzero_explicit(&block, sizeof(struct crypto_kw_block)); + memzero_explicit(block, sizeof(struct crypto_kw_block)); return 0; } diff --git a/crypto/shash.c b/crypto/shash.c index ecb1e3d39bf0..359754591653 100644 --- a/crypto/shash.c +++ b/crypto/shash.c @@ -354,9 +354,10 @@ int crypto_init_shash_ops_async(struct crypto_tfm *tfm) crt->final = shash_async_final; crt->finup = shash_async_finup; crt->digest = shash_async_digest; + crt->setkey = shash_async_setkey; + + crt->has_setkey = alg->setkey != shash_no_setkey; - if (alg->setkey) - crt->setkey = shash_async_setkey; if (alg->export) crt->export = shash_async_export; if (alg->import) diff --git a/crypto/skcipher.c b/crypto/skcipher.c index 7591928be7ca..d199c0b1751c 100644 --- a/crypto/skcipher.c +++ b/crypto/skcipher.c @@ -118,6 +118,7 @@ static int crypto_init_skcipher_ops_blkcipher(struct crypto_tfm *tfm) skcipher->decrypt = skcipher_decrypt_blkcipher; skcipher->ivsize = crypto_blkcipher_ivsize(blkcipher); + skcipher->has_setkey = calg->cra_blkcipher.max_keysize; return 0; } @@ -210,6 +211,7 @@ static int crypto_init_skcipher_ops_ablkcipher(struct crypto_tfm *tfm) skcipher->ivsize = crypto_ablkcipher_ivsize(ablkcipher); skcipher->reqsize = crypto_ablkcipher_reqsize(ablkcipher) + sizeof(struct ablkcipher_request); + skcipher->has_setkey = calg->cra_ablkcipher.max_keysize; return 0; } diff --git a/crypto/testmgr.c b/crypto/testmgr.c index ae8c57fd8bc7..d4944318ca1f 100644 --- a/crypto/testmgr.c +++ b/crypto/testmgr.c @@ -1849,6 +1849,7 @@ static int alg_test_drbg(const struct alg_test_desc *desc, const char *driver, static int do_test_rsa(struct crypto_akcipher *tfm, struct akcipher_testvec *vecs) { + char *xbuf[XBUFSIZE]; struct akcipher_request *req; void *outbuf_enc = NULL; void *outbuf_dec = NULL; @@ -1857,9 +1858,12 @@ static int do_test_rsa(struct crypto_akcipher *tfm, int err = -ENOMEM; struct scatterlist src, dst, src_tab[2]; + if (testmgr_alloc_buf(xbuf)) + return err; + req = akcipher_request_alloc(tfm, GFP_KERNEL); if (!req) - return err; + goto free_xbuf; init_completion(&result.completion); @@ -1877,9 +1881,14 @@ static int do_test_rsa(struct crypto_akcipher *tfm, if (!outbuf_enc) goto free_req; + if (WARN_ON(vecs->m_size > PAGE_SIZE)) + goto free_all; + + memcpy(xbuf[0], vecs->m, vecs->m_size); + sg_init_table(src_tab, 2); - sg_set_buf(&src_tab[0], vecs->m, 8); - sg_set_buf(&src_tab[1], vecs->m + 8, vecs->m_size - 8); + sg_set_buf(&src_tab[0], xbuf[0], 8); + sg_set_buf(&src_tab[1], xbuf[0] + 8, vecs->m_size - 8); sg_init_one(&dst, outbuf_enc, out_len_max); akcipher_request_set_crypt(req, src_tab, &dst, vecs->m_size, out_len_max); @@ -1898,7 +1907,7 @@ static int do_test_rsa(struct crypto_akcipher *tfm, goto free_all; } /* verify that encrypted message is equal to expected */ - if (memcmp(vecs->c, sg_virt(req->dst), vecs->c_size)) { + if (memcmp(vecs->c, outbuf_enc, vecs->c_size)) { pr_err("alg: rsa: encrypt test failed. Invalid output\n"); err = -EINVAL; goto free_all; @@ -1913,7 +1922,13 @@ static int do_test_rsa(struct crypto_akcipher *tfm, err = -ENOMEM; goto free_all; } - sg_init_one(&src, vecs->c, vecs->c_size); + + if (WARN_ON(vecs->c_size > PAGE_SIZE)) + goto free_all; + + memcpy(xbuf[0], vecs->c, vecs->c_size); + + sg_init_one(&src, xbuf[0], vecs->c_size); sg_init_one(&dst, outbuf_dec, out_len_max); init_completion(&result.completion); akcipher_request_set_crypt(req, &src, &dst, vecs->c_size, out_len_max); @@ -1940,6 +1955,8 @@ free_all: kfree(outbuf_enc); free_req: akcipher_request_free(req); +free_xbuf: + testmgr_free_buf(xbuf); return err; } diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c index 6979186dbd4b..9f77943653fb 100644 --- a/drivers/acpi/acpi_processor.c +++ b/drivers/acpi/acpi_processor.c @@ -491,6 +491,58 @@ static void acpi_processor_remove(struct acpi_device *device) } #endif /* CONFIG_ACPI_HOTPLUG_CPU */ +#ifdef CONFIG_X86 +static bool acpi_hwp_native_thermal_lvt_set; +static acpi_status __init acpi_hwp_native_thermal_lvt_osc(acpi_handle handle, + u32 lvl, + void *context, + void **rv) +{ + u8 sb_uuid_str[] = "4077A616-290C-47BE-9EBD-D87058713953"; + u32 capbuf[2]; + struct acpi_osc_context osc_context = { + .uuid_str = sb_uuid_str, + .rev = 1, + .cap.length = 8, + .cap.pointer = capbuf, + }; + + if (acpi_hwp_native_thermal_lvt_set) + return AE_CTRL_TERMINATE; + + capbuf[0] = 0x0000; + capbuf[1] = 0x1000; /* set bit 12 */ + + if (ACPI_SUCCESS(acpi_run_osc(handle, &osc_context))) { + if (osc_context.ret.pointer && osc_context.ret.length > 1) { + u32 *capbuf_ret = osc_context.ret.pointer; + + if (capbuf_ret[1] & 0x1000) { + acpi_handle_info(handle, + "_OSC native thermal LVT Acked\n"); + acpi_hwp_native_thermal_lvt_set = true; + } + } + kfree(osc_context.ret.pointer); + } + + return AE_OK; +} + +void __init acpi_early_processor_osc(void) +{ + if (boot_cpu_has(X86_FEATURE_HWP)) { + acpi_walk_namespace(ACPI_TYPE_PROCESSOR, ACPI_ROOT_OBJECT, + ACPI_UINT32_MAX, + acpi_hwp_native_thermal_lvt_osc, + NULL, NULL, NULL); + acpi_get_devices(ACPI_PROCESSOR_DEVICE_HID, + acpi_hwp_native_thermal_lvt_osc, + NULL, NULL); + } +} +#endif + /* * The following ACPI IDs are known to be suitable for representing as * processor devices. diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c index 3405f7a41e25..5fdac394207a 100644 --- a/drivers/acpi/acpi_video.c +++ b/drivers/acpi/acpi_video.c @@ -464,6 +464,15 @@ static struct dmi_system_id video_dmi_table[] = { * control on these systems, but do not register a backlight sysfs * as brightness control does not work. */ + { + /* https://bugzilla.kernel.org/show_bug.cgi?id=21012 */ + .callback = video_disable_backlight_sysfs_if, + .ident = "Toshiba Portege R700", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"), + DMI_MATCH(DMI_PRODUCT_NAME, "PORTEGE R700"), + }, + }, { /* https://bugs.freedesktop.org/show_bug.cgi?id=82634 */ .callback = video_disable_backlight_sysfs_if, @@ -473,6 +482,15 @@ static struct dmi_system_id video_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "PORTEGE R830"), }, }, + { + /* https://bugzilla.kernel.org/show_bug.cgi?id=21012 */ + .callback = video_disable_backlight_sysfs_if, + .ident = "Toshiba Satellite R830", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"), + DMI_MATCH(DMI_PRODUCT_NAME, "SATELLITE R830"), + }, + }, /* * Some machine's _DOD IDs don't have bit 31(Device ID Scheme) set * but the IDs actually follow the Device ID Scheme. diff --git a/drivers/acpi/acpica/dsmethod.c b/drivers/acpi/acpica/dsmethod.c index bc32f3194afe..28c50c6b5f45 100644 --- a/drivers/acpi/acpica/dsmethod.c +++ b/drivers/acpi/acpica/dsmethod.c @@ -417,6 +417,9 @@ acpi_ds_begin_method_execution(struct acpi_namespace_node *method_node, obj_desc->method.mutex->mutex. original_sync_level = obj_desc->method.mutex->mutex.sync_level; + + obj_desc->method.mutex->mutex.thread_id = + acpi_os_get_thread_id(); } } diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index a212cefae524..ca4f28432d87 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -1004,6 +1004,9 @@ static int __init acpi_bus_init(void) goto error1; } + /* Set capability bits for _OSC under processor scope */ + acpi_early_processor_osc(); + /* * _OSC method may exist in module level code, * so it must be run after ACPI_FULL_INITIALIZATION diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h index 11d87bf67e73..0f3f41c13b38 100644 --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -130,6 +130,12 @@ void acpi_early_processor_set_pdc(void); static inline void acpi_early_processor_set_pdc(void) {} #endif +#ifdef CONFIG_X86 +void acpi_early_processor_osc(void); +#else +static inline void acpi_early_processor_osc(void) {} +#endif + /* -------------------------------------------------------------------------- Embedded Controller -------------------------------------------------------------------------- */ diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c index aa45d4802707..11d8209e6e5d 100644 --- a/drivers/acpi/nfit.c +++ b/drivers/acpi/nfit.c @@ -468,37 +468,16 @@ static void nfit_mem_find_spa_bdw(struct acpi_nfit_desc *acpi_desc, nfit_mem->bdw = NULL; } -static int nfit_mem_add(struct acpi_nfit_desc *acpi_desc, +static void nfit_mem_init_bdw(struct acpi_nfit_desc *acpi_desc, struct nfit_mem *nfit_mem, struct acpi_nfit_system_address *spa) { u16 dcr = __to_nfit_memdev(nfit_mem)->region_index; struct nfit_memdev *nfit_memdev; struct nfit_flush *nfit_flush; - struct nfit_dcr *nfit_dcr; struct nfit_bdw *nfit_bdw; struct nfit_idt *nfit_idt; u16 idt_idx, range_index; - list_for_each_entry(nfit_dcr, &acpi_desc->dcrs, list) { - if (nfit_dcr->dcr->region_index != dcr) - continue; - nfit_mem->dcr = nfit_dcr->dcr; - break; - } - - if (!nfit_mem->dcr) { - dev_dbg(acpi_desc->dev, "SPA %d missing:%s%s\n", - spa->range_index, __to_nfit_memdev(nfit_mem) - ? "" : " MEMDEV", nfit_mem->dcr ? "" : " DCR"); - return -ENODEV; - } - - /* - * We've found enough to create an nvdimm, optionally - * find an associated BDW - */ - list_add(&nfit_mem->list, &acpi_desc->dimms); - list_for_each_entry(nfit_bdw, &acpi_desc->bdws, list) { if (nfit_bdw->bdw->region_index != dcr) continue; @@ -507,12 +486,12 @@ static int nfit_mem_add(struct acpi_nfit_desc *acpi_desc, } if (!nfit_mem->bdw) - return 0; + return; nfit_mem_find_spa_bdw(acpi_desc, nfit_mem); if (!nfit_mem->spa_bdw) - return 0; + return; range_index = nfit_mem->spa_bdw->range_index; list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) { @@ -537,8 +516,6 @@ static int nfit_mem_add(struct acpi_nfit_desc *acpi_desc, } break; } - - return 0; } static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc, @@ -547,7 +524,6 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc, struct nfit_mem *nfit_mem, *found; struct nfit_memdev *nfit_memdev; int type = nfit_spa_type(spa); - u16 dcr; switch (type) { case NFIT_SPA_DCR: @@ -558,14 +534,18 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc, } list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) { - int rc; + struct nfit_dcr *nfit_dcr; + u32 device_handle; + u16 dcr; if (nfit_memdev->memdev->range_index != spa->range_index) continue; found = NULL; dcr = nfit_memdev->memdev->region_index; + device_handle = nfit_memdev->memdev->device_handle; list_for_each_entry(nfit_mem, &acpi_desc->dimms, list) - if (__to_nfit_memdev(nfit_mem)->region_index == dcr) { + if (__to_nfit_memdev(nfit_mem)->device_handle + == device_handle) { found = nfit_mem; break; } @@ -578,6 +558,31 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc, if (!nfit_mem) return -ENOMEM; INIT_LIST_HEAD(&nfit_mem->list); + list_add(&nfit_mem->list, &acpi_desc->dimms); + } + + list_for_each_entry(nfit_dcr, &acpi_desc->dcrs, list) { + if (nfit_dcr->dcr->region_index != dcr) + continue; + /* + * Record the control region for the dimm. For + * the ACPI 6.1 case, where there are separate + * control regions for the pmem vs blk + * interfaces, be sure to record the extended + * blk details. + */ + if (!nfit_mem->dcr) + nfit_mem->dcr = nfit_dcr->dcr; + else if (nfit_mem->dcr->windows == 0 + && nfit_dcr->dcr->windows) + nfit_mem->dcr = nfit_dcr->dcr; + break; + } + + if (dcr && !nfit_mem->dcr) { + dev_err(acpi_desc->dev, "SPA %d missing DCR %d\n", + spa->range_index, dcr); + return -ENODEV; } if (type == NFIT_SPA_DCR) { @@ -594,6 +599,7 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc, nfit_mem->idt_dcr = nfit_idt->idt; break; } + nfit_mem_init_bdw(acpi_desc, nfit_mem, spa); } else { /* * A single dimm may belong to multiple SPA-PM @@ -602,13 +608,6 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc, */ nfit_mem->memdev_pmem = nfit_memdev->memdev; } - - if (found) - continue; - - rc = nfit_mem_add(acpi_desc, nfit_mem, spa); - if (rc) - return rc; } return 0; diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c index 32d684af0ec7..a000ecb995e6 100644 --- a/drivers/acpi/osl.c +++ b/drivers/acpi/osl.c @@ -135,7 +135,7 @@ static struct osi_linux { unsigned int enable:1; unsigned int dmi:1; unsigned int cmdline:1; - unsigned int default_disabling:1; + u8 default_disabling; } osi_linux = {0, 0, 0, 0}; static u32 acpi_osi_handler(acpi_string interface, u32 supported) @@ -1444,10 +1444,13 @@ void __init acpi_osi_setup(char *str) if (*str == '!') { str++; if (*str == '\0') { - osi_linux.default_disabling = 1; + /* Do not override acpi_osi=!* */ + if (!osi_linux.default_disabling) + osi_linux.default_disabling = + ACPI_DISABLE_ALL_VENDOR_STRINGS; return; } else if (*str == '*') { - acpi_update_interfaces(ACPI_DISABLE_ALL_STRINGS); + osi_linux.default_disabling = ACPI_DISABLE_ALL_STRINGS; for (i = 0; i < OSI_STRING_ENTRIES_MAX; i++) { osi = &osi_setup_entries[i]; osi->enable = false; @@ -1520,10 +1523,13 @@ static void __init acpi_osi_setup_late(void) acpi_status status; if (osi_linux.default_disabling) { - status = acpi_update_interfaces(ACPI_DISABLE_ALL_VENDOR_STRINGS); + status = acpi_update_interfaces(osi_linux.default_disabling); if (ACPI_SUCCESS(status)) - printk(KERN_INFO PREFIX "Disabled all _OSI OS vendors\n"); + printk(KERN_INFO PREFIX "Disabled all _OSI OS vendors%s\n", + osi_linux.default_disabling == + ACPI_DISABLE_ALL_STRINGS ? + " and feature groups" : ""); } for (i = 0; i < OSI_STRING_ENTRIES_MAX; i++) { diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c index c9336751e5e3..8a10a7ae6a8a 100644 --- a/drivers/acpi/pci_irq.c +++ b/drivers/acpi/pci_irq.c @@ -409,7 +409,7 @@ int acpi_pci_irq_enable(struct pci_dev *dev) return 0; } - if (pci_has_managed_irq(dev)) + if (dev->irq_managed && dev->irq > 0) return 0; entry = acpi_pci_irq_lookup(dev, pin); @@ -454,7 +454,8 @@ int acpi_pci_irq_enable(struct pci_dev *dev) kfree(entry); return rc; } - pci_set_managed_irq(dev, rc); + dev->irq = rc; + dev->irq_managed = 1; if (link) snprintf(link_desc, sizeof(link_desc), " -> Link[%s]", link); @@ -477,9 +478,17 @@ void acpi_pci_irq_disable(struct pci_dev *dev) u8 pin; pin = dev->pin; - if (!pin || !pci_has_managed_irq(dev)) + if (!pin || !dev->irq_managed || dev->irq <= 0) return; + /* Keep IOAPIC pin configuration when suspending */ + if (dev->dev.power.is_prepared) + return; +#ifdef CONFIG_PM + if (dev->dev.power.runtime_status == RPM_SUSPENDING) + return; +#endif + entry = acpi_pci_irq_lookup(dev, pin); if (!entry) return; @@ -499,6 +508,6 @@ void acpi_pci_irq_disable(struct pci_dev *dev) dev_dbg(&dev->dev, "PCI INT %c disabled\n", pin_name(pin)); if (gsi >= 0) { acpi_unregister_gsi(gsi); - pci_reset_managed_irq(dev); + dev->irq_managed = 0; } } diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index cdc5c2599beb..627f8fbb5e9a 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -26,8 +26,20 @@ #ifdef CONFIG_X86 #define valid_IRQ(i) (((i) != 0) && ((i) != 2)) +static inline bool acpi_iospace_resource_valid(struct resource *res) +{ + /* On X86 IO space is limited to the [0 - 64K] IO port range */ + return res->end < 0x10003; +} #else #define valid_IRQ(i) (true) +/* + * ACPI IO descriptors on arches other than X86 contain MMIO CPU physical + * addresses mapping IO space in CPU physical address space, IO space + * resources can be placed anywhere in the 64-bit physical address space. + */ +static inline bool +acpi_iospace_resource_valid(struct resource *res) { return true; } #endif static bool acpi_dev_resource_len_valid(u64 start, u64 end, u64 len, bool io) @@ -126,7 +138,7 @@ static void acpi_dev_ioresource_flags(struct resource *res, u64 len, if (!acpi_dev_resource_len_valid(res->start, res->end, len, true)) res->flags |= IORESOURCE_DISABLED | IORESOURCE_UNSET; - if (res->end >= 0x10003) + if (!acpi_iospace_resource_valid(res)) res->flags |= IORESOURCE_DISABLED | IORESOURCE_UNSET; if (io_decode == ACPI_DECODE_16) diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 0d94621dc856..e3322adaaae0 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -714,6 +714,7 @@ static int acpi_hibernation_enter(void) static void acpi_hibernation_leave(void) { + pm_set_resume_via_firmware(); /* * If ACPI is not enabled by the BIOS and the boot kernel, we need to * enable it here. diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index daaf1c4e1e0f..80e55cb0827b 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -135,14 +135,6 @@ static const struct dmi_system_id video_detect_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "UL30A"), }, }, - { - .callback = video_detect_force_vendor, - .ident = "Dell Inspiron 5737", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), - DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 5737"), - }, - }, /* * These models have a working acpi_video backlight control, and using diff --git a/drivers/android/binder.c b/drivers/android/binder.c index f0ce9959d14d..57f52a2afa35 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -2081,7 +2081,7 @@ static int binder_thread_write(struct binder_proc *proc, if (get_user(cookie, (binder_uintptr_t __user *)ptr)) return -EFAULT; - ptr += sizeof(void *); + ptr += sizeof(cookie); list_for_each_entry(w, &proc->delivered_death, entry) { struct binder_ref_death *tmp_death = container_of(w, struct binder_ref_death, work); diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index cdfbcc54821f..60a15831c009 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -264,6 +264,26 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0x3b2b), board_ahci }, /* PCH RAID */ { PCI_VDEVICE(INTEL, 0x3b2c), board_ahci }, /* PCH RAID */ { PCI_VDEVICE(INTEL, 0x3b2f), board_ahci }, /* PCH AHCI */ + { PCI_VDEVICE(INTEL, 0x19b0), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19b1), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19b2), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19b3), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19b4), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19b5), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19b6), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19b7), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19bE), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19bF), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c0), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c1), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c2), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c3), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c4), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c5), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c6), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19c7), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19cE), board_ahci }, /* DNV AHCI */ + { PCI_VDEVICE(INTEL, 0x19cF), board_ahci }, /* DNV AHCI */ { PCI_VDEVICE(INTEL, 0x1c02), board_ahci }, /* CPT AHCI */ { PCI_VDEVICE(INTEL, 0x1c03), board_ahci }, /* CPT AHCI */ { PCI_VDEVICE(INTEL, 0x1c04), board_ahci }, /* CPT RAID */ @@ -347,15 +367,21 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0xa107), board_ahci }, /* Sunrise Point-H RAID */ { PCI_VDEVICE(INTEL, 0xa10f), board_ahci }, /* Sunrise Point-H RAID */ { PCI_VDEVICE(INTEL, 0x2822), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0x2823), board_ahci }, /* Lewisburg AHCI*/ { PCI_VDEVICE(INTEL, 0x2826), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0x2827), board_ahci }, /* Lewisburg RAID*/ { PCI_VDEVICE(INTEL, 0xa182), board_ahci }, /* Lewisburg AHCI*/ { PCI_VDEVICE(INTEL, 0xa184), board_ahci }, /* Lewisburg RAID*/ { PCI_VDEVICE(INTEL, 0xa186), board_ahci }, /* Lewisburg RAID*/ { PCI_VDEVICE(INTEL, 0xa18e), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0xa1d2), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0xa1d6), board_ahci }, /* Lewisburg RAID*/ { PCI_VDEVICE(INTEL, 0xa202), board_ahci }, /* Lewisburg AHCI*/ { PCI_VDEVICE(INTEL, 0xa204), board_ahci }, /* Lewisburg RAID*/ { PCI_VDEVICE(INTEL, 0xa206), board_ahci }, /* Lewisburg RAID*/ { PCI_VDEVICE(INTEL, 0xa20e), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0xa252), board_ahci }, /* Lewisburg RAID*/ + { PCI_VDEVICE(INTEL, 0xa256), board_ahci }, /* Lewisburg RAID*/ /* JMicron 360/1/3/5/6, match class to avoid IDE function */ { PCI_VENDOR_ID_JMICRON, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID, diff --git a/drivers/ata/ahci_platform.c b/drivers/ata/ahci_platform.c index 04975b851c23..639adb1f8abd 100644 --- a/drivers/ata/ahci_platform.c +++ b/drivers/ata/ahci_platform.c @@ -51,6 +51,9 @@ static int ahci_probe(struct platform_device *pdev) if (rc) return rc; + of_property_read_u32(dev->of_node, + "ports-implemented", &hpriv->force_port_map); + if (of_device_is_compatible(dev->of_node, "hisilicon,hisi-ahci")) hpriv->flags |= AHCI_HFLAG_NO_FBS | AHCI_HFLAG_NO_NCQ; diff --git a/drivers/ata/ahci_xgene.c b/drivers/ata/ahci_xgene.c index e2c6d9e0c5ac..e916bff6cee8 100644 --- a/drivers/ata/ahci_xgene.c +++ b/drivers/ata/ahci_xgene.c @@ -739,9 +739,9 @@ static int xgene_ahci_probe(struct platform_device *pdev) dev_warn(&pdev->dev, "%s: Error reading device info. Assume version1\n", __func__); version = XGENE_AHCI_V1; - } - if (info->valid & ACPI_VALID_CID) + } else if (info->valid & ACPI_VALID_CID) { version = XGENE_AHCI_V2; + } } } #endif diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index 4665512dae44..9628fa131757 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -467,6 +467,7 @@ void ahci_save_initial_config(struct device *dev, struct ahci_host_priv *hpriv) dev_info(dev, "forcing port_map 0x%x -> 0x%x\n", port_map, hpriv->force_port_map); port_map = hpriv->force_port_map; + hpriv->saved_port_map = port_map; } if (hpriv->mask_port_map) { @@ -495,8 +496,8 @@ void ahci_save_initial_config(struct device *dev, struct ahci_host_priv *hpriv) } } - /* fabricate port_map from cap.nr_ports */ - if (!port_map) { + /* fabricate port_map from cap.nr_ports for < AHCI 1.3 */ + if (!port_map && vers < 0x10300) { port_map = (1 << ahci_nr_ports(cap)) - 1; dev_warn(dev, "forcing PORTS_IMPL to 0x%x\n", port_map); @@ -1142,8 +1143,7 @@ static void ahci_port_init(struct device *dev, struct ata_port *ap, /* mark esata ports */ tmp = readl(port_mmio + PORT_CMD); - if ((tmp & PORT_CMD_HPCP) || - ((tmp & PORT_CMD_ESP) && (hpriv->cap & HOST_CAP_SXS))) + if ((tmp & PORT_CMD_ESP) && (hpriv->cap & HOST_CAP_SXS)) ap->pflags |= ATA_PFLAG_EXTERNAL; } diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index 961acc788f44..91a9e6af2ec4 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -606,7 +606,7 @@ void ata_scsi_error(struct Scsi_Host *host) ata_scsi_port_error_handler(host, ap); /* finish or retry handled scmd's and clean up */ - WARN_ON(host->host_failed || !list_empty(&eh_work_q)); + WARN_ON(!list_empty(&eh_work_q)); DPRINTK("EXIT\n"); } diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 7e959f90c020..e417e1a1d02c 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -675,19 +675,18 @@ static int ata_ioc32(struct ata_port *ap) int ata_sas_scsi_ioctl(struct ata_port *ap, struct scsi_device *scsidev, int cmd, void __user *arg) { - int val = -EINVAL, rc = -EINVAL; + unsigned long val; + int rc = -EINVAL; unsigned long flags; switch (cmd) { - case ATA_IOC_GET_IO32: + case HDIO_GET_32BIT: spin_lock_irqsave(ap->lock, flags); val = ata_ioc32(ap); spin_unlock_irqrestore(ap->lock, flags); - if (copy_to_user(arg, &val, 1)) - return -EFAULT; - return 0; + return put_user(val, (unsigned long __user *)arg); - case ATA_IOC_SET_IO32: + case HDIO_SET_32BIT: val = (unsigned long) arg; rc = 0; spin_lock_irqsave(ap->lock, flags); diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index cdf6215a9a22..7dbba387d12a 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -997,12 +997,9 @@ static inline int ata_hsm_ok_in_wq(struct ata_port *ap, static void ata_hsm_qc_complete(struct ata_queued_cmd *qc, int in_wq) { struct ata_port *ap = qc->ap; - unsigned long flags; if (ap->ops->error_handler) { if (in_wq) { - spin_lock_irqsave(ap->lock, flags); - /* EH might have kicked in while host lock is * released. */ @@ -1014,8 +1011,6 @@ static void ata_hsm_qc_complete(struct ata_queued_cmd *qc, int in_wq) } else ata_port_freeze(ap); } - - spin_unlock_irqrestore(ap->lock, flags); } else { if (likely(!(qc->err_mask & AC_ERR_HSM))) ata_qc_complete(qc); @@ -1024,10 +1019,8 @@ static void ata_hsm_qc_complete(struct ata_queued_cmd *qc, int in_wq) } } else { if (in_wq) { - spin_lock_irqsave(ap->lock, flags); ata_sff_irq_on(ap); ata_qc_complete(qc); - spin_unlock_irqrestore(ap->lock, flags); } else ata_qc_complete(qc); } @@ -1048,9 +1041,10 @@ int ata_sff_hsm_move(struct ata_port *ap, struct ata_queued_cmd *qc, { struct ata_link *link = qc->dev->link; struct ata_eh_info *ehi = &link->eh_info; - unsigned long flags = 0; int poll_next; + lockdep_assert_held(ap->lock); + WARN_ON_ONCE((qc->flags & ATA_QCFLAG_ACTIVE) == 0); /* Make sure ata_sff_qc_issue() does not throw things @@ -1112,14 +1106,6 @@ fsm_start: } } - /* Send the CDB (atapi) or the first data block (ata pio out). - * During the state transition, interrupt handler shouldn't - * be invoked before the data transfer is complete and - * hsm_task_state is changed. Hence, the following locking. - */ - if (in_wq) - spin_lock_irqsave(ap->lock, flags); - if (qc->tf.protocol == ATA_PROT_PIO) { /* PIO data out protocol. * send first data block. @@ -1135,9 +1121,6 @@ fsm_start: /* send CDB */ atapi_send_cdb(ap, qc); - if (in_wq) - spin_unlock_irqrestore(ap->lock, flags); - /* if polling, ata_sff_pio_task() handles the rest. * otherwise, interrupt handler takes over from here. */ @@ -1361,12 +1344,14 @@ static void ata_sff_pio_task(struct work_struct *work) u8 status; int poll_next; + spin_lock_irq(ap->lock); + BUG_ON(ap->sff_pio_task_link == NULL); /* qc can be NULL if timeout occurred */ qc = ata_qc_from_tag(ap, link->active_tag); if (!qc) { ap->sff_pio_task_link = NULL; - return; + goto out_unlock; } fsm_start: @@ -1381,11 +1366,14 @@ fsm_start: */ status = ata_sff_busy_wait(ap, ATA_BUSY, 5); if (status & ATA_BUSY) { + spin_unlock_irq(ap->lock); ata_msleep(ap, 2); + spin_lock_irq(ap->lock); + status = ata_sff_busy_wait(ap, ATA_BUSY, 10); if (status & ATA_BUSY) { ata_sff_queue_pio_task(link, ATA_SHORT_PAUSE); - return; + goto out_unlock; } } @@ -1402,6 +1390,8 @@ fsm_start: */ if (poll_next) goto fsm_start; +out_unlock: + spin_unlock_irq(ap->lock); } /** diff --git a/drivers/ata/pata_rb532_cf.c b/drivers/ata/pata_rb532_cf.c index 12fe0f3bb7e9..c8b6a780a290 100644 --- a/drivers/ata/pata_rb532_cf.c +++ b/drivers/ata/pata_rb532_cf.c @@ -32,6 +32,8 @@ #include #include +#include + #define DRV_NAME "pata-rb532-cf" #define DRV_VERSION "0.1.0" #define DRV_DESC "PATA driver for RouterBOARD 532 Compact Flash" @@ -107,6 +109,7 @@ static int rb532_pata_driver_probe(struct platform_device *pdev) int gpio; struct resource *res; struct ata_host *ah; + struct cf_device *pdata; struct rb532_cf_info *info; int ret; @@ -122,7 +125,13 @@ static int rb532_pata_driver_probe(struct platform_device *pdev) return -ENOENT; } - gpio = irq_to_gpio(irq); + pdata = dev_get_platdata(&pdev->dev); + if (!pdata) { + dev_err(&pdev->dev, "no platform data specified\n"); + return -EINVAL; + } + + gpio = pdata->gpio_pin; if (gpio < 0) { dev_err(&pdev->dev, "no GPIO found for irq%d\n", irq); return -ENOENT; diff --git a/drivers/base/module.c b/drivers/base/module.c index db930d3ee312..2a215780eda2 100644 --- a/drivers/base/module.c +++ b/drivers/base/module.c @@ -24,10 +24,12 @@ static char *make_driver_name(struct device_driver *drv) static void module_create_drivers_dir(struct module_kobject *mk) { - if (!mk || mk->drivers_dir) - return; + static DEFINE_MUTEX(drivers_dir_mutex); - mk->drivers_dir = kobject_create_and_add("drivers", &mk->kobj); + mutex_lock(&drivers_dir_mutex); + if (mk && !mk->drivers_dir) + mk->drivers_dir = kobject_create_and_add("drivers", &mk->kobj); + mutex_unlock(&drivers_dir_mutex); } void module_add_driver(struct module *mod, struct device_driver *drv) diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 1dd6d3bf1098..176b59f5bc47 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -513,10 +513,15 @@ static int platform_drv_probe(struct device *_dev) return ret; ret = dev_pm_domain_attach(_dev, true); - if (ret != -EPROBE_DEFER && drv->probe) { - ret = drv->probe(dev); - if (ret) - dev_pm_domain_detach(_dev, true); + if (ret != -EPROBE_DEFER) { + if (drv->probe) { + ret = drv->probe(dev); + if (ret) + dev_pm_domain_detach(_dev, true); + } else { + /* don't fail if just dev_pm_domain_attach failed */ + ret = 0; + } } if (drv->prevent_deferred_probe && ret == -EPROBE_DEFER) { diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index 65f50eccd49b..a48824deabc5 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -1381,7 +1381,7 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd, mutex_lock(&genpd->lock); - if (!list_empty(&subdomain->slave_links) || subdomain->device_count) { + if (!list_empty(&subdomain->master_links) || subdomain->device_count) { pr_warn("%s: unable to remove subdomain %s\n", genpd->name, subdomain->name); ret = -EBUSY; diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index 77379f3d136a..7eea95d490e6 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -1265,14 +1265,15 @@ int dpm_suspend_late(pm_message_t state) error = device_suspend_late(dev); mutex_lock(&dpm_list_mtx); + if (!list_empty(&dev->power.entry)) + list_move(&dev->power.entry, &dpm_late_early_list); + if (error) { pm_dev_err(dev, state, " late", error); dpm_save_failed_dev(dev_name(dev)); put_device(dev); break; } - if (!list_empty(&dev->power.entry)) - list_move(&dev->power.entry, &dpm_late_early_list); put_device(dev); if (async_error) diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c index b8e76f75073b..f8580900c273 100644 --- a/drivers/base/power/opp/core.c +++ b/drivers/base/power/opp/core.c @@ -809,8 +809,14 @@ static int opp_parse_supplies(struct dev_pm_opp *opp, struct device *dev) } opp->u_volt = microvolt[0]; - opp->u_volt_min = microvolt[1]; - opp->u_volt_max = microvolt[2]; + + if (count == 1) { + opp->u_volt_min = opp->u_volt; + opp->u_volt_max = opp->u_volt; + } else { + opp->u_volt_min = microvolt[1]; + opp->u_volt_max = microvolt[2]; + } if (!of_property_read_u32(opp->np, "opp-microamp", &val)) opp->u_amp = val; diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index e1a10a03df8e..9796a1a15ef6 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -1468,11 +1468,16 @@ int pm_runtime_force_resume(struct device *dev) goto out; } - ret = callback(dev); + ret = pm_runtime_set_active(dev); if (ret) goto out; - pm_runtime_set_active(dev); + ret = callback(dev); + if (ret) { + pm_runtime_set_suspended(dev); + goto out; + } + pm_runtime_mark_last_busy(dev); out: pm_runtime_enable(dev); diff --git a/drivers/base/regmap/regmap-spmi.c b/drivers/base/regmap/regmap-spmi.c index 7e58f6560399..4a36e415e938 100644 --- a/drivers/base/regmap/regmap-spmi.c +++ b/drivers/base/regmap/regmap-spmi.c @@ -142,7 +142,7 @@ static int regmap_spmi_ext_read(void *context, while (val_size) { len = min_t(size_t, val_size, 8); - err = spmi_ext_register_readl(context, addr, val, val_size); + err = spmi_ext_register_readl(context, addr, val, len); if (err) goto err_out; diff --git a/drivers/block/brd.c b/drivers/block/brd.c index a5880f4ab40e..1914c63ca8b1 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -338,7 +338,7 @@ static blk_qc_t brd_make_request(struct request_queue *q, struct bio *bio) if (unlikely(bio->bi_rw & REQ_DISCARD)) { if (sector & ((PAGE_SIZE >> SECTOR_SHIFT) - 1) || - bio->bi_iter.bi_size & PAGE_MASK) + bio->bi_iter.bi_size & ~PAGE_MASK) goto io_error; discard_from_brd(brd, sector, bio->bi_iter.bi_size); goto out; diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 423f4ca7d712..80cf8add46ff 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -488,6 +488,12 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd, bvec = __bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter); iov_iter_bvec(&iter, ITER_BVEC | rw, bvec, bio_segments(bio), blk_rq_bytes(cmd->rq)); + /* + * This bio may be started from the middle of the 'bvec' + * because of bio splitting, so offset from the bvec must + * be passed to iov iterator + */ + iter.iov_offset = bio->bi_iter.bi_bvec_done; cmd->iocb.ki_pos = pos; cmd->iocb.ki_filp = file; diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index 3457ac8c03e2..55d3d1da72de 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -173,7 +173,13 @@ static struct mtip_cmd *mtip_get_int_command(struct driver_data *dd) { struct request *rq; + if (mtip_check_surprise_removal(dd->pdev)) + return NULL; + rq = blk_mq_alloc_request(dd->queue, 0, __GFP_RECLAIM, true); + if (IS_ERR(rq)) + return NULL; + return blk_mq_rq_to_pdu(rq); } @@ -233,15 +239,9 @@ static void mtip_async_complete(struct mtip_port *port, "Command tag %d failed due to TFE\n", tag); } - /* Unmap the DMA scatter list entries */ - dma_unmap_sg(&dd->pdev->dev, cmd->sg, cmd->scatter_ents, cmd->direction); - rq = mtip_rq_from_tag(dd, tag); - if (unlikely(cmd->unaligned)) - up(&port->cmd_slot_unal); - - blk_mq_end_request(rq, status ? -EIO : 0); + blk_mq_complete_request(rq, status); } /* @@ -581,6 +581,8 @@ static void mtip_completion(struct mtip_port *port, dev_warn(&port->dd->pdev->dev, "Internal command %d completed with TFE\n", tag); + command->comp_func = NULL; + command->comp_data = NULL; complete(waiting); } @@ -618,8 +620,6 @@ static void mtip_handle_tfe(struct driver_data *dd) port = dd->port; - set_bit(MTIP_PF_EH_ACTIVE_BIT, &port->flags); - if (test_bit(MTIP_PF_IC_ACTIVE_BIT, &port->flags)) { cmd = mtip_cmd_from_tag(dd, MTIP_TAG_INTERNAL); dbg_printk(MTIP_DRV_NAME " TFE for the internal command\n"); @@ -628,7 +628,7 @@ static void mtip_handle_tfe(struct driver_data *dd) cmd->comp_func(port, MTIP_TAG_INTERNAL, cmd, PORT_IRQ_TF_ERR); } - goto handle_tfe_exit; + return; } /* clear the tag accumulator */ @@ -701,7 +701,7 @@ static void mtip_handle_tfe(struct driver_data *dd) fail_reason = "thermal shutdown"; } if (buf[288] == 0xBF) { - set_bit(MTIP_DDF_SEC_LOCK_BIT, &dd->dd_flag); + set_bit(MTIP_DDF_REBUILD_FAILED_BIT, &dd->dd_flag); dev_info(&dd->pdev->dev, "Drive indicates rebuild has failed. Secure erase required.\n"); fail_all_ncq_cmds = 1; @@ -771,11 +771,6 @@ static void mtip_handle_tfe(struct driver_data *dd) } } print_tags(dd, "reissued (TFE)", tagaccum, cmd_cnt); - -handle_tfe_exit: - /* clear eh_active */ - clear_bit(MTIP_PF_EH_ACTIVE_BIT, &port->flags); - wake_up_interruptible(&port->svc_wait); } /* @@ -1007,6 +1002,7 @@ static bool mtip_pause_ncq(struct mtip_port *port, (fis->features == 0x27 || fis->features == 0x72 || fis->features == 0x62 || fis->features == 0x26))) { clear_bit(MTIP_DDF_SEC_LOCK_BIT, &port->dd->dd_flag); + clear_bit(MTIP_DDF_REBUILD_FAILED_BIT, &port->dd->dd_flag); /* Com reset after secure erase or lowlevel format */ mtip_restart_port(port); clear_bit(MTIP_PF_SE_ACTIVE_BIT, &port->flags); @@ -1021,12 +1017,14 @@ static bool mtip_pause_ncq(struct mtip_port *port, * * @port Pointer to port data structure * @timeout Max duration to wait (ms) + * @atomic gfp_t flag to indicate blockable context or not * * return value * 0 Success * -EBUSY Commands still active */ -static int mtip_quiesce_io(struct mtip_port *port, unsigned long timeout) +static int mtip_quiesce_io(struct mtip_port *port, unsigned long timeout, + gfp_t atomic) { unsigned long to; unsigned int n; @@ -1037,16 +1035,21 @@ static int mtip_quiesce_io(struct mtip_port *port, unsigned long timeout) to = jiffies + msecs_to_jiffies(timeout); do { if (test_bit(MTIP_PF_SVC_THD_ACTIVE_BIT, &port->flags) && - test_bit(MTIP_PF_ISSUE_CMDS_BIT, &port->flags)) { + test_bit(MTIP_PF_ISSUE_CMDS_BIT, &port->flags) && + atomic == GFP_KERNEL) { msleep(20); continue; /* svc thd is actively issuing commands */ } - msleep(100); + if (atomic == GFP_KERNEL) + msleep(100); + else { + cpu_relax(); + udelay(100); + } + if (mtip_check_surprise_removal(port->dd->pdev)) goto err_fault; - if (test_bit(MTIP_DDF_REMOVE_PENDING_BIT, &port->dd->dd_flag)) - goto err_fault; /* * Ignore s_active bit 0 of array element 0. @@ -1099,6 +1102,7 @@ static int mtip_exec_internal_command(struct mtip_port *port, struct mtip_cmd *int_cmd; struct driver_data *dd = port->dd; int rv = 0; + unsigned long start; /* Make sure the buffer is 8 byte aligned. This is asic specific. */ if (buffer & 0x00000007) { @@ -1107,6 +1111,10 @@ static int mtip_exec_internal_command(struct mtip_port *port, } int_cmd = mtip_get_int_command(dd); + if (!int_cmd) { + dbg_printk(MTIP_DRV_NAME "Unable to allocate tag for PIO cmd\n"); + return -EFAULT; + } set_bit(MTIP_PF_IC_ACTIVE_BIT, &port->flags); @@ -1119,7 +1127,7 @@ static int mtip_exec_internal_command(struct mtip_port *port, if (fis->command != ATA_CMD_STANDBYNOW1) { /* wait for io to complete if non atomic */ if (mtip_quiesce_io(port, - MTIP_QUIESCE_IO_TIMEOUT_MS) < 0) { + MTIP_QUIESCE_IO_TIMEOUT_MS, atomic) < 0) { dev_warn(&dd->pdev->dev, "Failed to quiesce IO\n"); mtip_put_int_command(dd, int_cmd); @@ -1162,6 +1170,8 @@ static int mtip_exec_internal_command(struct mtip_port *port, /* Populate the command header */ int_cmd->command_header->byte_count = 0; + start = jiffies; + /* Issue the command to the hardware */ mtip_issue_non_ncq_command(port, MTIP_TAG_INTERNAL); @@ -1170,10 +1180,12 @@ static int mtip_exec_internal_command(struct mtip_port *port, if ((rv = wait_for_completion_interruptible_timeout( &wait, msecs_to_jiffies(timeout))) <= 0) { + if (rv == -ERESTARTSYS) { /* interrupted */ dev_err(&dd->pdev->dev, - "Internal command [%02X] was interrupted after %lu ms\n", - fis->command, timeout); + "Internal command [%02X] was interrupted after %u ms\n", + fis->command, + jiffies_to_msecs(jiffies - start)); rv = -EINTR; goto exec_ic_exit; } else if (rv == 0) /* timeout */ @@ -2897,6 +2909,42 @@ static int mtip_ftl_rebuild_poll(struct driver_data *dd) return -EFAULT; } +static void mtip_softirq_done_fn(struct request *rq) +{ + struct mtip_cmd *cmd = blk_mq_rq_to_pdu(rq); + struct driver_data *dd = rq->q->queuedata; + + /* Unmap the DMA scatter list entries */ + dma_unmap_sg(&dd->pdev->dev, cmd->sg, cmd->scatter_ents, + cmd->direction); + + if (unlikely(cmd->unaligned)) + up(&dd->port->cmd_slot_unal); + + blk_mq_end_request(rq, rq->errors); +} + +static void mtip_abort_cmd(struct request *req, void *data, + bool reserved) +{ + struct driver_data *dd = data; + + dbg_printk(MTIP_DRV_NAME " Aborting request, tag = %d\n", req->tag); + + clear_bit(req->tag, dd->port->cmds_to_issue); + req->errors = -EIO; + mtip_softirq_done_fn(req); +} + +static void mtip_queue_cmd(struct request *req, void *data, + bool reserved) +{ + struct driver_data *dd = data; + + set_bit(req->tag, dd->port->cmds_to_issue); + blk_abort_request(req); +} + /* * service thread to issue queued commands * @@ -2909,7 +2957,7 @@ static int mtip_ftl_rebuild_poll(struct driver_data *dd) static int mtip_service_thread(void *data) { struct driver_data *dd = (struct driver_data *)data; - unsigned long slot, slot_start, slot_wrap; + unsigned long slot, slot_start, slot_wrap, to; unsigned int num_cmd_slots = dd->slot_groups * 32; struct mtip_port *port = dd->port; @@ -2924,9 +2972,7 @@ static int mtip_service_thread(void *data) * is in progress nor error handling is active */ wait_event_interruptible(port->svc_wait, (port->flags) && - !(port->flags & MTIP_PF_PAUSE_IO)); - - set_bit(MTIP_PF_SVC_THD_ACTIVE_BIT, &port->flags); + (port->flags & MTIP_PF_SVC_THD_WORK)); if (kthread_should_stop() || test_bit(MTIP_PF_SVC_THD_STOP_BIT, &port->flags)) @@ -2936,6 +2982,8 @@ static int mtip_service_thread(void *data) &dd->dd_flag))) goto st_out; + set_bit(MTIP_PF_SVC_THD_ACTIVE_BIT, &port->flags); + restart_eh: /* Demux bits: start with error handling */ if (test_bit(MTIP_PF_EH_ACTIVE_BIT, &port->flags)) { @@ -2946,6 +2994,32 @@ restart_eh: if (test_bit(MTIP_PF_EH_ACTIVE_BIT, &port->flags)) goto restart_eh; + if (test_bit(MTIP_PF_TO_ACTIVE_BIT, &port->flags)) { + to = jiffies + msecs_to_jiffies(5000); + + do { + mdelay(100); + } while (atomic_read(&dd->irq_workers_active) != 0 && + time_before(jiffies, to)); + + if (atomic_read(&dd->irq_workers_active) != 0) + dev_warn(&dd->pdev->dev, + "Completion workers still active!"); + + spin_lock(dd->queue->queue_lock); + blk_mq_all_tag_busy_iter(*dd->tags.tags, + mtip_queue_cmd, dd); + spin_unlock(dd->queue->queue_lock); + + set_bit(MTIP_PF_ISSUE_CMDS_BIT, &dd->port->flags); + + if (mtip_device_reset(dd)) + blk_mq_all_tag_busy_iter(*dd->tags.tags, + mtip_abort_cmd, dd); + + clear_bit(MTIP_PF_TO_ACTIVE_BIT, &dd->port->flags); + } + if (test_bit(MTIP_PF_ISSUE_CMDS_BIT, &port->flags)) { slot = 1; /* used to restrict the loop to one iteration */ @@ -2978,10 +3052,8 @@ restart_eh: } if (test_bit(MTIP_PF_REBUILD_BIT, &port->flags)) { - if (mtip_ftl_rebuild_poll(dd) < 0) - set_bit(MTIP_DDF_REBUILD_FAILED_BIT, - &dd->dd_flag); - clear_bit(MTIP_PF_REBUILD_BIT, &port->flags); + if (mtip_ftl_rebuild_poll(dd) == 0) + clear_bit(MTIP_PF_REBUILD_BIT, &port->flags); } } @@ -3096,7 +3168,7 @@ static int mtip_hw_get_identify(struct driver_data *dd) if (buf[288] == 0xBF) { dev_info(&dd->pdev->dev, "Drive indicates rebuild has failed.\n"); - /* TODO */ + set_bit(MTIP_DDF_REBUILD_FAILED_BIT, &dd->dd_flag); } } @@ -3270,20 +3342,25 @@ out1: return rv; } -static void mtip_standby_drive(struct driver_data *dd) +static int mtip_standby_drive(struct driver_data *dd) { - if (dd->sr) - return; + int rv = 0; + if (dd->sr || !dd->port) + return -ENODEV; /* * Send standby immediate (E0h) to the drive so that it * saves its state. */ if (!test_bit(MTIP_PF_REBUILD_BIT, &dd->port->flags) && - !test_bit(MTIP_DDF_SEC_LOCK_BIT, &dd->dd_flag)) - if (mtip_standby_immediate(dd->port)) + !test_bit(MTIP_DDF_REBUILD_FAILED_BIT, &dd->dd_flag) && + !test_bit(MTIP_DDF_SEC_LOCK_BIT, &dd->dd_flag)) { + rv = mtip_standby_immediate(dd->port); + if (rv) dev_warn(&dd->pdev->dev, "STANDBY IMMEDIATE failed\n"); + } + return rv; } /* @@ -3296,10 +3373,6 @@ static void mtip_standby_drive(struct driver_data *dd) */ static int mtip_hw_exit(struct driver_data *dd) { - /* - * Send standby immediate (E0h) to the drive so that it - * saves its state. - */ if (!dd->sr) { /* de-initialize the port. */ mtip_deinit_port(dd->port); @@ -3341,8 +3414,7 @@ static int mtip_hw_shutdown(struct driver_data *dd) * Send standby immediate (E0h) to the drive so that it * saves its state. */ - if (!dd->sr && dd->port) - mtip_standby_immediate(dd->port); + mtip_standby_drive(dd); return 0; } @@ -3365,7 +3437,7 @@ static int mtip_hw_suspend(struct driver_data *dd) * Send standby immediate (E0h) to the drive * so that it saves its state. */ - if (mtip_standby_immediate(dd->port) != 0) { + if (mtip_standby_drive(dd) != 0) { dev_err(&dd->pdev->dev, "Failed standby-immediate command\n"); return -EFAULT; @@ -3603,6 +3675,28 @@ static int mtip_block_getgeo(struct block_device *dev, return 0; } +static int mtip_block_open(struct block_device *dev, fmode_t mode) +{ + struct driver_data *dd; + + if (dev && dev->bd_disk) { + dd = (struct driver_data *) dev->bd_disk->private_data; + + if (dd) { + if (test_bit(MTIP_DDF_REMOVAL_BIT, + &dd->dd_flag)) { + return -ENODEV; + } + return 0; + } + } + return -ENODEV; +} + +void mtip_block_release(struct gendisk *disk, fmode_t mode) +{ +} + /* * Block device operation function. * @@ -3610,6 +3704,8 @@ static int mtip_block_getgeo(struct block_device *dev, * layer. */ static const struct block_device_operations mtip_block_ops = { + .open = mtip_block_open, + .release = mtip_block_release, .ioctl = mtip_block_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = mtip_block_compat_ioctl, @@ -3671,10 +3767,9 @@ static int mtip_submit_request(struct blk_mq_hw_ctx *hctx, struct request *rq) rq_data_dir(rq))) { return -ENODATA; } - if (unlikely(test_bit(MTIP_DDF_SEC_LOCK_BIT, &dd->dd_flag))) + if (unlikely(test_bit(MTIP_DDF_SEC_LOCK_BIT, &dd->dd_flag) || + test_bit(MTIP_DDF_REBUILD_FAILED_BIT, &dd->dd_flag))) return -ENODATA; - if (test_bit(MTIP_DDF_REBUILD_FAILED_BIT, &dd->dd_flag)) - return -ENXIO; } if (rq->cmd_flags & REQ_DISCARD) { @@ -3786,11 +3881,33 @@ static int mtip_init_cmd(void *data, struct request *rq, unsigned int hctx_idx, return 0; } +static enum blk_eh_timer_return mtip_cmd_timeout(struct request *req, + bool reserved) +{ + struct driver_data *dd = req->q->queuedata; + int ret = BLK_EH_RESET_TIMER; + + if (reserved) + goto exit_handler; + + if (test_bit(req->tag, dd->port->cmds_to_issue)) + goto exit_handler; + + if (test_and_set_bit(MTIP_PF_TO_ACTIVE_BIT, &dd->port->flags)) + goto exit_handler; + + wake_up_interruptible(&dd->port->svc_wait); +exit_handler: + return ret; +} + static struct blk_mq_ops mtip_mq_ops = { .queue_rq = mtip_queue_rq, .map_queue = blk_mq_map_queue, .init_request = mtip_init_cmd, .exit_request = mtip_free_cmd, + .complete = mtip_softirq_done_fn, + .timeout = mtip_cmd_timeout, }; /* @@ -3857,7 +3974,6 @@ static int mtip_block_initialize(struct driver_data *dd) mtip_hw_debugfs_init(dd); -skip_create_disk: memset(&dd->tags, 0, sizeof(dd->tags)); dd->tags.ops = &mtip_mq_ops; dd->tags.nr_hw_queues = 1; @@ -3867,12 +3983,13 @@ skip_create_disk: dd->tags.numa_node = dd->numa_node; dd->tags.flags = BLK_MQ_F_SHOULD_MERGE; dd->tags.driver_data = dd; + dd->tags.timeout = MTIP_NCQ_CMD_TIMEOUT_MS; rv = blk_mq_alloc_tag_set(&dd->tags); if (rv) { dev_err(&dd->pdev->dev, "Unable to allocate request queue\n"); - goto block_queue_alloc_init_error; + goto block_queue_alloc_tag_error; } /* Allocate the request queue. */ @@ -3887,6 +4004,7 @@ skip_create_disk: dd->disk->queue = dd->queue; dd->queue->queuedata = dd; +skip_create_disk: /* Initialize the protocol layer. */ wait_for_rebuild = mtip_hw_get_identify(dd); if (wait_for_rebuild < 0) { @@ -3983,8 +4101,9 @@ kthread_run_error: read_capacity_error: init_hw_cmds_error: blk_cleanup_queue(dd->queue); - blk_mq_free_tag_set(&dd->tags); block_queue_alloc_init_error: + blk_mq_free_tag_set(&dd->tags); +block_queue_alloc_tag_error: mtip_hw_debugfs_exit(dd); disk_index_error: spin_lock(&rssd_index_lock); @@ -4001,6 +4120,22 @@ protocol_init_error: return rv; } +static void mtip_no_dev_cleanup(struct request *rq, void *data, bool reserv) +{ + struct driver_data *dd = (struct driver_data *)data; + struct mtip_cmd *cmd; + + if (likely(!reserv)) + blk_mq_complete_request(rq, -ENODEV); + else if (test_bit(MTIP_PF_IC_ACTIVE_BIT, &dd->port->flags)) { + + cmd = mtip_cmd_from_tag(dd, MTIP_TAG_INTERNAL); + if (cmd->comp_func) + cmd->comp_func(dd->port, MTIP_TAG_INTERNAL, + cmd, -ENODEV); + } +} + /* * Block layer deinitialization function. * @@ -4032,12 +4167,23 @@ static int mtip_block_remove(struct driver_data *dd) } } - if (!dd->sr) - mtip_standby_drive(dd); + if (!dd->sr) { + /* + * Explicitly wait here for IOs to quiesce, + * as mtip_standby_drive usually won't wait for IOs. + */ + if (!mtip_quiesce_io(dd->port, MTIP_QUIESCE_IO_TIMEOUT_MS, + GFP_KERNEL)) + mtip_standby_drive(dd); + } else dev_info(&dd->pdev->dev, "device %s surprise removal\n", dd->disk->disk_name); + blk_mq_freeze_queue_start(dd->queue); + blk_mq_stop_hw_queues(dd->queue); + blk_mq_all_tag_busy_iter(dd->tags.tags[0], mtip_no_dev_cleanup, dd); + /* * Delete our gendisk structure. This also removes the device * from /dev @@ -4047,7 +4193,8 @@ static int mtip_block_remove(struct driver_data *dd) dd->bdev = NULL; } if (dd->disk) { - del_gendisk(dd->disk); + if (test_bit(MTIP_DDF_INIT_DONE_BIT, &dd->dd_flag)) + del_gendisk(dd->disk); if (dd->disk->queue) { blk_cleanup_queue(dd->queue); blk_mq_free_tag_set(&dd->tags); @@ -4088,7 +4235,8 @@ static int mtip_block_shutdown(struct driver_data *dd) dev_info(&dd->pdev->dev, "Shutting down %s ...\n", dd->disk->disk_name); - del_gendisk(dd->disk); + if (test_bit(MTIP_DDF_INIT_DONE_BIT, &dd->dd_flag)) + del_gendisk(dd->disk); if (dd->disk->queue) { blk_cleanup_queue(dd->queue); blk_mq_free_tag_set(&dd->tags); @@ -4433,7 +4581,7 @@ static void mtip_pci_remove(struct pci_dev *pdev) struct driver_data *dd = pci_get_drvdata(pdev); unsigned long flags, to; - set_bit(MTIP_DDF_REMOVE_PENDING_BIT, &dd->dd_flag); + set_bit(MTIP_DDF_REMOVAL_BIT, &dd->dd_flag); spin_lock_irqsave(&dev_lock, flags); list_del_init(&dd->online_list); @@ -4450,12 +4598,17 @@ static void mtip_pci_remove(struct pci_dev *pdev) } while (atomic_read(&dd->irq_workers_active) != 0 && time_before(jiffies, to)); + if (!dd->sr) + fsync_bdev(dd->bdev); + if (atomic_read(&dd->irq_workers_active) != 0) { dev_warn(&dd->pdev->dev, "Completion workers still active!\n"); } - blk_mq_stop_hw_queues(dd->queue); + blk_set_queue_dying(dd->queue); + set_bit(MTIP_DDF_REMOVE_PENDING_BIT, &dd->dd_flag); + /* Clean up the block layer. */ mtip_block_remove(dd); diff --git a/drivers/block/mtip32xx/mtip32xx.h b/drivers/block/mtip32xx/mtip32xx.h index 3274784008eb..7617888f7944 100644 --- a/drivers/block/mtip32xx/mtip32xx.h +++ b/drivers/block/mtip32xx/mtip32xx.h @@ -134,16 +134,24 @@ enum { MTIP_PF_EH_ACTIVE_BIT = 1, /* error handling */ MTIP_PF_SE_ACTIVE_BIT = 2, /* secure erase */ MTIP_PF_DM_ACTIVE_BIT = 3, /* download microcde */ + MTIP_PF_TO_ACTIVE_BIT = 9, /* timeout handling */ MTIP_PF_PAUSE_IO = ((1 << MTIP_PF_IC_ACTIVE_BIT) | (1 << MTIP_PF_EH_ACTIVE_BIT) | (1 << MTIP_PF_SE_ACTIVE_BIT) | - (1 << MTIP_PF_DM_ACTIVE_BIT)), + (1 << MTIP_PF_DM_ACTIVE_BIT) | + (1 << MTIP_PF_TO_ACTIVE_BIT)), MTIP_PF_SVC_THD_ACTIVE_BIT = 4, MTIP_PF_ISSUE_CMDS_BIT = 5, MTIP_PF_REBUILD_BIT = 6, MTIP_PF_SVC_THD_STOP_BIT = 8, + MTIP_PF_SVC_THD_WORK = ((1 << MTIP_PF_EH_ACTIVE_BIT) | + (1 << MTIP_PF_ISSUE_CMDS_BIT) | + (1 << MTIP_PF_REBUILD_BIT) | + (1 << MTIP_PF_SVC_THD_STOP_BIT) | + (1 << MTIP_PF_TO_ACTIVE_BIT)), + /* below are bit numbers in 'dd_flag' defined in driver_data */ MTIP_DDF_SEC_LOCK_BIT = 0, MTIP_DDF_REMOVE_PENDING_BIT = 1, @@ -153,6 +161,7 @@ enum { MTIP_DDF_RESUME_BIT = 6, MTIP_DDF_INIT_DONE_BIT = 7, MTIP_DDF_REBUILD_FAILED_BIT = 8, + MTIP_DDF_REMOVAL_BIT = 9, MTIP_DDF_STOP_IO = ((1 << MTIP_DDF_REMOVE_PENDING_BIT) | (1 << MTIP_DDF_SEC_LOCK_BIT) | diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 93b3f99b6865..8f1ce6d57a08 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -618,8 +618,8 @@ static void nbd_request_handler(struct request_queue *q) req, req->cmd_type); if (unlikely(!nbd->sock)) { - dev_err(disk_to_dev(nbd->disk), - "Attempted send on closed socket\n"); + dev_err_ratelimited(disk_to_dev(nbd->disk), + "Attempted send on closed socket\n"); req->errors++; nbd_end_request(nbd, req); spin_lock_irq(q->queue_lock); diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c index 562b5a4ca7b7..78a39f736c64 100644 --- a/drivers/block/paride/pd.c +++ b/drivers/block/paride/pd.c @@ -126,7 +126,7 @@ */ #include -static bool verbose = 0; +static int verbose = 0; static int major = PD_MAJOR; static char *name = PD_NAME; static int cluster = 64; @@ -161,7 +161,7 @@ enum {D_PRT, D_PRO, D_UNI, D_MOD, D_GEO, D_SBY, D_DLY, D_SLV}; static DEFINE_MUTEX(pd_mutex); static DEFINE_SPINLOCK(pd_lock); -module_param(verbose, bool, 0); +module_param(verbose, int, 0); module_param(major, int, 0); module_param(name, charp, 0); module_param(cluster, int, 0); diff --git a/drivers/block/paride/pt.c b/drivers/block/paride/pt.c index 1740d75e8a32..216a94fed5b4 100644 --- a/drivers/block/paride/pt.c +++ b/drivers/block/paride/pt.c @@ -117,7 +117,7 @@ */ -static bool verbose = 0; +static int verbose = 0; static int major = PT_MAJOR; static char *name = PT_NAME; static int disable = 0; @@ -152,7 +152,7 @@ static int (*drives[4])[6] = {&drive0, &drive1, &drive2, &drive3}; #include -module_param(verbose, bool, 0); +module_param(verbose, int, 0); module_param(major, int, 0); module_param(name, charp, 0); module_param_array(drive0, int, NULL, 0); diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 81ea69fee7ca..fbdddd6f94b8 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -1955,7 +1955,7 @@ static struct ceph_osd_request *rbd_osd_req_create( osdc = &rbd_dev->rbd_client->client->osdc; osd_req = ceph_osdc_alloc_request(osdc, snapc, num_ops, false, - GFP_ATOMIC); + GFP_NOIO); if (!osd_req) return NULL; /* ENOMEM */ @@ -2004,7 +2004,7 @@ rbd_osd_req_create_copyup(struct rbd_obj_request *obj_request) rbd_dev = img_request->rbd_dev; osdc = &rbd_dev->rbd_client->client->osdc; osd_req = ceph_osdc_alloc_request(osdc, snapc, num_osd_ops, - false, GFP_ATOMIC); + false, GFP_NOIO); if (!osd_req) return NULL; /* ENOMEM */ @@ -2506,7 +2506,7 @@ static int rbd_img_request_fill(struct rbd_img_request *img_request, bio_chain_clone_range(&bio_list, &bio_offset, clone_size, - GFP_ATOMIC); + GFP_NOIO); if (!obj_request->bio_list) goto out_unwind; } else if (type == OBJ_REQUEST_PAGES) { diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c index 5cb13ca3a3ac..c53617752b93 100644 --- a/drivers/block/zram/zcomp.c +++ b/drivers/block/zram/zcomp.c @@ -76,7 +76,7 @@ static void zcomp_strm_free(struct zcomp *comp, struct zcomp_strm *zstrm) */ static struct zcomp_strm *zcomp_strm_alloc(struct zcomp *comp) { - struct zcomp_strm *zstrm = kmalloc(sizeof(*zstrm), GFP_KERNEL); + struct zcomp_strm *zstrm = kmalloc(sizeof(*zstrm), GFP_NOIO); if (!zstrm) return NULL; @@ -85,7 +85,7 @@ static struct zcomp_strm *zcomp_strm_alloc(struct zcomp *comp) * allocate 2 pages. 1 for compressed data, plus 1 extra for the * case when compressed size is larger than the original one */ - zstrm->buffer = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, 1); + zstrm->buffer = (void *)__get_free_pages(GFP_NOIO | __GFP_ZERO, 1); if (!zstrm->private || !zstrm->buffer) { zcomp_strm_free(comp, zstrm); zstrm = NULL; diff --git a/drivers/block/zram/zcomp_lz4.c b/drivers/block/zram/zcomp_lz4.c index f2afb7e988c3..dd6083124276 100644 --- a/drivers/block/zram/zcomp_lz4.c +++ b/drivers/block/zram/zcomp_lz4.c @@ -10,17 +10,36 @@ #include #include #include +#include +#include #include "zcomp_lz4.h" static void *zcomp_lz4_create(void) { - return kzalloc(LZ4_MEM_COMPRESS, GFP_KERNEL); + void *ret; + + /* + * This function can be called in swapout/fs write path + * so we can't use GFP_FS|IO. And it assumes we already + * have at least one stream in zram initialization so we + * don't do best effort to allocate more stream in here. + * A default stream will work well without further multiple + * streams. That's why we use NORETRY | NOWARN. + */ + ret = kzalloc(LZ4_MEM_COMPRESS, GFP_NOIO | __GFP_NORETRY | + __GFP_NOWARN); + if (!ret) + ret = __vmalloc(LZ4_MEM_COMPRESS, + GFP_NOIO | __GFP_NORETRY | __GFP_NOWARN | + __GFP_ZERO | __GFP_HIGHMEM, + PAGE_KERNEL); + return ret; } static void zcomp_lz4_destroy(void *private) { - kfree(private); + kvfree(private); } static int zcomp_lz4_compress(const unsigned char *src, unsigned char *dst, diff --git a/drivers/block/zram/zcomp_lzo.c b/drivers/block/zram/zcomp_lzo.c index da1bc47d588e..edc549920fa0 100644 --- a/drivers/block/zram/zcomp_lzo.c +++ b/drivers/block/zram/zcomp_lzo.c @@ -10,17 +10,36 @@ #include #include #include +#include +#include #include "zcomp_lzo.h" static void *lzo_create(void) { - return kzalloc(LZO1X_MEM_COMPRESS, GFP_KERNEL); + void *ret; + + /* + * This function can be called in swapout/fs write path + * so we can't use GFP_FS|IO. And it assumes we already + * have at least one stream in zram initialization so we + * don't do best effort to allocate more stream in here. + * A default stream will work well without further multiple + * streams. That's why we use NORETRY | NOWARN. + */ + ret = kzalloc(LZO1X_MEM_COMPRESS, GFP_NOIO | __GFP_NORETRY | + __GFP_NOWARN); + if (!ret) + ret = __vmalloc(LZO1X_MEM_COMPRESS, + GFP_NOIO | __GFP_NORETRY | __GFP_NOWARN | + __GFP_ZERO | __GFP_HIGHMEM, + PAGE_KERNEL); + return ret; } static void lzo_destroy(void *private) { - kfree(private); + kvfree(private); } static int lzo_compress(const unsigned char *src, unsigned char *dst, diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 47915d736f8d..370c2f76016d 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1325,7 +1325,6 @@ static int zram_remove(struct zram *zram) pr_info("Removed device: %s\n", zram->disk->disk_name); - idr_remove(&zram_index_idr, zram->disk->first_minor); blk_cleanup_queue(zram->disk->queue); del_gendisk(zram->disk); put_disk(zram->disk); @@ -1367,10 +1366,12 @@ static ssize_t hot_remove_store(struct class *class, mutex_lock(&zram_index_mutex); zram = idr_find(&zram_index_idr, dev_id); - if (zram) + if (zram) { ret = zram_remove(zram); - else + idr_remove(&zram_index_idr, dev_id); + } else { ret = -ENODEV; + } mutex_unlock(&zram_index_mutex); return ret ? ret : count; diff --git a/drivers/bluetooth/ath3k.c b/drivers/bluetooth/ath3k.c index fa893c3ec408..0beaa52df66b 100644 --- a/drivers/bluetooth/ath3k.c +++ b/drivers/bluetooth/ath3k.c @@ -82,6 +82,7 @@ static const struct usb_device_id ath3k_table[] = { { USB_DEVICE(0x0489, 0xe05f) }, { USB_DEVICE(0x0489, 0xe076) }, { USB_DEVICE(0x0489, 0xe078) }, + { USB_DEVICE(0x0489, 0xe095) }, { USB_DEVICE(0x04c5, 0x1330) }, { USB_DEVICE(0x04CA, 0x3004) }, { USB_DEVICE(0x04CA, 0x3005) }, @@ -92,6 +93,7 @@ static const struct usb_device_id ath3k_table[] = { { USB_DEVICE(0x04CA, 0x300d) }, { USB_DEVICE(0x04CA, 0x300f) }, { USB_DEVICE(0x04CA, 0x3010) }, + { USB_DEVICE(0x04CA, 0x3014) }, { USB_DEVICE(0x0930, 0x0219) }, { USB_DEVICE(0x0930, 0x021c) }, { USB_DEVICE(0x0930, 0x0220) }, @@ -113,10 +115,12 @@ static const struct usb_device_id ath3k_table[] = { { USB_DEVICE(0x13d3, 0x3362) }, { USB_DEVICE(0x13d3, 0x3375) }, { USB_DEVICE(0x13d3, 0x3393) }, + { USB_DEVICE(0x13d3, 0x3395) }, { USB_DEVICE(0x13d3, 0x3402) }, { USB_DEVICE(0x13d3, 0x3408) }, { USB_DEVICE(0x13d3, 0x3423) }, { USB_DEVICE(0x13d3, 0x3432) }, + { USB_DEVICE(0x13d3, 0x3472) }, { USB_DEVICE(0x13d3, 0x3474) }, /* Atheros AR5BBU12 with sflash firmware */ @@ -144,6 +148,7 @@ static const struct usb_device_id ath3k_blist_tbl[] = { { USB_DEVICE(0x0489, 0xe05f), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0489, 0xe076), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0489, 0xe078), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0489, 0xe095), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04c5, 0x1330), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3004), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3005), .driver_info = BTUSB_ATH3012 }, @@ -154,6 +159,7 @@ static const struct usb_device_id ath3k_blist_tbl[] = { { USB_DEVICE(0x04ca, 0x300d), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x300f), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3010), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x04ca, 0x3014), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0930, 0x021c), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0930, 0x0220), .driver_info = BTUSB_ATH3012 }, @@ -175,10 +181,12 @@ static const struct usb_device_id ath3k_blist_tbl[] = { { USB_DEVICE(0x13d3, 0x3362), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3375), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3393), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x13d3, 0x3395), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3402), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3408), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3423), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3432), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x13d3, 0x3472), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3474), .driver_info = BTUSB_ATH3012 }, /* Atheros AR5BBU22 with sflash firmware */ diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 92f0ee388f9e..79107597a594 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -153,6 +153,10 @@ static const struct usb_device_id btusb_table[] = { { USB_VENDOR_AND_INTERFACE_INFO(0x13d3, 0xff, 0x01, 0x01), .driver_info = BTUSB_BCM_PATCHRAM }, + /* Toshiba Corp - Broadcom based */ + { USB_VENDOR_AND_INTERFACE_INFO(0x0930, 0xff, 0x01, 0x01), + .driver_info = BTUSB_BCM_PATCHRAM }, + /* Intel Bluetooth USB Bootloader (RAM module) */ { USB_DEVICE(0x8087, 0x0a5a), .driver_info = BTUSB_INTEL_BOOT | BTUSB_BROKEN_ISOC }, @@ -192,6 +196,7 @@ static const struct usb_device_id blacklist_table[] = { { USB_DEVICE(0x0489, 0xe05f), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0489, 0xe076), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0489, 0xe078), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0489, 0xe095), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04c5, 0x1330), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3004), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3005), .driver_info = BTUSB_ATH3012 }, @@ -202,6 +207,7 @@ static const struct usb_device_id blacklist_table[] = { { USB_DEVICE(0x04ca, 0x300d), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x300f), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3010), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x04ca, 0x3014), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0930, 0x021c), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0930, 0x0220), .driver_info = BTUSB_ATH3012 }, @@ -223,10 +229,12 @@ static const struct usb_device_id blacklist_table[] = { { USB_DEVICE(0x13d3, 0x3362), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3375), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3393), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x13d3, 0x3395), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3402), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3408), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3423), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3432), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x13d3, 0x3472), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3474), .driver_info = BTUSB_ATH3012 }, /* Atheros AR5BBU12 with sflash firmware */ diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c index ed888e302bc3..597b2d16b775 100644 --- a/drivers/bluetooth/hci_vhci.c +++ b/drivers/bluetooth/hci_vhci.c @@ -50,6 +50,7 @@ struct vhci_data { wait_queue_head_t read_wait; struct sk_buff_head readq; + struct mutex open_mutex; struct delayed_work open_timeout; }; @@ -87,12 +88,15 @@ static int vhci_send_frame(struct hci_dev *hdev, struct sk_buff *skb) return 0; } -static int vhci_create_device(struct vhci_data *data, __u8 opcode) +static int __vhci_create_device(struct vhci_data *data, __u8 opcode) { struct hci_dev *hdev; struct sk_buff *skb; __u8 dev_type; + if (data->hdev) + return -EBADFD; + /* bits 0-1 are dev_type (BR/EDR or AMP) */ dev_type = opcode & 0x03; @@ -151,6 +155,17 @@ static int vhci_create_device(struct vhci_data *data, __u8 opcode) return 0; } +static int vhci_create_device(struct vhci_data *data, __u8 opcode) +{ + int err; + + mutex_lock(&data->open_mutex); + err = __vhci_create_device(data, opcode); + mutex_unlock(&data->open_mutex); + + return err; +} + static inline ssize_t vhci_get_user(struct vhci_data *data, struct iov_iter *from) { @@ -189,11 +204,6 @@ static inline ssize_t vhci_get_user(struct vhci_data *data, break; case HCI_VENDOR_PKT: - if (data->hdev) { - kfree_skb(skb); - return -EBADFD; - } - cancel_delayed_work_sync(&data->open_timeout); opcode = *((__u8 *) skb->data); @@ -320,6 +330,7 @@ static int vhci_open(struct inode *inode, struct file *file) skb_queue_head_init(&data->readq); init_waitqueue_head(&data->read_wait); + mutex_init(&data->open_mutex); INIT_DELAYED_WORK(&data->open_timeout, vhci_open_timeout); file->private_data = data; @@ -333,15 +344,18 @@ static int vhci_open(struct inode *inode, struct file *file) static int vhci_release(struct inode *inode, struct file *file) { struct vhci_data *data = file->private_data; - struct hci_dev *hdev = data->hdev; + struct hci_dev *hdev; cancel_delayed_work_sync(&data->open_timeout); + hdev = data->hdev; + if (hdev) { hci_unregister_dev(hdev); hci_free_dev(hdev); } + skb_queue_purge(&data->readq); file->private_data = NULL; kfree(data); diff --git a/drivers/bus/imx-weim.c b/drivers/bus/imx-weim.c index e98d15eaa799..1827fc4d15c1 100644 --- a/drivers/bus/imx-weim.c +++ b/drivers/bus/imx-weim.c @@ -150,7 +150,7 @@ static int __init weim_parse_dt(struct platform_device *pdev, return ret; } - for_each_child_of_node(pdev->dev.of_node, child) { + for_each_available_child_of_node(pdev->dev.of_node, child) { if (!child->name) continue; diff --git a/drivers/char/hw_random/exynos-rng.c b/drivers/char/hw_random/exynos-rng.c index 30cf4623184f..aa30af5f0f2b 100644 --- a/drivers/char/hw_random/exynos-rng.c +++ b/drivers/char/hw_random/exynos-rng.c @@ -89,6 +89,7 @@ static int exynos_read(struct hwrng *rng, void *buf, struct exynos_rng, rng); u32 *data = buf; int retry = 100; + int ret = 4; pm_runtime_get_sync(exynos_rng->dev); @@ -97,17 +98,20 @@ static int exynos_read(struct hwrng *rng, void *buf, while (!(exynos_rng_readl(exynos_rng, EXYNOS_PRNG_STATUS_OFFSET) & PRNG_DONE) && --retry) cpu_relax(); - if (!retry) - return -ETIMEDOUT; + if (!retry) { + ret = -ETIMEDOUT; + goto out; + } exynos_rng_writel(exynos_rng, PRNG_DONE, EXYNOS_PRNG_STATUS_OFFSET); *data = exynos_rng_readl(exynos_rng, EXYNOS_PRNG_OUT1_OFFSET); +out: pm_runtime_mark_last_busy(exynos_rng->dev); pm_runtime_put_sync_autosuspend(exynos_rng->dev); - return 4; + return ret; } static int exynos_rng_probe(struct platform_device *pdev) diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c index e3536da05c88..a084a4751fa9 100644 --- a/drivers/char/ipmi/ipmi_msghandler.c +++ b/drivers/char/ipmi/ipmi_msghandler.c @@ -3819,6 +3819,7 @@ static void handle_new_recv_msgs(ipmi_smi_t intf) while (!list_empty(&intf->waiting_rcv_msgs)) { smi_msg = list_entry(intf->waiting_rcv_msgs.next, struct ipmi_smi_msg, link); + list_del(&smi_msg->link); if (!run_to_completion) spin_unlock_irqrestore(&intf->waiting_rcv_msgs_lock, flags); @@ -3828,11 +3829,14 @@ static void handle_new_recv_msgs(ipmi_smi_t intf) if (rv > 0) { /* * To preserve message order, quit if we - * can't handle a message. + * can't handle a message. Add the message + * back at the head, this is safe because this + * tasklet is the only thing that pulls the + * messages. */ + list_add(&smi_msg->link, &intf->waiting_rcv_msgs); break; } else { - list_del(&smi_msg->link); if (rv == 0) /* Message handled */ ipmi_free_smi_msg(smi_msg); diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c index 45cc39aabeee..252142524ff2 100644 --- a/drivers/char/tpm/tpm-chip.c +++ b/drivers/char/tpm/tpm-chip.c @@ -136,11 +136,13 @@ struct tpm_chip *tpmm_chip_alloc(struct device *dev, chip->cdev.owner = chip->pdev->driver->owner; chip->cdev.kobj.parent = &chip->dev.kobj; + devm_add_action(dev, (void (*)(void *)) put_device, &chip->dev); + return chip; } EXPORT_SYMBOL_GPL(tpmm_chip_alloc); -static int tpm_dev_add_device(struct tpm_chip *chip) +static int tpm_add_char_device(struct tpm_chip *chip) { int rc; @@ -151,7 +153,6 @@ static int tpm_dev_add_device(struct tpm_chip *chip) chip->devname, MAJOR(chip->dev.devt), MINOR(chip->dev.devt), rc); - device_unregister(&chip->dev); return rc; } @@ -162,16 +163,17 @@ static int tpm_dev_add_device(struct tpm_chip *chip) chip->devname, MAJOR(chip->dev.devt), MINOR(chip->dev.devt), rc); + cdev_del(&chip->cdev); return rc; } return rc; } -static void tpm_dev_del_device(struct tpm_chip *chip) +static void tpm_del_char_device(struct tpm_chip *chip) { cdev_del(&chip->cdev); - device_unregister(&chip->dev); + device_del(&chip->dev); } static int tpm1_chip_register(struct tpm_chip *chip) @@ -222,7 +224,7 @@ int tpm_chip_register(struct tpm_chip *chip) tpm_add_ppi(chip); - rc = tpm_dev_add_device(chip); + rc = tpm_add_char_device(chip); if (rc) goto out_err; @@ -274,6 +276,6 @@ void tpm_chip_unregister(struct tpm_chip *chip) sysfs_remove_link(&chip->pdev->kobj, "ppi"); tpm1_chip_unregister(chip); - tpm_dev_del_device(chip); + tpm_del_char_device(chip); } EXPORT_SYMBOL_GPL(tpm_chip_unregister); diff --git a/drivers/char/tpm/tpm_crb.c b/drivers/char/tpm/tpm_crb.c index 4bb9727c1047..61e64293b765 100644 --- a/drivers/char/tpm/tpm_crb.c +++ b/drivers/char/tpm/tpm_crb.c @@ -310,11 +310,11 @@ static int crb_acpi_remove(struct acpi_device *device) struct device *dev = &device->dev; struct tpm_chip *chip = dev_get_drvdata(dev); - tpm_chip_unregister(chip); - if (chip->flags & TPM_CHIP_FLAG_TPM2) tpm2_shutdown(chip, TPM2_SU_CLEAR); + tpm_chip_unregister(chip); + return 0; } diff --git a/drivers/char/tpm/tpm_eventlog.c b/drivers/char/tpm/tpm_eventlog.c index bd72fb04225e..4e6940acf639 100644 --- a/drivers/char/tpm/tpm_eventlog.c +++ b/drivers/char/tpm/tpm_eventlog.c @@ -232,7 +232,7 @@ static int tpm_binary_bios_measurements_show(struct seq_file *m, void *v) { struct tcpa_event *event = v; struct tcpa_event temp_event; - char *tempPtr; + char *temp_ptr; int i; memcpy(&temp_event, event, sizeof(struct tcpa_event)); @@ -242,10 +242,16 @@ static int tpm_binary_bios_measurements_show(struct seq_file *m, void *v) temp_event.event_type = do_endian_conversion(event->event_type); temp_event.event_size = do_endian_conversion(event->event_size); - tempPtr = (char *)&temp_event; + temp_ptr = (char *) &temp_event; - for (i = 0; i < sizeof(struct tcpa_event) + temp_event.event_size; i++) - seq_putc(m, tempPtr[i]); + for (i = 0; i < (sizeof(struct tcpa_event) - 1) ; i++) + seq_putc(m, temp_ptr[i]); + + temp_ptr = (char *) v; + + for (i = (sizeof(struct tcpa_event) - 1); + i < (sizeof(struct tcpa_event) + temp_event.event_size); i++) + seq_putc(m, temp_ptr[i]); return 0; diff --git a/drivers/clk/at91/clk-h32mx.c b/drivers/clk/at91/clk-h32mx.c index 61566bcefa53..a165230e7eda 100644 --- a/drivers/clk/at91/clk-h32mx.c +++ b/drivers/clk/at91/clk-h32mx.c @@ -116,7 +116,7 @@ void __init of_sama5d4_clk_h32mx_setup(struct device_node *np, h32mxclk->pmc = pmc; clk = clk_register(NULL, &h32mxclk->hw); - if (!clk) { + if (IS_ERR(clk)) { kfree(h32mxclk); return; } diff --git a/drivers/clk/bcm/clk-bcm2835.c b/drivers/clk/bcm/clk-bcm2835.c index 39bf5820297e..6029313aa995 100644 --- a/drivers/clk/bcm/clk-bcm2835.c +++ b/drivers/clk/bcm/clk-bcm2835.c @@ -890,8 +890,14 @@ static void bcm2835_pll_off(struct clk_hw *hw) struct bcm2835_cprman *cprman = pll->cprman; const struct bcm2835_pll_data *data = pll->data; - cprman_write(cprman, data->cm_ctrl_reg, CM_PLL_ANARST); - cprman_write(cprman, data->a2w_ctrl_reg, A2W_PLL_CTRL_PWRDN); + spin_lock(&cprman->regs_lock); + cprman_write(cprman, data->cm_ctrl_reg, + cprman_read(cprman, data->cm_ctrl_reg) | + CM_PLL_ANARST); + cprman_write(cprman, data->a2w_ctrl_reg, + cprman_read(cprman, data->a2w_ctrl_reg) | + A2W_PLL_CTRL_PWRDN); + spin_unlock(&cprman->regs_lock); } static int bcm2835_pll_on(struct clk_hw *hw) @@ -901,6 +907,10 @@ static int bcm2835_pll_on(struct clk_hw *hw) const struct bcm2835_pll_data *data = pll->data; ktime_t timeout; + cprman_write(cprman, data->a2w_ctrl_reg, + cprman_read(cprman, data->a2w_ctrl_reg) & + ~A2W_PLL_CTRL_PWRDN); + /* Take the PLL out of reset. */ cprman_write(cprman, data->cm_ctrl_reg, cprman_read(cprman, data->cm_ctrl_reg) & ~CM_PLL_ANARST); @@ -1068,10 +1078,12 @@ static void bcm2835_pll_divider_off(struct clk_hw *hw) struct bcm2835_cprman *cprman = divider->cprman; const struct bcm2835_pll_divider_data *data = divider->data; + spin_lock(&cprman->regs_lock); cprman_write(cprman, data->cm_reg, (cprman_read(cprman, data->cm_reg) & ~data->load_mask) | data->hold_mask); cprman_write(cprman, data->a2w_reg, A2W_PLL_CHANNEL_DISABLE); + spin_unlock(&cprman->regs_lock); } static int bcm2835_pll_divider_on(struct clk_hw *hw) @@ -1080,12 +1092,14 @@ static int bcm2835_pll_divider_on(struct clk_hw *hw) struct bcm2835_cprman *cprman = divider->cprman; const struct bcm2835_pll_divider_data *data = divider->data; + spin_lock(&cprman->regs_lock); cprman_write(cprman, data->a2w_reg, cprman_read(cprman, data->a2w_reg) & ~A2W_PLL_CHANNEL_DISABLE); cprman_write(cprman, data->cm_reg, cprman_read(cprman, data->cm_reg) & ~data->hold_mask); + spin_unlock(&cprman->regs_lock); return 0; } @@ -1097,13 +1111,15 @@ static int bcm2835_pll_divider_set_rate(struct clk_hw *hw, struct bcm2835_pll_divider *divider = bcm2835_pll_divider_from_hw(hw); struct bcm2835_cprman *cprman = divider->cprman; const struct bcm2835_pll_divider_data *data = divider->data; - u32 cm; - int ret; + u32 cm, div, max_div = 1 << A2W_PLL_DIV_BITS; - ret = clk_divider_ops.set_rate(hw, rate, parent_rate); - if (ret) - return ret; + div = DIV_ROUND_UP_ULL(parent_rate, rate); + div = min(div, max_div); + if (div == max_div) + div = 0; + + cprman_write(cprman, data->a2w_reg, div); cm = cprman_read(cprman, data->cm_reg); cprman_write(cprman, data->cm_reg, cm | data->load_mask); cprman_write(cprman, data->cm_reg, cm & ~data->load_mask); @@ -1165,8 +1181,9 @@ static u32 bcm2835_clock_choose_div(struct clk_hw *hw, div &= ~unused_frac_mask; } - /* Clamp to the limits. */ - div = max(div, unused_frac_mask + 1); + /* clamp to min divider of 1 */ + div = max_t(u32, div, 1 << CM_DIV_FRAC_BITS); + /* clamp to the highest possible fractional divider */ div = min_t(u32, div, GENMASK(data->int_bits + CM_DIV_FRAC_BITS - 1, CM_DIV_FRAC_BITS - data->frac_bits)); diff --git a/drivers/clk/clk-divider.c b/drivers/clk/clk-divider.c index 3ace102a2a0a..bbf206e3da0d 100644 --- a/drivers/clk/clk-divider.c +++ b/drivers/clk/clk-divider.c @@ -422,6 +422,12 @@ const struct clk_ops clk_divider_ops = { }; EXPORT_SYMBOL_GPL(clk_divider_ops); +const struct clk_ops clk_divider_ro_ops = { + .recalc_rate = clk_divider_recalc_rate, + .round_rate = clk_divider_round_rate, +}; +EXPORT_SYMBOL_GPL(clk_divider_ro_ops); + static struct clk *_register_divider(struct device *dev, const char *name, const char *parent_name, unsigned long flags, void __iomem *reg, u8 shift, u8 width, @@ -445,7 +451,10 @@ static struct clk *_register_divider(struct device *dev, const char *name, return ERR_PTR(-ENOMEM); init.name = name; - init.ops = &clk_divider_ops; + if (clk_divider_flags & CLK_DIVIDER_READ_ONLY) + init.ops = &clk_divider_ro_ops; + else + init.ops = &clk_divider_ops; init.flags = flags | CLK_IS_BASIC; init.parent_names = (parent_name ? &parent_name: NULL); init.num_parents = (parent_name ? 1 : 0); diff --git a/drivers/clk/imx/clk-imx35.c b/drivers/clk/imx/clk-imx35.c index a71d24cb4c06..b0978d3b83e2 100644 --- a/drivers/clk/imx/clk-imx35.c +++ b/drivers/clk/imx/clk-imx35.c @@ -66,7 +66,7 @@ static const char *std_sel[] = {"ppll", "arm"}; static const char *ipg_per_sel[] = {"ahb_per_div", "arm_per_div"}; enum mx35_clks { - ckih, ckil, mpll, ppll, mpll_075, arm, hsp, hsp_div, hsp_sel, ahb, ipg, + ckih, mpll, ppll, mpll_075, arm, hsp, hsp_div, hsp_sel, ahb, ipg, arm_per_div, ahb_per_div, ipg_per, uart_sel, uart_div, esdhc_sel, esdhc1_div, esdhc2_div, esdhc3_div, spdif_sel, spdif_div_pre, spdif_div_post, ssi_sel, ssi1_div_pre, ssi1_div_post, ssi2_div_pre, @@ -79,7 +79,7 @@ enum mx35_clks { rtc_gate, rtic_gate, scc_gate, sdma_gate, spba_gate, spdif_gate, ssi1_gate, ssi2_gate, uart1_gate, uart2_gate, uart3_gate, usbotg_gate, wdog_gate, max_gate, admux_gate, csi_gate, csi_div, csi_sel, iim_gate, - gpu2d_gate, clk_max + gpu2d_gate, ckil, clk_max }; static struct clk *clk[clk_max]; diff --git a/drivers/clk/meson/clkc.c b/drivers/clk/meson/clkc.c index c83ae1367abc..d920d410b51d 100644 --- a/drivers/clk/meson/clkc.c +++ b/drivers/clk/meson/clkc.c @@ -198,7 +198,7 @@ meson_clk_register_fixed_rate(const struct clk_conf *clk_conf, } void __init meson_clk_register_clks(const struct clk_conf *clk_confs, - size_t nr_confs, + unsigned int nr_confs, void __iomem *clk_base) { unsigned int i; diff --git a/drivers/clk/nxp/clk-lpc18xx-ccu.c b/drivers/clk/nxp/clk-lpc18xx-ccu.c index 13aabbb3acbe..558da89555af 100644 --- a/drivers/clk/nxp/clk-lpc18xx-ccu.c +++ b/drivers/clk/nxp/clk-lpc18xx-ccu.c @@ -222,7 +222,7 @@ static void lpc18xx_ccu_register_branch_gate_div(struct lpc18xx_clk_branch *bran div->width = 1; div_hw = &div->hw; - div_ops = &clk_divider_ops; + div_ops = &clk_divider_ro_ops; } branch->gate.reg = branch->offset + reg_base; diff --git a/drivers/clk/qcom/gcc-msm8916.c b/drivers/clk/qcom/gcc-msm8916.c index d0a0313d6bef..2e7f03d50f4e 100644 --- a/drivers/clk/qcom/gcc-msm8916.c +++ b/drivers/clk/qcom/gcc-msm8916.c @@ -2346,6 +2346,7 @@ static struct clk_branch gcc_crypto_ahb_clk = { "pcnoc_bfdcd_clk_src", }, .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -2381,6 +2382,7 @@ static struct clk_branch gcc_crypto_clk = { "crypto_clk_src", }, .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, diff --git a/drivers/clk/qcom/gcc-msm8960.c b/drivers/clk/qcom/gcc-msm8960.c index 66c18bc97857..bdc4b2d07a23 100644 --- a/drivers/clk/qcom/gcc-msm8960.c +++ b/drivers/clk/qcom/gcc-msm8960.c @@ -2753,7 +2753,7 @@ static struct clk_rcg ce3_src = { }, .freq_tbl = clk_tbl_ce3, .clkr = { - .enable_reg = 0x2c08, + .enable_reg = 0x36c0, .enable_mask = BIT(7), .hw.init = &(struct clk_init_data){ .name = "ce3_src", @@ -2769,7 +2769,7 @@ static struct clk_branch ce3_core_clk = { .halt_reg = 0x2fdc, .halt_bit = 5, .clkr = { - .enable_reg = 0x36c4, + .enable_reg = 0x36cc, .enable_mask = BIT(4), .hw.init = &(struct clk_init_data){ .name = "ce3_core_clk", diff --git a/drivers/clk/rockchip/clk-rk3188.c b/drivers/clk/rockchip/clk-rk3188.c index abb47608713b..fe728f8dcbe4 100644 --- a/drivers/clk/rockchip/clk-rk3188.c +++ b/drivers/clk/rockchip/clk-rk3188.c @@ -718,6 +718,7 @@ static const char *const rk3188_critical_clocks[] __initconst = { "hclk_peri", "pclk_cpu", "pclk_peri", + "hclk_cpubus" }; static void __init rk3188_common_clk_init(struct device_node *np) diff --git a/drivers/clk/rockchip/clk-rk3368.c b/drivers/clk/rockchip/clk-rk3368.c index 7e6b783e6eee..1b148694b633 100644 --- a/drivers/clk/rockchip/clk-rk3368.c +++ b/drivers/clk/rockchip/clk-rk3368.c @@ -165,7 +165,7 @@ static const struct rockchip_cpuclk_reg_data rk3368_cpuclkb_data = { .core_reg = RK3368_CLKSEL_CON(0), .div_core_shift = 0, .div_core_mask = 0x1f, - .mux_core_shift = 15, + .mux_core_shift = 7, }; static const struct rockchip_cpuclk_reg_data rk3368_cpuclkl_data = { @@ -218,29 +218,29 @@ static const struct rockchip_cpuclk_reg_data rk3368_cpuclkl_data = { } static struct rockchip_cpuclk_rate_table rk3368_cpuclkb_rates[] __initdata = { - RK3368_CPUCLKB_RATE(1512000000, 2, 6, 6), - RK3368_CPUCLKB_RATE(1488000000, 2, 5, 5), - RK3368_CPUCLKB_RATE(1416000000, 2, 5, 5), - RK3368_CPUCLKB_RATE(1200000000, 2, 4, 4), - RK3368_CPUCLKB_RATE(1008000000, 2, 4, 4), - RK3368_CPUCLKB_RATE( 816000000, 2, 3, 3), - RK3368_CPUCLKB_RATE( 696000000, 2, 3, 3), - RK3368_CPUCLKB_RATE( 600000000, 2, 2, 2), - RK3368_CPUCLKB_RATE( 408000000, 2, 2, 2), - RK3368_CPUCLKB_RATE( 312000000, 2, 2, 2), + RK3368_CPUCLKB_RATE(1512000000, 1, 5, 5), + RK3368_CPUCLKB_RATE(1488000000, 1, 4, 4), + RK3368_CPUCLKB_RATE(1416000000, 1, 4, 4), + RK3368_CPUCLKB_RATE(1200000000, 1, 3, 3), + RK3368_CPUCLKB_RATE(1008000000, 1, 3, 3), + RK3368_CPUCLKB_RATE( 816000000, 1, 2, 2), + RK3368_CPUCLKB_RATE( 696000000, 1, 2, 2), + RK3368_CPUCLKB_RATE( 600000000, 1, 1, 1), + RK3368_CPUCLKB_RATE( 408000000, 1, 1, 1), + RK3368_CPUCLKB_RATE( 312000000, 1, 1, 1), }; static struct rockchip_cpuclk_rate_table rk3368_cpuclkl_rates[] __initdata = { - RK3368_CPUCLKL_RATE(1512000000, 2, 7, 7), - RK3368_CPUCLKL_RATE(1488000000, 2, 6, 6), - RK3368_CPUCLKL_RATE(1416000000, 2, 6, 6), - RK3368_CPUCLKL_RATE(1200000000, 2, 5, 5), - RK3368_CPUCLKL_RATE(1008000000, 2, 5, 5), - RK3368_CPUCLKL_RATE( 816000000, 2, 4, 4), - RK3368_CPUCLKL_RATE( 696000000, 2, 3, 3), - RK3368_CPUCLKL_RATE( 600000000, 2, 3, 3), - RK3368_CPUCLKL_RATE( 408000000, 2, 2, 2), - RK3368_CPUCLKL_RATE( 312000000, 2, 2, 2), + RK3368_CPUCLKL_RATE(1512000000, 1, 6, 6), + RK3368_CPUCLKL_RATE(1488000000, 1, 5, 5), + RK3368_CPUCLKL_RATE(1416000000, 1, 5, 5), + RK3368_CPUCLKL_RATE(1200000000, 1, 4, 4), + RK3368_CPUCLKL_RATE(1008000000, 1, 4, 4), + RK3368_CPUCLKL_RATE( 816000000, 1, 3, 3), + RK3368_CPUCLKL_RATE( 696000000, 1, 2, 2), + RK3368_CPUCLKL_RATE( 600000000, 1, 2, 2), + RK3368_CPUCLKL_RATE( 408000000, 1, 1, 1), + RK3368_CPUCLKL_RATE( 312000000, 1, 1, 1), }; static struct rockchip_clk_branch rk3368_clk_branches[] __initdata = { @@ -384,10 +384,10 @@ static struct rockchip_clk_branch rk3368_clk_branches[] __initdata = { * Clock-Architecture Diagram 3 */ - COMPOSITE(0, "aclk_vepu", mux_pll_src_cpll_gpll_usb_p, 0, + COMPOSITE(0, "aclk_vepu", mux_pll_src_cpll_gpll_npll_usb_p, 0, RK3368_CLKSEL_CON(15), 6, 2, MFLAGS, 0, 5, DFLAGS, RK3368_CLKGATE_CON(4), 6, GFLAGS), - COMPOSITE(0, "aclk_vdpu", mux_pll_src_cpll_gpll_usb_p, 0, + COMPOSITE(0, "aclk_vdpu", mux_pll_src_cpll_gpll_npll_usb_p, 0, RK3368_CLKSEL_CON(15), 14, 2, MFLAGS, 8, 5, DFLAGS, RK3368_CLKGATE_CON(4), 7, GFLAGS), @@ -442,7 +442,7 @@ static struct rockchip_clk_branch rk3368_clk_branches[] __initdata = { GATE(SCLK_HDMI_HDCP, "sclk_hdmi_hdcp", "xin24m", 0, RK3368_CLKGATE_CON(4), 13, GFLAGS), GATE(SCLK_HDMI_CEC, "sclk_hdmi_cec", "xin32k", 0, - RK3368_CLKGATE_CON(5), 12, GFLAGS), + RK3368_CLKGATE_CON(4), 12, GFLAGS), COMPOSITE_NODIV(0, "vip_src", mux_pll_src_cpll_gpll_p, 0, RK3368_CLKSEL_CON(21), 15, 1, MFLAGS, diff --git a/drivers/clk/rockchip/clk.c b/drivers/clk/rockchip/clk.c index be6c7fd8315d..9b6c8188efac 100644 --- a/drivers/clk/rockchip/clk.c +++ b/drivers/clk/rockchip/clk.c @@ -70,7 +70,7 @@ static struct clk *rockchip_clk_register_branch(const char *name, if (gate_offset >= 0) { gate = kzalloc(sizeof(*gate), GFP_KERNEL); if (!gate) - return ERR_PTR(-ENOMEM); + goto err_gate; gate->flags = gate_flags; gate->reg = base + gate_offset; @@ -82,7 +82,7 @@ static struct clk *rockchip_clk_register_branch(const char *name, if (div_width > 0) { div = kzalloc(sizeof(*div), GFP_KERNEL); if (!div) - return ERR_PTR(-ENOMEM); + goto err_div; div->flags = div_flags; div->reg = base + muxdiv_offset; @@ -90,7 +90,9 @@ static struct clk *rockchip_clk_register_branch(const char *name, div->width = div_width; div->lock = lock; div->table = div_table; - div_ops = &clk_divider_ops; + div_ops = (div_flags & CLK_DIVIDER_READ_ONLY) + ? &clk_divider_ro_ops + : &clk_divider_ops; } clk = clk_register_composite(NULL, name, parent_names, num_parents, @@ -100,6 +102,11 @@ static struct clk *rockchip_clk_register_branch(const char *name, flags); return clk; +err_div: + kfree(gate); +err_gate: + kfree(mux); + return ERR_PTR(-ENOMEM); } static struct clk *rockchip_clk_register_frac_branch(const char *name, diff --git a/drivers/clk/samsung/clk-cpu.c b/drivers/clk/samsung/clk-cpu.c index 2fe37f708dc7..813003d6ce09 100644 --- a/drivers/clk/samsung/clk-cpu.c +++ b/drivers/clk/samsung/clk-cpu.c @@ -148,6 +148,7 @@ static int exynos_cpuclk_pre_rate_change(struct clk_notifier_data *ndata, unsigned long alt_prate = clk_get_rate(cpuclk->alt_parent); unsigned long alt_div = 0, alt_div_mask = DIV_MASK; unsigned long div0, div1 = 0, mux_reg; + unsigned long flags; /* find out the divider values to use for clock data */ while ((cfg_data->prate * 1000) != ndata->new_rate) { @@ -156,7 +157,7 @@ static int exynos_cpuclk_pre_rate_change(struct clk_notifier_data *ndata, cfg_data++; } - spin_lock(cpuclk->lock); + spin_lock_irqsave(cpuclk->lock, flags); /* * For the selected PLL clock frequency, get the pre-defined divider @@ -212,7 +213,7 @@ static int exynos_cpuclk_pre_rate_change(struct clk_notifier_data *ndata, DIV_MASK_ALL); } - spin_unlock(cpuclk->lock); + spin_unlock_irqrestore(cpuclk->lock, flags); return 0; } @@ -223,6 +224,7 @@ static int exynos_cpuclk_post_rate_change(struct clk_notifier_data *ndata, const struct exynos_cpuclk_cfg_data *cfg_data = cpuclk->cfg; unsigned long div = 0, div_mask = DIV_MASK; unsigned long mux_reg; + unsigned long flags; /* find out the divider values to use for clock data */ if (cpuclk->flags & CLK_CPU_NEEDS_DEBUG_ALT_DIV) { @@ -233,7 +235,7 @@ static int exynos_cpuclk_post_rate_change(struct clk_notifier_data *ndata, } } - spin_lock(cpuclk->lock); + spin_lock_irqsave(cpuclk->lock, flags); /* select mout_apll as the alternate parent */ mux_reg = readl(base + E4210_SRC_CPU); @@ -246,7 +248,7 @@ static int exynos_cpuclk_post_rate_change(struct clk_notifier_data *ndata, } exynos_set_safe_div(base, div, div_mask); - spin_unlock(cpuclk->lock); + spin_unlock_irqrestore(cpuclk->lock, flags); return 0; } diff --git a/drivers/clk/versatile/clk-sp810.c b/drivers/clk/versatile/clk-sp810.c index a1cdef6b0f90..897c36c1754a 100644 --- a/drivers/clk/versatile/clk-sp810.c +++ b/drivers/clk/versatile/clk-sp810.c @@ -92,6 +92,7 @@ static void __init clk_sp810_of_setup(struct device_node *node) int num = ARRAY_SIZE(parent_names); char name[12]; struct clk_init_data init; + static int instance; int i; bool deprecated; @@ -118,7 +119,7 @@ static void __init clk_sp810_of_setup(struct device_node *node) deprecated = !of_find_property(node, "assigned-clock-parents", NULL); for (i = 0; i < ARRAY_SIZE(sp810->timerclken); i++) { - snprintf(name, ARRAY_SIZE(name), "timerclken%d", i); + snprintf(name, sizeof(name), "sp810_%d_%d", instance, i); sp810->timerclken[i].sp810 = sp810; sp810->timerclken[i].channel = i; @@ -139,5 +140,6 @@ static void __init clk_sp810_of_setup(struct device_node *node) } of_clk_add_provider(node, clk_sp810_timerclken_of_get, sp810); + instance++; } CLK_OF_DECLARE(sp810, "arm,sp810", clk_sp810_of_setup); diff --git a/drivers/clocksource/tcb_clksrc.c b/drivers/clocksource/tcb_clksrc.c index 6ee91401918e..4da2af9694a2 100644 --- a/drivers/clocksource/tcb_clksrc.c +++ b/drivers/clocksource/tcb_clksrc.c @@ -98,7 +98,8 @@ static int tc_shutdown(struct clock_event_device *d) __raw_writel(0xff, regs + ATMEL_TC_REG(2, IDR)); __raw_writel(ATMEL_TC_CLKDIS, regs + ATMEL_TC_REG(2, CCR)); - clk_disable(tcd->clk); + if (!clockevent_state_detached(d)) + clk_disable(tcd->clk); return 0; } diff --git a/drivers/clocksource/vt8500_timer.c b/drivers/clocksource/vt8500_timer.c index a92e94b40b5b..dfc3bb410b00 100644 --- a/drivers/clocksource/vt8500_timer.c +++ b/drivers/clocksource/vt8500_timer.c @@ -50,6 +50,8 @@ #define msecs_to_loops(t) (loops_per_jiffy / 1000 * HZ * t) +#define MIN_OSCR_DELTA 16 + static void __iomem *regbase; static cycle_t vt8500_timer_read(struct clocksource *cs) @@ -80,7 +82,7 @@ static int vt8500_timer_set_next_event(unsigned long cycles, cpu_relax(); writel((unsigned long)alarm, regbase + TIMER_MATCH_VAL); - if ((signed)(alarm - clocksource.read(&clocksource)) <= 16) + if ((signed)(alarm - clocksource.read(&clocksource)) <= MIN_OSCR_DELTA) return -ETIME; writel(1, regbase + TIMER_IER_VAL); @@ -151,7 +153,7 @@ static void __init vt8500_timer_init(struct device_node *np) pr_err("%s: setup_irq failed for %s\n", __func__, clockevent.name); clockevents_config_and_register(&clockevent, VT8500_TIMER_HZ, - 4, 0xf0000000); + MIN_OSCR_DELTA * 2, 0xf0000000); } CLOCKSOURCE_OF_DECLARE(vt8500, "via,vt8500-timer", vt8500_timer_init); diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c index b260576ddb12..d994b0f652d3 100644 --- a/drivers/cpufreq/cpufreq_governor.c +++ b/drivers/cpufreq/cpufreq_governor.c @@ -356,16 +356,18 @@ static int cpufreq_governor_init(struct cpufreq_policy *policy, if (!have_governor_per_policy()) cdata->gdbs_data = dbs_data; + policy->governor_data = dbs_data; + ret = sysfs_create_group(get_governor_parent_kobj(policy), get_sysfs_attr(dbs_data)); if (ret) goto reset_gdbs_data; - policy->governor_data = dbs_data; - return 0; reset_gdbs_data: + policy->governor_data = NULL; + if (!have_governor_per_policy()) cdata->gdbs_data = NULL; cdata->exit(dbs_data, !policy->governor->initialized); @@ -386,16 +388,19 @@ static int cpufreq_governor_exit(struct cpufreq_policy *policy, if (!cdbs->shared || cdbs->shared->policy) return -EBUSY; - policy->governor_data = NULL; if (!--dbs_data->usage_count) { sysfs_remove_group(get_governor_parent_kobj(policy), get_sysfs_attr(dbs_data)); + policy->governor_data = NULL; + if (!have_governor_per_policy()) cdata->gdbs_data = NULL; cdata->exit(dbs_data, policy->governor->initialized == 1); kfree(dbs_data); + } else { + policy->governor_data = NULL; } free_common_dbs_info(policy, cdata); diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 98fb8821382d..f53b02a6bc05 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -667,6 +667,11 @@ static int core_get_max_pstate(void) if (err) goto skip_tar; + /* For level 1 and 2, bits[23:16] contain the ratio */ + if (tdp_ctrl) + tdp_ratio >>= 16; + + tdp_ratio &= 0xff; /* ratios are only 8 bits long */ if (tdp_ratio - 1 == tar) { max_pstate = tar; pr_debug("max_pstate=TAC %x\n", max_pstate); diff --git a/drivers/cpufreq/pxa2xx-cpufreq.c b/drivers/cpufreq/pxa2xx-cpufreq.c index 1d99c97defa9..096377232747 100644 --- a/drivers/cpufreq/pxa2xx-cpufreq.c +++ b/drivers/cpufreq/pxa2xx-cpufreq.c @@ -202,7 +202,7 @@ static void __init pxa_cpufreq_init_voltages(void) } } #else -static int pxa_cpufreq_change_voltage(struct pxa_freqs *pxa_freq) +static int pxa_cpufreq_change_voltage(const struct pxa_freqs *pxa_freq) { return 0; } diff --git a/drivers/cpuidle/cpuidle-arm.c b/drivers/cpuidle/cpuidle-arm.c index 545069d5fdfb..e342565e8715 100644 --- a/drivers/cpuidle/cpuidle-arm.c +++ b/drivers/cpuidle/cpuidle-arm.c @@ -50,7 +50,7 @@ static int arm_enter_idle_state(struct cpuidle_device *dev, * call the CPU ops suspend protocol with idle index as a * parameter. */ - arm_cpuidle_suspend(idx); + ret = arm_cpuidle_suspend(idx); cpu_pm_exit(); } diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 17a6dc0e2111..d40b2c077746 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -214,7 +214,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, tick_broadcast_exit(); } - if (!cpuidle_state_is_coupled(drv, entered_state)) + if (!cpuidle_state_is_coupled(drv, index)) local_irq_enable(); diff = ktime_to_us(ktime_sub(time_end, time_start)); @@ -433,6 +433,8 @@ static void __cpuidle_unregister_device(struct cpuidle_device *dev) list_del(&dev->device_list); per_cpu(cpuidle_devices, dev->cpu) = NULL; module_put(drv->owner); + + dev->registered = 0; } static void __cpuidle_device_init(struct cpuidle_device *dev) diff --git a/drivers/crypto/atmel-aes.c b/drivers/crypto/atmel-aes.c index fb16d812c8f5..1dffb13e5c2f 100644 --- a/drivers/crypto/atmel-aes.c +++ b/drivers/crypto/atmel-aes.c @@ -1396,9 +1396,9 @@ static int atmel_aes_probe(struct platform_device *pdev) } aes_dd->io_base = devm_ioremap_resource(&pdev->dev, aes_res); - if (!aes_dd->io_base) { + if (IS_ERR(aes_dd->io_base)) { dev_err(dev, "can't ioremap\n"); - err = -ENOMEM; + err = PTR_ERR(aes_dd->io_base); goto res_err; } diff --git a/drivers/crypto/atmel-sha.c b/drivers/crypto/atmel-sha.c index 660d8c06540b..0dadb6332f0e 100644 --- a/drivers/crypto/atmel-sha.c +++ b/drivers/crypto/atmel-sha.c @@ -783,7 +783,7 @@ static void atmel_sha_finish_req(struct ahash_request *req, int err) dd->flags &= ~(SHA_FLAGS_BUSY | SHA_FLAGS_FINAL | SHA_FLAGS_CPU | SHA_FLAGS_DMA_READY | SHA_FLAGS_OUTPUT_READY); - clk_disable_unprepare(dd->iclk); + clk_disable(dd->iclk); if (req->base.complete) req->base.complete(&req->base, err); @@ -796,7 +796,7 @@ static int atmel_sha_hw_init(struct atmel_sha_dev *dd) { int err; - err = clk_prepare_enable(dd->iclk); + err = clk_enable(dd->iclk); if (err) return err; @@ -823,7 +823,7 @@ static void atmel_sha_hw_version_init(struct atmel_sha_dev *dd) dev_info(dd->dev, "version: 0x%x\n", dd->hw_version); - clk_disable_unprepare(dd->iclk); + clk_disable(dd->iclk); } static int atmel_sha_handle_queue(struct atmel_sha_dev *dd, @@ -1405,12 +1405,16 @@ static int atmel_sha_probe(struct platform_device *pdev) } sha_dd->io_base = devm_ioremap_resource(&pdev->dev, sha_res); - if (!sha_dd->io_base) { + if (IS_ERR(sha_dd->io_base)) { dev_err(dev, "can't ioremap\n"); - err = -ENOMEM; + err = PTR_ERR(sha_dd->io_base); goto res_err; } + err = clk_prepare(sha_dd->iclk); + if (err) + goto res_err; + atmel_sha_hw_version_init(sha_dd); atmel_sha_get_cap(sha_dd); @@ -1422,12 +1426,12 @@ static int atmel_sha_probe(struct platform_device *pdev) if (IS_ERR(pdata)) { dev_err(&pdev->dev, "platform data not available\n"); err = PTR_ERR(pdata); - goto res_err; + goto iclk_unprepare; } } if (!pdata->dma_slave) { err = -ENXIO; - goto res_err; + goto iclk_unprepare; } err = atmel_sha_dma_init(sha_dd, pdata); if (err) @@ -1458,6 +1462,8 @@ err_algs: if (sha_dd->caps.has_dma) atmel_sha_dma_cleanup(sha_dd); err_sha_dma: +iclk_unprepare: + clk_unprepare(sha_dd->iclk); res_err: tasklet_kill(&sha_dd->done_task); sha_dd_err: @@ -1484,12 +1490,7 @@ static int atmel_sha_remove(struct platform_device *pdev) if (sha_dd->caps.has_dma) atmel_sha_dma_cleanup(sha_dd); - iounmap(sha_dd->io_base); - - clk_put(sha_dd->iclk); - - if (sha_dd->irq >= 0) - free_irq(sha_dd->irq, sha_dd); + clk_unprepare(sha_dd->iclk); return 0; } diff --git a/drivers/crypto/atmel-tdes.c b/drivers/crypto/atmel-tdes.c index 2c7a628d0375..bf467d7be35c 100644 --- a/drivers/crypto/atmel-tdes.c +++ b/drivers/crypto/atmel-tdes.c @@ -1417,9 +1417,9 @@ static int atmel_tdes_probe(struct platform_device *pdev) } tdes_dd->io_base = devm_ioremap_resource(&pdev->dev, tdes_res); - if (!tdes_dd->io_base) { + if (IS_ERR(tdes_dd->io_base)) { dev_err(dev, "can't ioremap\n"); - err = -ENOMEM; + err = PTR_ERR(tdes_dd->io_base); goto res_err; } diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c index 8abb4bc548cc..69d4a1326fee 100644 --- a/drivers/crypto/caam/ctrl.c +++ b/drivers/crypto/caam/ctrl.c @@ -534,8 +534,8 @@ static int caam_probe(struct platform_device *pdev) * long pointers in master configuration register */ clrsetbits_32(&ctrl->mcr, MCFGR_AWCACHE_MASK, MCFGR_AWCACHE_CACH | - MCFGR_WDENABLE | (sizeof(dma_addr_t) == sizeof(u64) ? - MCFGR_LONG_PTR : 0)); + MCFGR_AWCACHE_BUFF | MCFGR_WDENABLE | + (sizeof(dma_addr_t) == sizeof(u64) ? MCFGR_LONG_PTR : 0)); /* * Read the Compile Time paramters and SCFGR to determine diff --git a/drivers/crypto/caam/jr.c b/drivers/crypto/caam/jr.c index f7e0d8d4c3da..8f50a02ff68d 100644 --- a/drivers/crypto/caam/jr.c +++ b/drivers/crypto/caam/jr.c @@ -248,7 +248,7 @@ static void caam_jr_dequeue(unsigned long devarg) struct device *caam_jr_alloc(void) { struct caam_drv_private_jr *jrpriv, *min_jrpriv = NULL; - struct device *dev = NULL; + struct device *dev = ERR_PTR(-ENODEV); int min_tfm_cnt = INT_MAX; int tfm_cnt; diff --git a/drivers/crypto/ccp/ccp-crypto-aes-cmac.c b/drivers/crypto/ccp/ccp-crypto-aes-cmac.c index d89f20c04266..60fc0fa26fd3 100644 --- a/drivers/crypto/ccp/ccp-crypto-aes-cmac.c +++ b/drivers/crypto/ccp/ccp-crypto-aes-cmac.c @@ -220,6 +220,42 @@ static int ccp_aes_cmac_digest(struct ahash_request *req) return ccp_aes_cmac_finup(req); } +static int ccp_aes_cmac_export(struct ahash_request *req, void *out) +{ + struct ccp_aes_cmac_req_ctx *rctx = ahash_request_ctx(req); + struct ccp_aes_cmac_exp_ctx state; + + /* Don't let anything leak to 'out' */ + memset(&state, 0, sizeof(state)); + + state.null_msg = rctx->null_msg; + memcpy(state.iv, rctx->iv, sizeof(state.iv)); + state.buf_count = rctx->buf_count; + memcpy(state.buf, rctx->buf, sizeof(state.buf)); + + /* 'out' may not be aligned so memcpy from local variable */ + memcpy(out, &state, sizeof(state)); + + return 0; +} + +static int ccp_aes_cmac_import(struct ahash_request *req, const void *in) +{ + struct ccp_aes_cmac_req_ctx *rctx = ahash_request_ctx(req); + struct ccp_aes_cmac_exp_ctx state; + + /* 'in' may not be aligned so memcpy to local variable */ + memcpy(&state, in, sizeof(state)); + + memset(rctx, 0, sizeof(*rctx)); + rctx->null_msg = state.null_msg; + memcpy(rctx->iv, state.iv, sizeof(rctx->iv)); + rctx->buf_count = state.buf_count; + memcpy(rctx->buf, state.buf, sizeof(rctx->buf)); + + return 0; +} + static int ccp_aes_cmac_setkey(struct crypto_ahash *tfm, const u8 *key, unsigned int key_len) { @@ -352,10 +388,13 @@ int ccp_register_aes_cmac_algs(struct list_head *head) alg->final = ccp_aes_cmac_final; alg->finup = ccp_aes_cmac_finup; alg->digest = ccp_aes_cmac_digest; + alg->export = ccp_aes_cmac_export; + alg->import = ccp_aes_cmac_import; alg->setkey = ccp_aes_cmac_setkey; halg = &alg->halg; halg->digestsize = AES_BLOCK_SIZE; + halg->statesize = sizeof(struct ccp_aes_cmac_exp_ctx); base = &halg->base; snprintf(base->cra_name, CRYPTO_MAX_ALG_NAME, "cmac(aes)"); diff --git a/drivers/crypto/ccp/ccp-crypto-aes-xts.c b/drivers/crypto/ccp/ccp-crypto-aes-xts.c index 52c7395cb8d8..0d0d4529ee36 100644 --- a/drivers/crypto/ccp/ccp-crypto-aes-xts.c +++ b/drivers/crypto/ccp/ccp-crypto-aes-xts.c @@ -122,6 +122,7 @@ static int ccp_aes_xts_crypt(struct ablkcipher_request *req, struct ccp_ctx *ctx = crypto_tfm_ctx(req->base.tfm); struct ccp_aes_req_ctx *rctx = ablkcipher_request_ctx(req); unsigned int unit; + u32 unit_size; int ret; if (!ctx->u.aes.key_len) @@ -133,11 +134,17 @@ static int ccp_aes_xts_crypt(struct ablkcipher_request *req, if (!req->info) return -EINVAL; - for (unit = 0; unit < ARRAY_SIZE(unit_size_map); unit++) - if (!(req->nbytes & (unit_size_map[unit].size - 1))) - break; + unit_size = CCP_XTS_AES_UNIT_SIZE__LAST; + if (req->nbytes <= unit_size_map[0].size) { + for (unit = 0; unit < ARRAY_SIZE(unit_size_map); unit++) { + if (!(req->nbytes & (unit_size_map[unit].size - 1))) { + unit_size = unit_size_map[unit].value; + break; + } + } + } - if ((unit_size_map[unit].value == CCP_XTS_AES_UNIT_SIZE__LAST) || + if ((unit_size == CCP_XTS_AES_UNIT_SIZE__LAST) || (ctx->u.aes.key_len != AES_KEYSIZE_128)) { /* Use the fallback to process the request for any * unsupported unit sizes or key sizes @@ -158,7 +165,7 @@ static int ccp_aes_xts_crypt(struct ablkcipher_request *req, rctx->cmd.engine = CCP_ENGINE_XTS_AES_128; rctx->cmd.u.xts.action = (encrypt) ? CCP_AES_ACTION_ENCRYPT : CCP_AES_ACTION_DECRYPT; - rctx->cmd.u.xts.unit_size = unit_size_map[unit].value; + rctx->cmd.u.xts.unit_size = unit_size; rctx->cmd.u.xts.key = &ctx->u.aes.key_sg; rctx->cmd.u.xts.key_len = ctx->u.aes.key_len; rctx->cmd.u.xts.iv = &rctx->iv_sg; diff --git a/drivers/crypto/ccp/ccp-crypto-sha.c b/drivers/crypto/ccp/ccp-crypto-sha.c index d14b3f28e010..ab9945f2cb7a 100644 --- a/drivers/crypto/ccp/ccp-crypto-sha.c +++ b/drivers/crypto/ccp/ccp-crypto-sha.c @@ -207,6 +207,46 @@ static int ccp_sha_digest(struct ahash_request *req) return ccp_sha_finup(req); } +static int ccp_sha_export(struct ahash_request *req, void *out) +{ + struct ccp_sha_req_ctx *rctx = ahash_request_ctx(req); + struct ccp_sha_exp_ctx state; + + /* Don't let anything leak to 'out' */ + memset(&state, 0, sizeof(state)); + + state.type = rctx->type; + state.msg_bits = rctx->msg_bits; + state.first = rctx->first; + memcpy(state.ctx, rctx->ctx, sizeof(state.ctx)); + state.buf_count = rctx->buf_count; + memcpy(state.buf, rctx->buf, sizeof(state.buf)); + + /* 'out' may not be aligned so memcpy from local variable */ + memcpy(out, &state, sizeof(state)); + + return 0; +} + +static int ccp_sha_import(struct ahash_request *req, const void *in) +{ + struct ccp_sha_req_ctx *rctx = ahash_request_ctx(req); + struct ccp_sha_exp_ctx state; + + /* 'in' may not be aligned so memcpy to local variable */ + memcpy(&state, in, sizeof(state)); + + memset(rctx, 0, sizeof(*rctx)); + rctx->type = state.type; + rctx->msg_bits = state.msg_bits; + rctx->first = state.first; + memcpy(rctx->ctx, state.ctx, sizeof(rctx->ctx)); + rctx->buf_count = state.buf_count; + memcpy(rctx->buf, state.buf, sizeof(rctx->buf)); + + return 0; +} + static int ccp_sha_setkey(struct crypto_ahash *tfm, const u8 *key, unsigned int key_len) { @@ -403,9 +443,12 @@ static int ccp_register_sha_alg(struct list_head *head, alg->final = ccp_sha_final; alg->finup = ccp_sha_finup; alg->digest = ccp_sha_digest; + alg->export = ccp_sha_export; + alg->import = ccp_sha_import; halg = &alg->halg; halg->digestsize = def->digest_size; + halg->statesize = sizeof(struct ccp_sha_exp_ctx); base = &halg->base; snprintf(base->cra_name, CRYPTO_MAX_ALG_NAME, "%s", def->name); diff --git a/drivers/crypto/ccp/ccp-crypto.h b/drivers/crypto/ccp/ccp-crypto.h index 76a96f0f44c6..a326ec20bfa8 100644 --- a/drivers/crypto/ccp/ccp-crypto.h +++ b/drivers/crypto/ccp/ccp-crypto.h @@ -129,6 +129,15 @@ struct ccp_aes_cmac_req_ctx { struct ccp_cmd cmd; }; +struct ccp_aes_cmac_exp_ctx { + unsigned int null_msg; + + u8 iv[AES_BLOCK_SIZE]; + + unsigned int buf_count; + u8 buf[AES_BLOCK_SIZE]; +}; + /***** SHA related defines *****/ #define MAX_SHA_CONTEXT_SIZE SHA256_DIGEST_SIZE #define MAX_SHA_BLOCK_SIZE SHA256_BLOCK_SIZE @@ -171,6 +180,19 @@ struct ccp_sha_req_ctx { struct ccp_cmd cmd; }; +struct ccp_sha_exp_ctx { + enum ccp_sha_type type; + + u64 msg_bits; + + unsigned int first; + + u8 ctx[MAX_SHA_CONTEXT_SIZE]; + + unsigned int buf_count; + u8 buf[MAX_SHA_BLOCK_SIZE]; +}; + /***** Common Context Structure *****/ struct ccp_ctx { int (*complete)(struct crypto_async_request *req, int ret); diff --git a/drivers/crypto/marvell/cesa.c b/drivers/crypto/marvell/cesa.c index 0643e3366e33..80239ae69527 100644 --- a/drivers/crypto/marvell/cesa.c +++ b/drivers/crypto/marvell/cesa.c @@ -306,7 +306,7 @@ static int mv_cesa_dev_dma_init(struct mv_cesa_dev *cesa) return -ENOMEM; dma->padding_pool = dmam_pool_create("cesa_padding", dev, 72, 1, 0); - if (!dma->cache_pool) + if (!dma->padding_pool) return -ENOMEM; cesa->dma = dma; @@ -420,7 +420,7 @@ static int mv_cesa_probe(struct platform_device *pdev) res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "regs"); cesa->regs = devm_ioremap_resource(dev, res); if (IS_ERR(cesa->regs)) - return -ENOMEM; + return PTR_ERR(cesa->regs); ret = mv_cesa_dev_dma_init(cesa); if (ret) diff --git a/drivers/crypto/qat/qat_common/Makefile b/drivers/crypto/qat/qat_common/Makefile index 9e9e196c6d51..45b5adaafa6f 100644 --- a/drivers/crypto/qat/qat_common/Makefile +++ b/drivers/crypto/qat/qat_common/Makefile @@ -2,6 +2,7 @@ $(obj)/qat_rsapubkey-asn1.o: $(obj)/qat_rsapubkey-asn1.c \ $(obj)/qat_rsapubkey-asn1.h $(obj)/qat_rsaprivkey-asn1.o: $(obj)/qat_rsaprivkey-asn1.c \ $(obj)/qat_rsaprivkey-asn1.h +$(obj)/qat_asym_algs.o: $(obj)/qat_rsapubkey-asn1.h $(obj)/qat_rsaprivkey-asn1.h clean-files += qat_rsapubkey-asn1.c qat_rsapubkey-asn1.h clean-files += qat_rsaprivkey-asn1.c qat_rsapvivkey-asn1.h diff --git a/drivers/crypto/qat/qat_common/adf_common_drv.h b/drivers/crypto/qat/qat_common/adf_common_drv.h index 3f76bd495bcb..aa1dbeaa9b49 100644 --- a/drivers/crypto/qat/qat_common/adf_common_drv.h +++ b/drivers/crypto/qat/qat_common/adf_common_drv.h @@ -227,6 +227,8 @@ void adf_disable_vf2pf_interrupts(struct adf_accel_dev *accel_dev, uint32_t vf_mask); void adf_enable_vf2pf_interrupts(struct adf_accel_dev *accel_dev, uint32_t vf_mask); +int adf_init_pf_wq(void); +void adf_exit_pf_wq(void); #else static inline int adf_sriov_configure(struct pci_dev *pdev, int numvfs) { @@ -236,5 +238,14 @@ static inline int adf_sriov_configure(struct pci_dev *pdev, int numvfs) static inline void adf_disable_sriov(struct adf_accel_dev *accel_dev) { } + +static inline int adf_init_pf_wq(void) +{ + return 0; +} + +static inline void adf_exit_pf_wq(void) +{ +} #endif #endif diff --git a/drivers/crypto/qat/qat_common/adf_ctl_drv.c b/drivers/crypto/qat/qat_common/adf_ctl_drv.c index 473d36d91644..e7480f373532 100644 --- a/drivers/crypto/qat/qat_common/adf_ctl_drv.c +++ b/drivers/crypto/qat/qat_common/adf_ctl_drv.c @@ -469,12 +469,17 @@ static int __init adf_register_ctl_device_driver(void) if (adf_init_aer()) goto err_aer; + if (adf_init_pf_wq()) + goto err_pf_wq; + if (qat_crypto_register()) goto err_crypto_register; return 0; err_crypto_register: + adf_exit_pf_wq(); +err_pf_wq: adf_exit_aer(); err_aer: adf_chr_drv_destroy(); @@ -487,6 +492,7 @@ static void __exit adf_unregister_ctl_device_driver(void) { adf_chr_drv_destroy(); adf_exit_aer(); + adf_exit_pf_wq(); qat_crypto_unregister(); adf_clean_vf_map(false); mutex_destroy(&adf_ctl_lock); diff --git a/drivers/crypto/qat/qat_common/adf_sriov.c b/drivers/crypto/qat/qat_common/adf_sriov.c index 1117a8b58280..38a0415e767d 100644 --- a/drivers/crypto/qat/qat_common/adf_sriov.c +++ b/drivers/crypto/qat/qat_common/adf_sriov.c @@ -119,11 +119,6 @@ static int adf_enable_sriov(struct adf_accel_dev *accel_dev) int i; u32 reg; - /* Workqueue for PF2VF responses */ - pf2vf_resp_wq = create_workqueue("qat_pf2vf_resp_wq"); - if (!pf2vf_resp_wq) - return -ENOMEM; - for (i = 0, vf_info = accel_dev->pf.vf_info; i < totalvfs; i++, vf_info++) { /* This ptr will be populated when VFs will be created */ @@ -216,11 +211,6 @@ void adf_disable_sriov(struct adf_accel_dev *accel_dev) kfree(accel_dev->pf.vf_info); accel_dev->pf.vf_info = NULL; - - if (pf2vf_resp_wq) { - destroy_workqueue(pf2vf_resp_wq); - pf2vf_resp_wq = NULL; - } } EXPORT_SYMBOL_GPL(adf_disable_sriov); @@ -304,3 +294,19 @@ int adf_sriov_configure(struct pci_dev *pdev, int numvfs) return numvfs; } EXPORT_SYMBOL_GPL(adf_sriov_configure); + +int __init adf_init_pf_wq(void) +{ + /* Workqueue for PF2VF responses */ + pf2vf_resp_wq = create_workqueue("qat_pf2vf_resp_wq"); + + return !pf2vf_resp_wq ? -ENOMEM : 0; +} + +void adf_exit_pf_wq(void) +{ + if (pf2vf_resp_wq) { + destroy_workqueue(pf2vf_resp_wq); + pf2vf_resp_wq = NULL; + } +} diff --git a/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c b/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c index a19ee127edca..e72fea737a0d 100644 --- a/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c +++ b/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c @@ -35,6 +35,7 @@ static int sun4i_ss_opti_poll(struct ablkcipher_request *areq) unsigned int todo; struct sg_mapping_iter mi, mo; unsigned int oi, oo; /* offset for in and out */ + unsigned long flags; if (areq->nbytes == 0) return 0; @@ -49,7 +50,7 @@ static int sun4i_ss_opti_poll(struct ablkcipher_request *areq) return -EINVAL; } - spin_lock_bh(&ss->slock); + spin_lock_irqsave(&ss->slock, flags); for (i = 0; i < op->keylen; i += 4) writel(*(op->key + i / 4), ss->base + SS_KEY0 + i); @@ -117,7 +118,7 @@ release_ss: sg_miter_stop(&mi); sg_miter_stop(&mo); writel(0, ss->base + SS_CTL); - spin_unlock_bh(&ss->slock); + spin_unlock_irqrestore(&ss->slock, flags); return err; } @@ -149,6 +150,7 @@ static int sun4i_ss_cipher_poll(struct ablkcipher_request *areq) unsigned int ob = 0; /* offset in buf */ unsigned int obo = 0; /* offset in bufo*/ unsigned int obl = 0; /* length of data in bufo */ + unsigned long flags; if (areq->nbytes == 0) return 0; @@ -181,7 +183,7 @@ static int sun4i_ss_cipher_poll(struct ablkcipher_request *areq) if (no_chunk == 1) return sun4i_ss_opti_poll(areq); - spin_lock_bh(&ss->slock); + spin_lock_irqsave(&ss->slock, flags); for (i = 0; i < op->keylen; i += 4) writel(*(op->key + i / 4), ss->base + SS_KEY0 + i); @@ -308,7 +310,7 @@ release_ss: sg_miter_stop(&mi); sg_miter_stop(&mo); writel(0, ss->base + SS_CTL); - spin_unlock_bh(&ss->slock); + spin_unlock_irqrestore(&ss->slock, flags); return err; } diff --git a/drivers/crypto/sunxi-ss/sun4i-ss-core.c b/drivers/crypto/sunxi-ss/sun4i-ss-core.c index eab6fe227fa0..107cd2a41cae 100644 --- a/drivers/crypto/sunxi-ss/sun4i-ss-core.c +++ b/drivers/crypto/sunxi-ss/sun4i-ss-core.c @@ -39,6 +39,7 @@ static struct sun4i_ss_alg_template ss_algs[] = { .import = sun4i_hash_import_md5, .halg = { .digestsize = MD5_DIGEST_SIZE, + .statesize = sizeof(struct md5_state), .base = { .cra_name = "md5", .cra_driver_name = "md5-sun4i-ss", @@ -66,6 +67,7 @@ static struct sun4i_ss_alg_template ss_algs[] = { .import = sun4i_hash_import_sha1, .halg = { .digestsize = SHA1_DIGEST_SIZE, + .statesize = sizeof(struct sha1_state), .base = { .cra_name = "sha1", .cra_driver_name = "sha1-sun4i-ss", diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c index b6f9f42e2985..9a8a18aafd5c 100644 --- a/drivers/crypto/talitos.c +++ b/drivers/crypto/talitos.c @@ -63,6 +63,14 @@ static void to_talitos_ptr(struct talitos_ptr *ptr, dma_addr_t dma_addr, ptr->eptr = upper_32_bits(dma_addr); } +static void copy_talitos_ptr(struct talitos_ptr *dst_ptr, + struct talitos_ptr *src_ptr, bool is_sec1) +{ + dst_ptr->ptr = src_ptr->ptr; + if (!is_sec1) + dst_ptr->eptr = src_ptr->eptr; +} + static void to_talitos_ptr_len(struct talitos_ptr *ptr, unsigned int len, bool is_sec1) { @@ -827,6 +835,16 @@ struct talitos_ahash_req_ctx { struct scatterlist *psrc; }; +struct talitos_export_state { + u32 hw_context[TALITOS_MDEU_MAX_CONTEXT_SIZE / sizeof(u32)]; + u8 buf[HASH_MAX_BLOCK_SIZE]; + unsigned int swinit; + unsigned int first; + unsigned int last; + unsigned int to_hash_later; + unsigned int nbuf; +}; + static int aead_setkey(struct crypto_aead *authenc, const u8 *key, unsigned int keylen) { @@ -1083,21 +1101,20 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq, sg_count = dma_map_sg(dev, areq->src, edesc->src_nents ?: 1, (areq->src == areq->dst) ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE); - /* hmac data */ desc->ptr[1].len = cpu_to_be16(areq->assoclen); if (sg_count > 1 && (ret = sg_to_link_tbl_offset(areq->src, sg_count, 0, areq->assoclen, &edesc->link_tbl[tbl_off])) > 1) { - tbl_off += ret; - to_talitos_ptr(&desc->ptr[1], edesc->dma_link_tbl + tbl_off * sizeof(struct talitos_ptr), 0); desc->ptr[1].j_extent = DESC_PTR_LNKTBL_JUMP; dma_sync_single_for_device(dev, edesc->dma_link_tbl, edesc->dma_len, DMA_BIDIRECTIONAL); + + tbl_off += ret; } else { to_talitos_ptr(&desc->ptr[1], sg_dma_address(areq->src), 0); desc->ptr[1].j_extent = 0; @@ -1126,11 +1143,13 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq, if (edesc->desc.hdr & DESC_HDR_MODE1_MDEU_CICV) sg_link_tbl_len += authsize; - if (sg_count > 1 && - (ret = sg_to_link_tbl_offset(areq->src, sg_count, areq->assoclen, - sg_link_tbl_len, - &edesc->link_tbl[tbl_off])) > 1) { - tbl_off += ret; + if (sg_count == 1) { + to_talitos_ptr(&desc->ptr[4], sg_dma_address(areq->src) + + areq->assoclen, 0); + } else if ((ret = sg_to_link_tbl_offset(areq->src, sg_count, + areq->assoclen, sg_link_tbl_len, + &edesc->link_tbl[tbl_off])) > + 1) { desc->ptr[4].j_extent |= DESC_PTR_LNKTBL_JUMP; to_talitos_ptr(&desc->ptr[4], edesc->dma_link_tbl + tbl_off * @@ -1138,8 +1157,10 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq, dma_sync_single_for_device(dev, edesc->dma_link_tbl, edesc->dma_len, DMA_BIDIRECTIONAL); - } else - to_talitos_ptr(&desc->ptr[4], sg_dma_address(areq->src), 0); + tbl_off += ret; + } else { + copy_talitos_ptr(&desc->ptr[4], &edesc->link_tbl[tbl_off], 0); + } /* cipher out */ desc->ptr[5].len = cpu_to_be16(cryptlen); @@ -1151,11 +1172,13 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq, edesc->icv_ool = false; - if (sg_count > 1 && - (sg_count = sg_to_link_tbl_offset(areq->dst, sg_count, + if (sg_count == 1) { + to_talitos_ptr(&desc->ptr[5], sg_dma_address(areq->dst) + + areq->assoclen, 0); + } else if ((sg_count = + sg_to_link_tbl_offset(areq->dst, sg_count, areq->assoclen, cryptlen, - &edesc->link_tbl[tbl_off])) > - 1) { + &edesc->link_tbl[tbl_off])) > 1) { struct talitos_ptr *tbl_ptr = &edesc->link_tbl[tbl_off]; to_talitos_ptr(&desc->ptr[5], edesc->dma_link_tbl + @@ -1178,8 +1201,9 @@ static int ipsec_esp(struct talitos_edesc *edesc, struct aead_request *areq, edesc->dma_len, DMA_BIDIRECTIONAL); edesc->icv_ool = true; - } else - to_talitos_ptr(&desc->ptr[5], sg_dma_address(areq->dst), 0); + } else { + copy_talitos_ptr(&desc->ptr[5], &edesc->link_tbl[tbl_off], 0); + } /* iv out */ map_single_talitos_ptr(dev, &desc->ptr[6], ivsize, ctx->iv, @@ -1940,6 +1964,46 @@ static int ahash_digest(struct ahash_request *areq) return ahash_process_req(areq, areq->nbytes); } +static int ahash_export(struct ahash_request *areq, void *out) +{ + struct talitos_ahash_req_ctx *req_ctx = ahash_request_ctx(areq); + struct talitos_export_state *export = out; + + memcpy(export->hw_context, req_ctx->hw_context, + req_ctx->hw_context_size); + memcpy(export->buf, req_ctx->buf, req_ctx->nbuf); + export->swinit = req_ctx->swinit; + export->first = req_ctx->first; + export->last = req_ctx->last; + export->to_hash_later = req_ctx->to_hash_later; + export->nbuf = req_ctx->nbuf; + + return 0; +} + +static int ahash_import(struct ahash_request *areq, const void *in) +{ + struct talitos_ahash_req_ctx *req_ctx = ahash_request_ctx(areq); + struct crypto_ahash *tfm = crypto_ahash_reqtfm(areq); + const struct talitos_export_state *export = in; + + memset(req_ctx, 0, sizeof(*req_ctx)); + req_ctx->hw_context_size = + (crypto_ahash_digestsize(tfm) <= SHA256_DIGEST_SIZE) + ? TALITOS_MDEU_CONTEXT_SIZE_MD5_SHA1_SHA256 + : TALITOS_MDEU_CONTEXT_SIZE_SHA384_SHA512; + memcpy(req_ctx->hw_context, export->hw_context, + req_ctx->hw_context_size); + memcpy(req_ctx->buf, export->buf, export->nbuf); + req_ctx->swinit = export->swinit; + req_ctx->first = export->first; + req_ctx->last = export->last; + req_ctx->to_hash_later = export->to_hash_later; + req_ctx->nbuf = export->nbuf; + + return 0; +} + struct keyhash_result { struct completion completion; int err; @@ -2334,6 +2398,7 @@ static struct talitos_alg_template driver_algs[] = { { .type = CRYPTO_ALG_TYPE_AHASH, .alg.hash = { .halg.digestsize = MD5_DIGEST_SIZE, + .halg.statesize = sizeof(struct talitos_export_state), .halg.base = { .cra_name = "md5", .cra_driver_name = "md5-talitos", @@ -2349,6 +2414,7 @@ static struct talitos_alg_template driver_algs[] = { { .type = CRYPTO_ALG_TYPE_AHASH, .alg.hash = { .halg.digestsize = SHA1_DIGEST_SIZE, + .halg.statesize = sizeof(struct talitos_export_state), .halg.base = { .cra_name = "sha1", .cra_driver_name = "sha1-talitos", @@ -2364,6 +2430,7 @@ static struct talitos_alg_template driver_algs[] = { { .type = CRYPTO_ALG_TYPE_AHASH, .alg.hash = { .halg.digestsize = SHA224_DIGEST_SIZE, + .halg.statesize = sizeof(struct talitos_export_state), .halg.base = { .cra_name = "sha224", .cra_driver_name = "sha224-talitos", @@ -2379,6 +2446,7 @@ static struct talitos_alg_template driver_algs[] = { { .type = CRYPTO_ALG_TYPE_AHASH, .alg.hash = { .halg.digestsize = SHA256_DIGEST_SIZE, + .halg.statesize = sizeof(struct talitos_export_state), .halg.base = { .cra_name = "sha256", .cra_driver_name = "sha256-talitos", @@ -2394,6 +2462,7 @@ static struct talitos_alg_template driver_algs[] = { { .type = CRYPTO_ALG_TYPE_AHASH, .alg.hash = { .halg.digestsize = SHA384_DIGEST_SIZE, + .halg.statesize = sizeof(struct talitos_export_state), .halg.base = { .cra_name = "sha384", .cra_driver_name = "sha384-talitos", @@ -2409,6 +2478,7 @@ static struct talitos_alg_template driver_algs[] = { { .type = CRYPTO_ALG_TYPE_AHASH, .alg.hash = { .halg.digestsize = SHA512_DIGEST_SIZE, + .halg.statesize = sizeof(struct talitos_export_state), .halg.base = { .cra_name = "sha512", .cra_driver_name = "sha512-talitos", @@ -2424,6 +2494,7 @@ static struct talitos_alg_template driver_algs[] = { { .type = CRYPTO_ALG_TYPE_AHASH, .alg.hash = { .halg.digestsize = MD5_DIGEST_SIZE, + .halg.statesize = sizeof(struct talitos_export_state), .halg.base = { .cra_name = "hmac(md5)", .cra_driver_name = "hmac-md5-talitos", @@ -2439,6 +2510,7 @@ static struct talitos_alg_template driver_algs[] = { { .type = CRYPTO_ALG_TYPE_AHASH, .alg.hash = { .halg.digestsize = SHA1_DIGEST_SIZE, + .halg.statesize = sizeof(struct talitos_export_state), .halg.base = { .cra_name = "hmac(sha1)", .cra_driver_name = "hmac-sha1-talitos", @@ -2454,6 +2526,7 @@ static struct talitos_alg_template driver_algs[] = { { .type = CRYPTO_ALG_TYPE_AHASH, .alg.hash = { .halg.digestsize = SHA224_DIGEST_SIZE, + .halg.statesize = sizeof(struct talitos_export_state), .halg.base = { .cra_name = "hmac(sha224)", .cra_driver_name = "hmac-sha224-talitos", @@ -2469,6 +2542,7 @@ static struct talitos_alg_template driver_algs[] = { { .type = CRYPTO_ALG_TYPE_AHASH, .alg.hash = { .halg.digestsize = SHA256_DIGEST_SIZE, + .halg.statesize = sizeof(struct talitos_export_state), .halg.base = { .cra_name = "hmac(sha256)", .cra_driver_name = "hmac-sha256-talitos", @@ -2484,6 +2558,7 @@ static struct talitos_alg_template driver_algs[] = { { .type = CRYPTO_ALG_TYPE_AHASH, .alg.hash = { .halg.digestsize = SHA384_DIGEST_SIZE, + .halg.statesize = sizeof(struct talitos_export_state), .halg.base = { .cra_name = "hmac(sha384)", .cra_driver_name = "hmac-sha384-talitos", @@ -2499,6 +2574,7 @@ static struct talitos_alg_template driver_algs[] = { { .type = CRYPTO_ALG_TYPE_AHASH, .alg.hash = { .halg.digestsize = SHA512_DIGEST_SIZE, + .halg.statesize = sizeof(struct talitos_export_state), .halg.base = { .cra_name = "hmac(sha512)", .cra_driver_name = "hmac-sha512-talitos", @@ -2519,21 +2595,11 @@ struct talitos_crypto_alg { struct talitos_alg_template algt; }; -static int talitos_cra_init(struct crypto_tfm *tfm) +static int talitos_init_common(struct talitos_ctx *ctx, + struct talitos_crypto_alg *talitos_alg) { - struct crypto_alg *alg = tfm->__crt_alg; - struct talitos_crypto_alg *talitos_alg; - struct talitos_ctx *ctx = crypto_tfm_ctx(tfm); struct talitos_private *priv; - if ((alg->cra_flags & CRYPTO_ALG_TYPE_MASK) == CRYPTO_ALG_TYPE_AHASH) - talitos_alg = container_of(__crypto_ahash_alg(alg), - struct talitos_crypto_alg, - algt.alg.hash); - else - talitos_alg = container_of(alg, struct talitos_crypto_alg, - algt.alg.crypto); - /* update context with ptr to dev */ ctx->dev = talitos_alg->dev; @@ -2551,10 +2617,33 @@ static int talitos_cra_init(struct crypto_tfm *tfm) return 0; } +static int talitos_cra_init(struct crypto_tfm *tfm) +{ + struct crypto_alg *alg = tfm->__crt_alg; + struct talitos_crypto_alg *talitos_alg; + struct talitos_ctx *ctx = crypto_tfm_ctx(tfm); + + if ((alg->cra_flags & CRYPTO_ALG_TYPE_MASK) == CRYPTO_ALG_TYPE_AHASH) + talitos_alg = container_of(__crypto_ahash_alg(alg), + struct talitos_crypto_alg, + algt.alg.hash); + else + talitos_alg = container_of(alg, struct talitos_crypto_alg, + algt.alg.crypto); + + return talitos_init_common(ctx, talitos_alg); +} + static int talitos_cra_init_aead(struct crypto_aead *tfm) { - talitos_cra_init(crypto_aead_tfm(tfm)); - return 0; + struct aead_alg *alg = crypto_aead_alg(tfm); + struct talitos_crypto_alg *talitos_alg; + struct talitos_ctx *ctx = crypto_aead_ctx(tfm); + + talitos_alg = container_of(alg, struct talitos_crypto_alg, + algt.alg.aead); + + return talitos_init_common(ctx, talitos_alg); } static int talitos_cra_init_ahash(struct crypto_tfm *tfm) @@ -2677,6 +2766,8 @@ static struct talitos_crypto_alg *talitos_alg_alloc(struct device *dev, t_alg->algt.alg.hash.finup = ahash_finup; t_alg->algt.alg.hash.digest = ahash_digest; t_alg->algt.alg.hash.setkey = ahash_setkey; + t_alg->algt.alg.hash.import = ahash_import; + t_alg->algt.alg.hash.export = ahash_export; if (!(priv->features & TALITOS_FTR_HMAC_OK) && !strncmp(alg->cra_name, "hmac", 4)) { diff --git a/drivers/crypto/ux500/cryp/cryp_core.c b/drivers/crypto/ux500/cryp/cryp_core.c index 4c243c1ffc7f..790f7cadc1ed 100644 --- a/drivers/crypto/ux500/cryp/cryp_core.c +++ b/drivers/crypto/ux500/cryp/cryp_core.c @@ -1440,9 +1440,9 @@ static int ux500_cryp_probe(struct platform_device *pdev) device_data->phybase = res->start; device_data->base = devm_ioremap_resource(dev, res); - if (!device_data->base) { + if (IS_ERR(device_data->base)) { dev_err(dev, "[%s]: ioremap failed!", __func__); - ret = -ENOMEM; + ret = PTR_ERR(device_data->base); goto out; } diff --git a/drivers/crypto/ux500/hash/hash_core.c b/drivers/crypto/ux500/hash/hash_core.c index f47d112041b2..cd4398498495 100644 --- a/drivers/crypto/ux500/hash/hash_core.c +++ b/drivers/crypto/ux500/hash/hash_core.c @@ -797,7 +797,7 @@ static int hash_process_data(struct hash_device_data *device_data, &device_data->state); memmove(req_ctx->state.buffer, device_data->state.buffer, - HASH_BLOCK_SIZE / sizeof(u32)); + HASH_BLOCK_SIZE); if (ret) { dev_err(device_data->dev, "%s: hash_resume_state() failed!\n", @@ -848,7 +848,7 @@ static int hash_process_data(struct hash_device_data *device_data, memmove(device_data->state.buffer, req_ctx->state.buffer, - HASH_BLOCK_SIZE / sizeof(u32)); + HASH_BLOCK_SIZE); if (ret) { dev_err(device_data->dev, "%s: hash_save_state() failed!\n", __func__); @@ -1675,9 +1675,9 @@ static int ux500_hash_probe(struct platform_device *pdev) device_data->phybase = res->start; device_data->base = devm_ioremap_resource(dev, res); - if (!device_data->base) { + if (IS_ERR(device_data->base)) { dev_err(dev, "%s: ioremap() failed!\n", __func__); - ret = -ENOMEM; + ret = PTR_ERR(device_data->base); goto out; } spin_lock_init(&device_data->ctx_lock); diff --git a/drivers/crypto/vmx/aes_cbc.c b/drivers/crypto/vmx/aes_cbc.c index 0b8fe2ec5315..f3801b983f42 100644 --- a/drivers/crypto/vmx/aes_cbc.c +++ b/drivers/crypto/vmx/aes_cbc.c @@ -182,7 +182,7 @@ struct crypto_alg p8_aes_cbc_alg = { .cra_name = "cbc(aes)", .cra_driver_name = "p8_aes_cbc", .cra_module = THIS_MODULE, - .cra_priority = 1000, + .cra_priority = 2000, .cra_type = &crypto_blkcipher_type, .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | CRYPTO_ALG_NEED_FALLBACK, .cra_alignmask = 0, diff --git a/drivers/crypto/vmx/aes_ctr.c b/drivers/crypto/vmx/aes_ctr.c index ee1306cd8f59..404a1b69a3ab 100644 --- a/drivers/crypto/vmx/aes_ctr.c +++ b/drivers/crypto/vmx/aes_ctr.c @@ -166,7 +166,7 @@ struct crypto_alg p8_aes_ctr_alg = { .cra_name = "ctr(aes)", .cra_driver_name = "p8_aes_ctr", .cra_module = THIS_MODULE, - .cra_priority = 1000, + .cra_priority = 2000, .cra_type = &crypto_blkcipher_type, .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | CRYPTO_ALG_NEED_FALLBACK, .cra_alignmask = 0, diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index 370c661c7d7b..02f9aa4ebe05 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -176,6 +176,7 @@ #define AT_XDMAC_MAX_CHAN 0x20 #define AT_XDMAC_MAX_CSIZE 16 /* 16 data */ #define AT_XDMAC_MAX_DWIDTH 8 /* 64 bits */ +#define AT_XDMAC_RESIDUE_MAX_RETRIES 5 #define AT_XDMAC_DMA_BUSWIDTHS\ (BIT(DMA_SLAVE_BUSWIDTH_UNDEFINED) |\ @@ -1383,8 +1384,8 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie, struct at_xdmac_desc *desc, *_desc; struct list_head *descs_list; enum dma_status ret; - int residue; - u32 cur_nda, mask, value; + int residue, retry; + u32 cur_nda, check_nda, cur_ubc, mask, value; u8 dwidth = 0; unsigned long flags; @@ -1421,7 +1422,42 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie, cpu_relax(); } + /* + * When processing the residue, we need to read two registers but we + * can't do it in an atomic way. AT_XDMAC_CNDA is used to find where + * we stand in the descriptor list and AT_XDMAC_CUBC is used + * to know how many data are remaining for the current descriptor. + * Since the dma channel is not paused to not loose data, between the + * AT_XDMAC_CNDA and AT_XDMAC_CUBC read, we may have change of + * descriptor. + * For that reason, after reading AT_XDMAC_CUBC, we check if we are + * still using the same descriptor by reading a second time + * AT_XDMAC_CNDA. If AT_XDMAC_CNDA has changed, it means we have to + * read again AT_XDMAC_CUBC. + * Memory barriers are used to ensure the read order of the registers. + * A max number of retries is set because unlikely it can never ends if + * we are transferring a lot of data with small buffers. + */ cur_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc; + rmb(); + cur_ubc = at_xdmac_chan_read(atchan, AT_XDMAC_CUBC); + for (retry = 0; retry < AT_XDMAC_RESIDUE_MAX_RETRIES; retry++) { + rmb(); + check_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc; + + if (likely(cur_nda == check_nda)) + break; + + cur_nda = check_nda; + rmb(); + cur_ubc = at_xdmac_chan_read(atchan, AT_XDMAC_CUBC); + } + + if (unlikely(retry >= AT_XDMAC_RESIDUE_MAX_RETRIES)) { + ret = DMA_ERROR; + goto spin_unlock; + } + /* * Remove size of all microblocks already transferred and the current * one. Then add the remaining size to transfer of the current @@ -1434,7 +1470,7 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie, if ((desc->lld.mbr_nda & 0xfffffffc) == cur_nda) break; } - residue += at_xdmac_chan_read(atchan, AT_XDMAC_CUBC) << dwidth; + residue += cur_ubc << dwidth; dma_set_residue(txstate, residue); @@ -1688,6 +1724,7 @@ static int at_xdmac_device_terminate_all(struct dma_chan *chan) list_for_each_entry_safe(desc, _desc, &atchan->xfers_list, xfer_node) at_xdmac_remove_xfer(atchan, desc); + clear_bit(AT_XDMAC_CHAN_IS_PAUSED, &atchan->status); clear_bit(AT_XDMAC_CHAN_IS_CYCLIC, &atchan->status); spin_unlock_irqrestore(&atchan->lock, flags); @@ -1820,6 +1857,8 @@ static int atmel_xdmac_resume(struct device *dev) atchan = to_at_xdmac_chan(chan); at_xdmac_chan_write(atchan, AT_XDMAC_CC, atchan->save_cc); if (at_xdmac_chan_is_cyclic(atchan)) { + if (at_xdmac_chan_is_paused(atchan)) + at_xdmac_device_resume(chan); at_xdmac_chan_write(atchan, AT_XDMAC_CNDA, atchan->save_cnda); at_xdmac_chan_write(atchan, AT_XDMAC_CNDC, atchan->save_cndc); at_xdmac_chan_write(atchan, AT_XDMAC_CIE, atchan->save_cim); diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c index 7067b6ddc1db..c66133b5e852 100644 --- a/drivers/dma/dw/core.c +++ b/drivers/dma/dw/core.c @@ -130,26 +130,14 @@ static void dwc_desc_put(struct dw_dma_chan *dwc, struct dw_desc *desc) static void dwc_initialize(struct dw_dma_chan *dwc) { struct dw_dma *dw = to_dw_dma(dwc->chan.device); - struct dw_dma_slave *dws = dwc->chan.private; u32 cfghi = DWC_CFGH_FIFO_MODE; u32 cfglo = DWC_CFGL_CH_PRIOR(dwc->priority); if (dwc->initialized == true) return; - if (dws) { - /* - * We need controller-specific data to set up slave - * transfers. - */ - BUG_ON(!dws->dma_dev || dws->dma_dev != dw->dma.dev); - - cfghi |= DWC_CFGH_DST_PER(dws->dst_id); - cfghi |= DWC_CFGH_SRC_PER(dws->src_id); - } else { - cfghi |= DWC_CFGH_DST_PER(dwc->dst_id); - cfghi |= DWC_CFGH_SRC_PER(dwc->src_id); - } + cfghi |= DWC_CFGH_DST_PER(dwc->dst_id); + cfghi |= DWC_CFGH_SRC_PER(dwc->src_id); channel_writel(dwc, CFG_LO, cfglo); channel_writel(dwc, CFG_HI, cfghi); @@ -536,16 +524,17 @@ EXPORT_SYMBOL(dw_dma_get_dst_addr); /* Called with dwc->lock held and all DMAC interrupts disabled */ static void dwc_handle_cyclic(struct dw_dma *dw, struct dw_dma_chan *dwc, - u32 status_err, u32 status_xfer) + u32 status_block, u32 status_err, u32 status_xfer) { unsigned long flags; - if (dwc->mask) { + if (status_block & dwc->mask) { void (*callback)(void *param); void *callback_param; dev_vdbg(chan2dev(&dwc->chan), "new cyclic period llp 0x%08x\n", channel_readl(dwc, LLP)); + dma_writel(dw, CLEAR.BLOCK, dwc->mask); callback = dwc->cdesc->period_callback; callback_param = dwc->cdesc->period_callback_param; @@ -577,6 +566,7 @@ static void dwc_handle_cyclic(struct dw_dma *dw, struct dw_dma_chan *dwc, channel_writel(dwc, CTL_LO, 0); channel_writel(dwc, CTL_HI, 0); + dma_writel(dw, CLEAR.BLOCK, dwc->mask); dma_writel(dw, CLEAR.ERROR, dwc->mask); dma_writel(dw, CLEAR.XFER, dwc->mask); @@ -585,6 +575,9 @@ static void dwc_handle_cyclic(struct dw_dma *dw, struct dw_dma_chan *dwc, spin_unlock_irqrestore(&dwc->lock, flags); } + + /* Re-enable interrupts */ + channel_set_bit(dw, MASK.BLOCK, dwc->mask); } /* ------------------------------------------------------------------------- */ @@ -593,10 +586,12 @@ static void dw_dma_tasklet(unsigned long data) { struct dw_dma *dw = (struct dw_dma *)data; struct dw_dma_chan *dwc; + u32 status_block; u32 status_xfer; u32 status_err; int i; + status_block = dma_readl(dw, RAW.BLOCK); status_xfer = dma_readl(dw, RAW.XFER); status_err = dma_readl(dw, RAW.ERROR); @@ -605,16 +600,15 @@ static void dw_dma_tasklet(unsigned long data) for (i = 0; i < dw->dma.chancnt; i++) { dwc = &dw->chan[i]; if (test_bit(DW_DMA_IS_CYCLIC, &dwc->flags)) - dwc_handle_cyclic(dw, dwc, status_err, status_xfer); + dwc_handle_cyclic(dw, dwc, status_block, status_err, + status_xfer); else if (status_err & (1 << i)) dwc_handle_error(dw, dwc); else if (status_xfer & (1 << i)) dwc_scan_descriptors(dw, dwc); } - /* - * Re-enable interrupts. - */ + /* Re-enable interrupts */ channel_set_bit(dw, MASK.XFER, dw->all_chan_mask); channel_set_bit(dw, MASK.ERROR, dw->all_chan_mask); } @@ -635,6 +629,7 @@ static irqreturn_t dw_dma_interrupt(int irq, void *dev_id) * softirq handler. */ channel_clear_bit(dw, MASK.XFER, dw->all_chan_mask); + channel_clear_bit(dw, MASK.BLOCK, dw->all_chan_mask); channel_clear_bit(dw, MASK.ERROR, dw->all_chan_mask); status = dma_readl(dw, STATUS_INT); @@ -645,6 +640,7 @@ static irqreturn_t dw_dma_interrupt(int irq, void *dev_id) /* Try to recover */ channel_clear_bit(dw, MASK.XFER, (1 << 8) - 1); + channel_clear_bit(dw, MASK.BLOCK, (1 << 8) - 1); channel_clear_bit(dw, MASK.SRC_TRAN, (1 << 8) - 1); channel_clear_bit(dw, MASK.DST_TRAN, (1 << 8) - 1); channel_clear_bit(dw, MASK.ERROR, (1 << 8) - 1); @@ -928,7 +924,7 @@ bool dw_dma_filter(struct dma_chan *chan, void *param) struct dw_dma_chan *dwc = to_dw_dma_chan(chan); struct dw_dma_slave *dws = param; - if (!dws || dws->dma_dev != chan->device->dev) + if (dws->dma_dev != chan->device->dev) return false; /* We have to copy data since dws can be temporary storage */ @@ -1111,6 +1107,7 @@ static void dw_dma_off(struct dw_dma *dw) dma_writel(dw, CFG, 0); channel_clear_bit(dw, MASK.XFER, dw->all_chan_mask); + channel_clear_bit(dw, MASK.BLOCK, dw->all_chan_mask); channel_clear_bit(dw, MASK.SRC_TRAN, dw->all_chan_mask); channel_clear_bit(dw, MASK.DST_TRAN, dw->all_chan_mask); channel_clear_bit(dw, MASK.ERROR, dw->all_chan_mask); @@ -1151,6 +1148,14 @@ static int dwc_alloc_chan_resources(struct dma_chan *chan) * doesn't mean what you think it means), and status writeback. */ + /* + * We need controller-specific data to set up slave transfers. + */ + if (chan->private && !dw_dma_filter(chan, chan->private)) { + dev_warn(chan2dev(chan), "Wrong controller-specific data\n"); + return -EINVAL; + } + /* Enable controller here if needed */ if (!dw->in_use) dw_dma_on(dw); @@ -1212,10 +1217,19 @@ static void dwc_free_chan_resources(struct dma_chan *chan) spin_lock_irqsave(&dwc->lock, flags); list_splice_init(&dwc->free_list, &list); dwc->descs_allocated = 0; + + /* Clear custom channel configuration */ + dwc->src_id = 0; + dwc->dst_id = 0; + + dwc->src_master = 0; + dwc->dst_master = 0; + dwc->initialized = false; /* Disable interrupts */ channel_clear_bit(dw, MASK.XFER, dwc->mask); + channel_clear_bit(dw, MASK.BLOCK, dwc->mask); channel_clear_bit(dw, MASK.ERROR, dwc->mask); spin_unlock_irqrestore(&dwc->lock, flags); @@ -1245,7 +1259,7 @@ static void dwc_free_chan_resources(struct dma_chan *chan) int dw_dma_cyclic_start(struct dma_chan *chan) { struct dw_dma_chan *dwc = to_dw_dma_chan(chan); - struct dw_dma *dw = to_dw_dma(dwc->chan.device); + struct dw_dma *dw = to_dw_dma(chan->device); unsigned long flags; if (!test_bit(DW_DMA_IS_CYCLIC, &dwc->flags)) { @@ -1255,25 +1269,10 @@ int dw_dma_cyclic_start(struct dma_chan *chan) spin_lock_irqsave(&dwc->lock, flags); - /* Assert channel is idle */ - if (dma_readl(dw, CH_EN) & dwc->mask) { - dev_err(chan2dev(&dwc->chan), - "%s: BUG: Attempted to start non-idle channel\n", - __func__); - dwc_dump_chan_regs(dwc); - spin_unlock_irqrestore(&dwc->lock, flags); - return -EBUSY; - } + /* Enable interrupts to perform cyclic transfer */ + channel_set_bit(dw, MASK.BLOCK, dwc->mask); - dma_writel(dw, CLEAR.ERROR, dwc->mask); - dma_writel(dw, CLEAR.XFER, dwc->mask); - - /* Setup DMAC channel registers */ - channel_writel(dwc, LLP, dwc->cdesc->desc[0]->txd.phys); - channel_writel(dwc, CTL_LO, DWC_CTLL_LLP_D_EN | DWC_CTLL_LLP_S_EN); - channel_writel(dwc, CTL_HI, 0); - - channel_set_bit(dw, CH_EN, dwc->mask); + dwc_dostart(dwc, dwc->cdesc->desc[0]); spin_unlock_irqrestore(&dwc->lock, flags); @@ -1479,6 +1478,7 @@ void dw_dma_cyclic_free(struct dma_chan *chan) dwc_chan_disable(dw, dwc); + dma_writel(dw, CLEAR.BLOCK, dwc->mask); dma_writel(dw, CLEAR.ERROR, dwc->mask); dma_writel(dw, CLEAR.XFER, dwc->mask); @@ -1567,9 +1567,6 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata) /* Force dma off, just in case */ dw_dma_off(dw); - /* Disable BLOCK interrupts as well */ - channel_clear_bit(dw, MASK.BLOCK, dw->all_chan_mask); - /* Create a pool of consistent memory blocks for hardware descriptors */ dw->desc_pool = dmam_pool_create("dw_dmac_desc_pool", chip->dev, sizeof(struct dw_desc), 4, 0); diff --git a/drivers/dma/hsu/hsu.c b/drivers/dma/hsu/hsu.c index 823ad728aecf..efc02b98e6ba 100644 --- a/drivers/dma/hsu/hsu.c +++ b/drivers/dma/hsu/hsu.c @@ -135,7 +135,7 @@ static u32 hsu_dma_chan_get_sr(struct hsu_dma_chan *hsuc) sr = hsu_chan_readl(hsuc, HSU_CH_SR); spin_unlock_irqrestore(&hsuc->vchan.lock, flags); - return sr; + return sr & ~(HSU_CH_SR_DESCE_ANY | HSU_CH_SR_CDESC_ANY); } irqreturn_t hsu_dma_irq(struct hsu_dma_chip *chip, unsigned short nr) diff --git a/drivers/dma/hsu/hsu.h b/drivers/dma/hsu/hsu.h index f06579c6d548..26da2865b025 100644 --- a/drivers/dma/hsu/hsu.h +++ b/drivers/dma/hsu/hsu.h @@ -41,6 +41,9 @@ #define HSU_CH_SR_DESCTO(x) BIT(8 + (x)) #define HSU_CH_SR_DESCTO_ANY (BIT(11) | BIT(10) | BIT(9) | BIT(8)) #define HSU_CH_SR_CHE BIT(15) +#define HSU_CH_SR_DESCE(x) BIT(16 + (x)) +#define HSU_CH_SR_DESCE_ANY (BIT(19) | BIT(18) | BIT(17) | BIT(16)) +#define HSU_CH_SR_CDESC_ANY (BIT(31) | BIT(30)) /* Bits in HSU_CH_CR */ #define HSU_CH_CR_CHA BIT(0) diff --git a/drivers/dma/pxa_dma.c b/drivers/dma/pxa_dma.c index fc4156afa070..55f5d33f6dc7 100644 --- a/drivers/dma/pxa_dma.c +++ b/drivers/dma/pxa_dma.c @@ -122,6 +122,7 @@ struct pxad_chan { struct pxad_device { struct dma_device slave; int nr_chans; + int nr_requestors; void __iomem *base; struct pxad_phy *phys; spinlock_t phy_lock; /* Phy association */ @@ -473,7 +474,7 @@ static void pxad_free_phy(struct pxad_chan *chan) return; /* clear the channel mapping in DRCMR */ - if (chan->drcmr <= DRCMR_CHLNUM) { + if (chan->drcmr <= pdev->nr_requestors) { reg = pxad_drcmr(chan->drcmr); writel_relaxed(0, chan->phy->base + reg); } @@ -509,6 +510,7 @@ static bool is_running_chan_misaligned(struct pxad_chan *chan) static void phy_enable(struct pxad_phy *phy, bool misaligned) { + struct pxad_device *pdev; u32 reg, dalgn; if (!phy->vchan) @@ -518,7 +520,8 @@ static void phy_enable(struct pxad_phy *phy, bool misaligned) "%s(); phy=%p(%d) misaligned=%d\n", __func__, phy, phy->idx, misaligned); - if (phy->vchan->drcmr <= DRCMR_CHLNUM) { + pdev = to_pxad_dev(phy->vchan->vc.chan.device); + if (phy->vchan->drcmr <= pdev->nr_requestors) { reg = pxad_drcmr(phy->vchan->drcmr); writel_relaxed(DRCMR_MAPVLD | phy->idx, phy->base + reg); } @@ -583,6 +586,8 @@ static void set_updater_desc(struct pxad_desc_sw *sw_desc, (PXA_DCMD_LENGTH & sizeof(u32)); if (flags & DMA_PREP_INTERRUPT) updater->dcmd |= PXA_DCMD_ENDIRQEN; + if (sw_desc->cyclic) + sw_desc->hw_desc[sw_desc->nb_desc - 2]->ddadr = sw_desc->first; } static bool is_desc_completed(struct virt_dma_desc *vd) @@ -673,6 +678,10 @@ static irqreturn_t pxad_chan_handler(int irq, void *dev_id) dev_dbg(&chan->vc.chan.dev->device, "%s(): checking txd %p[%x]: completed=%d\n", __func__, vd, vd->tx.cookie, is_desc_completed(vd)); + if (to_pxad_sw_desc(vd)->cyclic) { + vchan_cyclic_callback(vd); + break; + } if (is_desc_completed(vd)) { list_del(&vd->node); vchan_cookie_complete(vd); @@ -908,6 +917,7 @@ static void pxad_get_config(struct pxad_chan *chan, { u32 maxburst = 0, dev_addr = 0; enum dma_slave_buswidth width = DMA_SLAVE_BUSWIDTH_UNDEFINED; + struct pxad_device *pdev = to_pxad_dev(chan->vc.chan.device); *dcmd = 0; if (dir == DMA_DEV_TO_MEM) { @@ -916,7 +926,7 @@ static void pxad_get_config(struct pxad_chan *chan, dev_addr = chan->cfg.src_addr; *dev_src = dev_addr; *dcmd |= PXA_DCMD_INCTRGADDR; - if (chan->drcmr <= DRCMR_CHLNUM) + if (chan->drcmr <= pdev->nr_requestors) *dcmd |= PXA_DCMD_FLOWSRC; } if (dir == DMA_MEM_TO_DEV) { @@ -925,7 +935,7 @@ static void pxad_get_config(struct pxad_chan *chan, dev_addr = chan->cfg.dst_addr; *dev_dst = dev_addr; *dcmd |= PXA_DCMD_INCSRCADDR; - if (chan->drcmr <= DRCMR_CHLNUM) + if (chan->drcmr <= pdev->nr_requestors) *dcmd |= PXA_DCMD_FLOWTRG; } if (dir == DMA_MEM_TO_MEM) @@ -1080,7 +1090,7 @@ pxad_prep_dma_cyclic(struct dma_chan *dchan, return NULL; pxad_get_config(chan, dir, &dcmd, &dsadr, &dtadr); - dcmd |= PXA_DCMD_ENDIRQEN | (PXA_DCMD_LENGTH | period_len); + dcmd |= PXA_DCMD_ENDIRQEN | (PXA_DCMD_LENGTH & period_len); dev_dbg(&chan->vc.chan.dev->device, "%s(): buf_addr=0x%lx len=%zu period=%zu dir=%d flags=%lx\n", __func__, (unsigned long)buf_addr, len, period_len, dir, flags); @@ -1335,13 +1345,15 @@ static struct dma_chan *pxad_dma_xlate(struct of_phandle_args *dma_spec, static int pxad_init_dmadev(struct platform_device *op, struct pxad_device *pdev, - unsigned int nr_phy_chans) + unsigned int nr_phy_chans, + unsigned int nr_requestors) { int ret; unsigned int i; struct pxad_chan *c; pdev->nr_chans = nr_phy_chans; + pdev->nr_requestors = nr_requestors; INIT_LIST_HEAD(&pdev->slave.channels); pdev->slave.device_alloc_chan_resources = pxad_alloc_chan_resources; pdev->slave.device_free_chan_resources = pxad_free_chan_resources; @@ -1376,7 +1388,7 @@ static int pxad_probe(struct platform_device *op) const struct of_device_id *of_id; struct mmp_dma_platdata *pdata = dev_get_platdata(&op->dev); struct resource *iores; - int ret, dma_channels = 0; + int ret, dma_channels = 0, nb_requestors = 0; const enum dma_slave_buswidth widths = DMA_SLAVE_BUSWIDTH_1_BYTE | DMA_SLAVE_BUSWIDTH_2_BYTES | DMA_SLAVE_BUSWIDTH_4_BYTES; @@ -1393,13 +1405,23 @@ static int pxad_probe(struct platform_device *op) return PTR_ERR(pdev->base); of_id = of_match_device(pxad_dt_ids, &op->dev); - if (of_id) + if (of_id) { of_property_read_u32(op->dev.of_node, "#dma-channels", &dma_channels); - else if (pdata && pdata->dma_channels) + ret = of_property_read_u32(op->dev.of_node, "#dma-requests", + &nb_requestors); + if (ret) { + dev_warn(pdev->slave.dev, + "#dma-requests set to default 32 as missing in OF: %d", + ret); + nb_requestors = 32; + }; + } else if (pdata && pdata->dma_channels) { dma_channels = pdata->dma_channels; - else + nb_requestors = pdata->nb_requestors; + } else { dma_channels = 32; /* default 32 channel */ + } dma_cap_set(DMA_SLAVE, pdev->slave.cap_mask); dma_cap_set(DMA_MEMCPY, pdev->slave.cap_mask); @@ -1416,7 +1438,7 @@ static int pxad_probe(struct platform_device *op) pdev->slave.residue_granularity = DMA_RESIDUE_GRANULARITY_DESCRIPTOR; pdev->slave.dev = &op->dev; - ret = pxad_init_dmadev(op, pdev, dma_channels); + ret = pxad_init_dmadev(op, pdev, dma_channels, nb_requestors); if (ret) { dev_err(pdev->slave.dev, "unable to register\n"); return ret; @@ -1435,7 +1457,8 @@ static int pxad_probe(struct platform_device *op) platform_set_drvdata(op, pdev); pxad_init_debugfs(pdev); - dev_info(pdev->slave.dev, "initialized %d channels\n", dma_channels); + dev_info(pdev->slave.dev, "initialized %d channels on %d requestors\n", + dma_channels, nb_requestors); return 0; } diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index 9eee13ef83a5..d87a47547ba5 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -1452,7 +1452,7 @@ static u64 f1x_get_norm_dct_addr(struct amd64_pvt *pvt, u8 range, u64 chan_off; u64 dram_base = get_dram_base(pvt, range); u64 hole_off = f10_dhar_offset(pvt); - u64 dct_sel_base_off = (pvt->dct_sel_hi & 0xFFFFFC00) << 16; + u64 dct_sel_base_off = (u64)(pvt->dct_sel_hi & 0xFFFFFC00) << 16; if (hi_rng) { /* diff --git a/drivers/edac/edac_device.c b/drivers/edac/edac_device.c index 592af5f0cf39..53587377e672 100644 --- a/drivers/edac/edac_device.c +++ b/drivers/edac/edac_device.c @@ -435,16 +435,13 @@ void edac_device_workq_setup(struct edac_device_ctl_info *edac_dev, */ void edac_device_workq_teardown(struct edac_device_ctl_info *edac_dev) { - int status; - if (!edac_dev->edac_check) return; - status = cancel_delayed_work(&edac_dev->work); - if (status == 0) { - /* workq instance might be running, wait for it */ - flush_workqueue(edac_workqueue); - } + edac_dev->op_state = OP_OFFLINE; + + cancel_delayed_work_sync(&edac_dev->work); + flush_workqueue(edac_workqueue); } /* diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c index 77ecd6a4179a..1b2c2187b347 100644 --- a/drivers/edac/edac_mc.c +++ b/drivers/edac/edac_mc.c @@ -586,18 +586,10 @@ static void edac_mc_workq_setup(struct mem_ctl_info *mci, unsigned msec, */ static void edac_mc_workq_teardown(struct mem_ctl_info *mci) { - int status; + mci->op_state = OP_OFFLINE; - if (mci->op_state != OP_RUNNING_POLL) - return; - - status = cancel_delayed_work(&mci->work); - if (status == 0) { - edac_dbg(0, "not canceled, flush the queue\n"); - - /* workq instance might be running, wait for it */ - flush_workqueue(edac_workqueue); - } + cancel_delayed_work_sync(&mci->work); + flush_workqueue(edac_workqueue); } /* diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c index a75acea0f674..58aed67b7eba 100644 --- a/drivers/edac/edac_mc_sysfs.c +++ b/drivers/edac/edac_mc_sysfs.c @@ -880,21 +880,26 @@ static struct device_type mci_attr_type = { int edac_create_sysfs_mci_device(struct mem_ctl_info *mci, const struct attribute_group **groups) { + char *name; int i, err; /* * The memory controller needs its own bus, in order to avoid * namespace conflicts at /sys/bus/edac. */ - mci->bus->name = kasprintf(GFP_KERNEL, "mc%d", mci->mc_idx); - if (!mci->bus->name) + name = kasprintf(GFP_KERNEL, "mc%d", mci->mc_idx); + if (!name) return -ENOMEM; + mci->bus->name = name; + edac_dbg(0, "creating bus %s\n", mci->bus->name); err = bus_register(mci->bus); - if (err < 0) - goto fail_free_name; + if (err < 0) { + kfree(name); + return err; + } /* get the /sys/devices/system/edac subsys reference */ mci->dev.type = &mci_attr_type; @@ -961,8 +966,8 @@ fail_unregister_dimm: device_unregister(&mci->dev); fail_unregister_bus: bus_unregister(mci->bus); -fail_free_name: - kfree(mci->bus->name); + kfree(name); + return err; } @@ -993,10 +998,12 @@ void edac_remove_sysfs_mci_device(struct mem_ctl_info *mci) void edac_unregister_sysfs(struct mem_ctl_info *mci) { + const char *name = mci->bus->name; + edac_dbg(1, "Unregistering device %s\n", dev_name(&mci->dev)); device_unregister(&mci->dev); bus_unregister(mci->bus); - kfree(mci->bus->name); + kfree(name); } static void mc_attr_release(struct device *dev) diff --git a/drivers/edac/edac_pci.c b/drivers/edac/edac_pci.c index 2cf44b4db80c..b4b38603b804 100644 --- a/drivers/edac/edac_pci.c +++ b/drivers/edac/edac_pci.c @@ -274,13 +274,12 @@ static void edac_pci_workq_setup(struct edac_pci_ctl_info *pci, */ static void edac_pci_workq_teardown(struct edac_pci_ctl_info *pci) { - int status; - edac_dbg(0, "\n"); - status = cancel_delayed_work(&pci->work); - if (status == 0) - flush_workqueue(edac_workqueue); + pci->op_state = OP_OFFLINE; + + cancel_delayed_work_sync(&pci->work); + flush_workqueue(edac_workqueue); } /* diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c index 01087a38da22..792bdae2b91d 100644 --- a/drivers/edac/i7core_edac.c +++ b/drivers/edac/i7core_edac.c @@ -1866,7 +1866,7 @@ static int i7core_mce_check_error(struct notifier_block *nb, unsigned long val, i7_dev = get_i7core_dev(mce->socketid); if (!i7_dev) - return NOTIFY_BAD; + return NOTIFY_DONE; mci = i7_dev->mci; pvt = mci->pvt_info; diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c index 429309c62699..ca64b174f8a3 100644 --- a/drivers/edac/sb_edac.c +++ b/drivers/edac/sb_edac.c @@ -218,8 +218,11 @@ static const u32 rir_offset[MAX_RIR_RANGES][MAX_RIR_WAY] = { { 0x1a0, 0x1a4, 0x1a8, 0x1ac, 0x1b0, 0x1b4, 0x1b8, 0x1bc }, }; -#define RIR_RNK_TGT(reg) GET_BITFIELD(reg, 16, 19) -#define RIR_OFFSET(reg) GET_BITFIELD(reg, 2, 14) +#define RIR_RNK_TGT(type, reg) (((type) == BROADWELL) ? \ + GET_BITFIELD(reg, 20, 23) : GET_BITFIELD(reg, 16, 19)) + +#define RIR_OFFSET(type, reg) (((type) == HASWELL || (type) == BROADWELL) ? \ + GET_BITFIELD(reg, 2, 15) : GET_BITFIELD(reg, 2, 14)) /* Device 16, functions 2-7 */ @@ -1117,8 +1120,8 @@ static void get_memory_layout(const struct mem_ctl_info *mci) edac_dbg(0, "TAD#%d: up to %u.%03u GB (0x%016Lx), socket interleave %d, memory interleave %d, TGT: %d, %d, %d, %d, reg=0x%08x\n", n_tads, gb, (mb*1000)/1024, ((u64)tmp_mb) << 20L, - (u32)TAD_SOCK(reg), - (u32)TAD_CH(reg), + (u32)(1 << TAD_SOCK(reg)), + (u32)TAD_CH(reg) + 1, (u32)TAD_TGT0(reg), (u32)TAD_TGT1(reg), (u32)TAD_TGT2(reg), @@ -1175,14 +1178,14 @@ static void get_memory_layout(const struct mem_ctl_info *mci) pci_read_config_dword(pvt->pci_tad[i], rir_offset[j][k], ®); - tmp_mb = RIR_OFFSET(reg) << 6; + tmp_mb = RIR_OFFSET(pvt->info.type, reg) << 6; gb = div_u64_rem(tmp_mb, 1024, &mb); edac_dbg(0, "CH#%d RIR#%d INTL#%d, offset %u.%03u GB (0x%016Lx), tgt: %d, reg=0x%08x\n", i, j, k, gb, (mb*1000)/1024, ((u64)tmp_mb) << 20L, - (u32)RIR_RNK_TGT(reg), + (u32)RIR_RNK_TGT(pvt->info.type, reg), reg); } } @@ -1396,7 +1399,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci, } ch_way = TAD_CH(reg) + 1; - sck_way = TAD_SOCK(reg) + 1; + sck_way = TAD_SOCK(reg); if (ch_way == 3) idx = addr >> 6; @@ -1435,7 +1438,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci, switch(ch_way) { case 2: case 4: - sck_xch = 1 << sck_way * (ch_way >> 1); + sck_xch = (1 << sck_way) * (ch_way >> 1); break; default: sprintf(msg, "Invalid mirror set. Can't decode addr"); @@ -1453,7 +1456,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci, n_tads, addr, limit, - (u32)TAD_SOCK(reg), + sck_way, ch_way, offset, idx, @@ -1468,18 +1471,12 @@ static int get_memory_error_data(struct mem_ctl_info *mci, offset, addr); return -EINVAL; } - addr -= offset; - /* Store the low bits [0:6] of the addr */ - ch_addr = addr & 0x7f; - /* Remove socket wayness and remove 6 bits */ - addr >>= 6; - addr = div_u64(addr, sck_xch); -#if 0 - /* Divide by channel way */ - addr = addr / ch_way; -#endif - /* Recover the last 6 bits */ - ch_addr |= addr << 6; + + ch_addr = addr - offset; + ch_addr >>= (6 + shiftup); + ch_addr /= sck_xch; + ch_addr <<= (6 + shiftup); + ch_addr |= addr & ((1 << (6 + shiftup)) - 1); /* * Step 3) Decode rank @@ -1518,7 +1515,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci, pci_read_config_dword(pvt->pci_tad[ch_add + base_ch], rir_offset[n_rir][idx], ®); - *rank = RIR_RNK_TGT(reg); + *rank = RIR_RNK_TGT(pvt->info.type, reg); edac_dbg(0, "RIR#%d: channel address 0x%08Lx < 0x%08Lx, RIR interleave %d, index %d\n", n_rir, @@ -2260,7 +2257,7 @@ static int sbridge_mce_check_error(struct notifier_block *nb, unsigned long val, mci = get_mci_for_node_id(mce->socketid); if (!mci) - return NOTIFY_BAD; + return NOTIFY_DONE; pvt = mci->pvt_info; /* diff --git a/drivers/extcon/extcon-max77843.c b/drivers/extcon/extcon-max77843.c index 9f9ea334399c..b6cb30d207be 100644 --- a/drivers/extcon/extcon-max77843.c +++ b/drivers/extcon/extcon-max77843.c @@ -803,7 +803,7 @@ static int max77843_muic_probe(struct platform_device *pdev) /* Clear IRQ bits before request IRQs */ ret = regmap_bulk_read(max77843->regmap_muic, MAX77843_MUIC_REG_INT1, info->status, - MAX77843_MUIC_IRQ_NUM); + MAX77843_MUIC_STATUS_NUM); if (ret) { dev_err(&pdev->dev, "Failed to Clear IRQ bits\n"); goto err_muic_irq; diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 027ca212179f..3b52677f459a 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -180,6 +180,7 @@ static int generic_ops_register(void) { generic_ops.get_variable = efi.get_variable; generic_ops.set_variable = efi.set_variable; + generic_ops.set_variable_nonblocking = efi.set_variable_nonblocking; generic_ops.get_next_variable = efi.get_next_variable; generic_ops.query_variable_store = efi_query_variable_store; diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c index 756eca8c4cf8..10e6774ab2a2 100644 --- a/drivers/firmware/efi/efivars.c +++ b/drivers/firmware/efi/efivars.c @@ -221,7 +221,7 @@ sanity_check(struct efi_variable *var, efi_char16_t *name, efi_guid_t vendor, } if ((attributes & ~EFI_VARIABLE_MASK) != 0 || - efivar_validate(name, data, size) == false) { + efivar_validate(vendor, name, data, size) == false) { printk(KERN_ERR "efivars: Malformed variable content\n"); return -EINVAL; } @@ -447,7 +447,8 @@ static ssize_t efivar_create(struct file *filp, struct kobject *kobj, } if ((attributes & ~EFI_VARIABLE_MASK) != 0 || - efivar_validate(name, data, size) == false) { + efivar_validate(new_var->VendorGuid, name, data, + size) == false) { printk(KERN_ERR "efivars: Malformed variable content\n"); return -EINVAL; } @@ -540,38 +541,30 @@ static ssize_t efivar_delete(struct file *filp, struct kobject *kobj, static int efivar_create_sysfs_entry(struct efivar_entry *new_var) { - int i, short_name_size; + int short_name_size; char *short_name; - unsigned long variable_name_size; - efi_char16_t *variable_name; + unsigned long utf8_name_size; + efi_char16_t *variable_name = new_var->var.VariableName; int ret; - variable_name = new_var->var.VariableName; - variable_name_size = ucs2_strlen(variable_name) * sizeof(efi_char16_t); - /* - * Length of the variable bytes in ASCII, plus the '-' separator, + * Length of the variable bytes in UTF8, plus the '-' separator, * plus the GUID, plus trailing NUL */ - short_name_size = variable_name_size / sizeof(efi_char16_t) - + 1 + EFI_VARIABLE_GUID_LEN + 1; - - short_name = kzalloc(short_name_size, GFP_KERNEL); + utf8_name_size = ucs2_utf8size(variable_name); + short_name_size = utf8_name_size + 1 + EFI_VARIABLE_GUID_LEN + 1; + short_name = kmalloc(short_name_size, GFP_KERNEL); if (!short_name) return -ENOMEM; - /* Convert Unicode to normal chars (assume top bits are 0), - ala UTF-8 */ - for (i=0; i < (int)(variable_name_size / sizeof(efi_char16_t)); i++) { - short_name[i] = variable_name[i] & 0xFF; - } + ucs2_as_utf8(short_name, variable_name, short_name_size); + /* This is ugly, but necessary to separate one vendor's private variables from another's. */ - - *(short_name + strlen(short_name)) = '-'; + short_name[utf8_name_size] = '-'; efi_guid_to_str(&new_var->var.VendorGuid, - short_name + strlen(short_name)); + short_name + utf8_name_size + 1); new_var->kobj.kset = efivars_kset; diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c index 70a0fb10517f..6f182fd91a6d 100644 --- a/drivers/firmware/efi/vars.c +++ b/drivers/firmware/efi/vars.c @@ -165,67 +165,148 @@ validate_ascii_string(efi_char16_t *var_name, int match, u8 *buffer, } struct variable_validate { + efi_guid_t vendor; char *name; bool (*validate)(efi_char16_t *var_name, int match, u8 *data, unsigned long len); }; +/* + * This is the list of variables we need to validate, as well as the + * whitelist for what we think is safe not to default to immutable. + * + * If it has a validate() method that's not NULL, it'll go into the + * validation routine. If not, it is assumed valid, but still used for + * whitelisting. + * + * Note that it's sorted by {vendor,name}, but globbed names must come after + * any other name with the same prefix. + */ static const struct variable_validate variable_validate[] = { - { "BootNext", validate_uint16 }, - { "BootOrder", validate_boot_order }, - { "DriverOrder", validate_boot_order }, - { "Boot*", validate_load_option }, - { "Driver*", validate_load_option }, - { "ConIn", validate_device_path }, - { "ConInDev", validate_device_path }, - { "ConOut", validate_device_path }, - { "ConOutDev", validate_device_path }, - { "ErrOut", validate_device_path }, - { "ErrOutDev", validate_device_path }, - { "Timeout", validate_uint16 }, - { "Lang", validate_ascii_string }, - { "PlatformLang", validate_ascii_string }, - { "", NULL }, + { EFI_GLOBAL_VARIABLE_GUID, "BootNext", validate_uint16 }, + { EFI_GLOBAL_VARIABLE_GUID, "BootOrder", validate_boot_order }, + { EFI_GLOBAL_VARIABLE_GUID, "Boot*", validate_load_option }, + { EFI_GLOBAL_VARIABLE_GUID, "DriverOrder", validate_boot_order }, + { EFI_GLOBAL_VARIABLE_GUID, "Driver*", validate_load_option }, + { EFI_GLOBAL_VARIABLE_GUID, "ConIn", validate_device_path }, + { EFI_GLOBAL_VARIABLE_GUID, "ConInDev", validate_device_path }, + { EFI_GLOBAL_VARIABLE_GUID, "ConOut", validate_device_path }, + { EFI_GLOBAL_VARIABLE_GUID, "ConOutDev", validate_device_path }, + { EFI_GLOBAL_VARIABLE_GUID, "ErrOut", validate_device_path }, + { EFI_GLOBAL_VARIABLE_GUID, "ErrOutDev", validate_device_path }, + { EFI_GLOBAL_VARIABLE_GUID, "Lang", validate_ascii_string }, + { EFI_GLOBAL_VARIABLE_GUID, "OsIndications", NULL }, + { EFI_GLOBAL_VARIABLE_GUID, "PlatformLang", validate_ascii_string }, + { EFI_GLOBAL_VARIABLE_GUID, "Timeout", validate_uint16 }, + { LINUX_EFI_CRASH_GUID, "*", NULL }, + { NULL_GUID, "", NULL }, }; -bool -efivar_validate(efi_char16_t *var_name, u8 *data, unsigned long len) +/* + * Check if @var_name matches the pattern given in @match_name. + * + * @var_name: an array of @len non-NUL characters. + * @match_name: a NUL-terminated pattern string, optionally ending in "*". A + * final "*" character matches any trailing characters @var_name, + * including the case when there are none left in @var_name. + * @match: on output, the number of non-wildcard characters in @match_name + * that @var_name matches, regardless of the return value. + * @return: whether @var_name fully matches @match_name. + */ +static bool +variable_matches(const char *var_name, size_t len, const char *match_name, + int *match) { - int i; - u16 *unicode_name = var_name; + for (*match = 0; ; (*match)++) { + char c = match_name[*match]; - for (i = 0; variable_validate[i].validate != NULL; i++) { - const char *name = variable_validate[i].name; - int match; + switch (c) { + case '*': + /* Wildcard in @match_name means we've matched. */ + return true; - for (match = 0; ; match++) { - char c = name[match]; - u16 u = unicode_name[match]; + case '\0': + /* @match_name has ended. Has @var_name too? */ + return (*match == len); - /* All special variables are plain ascii */ - if (u > 127) - return true; - - /* Wildcard in the matching name means we've matched */ - if (c == '*') - return variable_validate[i].validate(var_name, - match, data, len); - - /* Case sensitive match */ - if (c != u) - break; - - /* Reached the end of the string while matching */ - if (!c) - return variable_validate[i].validate(var_name, - match, data, len); + default: + /* + * We've reached a non-wildcard char in @match_name. + * Continue only if there's an identical character in + * @var_name. + */ + if (*match < len && c == var_name[*match]) + continue; + return false; } } +} +bool +efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data, + unsigned long data_size) +{ + int i; + unsigned long utf8_size; + u8 *utf8_name; + + utf8_size = ucs2_utf8size(var_name); + utf8_name = kmalloc(utf8_size + 1, GFP_KERNEL); + if (!utf8_name) + return false; + + ucs2_as_utf8(utf8_name, var_name, utf8_size); + utf8_name[utf8_size] = '\0'; + + for (i = 0; variable_validate[i].name[0] != '\0'; i++) { + const char *name = variable_validate[i].name; + int match = 0; + + if (efi_guidcmp(vendor, variable_validate[i].vendor)) + continue; + + if (variable_matches(utf8_name, utf8_size+1, name, &match)) { + if (variable_validate[i].validate == NULL) + break; + kfree(utf8_name); + return variable_validate[i].validate(var_name, match, + data, data_size); + } + } + kfree(utf8_name); return true; } EXPORT_SYMBOL_GPL(efivar_validate); +bool +efivar_variable_is_removable(efi_guid_t vendor, const char *var_name, + size_t len) +{ + int i; + bool found = false; + int match = 0; + + /* + * Check if our variable is in the validated variables list + */ + for (i = 0; variable_validate[i].name[0] != '\0'; i++) { + if (efi_guidcmp(variable_validate[i].vendor, vendor)) + continue; + + if (variable_matches(var_name, len, + variable_validate[i].name, &match)) { + found = true; + break; + } + } + + /* + * If it's in our list, it is removable. + */ + return found; +} +EXPORT_SYMBOL_GPL(efivar_variable_is_removable); + static efi_status_t check_var_size(u32 attributes, unsigned long size) { @@ -852,7 +933,7 @@ int efivar_entry_set_get_size(struct efivar_entry *entry, u32 attributes, *set = false; - if (efivar_validate(name, data, *size) == false) + if (efivar_validate(*vendor, name, data, *size) == false) return -EINVAL; /* diff --git a/drivers/gpio/gpio-bcm-kona.c b/drivers/gpio/gpio-bcm-kona.c index 33a1f9779b86..4ea71d505bce 100644 --- a/drivers/gpio/gpio-bcm-kona.c +++ b/drivers/gpio/gpio-bcm-kona.c @@ -551,11 +551,11 @@ static void bcm_kona_gpio_reset(struct bcm_kona_gpio *kona_gpio) /* disable interrupts and clear status */ for (i = 0; i < kona_gpio->num_bank; i++) { /* Unlock the entire bank first */ - bcm_kona_gpio_write_lock_regs(kona_gpio, i, UNLOCK_CODE); + bcm_kona_gpio_write_lock_regs(reg_base, i, UNLOCK_CODE); writel(0xffffffff, reg_base + GPIO_INT_MASK(i)); writel(0xffffffff, reg_base + GPIO_INT_STATUS(i)); /* Now re-lock the bank */ - bcm_kona_gpio_write_lock_regs(kona_gpio, i, LOCK_CODE); + bcm_kona_gpio_write_lock_regs(reg_base, i, LOCK_CODE); } } diff --git a/drivers/gpio/gpiolib-legacy.c b/drivers/gpio/gpiolib-legacy.c index 3a5c7011ad3b..8b830996fe02 100644 --- a/drivers/gpio/gpiolib-legacy.c +++ b/drivers/gpio/gpiolib-legacy.c @@ -28,6 +28,10 @@ int gpio_request_one(unsigned gpio, unsigned long flags, const char *label) if (!desc && gpio_is_valid(gpio)) return -EPROBE_DEFER; + err = gpiod_request(desc, label); + if (err) + return err; + if (flags & GPIOF_OPEN_DRAIN) set_bit(FLAG_OPEN_DRAIN, &desc->flags); @@ -37,10 +41,6 @@ int gpio_request_one(unsigned gpio, unsigned long flags, const char *label) if (flags & GPIOF_ACTIVE_LOW) set_bit(FLAG_ACTIVE_LOW, &desc->flags); - err = gpiod_request(desc, label); - if (err) - return err; - if (flags & GPIOF_DIR_IN) err = gpiod_direction_input(desc); else diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 4e4c3083ae56..06d345b087f8 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -927,14 +927,6 @@ static int __gpiod_request(struct gpio_desc *desc, const char *label) spin_lock_irqsave(&gpio_lock, flags); } done: - if (status < 0) { - /* Clear flags that might have been set by the caller before - * requesting the GPIO. - */ - clear_bit(FLAG_ACTIVE_LOW, &desc->flags); - clear_bit(FLAG_OPEN_DRAIN, &desc->flags); - clear_bit(FLAG_OPEN_SOURCE, &desc->flags); - } spin_unlock_irqrestore(&gpio_lock, flags); return status; } @@ -2062,28 +2054,13 @@ struct gpio_desc *__must_check gpiod_get_optional(struct device *dev, } EXPORT_SYMBOL_GPL(gpiod_get_optional); -/** - * gpiod_parse_flags - helper function to parse GPIO lookup flags - * @desc: gpio to be setup - * @lflags: gpio_lookup_flags - returned from of_find_gpio() or - * of_get_gpio_hog() - * - * Set the GPIO descriptor flags based on the given GPIO lookup flags. - */ -static void gpiod_parse_flags(struct gpio_desc *desc, unsigned long lflags) -{ - if (lflags & GPIO_ACTIVE_LOW) - set_bit(FLAG_ACTIVE_LOW, &desc->flags); - if (lflags & GPIO_OPEN_DRAIN) - set_bit(FLAG_OPEN_DRAIN, &desc->flags); - if (lflags & GPIO_OPEN_SOURCE) - set_bit(FLAG_OPEN_SOURCE, &desc->flags); -} /** * gpiod_configure_flags - helper function to configure a given GPIO * @desc: gpio whose value will be assigned * @con_id: function within the GPIO consumer + * @lflags: gpio_lookup_flags - returned from of_find_gpio() or + * of_get_gpio_hog() * @dflags: gpiod_flags - optional GPIO initialization flags * * Return 0 on success, -ENOENT if no GPIO has been assigned to the @@ -2091,10 +2068,17 @@ static void gpiod_parse_flags(struct gpio_desc *desc, unsigned long lflags) * occurred while trying to acquire the GPIO. */ static int gpiod_configure_flags(struct gpio_desc *desc, const char *con_id, - enum gpiod_flags dflags) + unsigned long lflags, enum gpiod_flags dflags) { int status; + if (lflags & GPIO_ACTIVE_LOW) + set_bit(FLAG_ACTIVE_LOW, &desc->flags); + if (lflags & GPIO_OPEN_DRAIN) + set_bit(FLAG_OPEN_DRAIN, &desc->flags); + if (lflags & GPIO_OPEN_SOURCE) + set_bit(FLAG_OPEN_SOURCE, &desc->flags); + /* No particular flag request, return here... */ if (!(dflags & GPIOD_FLAGS_BIT_DIR_SET)) { pr_debug("no flags found for %s\n", con_id); @@ -2161,13 +2145,11 @@ struct gpio_desc *__must_check gpiod_get_index(struct device *dev, return desc; } - gpiod_parse_flags(desc, lookupflags); - status = gpiod_request(desc, con_id); if (status < 0) return ERR_PTR(status); - status = gpiod_configure_flags(desc, con_id, flags); + status = gpiod_configure_flags(desc, con_id, lookupflags, flags); if (status < 0) { dev_dbg(dev, "setup of GPIO %s failed\n", con_id); gpiod_put(desc); @@ -2223,6 +2205,10 @@ struct gpio_desc *fwnode_get_named_gpiod(struct fwnode_handle *fwnode, if (IS_ERR(desc)) return desc; + ret = gpiod_request(desc, NULL); + if (ret) + return ERR_PTR(ret); + if (active_low) set_bit(FLAG_ACTIVE_LOW, &desc->flags); @@ -2233,10 +2219,6 @@ struct gpio_desc *fwnode_get_named_gpiod(struct fwnode_handle *fwnode, set_bit(FLAG_OPEN_SOURCE, &desc->flags); } - ret = gpiod_request(desc, NULL); - if (ret) - return ERR_PTR(ret); - return desc; } EXPORT_SYMBOL_GPL(fwnode_get_named_gpiod); @@ -2289,8 +2271,6 @@ int gpiod_hog(struct gpio_desc *desc, const char *name, chip = gpiod_to_chip(desc); hwnum = gpio_chip_hwgpio(desc); - gpiod_parse_flags(desc, lflags); - local_desc = gpiochip_request_own_desc(chip, hwnum, name); if (IS_ERR(local_desc)) { pr_err("requesting hog GPIO %s (chip %s, offset %d) failed\n", @@ -2298,7 +2278,7 @@ int gpiod_hog(struct gpio_desc *desc, const char *name, return PTR_ERR(local_desc); } - status = gpiod_configure_flags(desc, name, dflags); + status = gpiod_configure_flags(desc, name, lflags, dflags); if (status < 0) { pr_err("setup of hog GPIO %s (chip %s, offset %d) failed\n", name, chip->label, hwnum); diff --git a/drivers/gpu/drm/amd/amdgpu/Makefile b/drivers/gpu/drm/amd/amdgpu/Makefile index 04c270757030..ca066018ea34 100644 --- a/drivers/gpu/drm/amd/amdgpu/Makefile +++ b/drivers/gpu/drm/amd/amdgpu/Makefile @@ -22,7 +22,7 @@ amdgpu-y += amdgpu_device.o amdgpu_kms.o \ amdgpu_ucode.o amdgpu_bo_list.o amdgpu_ctx.o amdgpu_sync.o # add asic specific block -amdgpu-$(CONFIG_DRM_AMDGPU_CIK)+= cik.o gmc_v7_0.o cik_ih.o kv_smc.o kv_dpm.o \ +amdgpu-$(CONFIG_DRM_AMDGPU_CIK)+= cik.o cik_ih.o kv_smc.o kv_dpm.o \ ci_smc.o ci_dpm.o dce_v8_0.o gfx_v7_0.o cik_sdma.o uvd_v4_2.o vce_v2_0.o \ amdgpu_amdkfd_gfx_v7.o @@ -31,6 +31,7 @@ amdgpu-y += \ # add GMC block amdgpu-y += \ + gmc_v7_0.o \ gmc_v8_0.o # add IH block diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 048cfe073dae..053fc2f465df 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -604,8 +604,6 @@ struct amdgpu_sa_manager { uint32_t align; }; -struct amdgpu_sa_bo; - /* sub-allocation buffer */ struct amdgpu_sa_bo { struct list_head olist; @@ -1675,6 +1673,7 @@ struct amdgpu_uvd { struct amdgpu_bo *vcpu_bo; void *cpu_addr; uint64_t gpu_addr; + unsigned fw_version; atomic_t handles[AMDGPU_MAX_UVD_HANDLES]; struct drm_file *filp[AMDGPU_MAX_UVD_HANDLES]; struct delayed_work idle_work; @@ -2314,6 +2313,8 @@ bool amdgpu_ttm_bo_is_amdgpu_bo(struct ttm_buffer_object *bo); int amdgpu_ttm_tt_set_userptr(struct ttm_tt *ttm, uint64_t addr, uint32_t flags); bool amdgpu_ttm_tt_has_userptr(struct ttm_tt *ttm); +bool amdgpu_ttm_tt_affect_userptr(struct ttm_tt *ttm, unsigned long start, + unsigned long end); bool amdgpu_ttm_tt_is_readonly(struct ttm_tt *ttm); uint32_t amdgpu_ttm_tt_pte_flags(struct amdgpu_device *adev, struct ttm_tt *ttm, struct ttm_mem_reg *mem); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c index 89c3dd62ba21..7ef2c13921b4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c @@ -77,7 +77,7 @@ void amdgpu_connector_hotplug(struct drm_connector *connector) } else if (amdgpu_atombios_dp_needs_link_train(amdgpu_connector)) { /* Don't try to start link training before we * have the dpcd */ - if (!amdgpu_atombios_dp_get_dpcd(amdgpu_connector)) + if (amdgpu_atombios_dp_get_dpcd(amdgpu_connector)) return; /* set it to OFF so that drm_helper_connector_dpms() @@ -194,12 +194,12 @@ int amdgpu_connector_get_monitor_bpc(struct drm_connector *connector) bpc = 8; DRM_DEBUG("%s: HDMI deep color 10 bpc exceeds max tmds clock. Using %d bpc.\n", connector->name, bpc); - } else if (bpc > 8) { - /* max_tmds_clock missing, but hdmi spec mandates it for deep color. */ - DRM_DEBUG("%s: Required max tmds clock for HDMI deep color missing. Using 8 bpc.\n", - connector->name); - bpc = 8; } + } else if (bpc > 8) { + /* max_tmds_clock missing, but hdmi spec mandates it for deep color. */ + DRM_DEBUG("%s: Required max tmds clock for HDMI deep color missing. Using 8 bpc.\n", + connector->name); + bpc = 8; } } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index d5b421330145..c961fe093e12 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -1744,15 +1744,20 @@ int amdgpu_resume_kms(struct drm_device *dev, bool resume, bool fbcon) } /* post card */ - amdgpu_atom_asic_init(adev->mode_info.atom_context); + if (!amdgpu_card_posted(adev)) + amdgpu_atom_asic_init(adev->mode_info.atom_context); r = amdgpu_resume(adev); + if (r) + DRM_ERROR("amdgpu_resume failed (%d).\n", r); amdgpu_fence_driver_resume(adev); - r = amdgpu_ib_ring_tests(adev); - if (r) - DRM_ERROR("ib ring test failed (%d).\n", r); + if (resume) { + r = amdgpu_ib_ring_tests(adev); + if (r) + DRM_ERROR("ib ring test failed (%d).\n", r); + } r = amdgpu_late_init(adev); if (r) @@ -1788,6 +1793,7 @@ int amdgpu_resume_kms(struct drm_device *dev, bool resume, bool fbcon) } drm_kms_helper_poll_enable(dev); + drm_helper_hpd_irq_event(dev); if (fbcon) { amdgpu_fbdev_set_suspend(adev, 0); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index 5580d3420c3a..82903ca78529 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -72,8 +72,8 @@ static void amdgpu_flip_work_func(struct work_struct *__work) struct drm_crtc *crtc = &amdgpuCrtc->base; unsigned long flags; - unsigned i; - int vpos, hpos, stat, min_udelay; + unsigned i, repcnt = 4; + int vpos, hpos, stat, min_udelay = 0; struct drm_vblank_crtc *vblank = &crtc->dev->vblank[work->crtc_id]; amdgpu_flip_wait_fence(adev, &work->excl); @@ -96,7 +96,7 @@ static void amdgpu_flip_work_func(struct work_struct *__work) * In practice this won't execute very often unless on very fast * machines because the time window for this to happen is very small. */ - for (;;) { + while (amdgpuCrtc->enabled && --repcnt) { /* GET_DISTANCE_TO_VBLANKSTART returns distance to real vblank * start in hpos, and to the "fudged earlier" vblank start in * vpos. @@ -112,12 +112,24 @@ static void amdgpu_flip_work_func(struct work_struct *__work) break; /* Sleep at least until estimated real start of hw vblank */ - spin_unlock_irqrestore(&crtc->dev->event_lock, flags); min_udelay = (-hpos + 1) * max(vblank->linedur_ns / 1000, 5); + if (min_udelay > vblank->framedur_ns / 2000) { + /* Don't wait ridiculously long - something is wrong */ + repcnt = 0; + break; + } + spin_unlock_irqrestore(&crtc->dev->event_lock, flags); usleep_range(min_udelay, 2 * min_udelay); spin_lock_irqsave(&crtc->dev->event_lock, flags); }; + if (!repcnt) + DRM_DEBUG_DRIVER("Delay problem on crtc %d: min_udelay %d, " + "framedur %d, linedur %d, stat %d, vpos %d, " + "hpos %d\n", work->crtc_id, min_udelay, + vblank->framedur_ns / 1000, + vblank->linedur_ns / 1000, stat, vpos, hpos); + /* do the flip (mmio) */ adev->mode_info.funcs->page_flip(adev, work->crtc_id, work->base); /* set the flip status */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c index 7b7f4aba60c0..fe36caf1b7d7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c @@ -150,7 +150,7 @@ u32 amdgpu_dpm_get_vrefresh(struct amdgpu_device *adev) list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { amdgpu_crtc = to_amdgpu_crtc(crtc); if (crtc->enabled && amdgpu_crtc->enabled && amdgpu_crtc->hw_mode.clock) { - vrefresh = amdgpu_crtc->hw_mode.vrefresh; + vrefresh = drm_mode_vrefresh(&amdgpu_crtc->hw_mode); break; } } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 0508c5cd103a..8d6668cedf6d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -250,11 +250,11 @@ static struct pci_device_id pciidlist[] = { {0x1002, 0x985F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|AMD_IS_MOBILITY|AMD_IS_APU}, #endif /* topaz */ - {0x1002, 0x6900, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ|AMD_EXP_HW_SUPPORT}, - {0x1002, 0x6901, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ|AMD_EXP_HW_SUPPORT}, - {0x1002, 0x6902, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ|AMD_EXP_HW_SUPPORT}, - {0x1002, 0x6903, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ|AMD_EXP_HW_SUPPORT}, - {0x1002, 0x6907, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ|AMD_EXP_HW_SUPPORT}, + {0x1002, 0x6900, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ}, + {0x1002, 0x6901, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ}, + {0x1002, 0x6902, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ}, + {0x1002, 0x6903, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ}, + {0x1002, 0x6907, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TOPAZ}, /* tonga */ {0x1002, 0x6920, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TONGA}, {0x1002, 0x6921, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TONGA}, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index e23843f4d877..4488e82f87b0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -303,7 +303,7 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file fw_info.feature = adev->vce.fb_version; break; case AMDGPU_INFO_FW_UVD: - fw_info.ver = 0; + fw_info.ver = adev->uvd.fw_version; fw_info.feature = 0; break; case AMDGPU_INFO_FW_GMC: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c index b1969f2b2038..d4e2780c0796 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c @@ -142,7 +142,8 @@ static void amdgpu_mn_invalidate_range_start(struct mmu_notifier *mn, list_for_each_entry(bo, &node->bos, mn_list) { - if (!bo->tbo.ttm || bo->tbo.ttm->state != tt_bound) + if (!amdgpu_ttm_tt_affect_userptr(bo->tbo.ttm, start, + end)) continue; r = amdgpu_bo_reserve(bo, true); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h index 064ebb347074..89df7871653d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h @@ -52,7 +52,7 @@ struct amdgpu_hpd; #define AMDGPU_MAX_HPD_PINS 6 #define AMDGPU_MAX_CRTCS 6 -#define AMDGPU_MAX_AFMT_BLOCKS 7 +#define AMDGPU_MAX_AFMT_BLOCKS 9 enum amdgpu_rmx_type { RMX_OFF, @@ -308,8 +308,8 @@ struct amdgpu_mode_info { struct atom_context *atom_context; struct card_info *atom_card_info; bool mode_config_initialized; - struct amdgpu_crtc *crtcs[6]; - struct amdgpu_afmt *afmt[7]; + struct amdgpu_crtc *crtcs[AMDGPU_MAX_CRTCS]; + struct amdgpu_afmt *afmt[AMDGPU_MAX_AFMT_BLOCKS]; /* DVI-I properties */ struct drm_property *coherent_mode_property; /* DAC enable load detect */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index c3ce103b6a33..73628c7599e7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -33,6 +33,7 @@ #include #include #include +#include #include "amdgpu.h" #include "amdgpu_trace.h" @@ -261,6 +262,13 @@ int amdgpu_bo_create_restricted(struct amdgpu_device *adev, AMDGPU_GEM_DOMAIN_OA); bo->flags = flags; + + /* For architectures that don't support WC memory, + * mask out the WC flag from the BO + */ + if (!drm_arch_can_wc_memory()) + bo->flags &= ~AMDGPU_GEM_CREATE_CPU_GTT_USWC; + amdgpu_fill_placement_to_bo(bo, placement); /* Kernel allocation are uninterruptible */ r = ttm_bo_init(&adev->mman.bdev, &bo->tbo, size, type, @@ -399,7 +407,8 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain, } if (fpfn > bo->placements[i].fpfn) bo->placements[i].fpfn = fpfn; - if (lpfn && lpfn < bo->placements[i].lpfn) + if (!bo->placements[i].lpfn || + (lpfn && lpfn < bo->placements[i].lpfn)) bo->placements[i].lpfn = lpfn; bo->placements[i].flags |= TTM_PL_FLAG_NO_EVICT; } @@ -531,6 +540,7 @@ int amdgpu_bo_set_metadata (struct amdgpu_bo *bo, void *metadata, if (!metadata_size) { if (bo->metadata_size) { kfree(bo->metadata); + bo->metadata = NULL; bo->metadata_size = 0; } return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c index 22a8c7d3a3ab..7ae15fad16ed 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c @@ -595,11 +595,6 @@ force: /* update display watermarks based on new power state */ amdgpu_display_bandwidth_update(adev); - /* update displays */ - amdgpu_dpm_display_configuration_changed(adev); - - adev->pm.dpm.current_active_crtcs = adev->pm.dpm.new_active_crtcs; - adev->pm.dpm.current_active_crtc_count = adev->pm.dpm.new_active_crtc_count; /* wait for the rings to drain */ for (i = 0; i < AMDGPU_MAX_RINGS; i++) { @@ -616,6 +611,12 @@ force: amdgpu_dpm_post_set_power_state(adev); + /* update displays */ + amdgpu_dpm_display_configuration_changed(adev); + + adev->pm.dpm.current_active_crtcs = adev->pm.dpm.new_active_crtcs; + adev->pm.dpm.current_active_crtc_count = adev->pm.dpm.new_active_crtc_count; + if (adev->pm.funcs->force_performance_level) { if (adev->pm.dpm.thermal_active) { enum amdgpu_dpm_forced_level level = adev->pm.dpm.forced_level; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c index 8b88edb0434b..ca72a2e487b9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c @@ -354,12 +354,15 @@ int amdgpu_sa_bo_new(struct amdgpu_sa_manager *sa_manager, for (i = 0, count = 0; i < AMDGPU_MAX_RINGS; ++i) if (fences[i]) - fences[count++] = fences[i]; + fences[count++] = fence_get(fences[i]); if (count) { spin_unlock(&sa_manager->wq.lock); t = fence_wait_any_timeout(fences, count, false, MAX_SCHEDULE_TIMEOUT); + for (i = 0; i < count; ++i) + fence_put(fences[i]); + r = (t > 0) ? 0 : t; spin_lock(&sa_manager->wq.lock); } else { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c index dd005c336c97..181ce39ef5e5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c @@ -293,7 +293,8 @@ int amdgpu_sync_rings(struct amdgpu_sync *sync, fence = to_amdgpu_fence(sync->sync_to[i]); /* check if we really need to sync */ - if (!amdgpu_fence_need_sync(fence, ring)) + if (!amdgpu_enable_scheduler && + !amdgpu_fence_need_sync(fence, ring)) continue; /* prevent GPU deadlocks */ @@ -303,7 +304,7 @@ int amdgpu_sync_rings(struct amdgpu_sync *sync, } if (amdgpu_enable_scheduler || !amdgpu_enable_semaphores) { - r = fence_wait(&fence->base, true); + r = fence_wait(sync->sync_to[i], true); if (r) return r; continue; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 8a1752ff3d8e..1cbb16e15307 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -712,7 +712,7 @@ static int amdgpu_ttm_tt_populate(struct ttm_tt *ttm) 0, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); if (pci_dma_mapping_error(adev->pdev, gtt->ttm.dma_address[i])) { - while (--i) { + while (i--) { pci_unmap_page(adev->pdev, gtt->ttm.dma_address[i], PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); gtt->ttm.dma_address[i] = 0; @@ -783,6 +783,25 @@ bool amdgpu_ttm_tt_has_userptr(struct ttm_tt *ttm) return !!gtt->userptr; } +bool amdgpu_ttm_tt_affect_userptr(struct ttm_tt *ttm, unsigned long start, + unsigned long end) +{ + struct amdgpu_ttm_tt *gtt = (void *)ttm; + unsigned long size; + + if (gtt == NULL) + return false; + + if (gtt->ttm.ttm.state != tt_bound || !gtt->userptr) + return false; + + size = (unsigned long)gtt->ttm.ttm.num_pages * PAGE_SIZE; + if (gtt->userptr > end || gtt->userptr + size <= start) + return false; + + return true; +} + bool amdgpu_ttm_tt_is_readonly(struct ttm_tt *ttm) { struct amdgpu_ttm_tt *gtt = (void *)ttm; @@ -808,7 +827,7 @@ uint32_t amdgpu_ttm_tt_pte_flags(struct amdgpu_device *adev, struct ttm_tt *ttm, flags |= AMDGPU_PTE_SNOOPED; } - if (adev->asic_type >= CHIP_TOPAZ) + if (adev->asic_type >= CHIP_TONGA) flags |= AMDGPU_PTE_EXECUTABLE; flags |= AMDGPU_PTE_READABLE; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c index 53f987aeeacf..3b35ad83867c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c @@ -156,6 +156,9 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev) DRM_INFO("Found UVD firmware Version: %hu.%hu Family ID: %hu\n", version_major, version_minor, family_id); + adev->uvd.fw_version = ((version_major << 24) | (version_minor << 16) | + (family_id << 8)); + bo_size = AMDGPU_GPU_PAGE_ALIGN(le32_to_cpu(hdr->ucode_size_bytes) + 8) + AMDGPU_UVD_STACK_SIZE + AMDGPU_UVD_HEAP_SIZE; r = amdgpu_bo_create(adev, bo_size, PAGE_SIZE, true, @@ -273,6 +276,8 @@ int amdgpu_uvd_resume(struct amdgpu_device *adev) memcpy(adev->uvd.cpu_addr, (adev->uvd.fw->data) + offset, (adev->uvd.fw->size) - offset); + cancel_delayed_work_sync(&adev->uvd.idle_work); + size = amdgpu_bo_size(adev->uvd.vcpu_bo); size -= le32_to_cpu(hdr->ucode_size_bytes); ptr = adev->uvd.cpu_addr; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c index a745eeeb5d82..bb0da76051a1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c @@ -220,6 +220,7 @@ int amdgpu_vce_suspend(struct amdgpu_device *adev) if (i == AMDGPU_MAX_VCE_HANDLES) return 0; + cancel_delayed_work_sync(&adev->vce.idle_work); /* TODO: suspending running encoding sessions isn't supported */ return -EINVAL; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index b53d273eb7a1..8c5ec151ddac 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -1010,13 +1010,13 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev, return -EINVAL; /* make sure object fit at this offset */ - eaddr = saddr + size; + eaddr = saddr + size - 1; if ((saddr >= eaddr) || (offset + size > amdgpu_bo_size(bo_va->bo))) return -EINVAL; last_pfn = eaddr / AMDGPU_GPU_PAGE_SIZE; - if (last_pfn > adev->vm_manager.max_pfn) { - dev_err(adev->dev, "va above limit (0x%08X > 0x%08X)\n", + if (last_pfn >= adev->vm_manager.max_pfn) { + dev_err(adev->dev, "va above limit (0x%08X >= 0x%08X)\n", last_pfn, adev->vm_manager.max_pfn); return -EINVAL; } @@ -1025,7 +1025,7 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev, eaddr /= AMDGPU_GPU_PAGE_SIZE; spin_lock(&vm->it_lock); - it = interval_tree_iter_first(&vm->va, saddr, eaddr - 1); + it = interval_tree_iter_first(&vm->va, saddr, eaddr); spin_unlock(&vm->it_lock); if (it) { struct amdgpu_bo_va_mapping *tmp; @@ -1046,7 +1046,7 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev, INIT_LIST_HEAD(&mapping->list); mapping->it.start = saddr; - mapping->it.last = eaddr - 1; + mapping->it.last = eaddr; mapping->offset = offset; mapping->flags = flags; @@ -1248,7 +1248,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm) { const unsigned align = min(AMDGPU_VM_PTB_ALIGN_SIZE, AMDGPU_VM_PTE_COUNT * 8); - unsigned pd_size, pd_entries, pts_size; + unsigned pd_size, pd_entries; int i, r; for (i = 0; i < AMDGPU_MAX_RINGS; ++i) { @@ -1266,8 +1266,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm) pd_entries = amdgpu_vm_num_pdes(adev); /* allocate page table array */ - pts_size = pd_entries * sizeof(struct amdgpu_vm_pt); - vm->page_tables = kzalloc(pts_size, GFP_KERNEL); + vm->page_tables = drm_calloc_large(pd_entries, sizeof(struct amdgpu_vm_pt)); if (vm->page_tables == NULL) { DRM_ERROR("Cannot allocate memory for page table array\n"); return -ENOMEM; @@ -1327,7 +1326,7 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm) for (i = 0; i < amdgpu_vm_num_pdes(adev); i++) amdgpu_bo_unref(&vm->page_tables[i].bo); - kfree(vm->page_tables); + drm_free_large(vm->page_tables); amdgpu_bo_unref(&vm->page_directory); fence_put(vm->page_directory_fence); diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c index 1e0bba29e167..1cd6de575305 100644 --- a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c +++ b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c @@ -298,6 +298,10 @@ bool amdgpu_atombios_encoder_mode_fixup(struct drm_encoder *encoder, && (mode->crtc_vsync_start < (mode->crtc_vdisplay + 2))) adjusted_mode->crtc_vsync_start = adjusted_mode->crtc_vdisplay + 2; + /* vertical FP must be at least 1 */ + if (mode->crtc_vsync_start == mode->crtc_vdisplay) + adjusted_mode->crtc_vsync_start++; + /* get the native mode for scaling */ if (amdgpu_encoder->active_device & (ATOM_DEVICE_LCD_SUPPORT)) amdgpu_panel_mode_fixup(encoder, adjusted_mode); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c index 72793f93e2fc..b57fffc2d4af 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c @@ -3628,6 +3628,19 @@ static void gfx_v7_0_ring_emit_vm_flush(struct amdgpu_ring *ring, unsigned vm_id, uint64_t pd_addr) { int usepfp = (ring->type == AMDGPU_RING_TYPE_GFX); + uint32_t seq = ring->fence_drv.sync_seq[ring->idx]; + uint64_t addr = ring->fence_drv.gpu_addr; + + amdgpu_ring_write(ring, PACKET3(PACKET3_WAIT_REG_MEM, 5)); + amdgpu_ring_write(ring, (WAIT_REG_MEM_MEM_SPACE(1) | /* memory */ + WAIT_REG_MEM_FUNCTION(3) | /* equal */ + WAIT_REG_MEM_ENGINE(usepfp))); /* pfp or me */ + amdgpu_ring_write(ring, addr & 0xfffffffc); + amdgpu_ring_write(ring, upper_32_bits(addr) & 0xffffffff); + amdgpu_ring_write(ring, seq); + amdgpu_ring_write(ring, 0xffffffff); + amdgpu_ring_write(ring, 4); /* poll interval */ + if (usepfp) { /* synce CE with ME to prevent CE fetch CEIB before context switch done */ amdgpu_ring_write(ring, PACKET3(PACKET3_SWITCH_BUFFER, 0)); @@ -5450,7 +5463,7 @@ static int gfx_v7_0_eop_irq(struct amdgpu_device *adev, case 2: for (i = 0; i < adev->gfx.num_compute_rings; i++) { ring = &adev->gfx.compute_ring[i]; - if ((ring->me == me_id) & (ring->pipe == pipe_id)) + if ((ring->me == me_id) && (ring->pipe == pipe_id)) amdgpu_fence_process(ring); } break; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index e1dcab98e249..d1054034d14b 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -90,7 +90,6 @@ MODULE_FIRMWARE("amdgpu/topaz_ce.bin"); MODULE_FIRMWARE("amdgpu/topaz_pfp.bin"); MODULE_FIRMWARE("amdgpu/topaz_me.bin"); MODULE_FIRMWARE("amdgpu/topaz_mec.bin"); -MODULE_FIRMWARE("amdgpu/topaz_mec2.bin"); MODULE_FIRMWARE("amdgpu/topaz_rlc.bin"); MODULE_FIRMWARE("amdgpu/fiji_ce.bin"); @@ -807,7 +806,8 @@ static int gfx_v8_0_init_microcode(struct amdgpu_device *adev) adev->gfx.mec_fw_version = le32_to_cpu(cp_hdr->header.ucode_version); adev->gfx.mec_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version); - if (adev->asic_type != CHIP_STONEY) { + if ((adev->asic_type != CHIP_STONEY) && + (adev->asic_type != CHIP_TOPAZ)) { snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec2.bin", chip_name); err = request_firmware(&adev->gfx.mec2_fw, fw_name, adev->dev); if (!err) { @@ -4681,7 +4681,8 @@ static void gfx_v8_0_ring_emit_vm_flush(struct amdgpu_ring *ring, amdgpu_ring_write(ring, PACKET3(PACKET3_WAIT_REG_MEM, 5)); amdgpu_ring_write(ring, (WAIT_REG_MEM_MEM_SPACE(1) | /* memory */ - WAIT_REG_MEM_FUNCTION(3))); /* equal */ + WAIT_REG_MEM_FUNCTION(3) | /* equal */ + WAIT_REG_MEM_ENGINE(usepfp))); /* pfp or me */ amdgpu_ring_write(ring, addr & 0xfffffffc); amdgpu_ring_write(ring, upper_32_bits(addr) & 0xffffffff); amdgpu_ring_write(ring, seq); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c index ed8abb58a785..ea87033bfaf6 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c @@ -42,9 +42,39 @@ static void gmc_v7_0_set_irq_funcs(struct amdgpu_device *adev); MODULE_FIRMWARE("radeon/bonaire_mc.bin"); MODULE_FIRMWARE("radeon/hawaii_mc.bin"); +MODULE_FIRMWARE("amdgpu/topaz_mc.bin"); + +static const u32 golden_settings_iceland_a11[] = +{ + mmVM_PRT_APERTURE0_LOW_ADDR, 0x0fffffff, 0x0fffffff, + mmVM_PRT_APERTURE1_LOW_ADDR, 0x0fffffff, 0x0fffffff, + mmVM_PRT_APERTURE2_LOW_ADDR, 0x0fffffff, 0x0fffffff, + mmVM_PRT_APERTURE3_LOW_ADDR, 0x0fffffff, 0x0fffffff +}; + +static const u32 iceland_mgcg_cgcg_init[] = +{ + mmMC_MEM_POWER_LS, 0xffffffff, 0x00000104 +}; + +static void gmc_v7_0_init_golden_registers(struct amdgpu_device *adev) +{ + switch (adev->asic_type) { + case CHIP_TOPAZ: + amdgpu_program_register_sequence(adev, + iceland_mgcg_cgcg_init, + (const u32)ARRAY_SIZE(iceland_mgcg_cgcg_init)); + amdgpu_program_register_sequence(adev, + golden_settings_iceland_a11, + (const u32)ARRAY_SIZE(golden_settings_iceland_a11)); + break; + default: + break; + } +} /** - * gmc8_mc_wait_for_idle - wait for MC idle callback. + * gmc7_mc_wait_for_idle - wait for MC idle callback. * * @adev: amdgpu_device pointer * @@ -132,13 +162,20 @@ static int gmc_v7_0_init_microcode(struct amdgpu_device *adev) case CHIP_HAWAII: chip_name = "hawaii"; break; + case CHIP_TOPAZ: + chip_name = "topaz"; + break; case CHIP_KAVERI: case CHIP_KABINI: return 0; default: BUG(); } - snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", chip_name); + if (adev->asic_type == CHIP_TOPAZ) + snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mc.bin", chip_name); + else + snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", chip_name); + err = request_firmware(&adev->mc.fw, fw_name, adev->dev); if (err) goto out; @@ -861,14 +898,6 @@ static int gmc_v7_0_early_init(void *handle) gmc_v7_0_set_gart_funcs(adev); gmc_v7_0_set_irq_funcs(adev); - if (adev->flags & AMD_IS_APU) { - adev->mc.vram_type = AMDGPU_VRAM_TYPE_UNKNOWN; - } else { - u32 tmp = RREG32(mmMC_SEQ_MISC0); - tmp &= MC_SEQ_MISC0__MT__MASK; - adev->mc.vram_type = gmc_v7_0_convert_vram_type(tmp); - } - return 0; } @@ -889,6 +918,14 @@ static int gmc_v7_0_sw_init(void *handle) if (r) return r; + if (adev->flags & AMD_IS_APU) { + adev->mc.vram_type = AMDGPU_VRAM_TYPE_UNKNOWN; + } else { + u32 tmp = RREG32(mmMC_SEQ_MISC0); + tmp &= MC_SEQ_MISC0__MT__MASK; + adev->mc.vram_type = gmc_v7_0_convert_vram_type(tmp); + } + r = amdgpu_irq_add_id(adev, 146, &adev->mc.vm_fault); if (r) return r; @@ -980,6 +1017,8 @@ static int gmc_v7_0_hw_init(void *handle) int r; struct amdgpu_device *adev = (struct amdgpu_device *)handle; + gmc_v7_0_init_golden_registers(adev); + gmc_v7_0_mc_program(adev); if (!(adev->flags & AMD_IS_APU)) { diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c index d39028440814..08423089fb84 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c @@ -42,9 +42,7 @@ static void gmc_v8_0_set_gart_funcs(struct amdgpu_device *adev); static void gmc_v8_0_set_irq_funcs(struct amdgpu_device *adev); -MODULE_FIRMWARE("amdgpu/topaz_mc.bin"); MODULE_FIRMWARE("amdgpu/tonga_mc.bin"); -MODULE_FIRMWARE("amdgpu/fiji_mc.bin"); static const u32 golden_settings_tonga_a11[] = { @@ -75,19 +73,6 @@ static const u32 fiji_mgcg_cgcg_init[] = mmMC_MEM_POWER_LS, 0xffffffff, 0x00000104 }; -static const u32 golden_settings_iceland_a11[] = -{ - mmVM_PRT_APERTURE0_LOW_ADDR, 0x0fffffff, 0x0fffffff, - mmVM_PRT_APERTURE1_LOW_ADDR, 0x0fffffff, 0x0fffffff, - mmVM_PRT_APERTURE2_LOW_ADDR, 0x0fffffff, 0x0fffffff, - mmVM_PRT_APERTURE3_LOW_ADDR, 0x0fffffff, 0x0fffffff -}; - -static const u32 iceland_mgcg_cgcg_init[] = -{ - mmMC_MEM_POWER_LS, 0xffffffff, 0x00000104 -}; - static const u32 cz_mgcg_cgcg_init[] = { mmMC_MEM_POWER_LS, 0xffffffff, 0x00000104 @@ -102,14 +87,6 @@ static const u32 stoney_mgcg_cgcg_init[] = static void gmc_v8_0_init_golden_registers(struct amdgpu_device *adev) { switch (adev->asic_type) { - case CHIP_TOPAZ: - amdgpu_program_register_sequence(adev, - iceland_mgcg_cgcg_init, - (const u32)ARRAY_SIZE(iceland_mgcg_cgcg_init)); - amdgpu_program_register_sequence(adev, - golden_settings_iceland_a11, - (const u32)ARRAY_SIZE(golden_settings_iceland_a11)); - break; case CHIP_FIJI: amdgpu_program_register_sequence(adev, fiji_mgcg_cgcg_init, @@ -229,15 +206,10 @@ static int gmc_v8_0_init_microcode(struct amdgpu_device *adev) DRM_DEBUG("\n"); switch (adev->asic_type) { - case CHIP_TOPAZ: - chip_name = "topaz"; - break; case CHIP_TONGA: chip_name = "tonga"; break; case CHIP_FIJI: - chip_name = "fiji"; - break; case CHIP_CARRIZO: case CHIP_STONEY: return 0; @@ -880,14 +852,6 @@ static int gmc_v8_0_early_init(void *handle) gmc_v8_0_set_gart_funcs(adev); gmc_v8_0_set_irq_funcs(adev); - if (adev->flags & AMD_IS_APU) { - adev->mc.vram_type = AMDGPU_VRAM_TYPE_UNKNOWN; - } else { - u32 tmp = RREG32(mmMC_SEQ_MISC0); - tmp &= MC_SEQ_MISC0__MT__MASK; - adev->mc.vram_type = gmc_v8_0_convert_vram_type(tmp); - } - return 0; } @@ -898,6 +862,8 @@ static int gmc_v8_0_late_init(void *handle) return amdgpu_irq_get(adev, &adev->mc.vm_fault, 0); } +#define mmMC_SEQ_MISC0_FIJI 0xA71 + static int gmc_v8_0_sw_init(void *handle) { int r; @@ -908,6 +874,19 @@ static int gmc_v8_0_sw_init(void *handle) if (r) return r; + if (adev->flags & AMD_IS_APU) { + adev->mc.vram_type = AMDGPU_VRAM_TYPE_UNKNOWN; + } else { + u32 tmp; + + if (adev->asic_type == CHIP_FIJI) + tmp = RREG32(mmMC_SEQ_MISC0_FIJI); + else + tmp = RREG32(mmMC_SEQ_MISC0); + tmp &= MC_SEQ_MISC0__MT__MASK; + adev->mc.vram_type = gmc_v8_0_convert_vram_type(tmp); + } + r = amdgpu_irq_add_id(adev, 146, &adev->mc.vm_fault); if (r) return r; @@ -1003,7 +982,7 @@ static int gmc_v8_0_hw_init(void *handle) gmc_v8_0_mc_program(adev); - if (!(adev->flags & AMD_IS_APU)) { + if (adev->asic_type == CHIP_TONGA) { r = gmc_v8_0_mc_load_microcode(adev); if (r) { DRM_ERROR("Failed to load MC firmware!\n"); diff --git a/drivers/gpu/drm/amd/amdgpu/iceland_smc.c b/drivers/gpu/drm/amd/amdgpu/iceland_smc.c index 966d4b2ed9da..090486c18249 100644 --- a/drivers/gpu/drm/amd/amdgpu/iceland_smc.c +++ b/drivers/gpu/drm/amd/amdgpu/iceland_smc.c @@ -432,7 +432,7 @@ static uint32_t iceland_smu_get_mask_for_fw_type(uint32_t fw_type) case AMDGPU_UCODE_ID_CP_ME: return UCODE_ID_CP_ME_MASK; case AMDGPU_UCODE_ID_CP_MEC1: - return UCODE_ID_CP_MEC_MASK | UCODE_ID_CP_MEC_JT1_MASK | UCODE_ID_CP_MEC_JT2_MASK; + return UCODE_ID_CP_MEC_MASK | UCODE_ID_CP_MEC_JT1_MASK; case AMDGPU_UCODE_ID_CP_MEC2: return UCODE_ID_CP_MEC_MASK; case AMDGPU_UCODE_ID_RLC_G: @@ -522,12 +522,6 @@ static int iceland_smu_request_load_fw(struct amdgpu_device *adev) return -EINVAL; } - if (iceland_smu_populate_single_firmware_entry(adev, UCODE_ID_CP_MEC_JT2, - &toc->entry[toc->num_entries++])) { - DRM_ERROR("Failed to get firmware entry for MEC_JT2\n"); - return -EINVAL; - } - if (iceland_smu_populate_single_firmware_entry(adev, UCODE_ID_SDMA0, &toc->entry[toc->num_entries++])) { DRM_ERROR("Failed to get firmware entry for SDMA0\n"); @@ -550,8 +544,8 @@ static int iceland_smu_request_load_fw(struct amdgpu_device *adev) UCODE_ID_CP_ME_MASK | UCODE_ID_CP_PFP_MASK | UCODE_ID_CP_MEC_MASK | - UCODE_ID_CP_MEC_JT1_MASK | - UCODE_ID_CP_MEC_JT2_MASK; + UCODE_ID_CP_MEC_JT1_MASK; + if (iceland_send_msg_to_smc_with_parameter_without_waiting(adev, PPSMC_MSG_LoadUcodes, fw_to_load)) { DRM_ERROR("Fail to request SMU load ucode\n"); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c index 2cf50180cc51..b1c7a9b3631b 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c @@ -32,8 +32,8 @@ #include "oss/oss_2_4_d.h" #include "oss/oss_2_4_sh_mask.h" -#include "gmc/gmc_8_1_d.h" -#include "gmc/gmc_8_1_sh_mask.h" +#include "gmc/gmc_7_1_d.h" +#include "gmc/gmc_7_1_sh_mask.h" #include "gca/gfx_8_0_d.h" #include "gca/gfx_8_0_enum.h" diff --git a/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c b/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c index 204903897b4f..63d6cb3c1110 100644 --- a/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/tonga_dpm.c @@ -122,25 +122,12 @@ static int tonga_dpm_hw_fini(void *handle) static int tonga_dpm_suspend(void *handle) { - return 0; + return tonga_dpm_hw_fini(handle); } static int tonga_dpm_resume(void *handle) { - int ret; - struct amdgpu_device *adev = (struct amdgpu_device *)handle; - - mutex_lock(&adev->pm.mutex); - - ret = tonga_smu_start(adev); - if (ret) { - DRM_ERROR("SMU start failed\n"); - goto fail; - } - -fail: - mutex_unlock(&adev->pm.mutex); - return ret; + return tonga_dpm_hw_init(handle); } static int tonga_dpm_set_clockgating_state(void *handle, diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c index 2adc1c855e85..3e9cbe398151 100644 --- a/drivers/gpu/drm/amd/amdgpu/vi.c +++ b/drivers/gpu/drm/amd/amdgpu/vi.c @@ -60,6 +60,7 @@ #include "vi.h" #include "vi_dpm.h" #include "gmc_v8_0.h" +#include "gmc_v7_0.h" #include "gfx_v8_0.h" #include "sdma_v2_4.h" #include "sdma_v3_0.h" @@ -1081,10 +1082,10 @@ static const struct amdgpu_ip_block_version topaz_ip_blocks[] = }, { .type = AMD_IP_BLOCK_TYPE_GMC, - .major = 8, - .minor = 0, + .major = 7, + .minor = 4, .rev = 0, - .funcs = &gmc_v8_0_ip_funcs, + .funcs = &gmc_v7_0_ip_funcs, }, { .type = AMD_IP_BLOCK_TYPE_IH, diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c index c34c393e9aea..d5e19b5fbbfb 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c @@ -513,7 +513,7 @@ static int dbgdev_wave_control_set_registers( union SQ_CMD_BITS *in_reg_sq_cmd, union GRBM_GFX_INDEX_BITS *in_reg_gfx_index) { - int status; + int status = 0; union SQ_CMD_BITS reg_sq_cmd; union GRBM_GFX_INDEX_BITS reg_gfx_index; struct HsaDbgWaveMsgAMDGen2 *pMsg; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index 9be007081b72..eb1da83c9902 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -242,13 +242,19 @@ static void kfd_process_notifier_release(struct mmu_notifier *mn, pqm_uninit(&p->pqm); /* Iterate over all process device data structure and check - * if we should reset all wavefronts */ - list_for_each_entry(pdd, &p->per_device_data, per_device_list) + * if we should delete debug managers and reset all wavefronts + */ + list_for_each_entry(pdd, &p->per_device_data, per_device_list) { + if ((pdd->dev->dbgmgr) && + (pdd->dev->dbgmgr->pasid == p->pasid)) + kfd_dbgmgr_destroy(pdd->dev->dbgmgr); + if (pdd->reset_wavefronts) { pr_warn("amdkfd: Resetting all wave fronts\n"); dbgdev_wave_reset_wavefronts(pdd->dev, p); pdd->reset_wavefronts = false; } + } mutex_unlock(&p->mutex); @@ -404,42 +410,52 @@ void kfd_unbind_process_from_device(struct kfd_dev *dev, unsigned int pasid) idx = srcu_read_lock(&kfd_processes_srcu); + /* + * Look for the process that matches the pasid. If there is no such + * process, we either released it in amdkfd's own notifier, or there + * is a bug. Unfortunately, there is no way to tell... + */ hash_for_each_rcu(kfd_processes_table, i, p, kfd_processes) - if (p->pasid == pasid) - break; + if (p->pasid == pasid) { + + srcu_read_unlock(&kfd_processes_srcu, idx); + + pr_debug("Unbinding process %d from IOMMU\n", pasid); + + mutex_lock(&p->mutex); + + if ((dev->dbgmgr) && (dev->dbgmgr->pasid == p->pasid)) + kfd_dbgmgr_destroy(dev->dbgmgr); + + pqm_uninit(&p->pqm); + + pdd = kfd_get_process_device_data(dev, p); + + if (!pdd) { + mutex_unlock(&p->mutex); + return; + } + + if (pdd->reset_wavefronts) { + dbgdev_wave_reset_wavefronts(pdd->dev, p); + pdd->reset_wavefronts = false; + } + + /* + * Just mark pdd as unbound, because we still need it + * to call amd_iommu_unbind_pasid() in when the + * process exits. + * We don't call amd_iommu_unbind_pasid() here + * because the IOMMU called us. + */ + pdd->bound = false; + + mutex_unlock(&p->mutex); + + return; + } srcu_read_unlock(&kfd_processes_srcu, idx); - - BUG_ON(p->pasid != pasid); - - mutex_lock(&p->mutex); - - if ((dev->dbgmgr) && (dev->dbgmgr->pasid == p->pasid)) - kfd_dbgmgr_destroy(dev->dbgmgr); - - pqm_uninit(&p->pqm); - - pdd = kfd_get_process_device_data(dev, p); - - if (!pdd) { - mutex_unlock(&p->mutex); - return; - } - - if (pdd->reset_wavefronts) { - dbgdev_wave_reset_wavefronts(pdd->dev, p); - pdd->reset_wavefronts = false; - } - - /* - * Just mark pdd as unbound, because we still need it to call - * amd_iommu_unbind_pasid() in when the process exits. - * We don't call amd_iommu_unbind_pasid() here - * because the IOMMU called us. - */ - pdd->bound = false; - - mutex_unlock(&p->mutex); } struct kfd_process_device *kfd_get_first_process_device_data(struct kfd_process *p) diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c index 541a610667ad..e0b4586a26fd 100644 --- a/drivers/gpu/drm/ast/ast_main.c +++ b/drivers/gpu/drm/ast/ast_main.c @@ -227,7 +227,7 @@ static int ast_get_dram_info(struct drm_device *dev) } while (ast_read32(ast, 0x10000) != 0x01); data = ast_read32(ast, 0x10004); - if (data & 0x400) + if (data & 0x40) ast->dram_bus_width = 16; else ast->dram_bus_width = 32; diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c index d0299aed517e..59d1269626b1 100644 --- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c +++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c @@ -335,6 +335,8 @@ atmel_hlcdc_plane_update_pos_and_size(struct atmel_hlcdc_plane *plane, atmel_hlcdc_layer_update_cfg(&plane->layer, 13, 0xffffffff, factor_reg); + } else { + atmel_hlcdc_layer_update_cfg(&plane->layer, 13, 0xffffffff, 0); } } diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c index aeee083c7f95..6253775b8d9c 100644 --- a/drivers/gpu/drm/drm_atomic.c +++ b/drivers/gpu/drm/drm_atomic.c @@ -150,7 +150,7 @@ void drm_atomic_state_default_clear(struct drm_atomic_state *state) for (i = 0; i < state->num_connector; i++) { struct drm_connector *connector = state->connectors[i]; - if (!connector) + if (!connector || !connector->funcs) continue; /* @@ -367,6 +367,8 @@ int drm_atomic_set_mode_prop_for_crtc(struct drm_crtc_state *state, drm_property_unreference_blob(state->mode_blob); state->mode_blob = NULL; + memset(&state->mode, 0, sizeof(state->mode)); + if (blob) { if (blob->length != sizeof(struct drm_mode_modeinfo) || drm_mode_convert_umode(&state->mode, @@ -379,7 +381,6 @@ int drm_atomic_set_mode_prop_for_crtc(struct drm_crtc_state *state, DRM_DEBUG_ATOMIC("Set [MODE:%s] for CRTC state %p\n", state->mode.name, state); } else { - memset(&state->mode, 0, sizeof(state->mode)); state->enable = false; DRM_DEBUG_ATOMIC("Set [NOMODE] for CRTC state %p\n", state); diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index 24c5434abd1c..dc84003f694e 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -2682,8 +2682,6 @@ int drm_mode_setcrtc(struct drm_device *dev, void *data, goto out; } - drm_mode_set_crtcinfo(mode, CRTC_INTERLACE_HALVE_V); - /* * Check whether the primary plane supports the fb pixel format. * Drivers not implementing the universal planes API use a @@ -3316,6 +3314,24 @@ int drm_mode_addfb2(struct drm_device *dev, return 0; } +struct drm_mode_rmfb_work { + struct work_struct work; + struct list_head fbs; +}; + +static void drm_mode_rmfb_work_fn(struct work_struct *w) +{ + struct drm_mode_rmfb_work *arg = container_of(w, typeof(*arg), work); + + while (!list_empty(&arg->fbs)) { + struct drm_framebuffer *fb = + list_first_entry(&arg->fbs, typeof(*fb), filp_head); + + list_del_init(&fb->filp_head); + drm_framebuffer_remove(fb); + } +} + /** * drm_mode_rmfb - remove an FB from the configuration * @dev: drm device for the ioctl @@ -3356,7 +3372,25 @@ int drm_mode_rmfb(struct drm_device *dev, mutex_unlock(&dev->mode_config.fb_lock); mutex_unlock(&file_priv->fbs_lock); - drm_framebuffer_unreference(fb); + /* + * we now own the reference that was stored in the fbs list + * + * drm_framebuffer_remove may fail with -EINTR on pending signals, + * so run this in a separate stack as there's no way to correctly + * handle this after the fb is already removed from the lookup table. + */ + if (atomic_read(&fb->refcount.refcount) > 1) { + struct drm_mode_rmfb_work arg; + + INIT_WORK_ONSTACK(&arg.work, drm_mode_rmfb_work_fn); + INIT_LIST_HEAD(&arg.fbs); + list_add_tail(&fb->filp_head, &arg.fbs); + + schedule_work(&arg.work); + flush_work(&arg.work); + destroy_work_on_stack(&arg.work); + } else + drm_framebuffer_unreference(fb); return 0; @@ -3509,7 +3543,6 @@ out_err1: return ret; } - /** * drm_fb_release - remove and free the FBs on this file * @priv: drm file for the ioctl @@ -3524,6 +3557,9 @@ out_err1: void drm_fb_release(struct drm_file *priv) { struct drm_framebuffer *fb, *tfb; + struct drm_mode_rmfb_work arg; + + INIT_LIST_HEAD(&arg.fbs); /* * When the file gets released that means no one else can access the fb @@ -3536,10 +3572,22 @@ void drm_fb_release(struct drm_file *priv) * at it any more. */ list_for_each_entry_safe(fb, tfb, &priv->fbs, filp_head) { - list_del_init(&fb->filp_head); + if (atomic_read(&fb->refcount.refcount) > 1) { + list_move_tail(&fb->filp_head, &arg.fbs); + } else { + list_del_init(&fb->filp_head); - /* This drops the fpriv->fbs reference. */ - drm_framebuffer_unreference(fb); + /* This drops the fpriv->fbs reference. */ + drm_framebuffer_unreference(fb); + } + } + + if (!list_empty(&arg.fbs)) { + INIT_WORK_ONSTACK(&arg.work, drm_mode_rmfb_work_fn); + + schedule_work(&arg.work); + flush_work(&arg.work); + destroy_work_on_stack(&arg.work); } } diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c index 9535c5b60387..7e5a97204051 100644 --- a/drivers/gpu/drm/drm_dp_helper.c +++ b/drivers/gpu/drm/drm_dp_helper.c @@ -178,7 +178,7 @@ static int drm_dp_dpcd_access(struct drm_dp_aux *aux, u8 request, { struct drm_dp_aux_msg msg; unsigned int retry; - int err; + int err = 0; memset(&msg, 0, sizeof(msg)); msg.address = offset; @@ -186,6 +186,8 @@ static int drm_dp_dpcd_access(struct drm_dp_aux *aux, u8 request, msg.buffer = buffer; msg.size = size; + mutex_lock(&aux->hw_mutex); + /* * The specification doesn't give any recommendation on how often to * retry native transactions. We used to retry 7 times like for @@ -194,25 +196,24 @@ static int drm_dp_dpcd_access(struct drm_dp_aux *aux, u8 request, */ for (retry = 0; retry < 32; retry++) { - mutex_lock(&aux->hw_mutex); err = aux->transfer(aux, &msg); - mutex_unlock(&aux->hw_mutex); if (err < 0) { if (err == -EBUSY) continue; - return err; + goto unlock; } switch (msg.reply & DP_AUX_NATIVE_REPLY_MASK) { case DP_AUX_NATIVE_REPLY_ACK: if (err < size) - return -EPROTO; - return err; + err = -EPROTO; + goto unlock; case DP_AUX_NATIVE_REPLY_NACK: - return -EIO; + err = -EIO; + goto unlock; case DP_AUX_NATIVE_REPLY_DEFER: usleep_range(AUX_RETRY_INTERVAL, AUX_RETRY_INTERVAL + 100); @@ -221,7 +222,11 @@ static int drm_dp_dpcd_access(struct drm_dp_aux *aux, u8 request, } DRM_DEBUG_KMS("too many retries, giving up\n"); - return -EIO; + err = -EIO; + +unlock: + mutex_unlock(&aux->hw_mutex); + return err; } /** @@ -543,9 +548,7 @@ static int drm_dp_i2c_do_msg(struct drm_dp_aux *aux, struct drm_dp_aux_msg *msg) int max_retries = max(7, drm_dp_i2c_retry_count(msg, dp_aux_i2c_speed_khz)); for (retry = 0, defer_i2c = 0; retry < (max_retries + defer_i2c); retry++) { - mutex_lock(&aux->hw_mutex); ret = aux->transfer(aux, msg); - mutex_unlock(&aux->hw_mutex); if (ret < 0) { if (ret == -EBUSY) continue; @@ -684,6 +687,8 @@ static int drm_dp_i2c_xfer(struct i2c_adapter *adapter, struct i2c_msg *msgs, memset(&msg, 0, sizeof(msg)); + mutex_lock(&aux->hw_mutex); + for (i = 0; i < num; i++) { msg.address = msgs[i].addr; drm_dp_i2c_msg_set_request(&msg, &msgs[i]); @@ -738,6 +743,8 @@ static int drm_dp_i2c_xfer(struct i2c_adapter *adapter, struct i2c_msg *msgs, msg.size = 0; (void)drm_dp_i2c_do_msg(aux, &msg); + mutex_unlock(&aux->hw_mutex); + return err; } diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index 809959d56d78..2485fb652716 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -798,12 +798,33 @@ static struct drm_dp_mst_branch *drm_dp_add_mst_branch_device(u8 lct, u8 *rad) return mstb; } +static void drm_dp_free_mst_port(struct kref *kref); + +static void drm_dp_free_mst_branch_device(struct kref *kref) +{ + struct drm_dp_mst_branch *mstb = container_of(kref, struct drm_dp_mst_branch, kref); + if (mstb->port_parent) { + if (list_empty(&mstb->port_parent->next)) + kref_put(&mstb->port_parent->kref, drm_dp_free_mst_port); + } + kfree(mstb); +} + static void drm_dp_destroy_mst_branch_device(struct kref *kref) { struct drm_dp_mst_branch *mstb = container_of(kref, struct drm_dp_mst_branch, kref); struct drm_dp_mst_port *port, *tmp; bool wake_tx = false; + /* + * init kref again to be used by ports to remove mst branch when it is + * not needed anymore + */ + kref_init(kref); + + if (mstb->port_parent && list_empty(&mstb->port_parent->next)) + kref_get(&mstb->port_parent->kref); + /* * destroy all ports - don't need lock * as there are no more references to the mst branch @@ -830,7 +851,8 @@ static void drm_dp_destroy_mst_branch_device(struct kref *kref) if (wake_tx) wake_up(&mstb->mgr->tx_waitq); - kfree(mstb); + + kref_put(kref, drm_dp_free_mst_branch_device); } static void drm_dp_put_mst_branch_device(struct drm_dp_mst_branch *mstb) @@ -878,6 +900,7 @@ static void drm_dp_destroy_port(struct kref *kref) * from an EDID retrieval */ mutex_lock(&mgr->destroy_connector_lock); + kref_get(&port->parent->kref); list_add(&port->next, &mgr->destroy_connector_list); mutex_unlock(&mgr->destroy_connector_lock); schedule_work(&mgr->destroy_connector_work); @@ -973,17 +996,17 @@ static struct drm_dp_mst_port *drm_dp_get_port(struct drm_dp_mst_branch *mstb, u static u8 drm_dp_calculate_rad(struct drm_dp_mst_port *port, u8 *rad) { - int lct = port->parent->lct; + int parent_lct = port->parent->lct; int shift = 4; - int idx = lct / 2; - if (lct > 1) { - memcpy(rad, port->parent->rad, idx); - shift = (lct % 2) ? 4 : 0; + int idx = (parent_lct - 1) / 2; + if (parent_lct > 1) { + memcpy(rad, port->parent->rad, idx + 1); + shift = (parent_lct % 2) ? 4 : 0; } else rad[0] = 0; rad[idx] |= port->port_num << shift; - return lct + 1; + return parent_lct + 1; } /* @@ -1013,18 +1036,27 @@ static bool drm_dp_port_setup_pdt(struct drm_dp_mst_port *port) return send_link; } -static void drm_dp_check_port_guid(struct drm_dp_mst_branch *mstb, - struct drm_dp_mst_port *port) +static void drm_dp_check_mstb_guid(struct drm_dp_mst_branch *mstb, u8 *guid) { int ret; - if (port->dpcd_rev >= 0x12) { - port->guid_valid = drm_dp_validate_guid(mstb->mgr, port->guid); - if (!port->guid_valid) { - ret = drm_dp_send_dpcd_write(mstb->mgr, - port, - DP_GUID, - 16, port->guid); - port->guid_valid = true; + + memcpy(mstb->guid, guid, 16); + + if (!drm_dp_validate_guid(mstb->mgr, mstb->guid)) { + if (mstb->port_parent) { + ret = drm_dp_send_dpcd_write( + mstb->mgr, + mstb->port_parent, + DP_GUID, + 16, + mstb->guid); + } else { + + ret = drm_dp_dpcd_write( + mstb->mgr->aux, + DP_GUID, + mstb->guid, + 16); } } } @@ -1039,7 +1071,7 @@ static void build_mst_prop_path(const struct drm_dp_mst_branch *mstb, snprintf(proppath, proppath_size, "mst:%d", mstb->mgr->conn_base_id); for (i = 0; i < (mstb->lct - 1); i++) { int shift = (i % 2) ? 0 : 4; - int port_num = mstb->rad[i / 2] >> shift; + int port_num = (mstb->rad[i / 2] >> shift) & 0xf; snprintf(temp, sizeof(temp), "-%d", port_num); strlcat(proppath, temp, proppath_size); } @@ -1081,7 +1113,6 @@ static void drm_dp_add_port(struct drm_dp_mst_branch *mstb, port->dpcd_rev = port_msg->dpcd_revision; port->num_sdp_streams = port_msg->num_sdp_streams; port->num_sdp_stream_sinks = port_msg->num_sdp_stream_sinks; - memcpy(port->guid, port_msg->peer_guid, 16); /* manage mstb port lists with mgr lock - take a reference for this list */ @@ -1094,11 +1125,9 @@ static void drm_dp_add_port(struct drm_dp_mst_branch *mstb, if (old_ddps != port->ddps) { if (port->ddps) { - drm_dp_check_port_guid(mstb, port); if (!port->input) drm_dp_send_enum_path_resources(mstb->mgr, mstb, port); } else { - port->guid_valid = false; port->available_pbn = 0; } } @@ -1157,10 +1186,8 @@ static void drm_dp_update_port(struct drm_dp_mst_branch *mstb, if (old_ddps != port->ddps) { if (port->ddps) { - drm_dp_check_port_guid(mstb, port); dowork = true; } else { - port->guid_valid = false; port->available_pbn = 0; } } @@ -1190,7 +1217,7 @@ static struct drm_dp_mst_branch *drm_dp_get_mst_branch_device(struct drm_dp_mst_ for (i = 0; i < lct - 1; i++) { int shift = (i % 2) ? 0 : 4; - int port_num = rad[i / 2] >> shift; + int port_num = (rad[i / 2] >> shift) & 0xf; list_for_each_entry(port, &mstb->ports, next) { if (port->port_num == port_num) { @@ -1210,6 +1237,48 @@ out: return mstb; } +static struct drm_dp_mst_branch *get_mst_branch_device_by_guid_helper( + struct drm_dp_mst_branch *mstb, + uint8_t *guid) +{ + struct drm_dp_mst_branch *found_mstb; + struct drm_dp_mst_port *port; + + if (memcmp(mstb->guid, guid, 16) == 0) + return mstb; + + + list_for_each_entry(port, &mstb->ports, next) { + if (!port->mstb) + continue; + + found_mstb = get_mst_branch_device_by_guid_helper(port->mstb, guid); + + if (found_mstb) + return found_mstb; + } + + return NULL; +} + +static struct drm_dp_mst_branch *drm_dp_get_mst_branch_device_by_guid( + struct drm_dp_mst_topology_mgr *mgr, + uint8_t *guid) +{ + struct drm_dp_mst_branch *mstb; + + /* find the port by iterating down */ + mutex_lock(&mgr->lock); + + mstb = get_mst_branch_device_by_guid_helper(mgr->mst_primary, guid); + + if (mstb) + kref_get(&mstb->kref); + + mutex_unlock(&mgr->lock); + return mstb; +} + static void drm_dp_check_and_send_link_address(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_branch *mstb) { @@ -1320,6 +1389,7 @@ static int set_hdr_from_dst_qlock(struct drm_dp_sideband_msg_hdr *hdr, struct drm_dp_sideband_msg_tx *txmsg) { struct drm_dp_mst_branch *mstb = txmsg->dst; + u8 req_type; /* both msg slots are full */ if (txmsg->seqno == -1) { @@ -1336,7 +1406,13 @@ static int set_hdr_from_dst_qlock(struct drm_dp_sideband_msg_hdr *hdr, txmsg->seqno = 1; mstb->tx_slots[txmsg->seqno] = txmsg; } - hdr->broadcast = 0; + + req_type = txmsg->msg[0] & 0x7f; + if (req_type == DP_CONNECTION_STATUS_NOTIFY || + req_type == DP_RESOURCE_STATUS_NOTIFY) + hdr->broadcast = 1; + else + hdr->broadcast = 0; hdr->path_msg = txmsg->path_msg; hdr->lct = mstb->lct; hdr->lcr = mstb->lct - 1; @@ -1438,26 +1514,18 @@ static void process_single_down_tx_qlock(struct drm_dp_mst_topology_mgr *mgr) } /* called holding qlock */ -static void process_single_up_tx_qlock(struct drm_dp_mst_topology_mgr *mgr) +static void process_single_up_tx_qlock(struct drm_dp_mst_topology_mgr *mgr, + struct drm_dp_sideband_msg_tx *txmsg) { - struct drm_dp_sideband_msg_tx *txmsg; int ret; /* construct a chunk from the first msg in the tx_msg queue */ - if (list_empty(&mgr->tx_msg_upq)) { - mgr->tx_up_in_progress = false; - return; - } - - txmsg = list_first_entry(&mgr->tx_msg_upq, struct drm_dp_sideband_msg_tx, next); ret = process_single_tx_qlock(mgr, txmsg, true); - if (ret == 1) { - /* up txmsgs aren't put in slots - so free after we send it */ - list_del(&txmsg->next); - kfree(txmsg); - } else if (ret) + + if (ret != 1) DRM_DEBUG_KMS("failed to send msg in q %d\n", ret); - mgr->tx_up_in_progress = true; + + txmsg->dst->tx_slots[txmsg->seqno] = NULL; } static void drm_dp_queue_down_tx(struct drm_dp_mst_topology_mgr *mgr, @@ -1507,6 +1575,9 @@ static void drm_dp_send_link_address(struct drm_dp_mst_topology_mgr *mgr, txmsg->reply.u.link_addr.ports[i].num_sdp_streams, txmsg->reply.u.link_addr.ports[i].num_sdp_stream_sinks); } + + drm_dp_check_mstb_guid(mstb, txmsg->reply.u.link_addr.guid); + for (i = 0; i < txmsg->reply.u.link_addr.nports; i++) { drm_dp_add_port(mstb, mgr->dev, &txmsg->reply.u.link_addr.ports[i]); } @@ -1554,6 +1625,37 @@ static int drm_dp_send_enum_path_resources(struct drm_dp_mst_topology_mgr *mgr, return 0; } +static struct drm_dp_mst_port *drm_dp_get_last_connected_port_to_mstb(struct drm_dp_mst_branch *mstb) +{ + if (!mstb->port_parent) + return NULL; + + if (mstb->port_parent->mstb != mstb) + return mstb->port_parent; + + return drm_dp_get_last_connected_port_to_mstb(mstb->port_parent->parent); +} + +static struct drm_dp_mst_branch *drm_dp_get_last_connected_port_and_mstb(struct drm_dp_mst_topology_mgr *mgr, + struct drm_dp_mst_branch *mstb, + int *port_num) +{ + struct drm_dp_mst_branch *rmstb = NULL; + struct drm_dp_mst_port *found_port; + mutex_lock(&mgr->lock); + if (mgr->mst_primary) { + found_port = drm_dp_get_last_connected_port_to_mstb(mstb); + + if (found_port) { + rmstb = found_port->parent; + kref_get(&rmstb->kref); + *port_num = found_port->port_num; + } + } + mutex_unlock(&mgr->lock); + return rmstb; +} + static int drm_dp_payload_send_msg(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port, int id, @@ -1561,12 +1663,23 @@ static int drm_dp_payload_send_msg(struct drm_dp_mst_topology_mgr *mgr, { struct drm_dp_sideband_msg_tx *txmsg; struct drm_dp_mst_branch *mstb; - int len, ret; + int len, ret, port_num; - mstb = drm_dp_get_validated_mstb_ref(mgr, port->parent); - if (!mstb) + port = drm_dp_get_validated_port_ref(mgr, port); + if (!port) return -EINVAL; + port_num = port->port_num; + mstb = drm_dp_get_validated_mstb_ref(mgr, port->parent); + if (!mstb) { + mstb = drm_dp_get_last_connected_port_and_mstb(mgr, port->parent, &port_num); + + if (!mstb) { + drm_dp_put_port(port); + return -EINVAL; + } + } + txmsg = kzalloc(sizeof(*txmsg), GFP_KERNEL); if (!txmsg) { ret = -ENOMEM; @@ -1574,7 +1687,7 @@ static int drm_dp_payload_send_msg(struct drm_dp_mst_topology_mgr *mgr, } txmsg->dst = mstb; - len = build_allocate_payload(txmsg, port->port_num, + len = build_allocate_payload(txmsg, port_num, id, pbn); @@ -1590,6 +1703,7 @@ static int drm_dp_payload_send_msg(struct drm_dp_mst_topology_mgr *mgr, kfree(txmsg); fail_put: drm_dp_put_mst_branch_device(mstb); + drm_dp_put_port(port); return ret; } @@ -1672,6 +1786,11 @@ int drm_dp_update_payload_part1(struct drm_dp_mst_topology_mgr *mgr) req_payload.start_slot = cur_slots; if (mgr->proposed_vcpis[i]) { port = container_of(mgr->proposed_vcpis[i], struct drm_dp_mst_port, vcpi); + port = drm_dp_get_validated_port_ref(mgr, port); + if (!port) { + mutex_unlock(&mgr->payload_lock); + return -EINVAL; + } req_payload.num_slots = mgr->proposed_vcpis[i]->num_slots; } else { port = NULL; @@ -1697,6 +1816,9 @@ int drm_dp_update_payload_part1(struct drm_dp_mst_topology_mgr *mgr) mgr->payloads[i].payload_state = req_payload.payload_state; } cur_slots += req_payload.num_slots; + + if (port) + drm_dp_put_port(port); } for (i = 0; i < mgr->max_payloads; i++) { @@ -1844,11 +1966,12 @@ static int drm_dp_send_up_ack_reply(struct drm_dp_mst_topology_mgr *mgr, drm_dp_encode_up_ack_reply(txmsg, req_type); mutex_lock(&mgr->qlock); - list_add_tail(&txmsg->next, &mgr->tx_msg_upq); - if (!mgr->tx_up_in_progress) { - process_single_up_tx_qlock(mgr); - } + + process_single_up_tx_qlock(mgr, txmsg); + mutex_unlock(&mgr->qlock); + + kfree(txmsg); return 0; } @@ -1927,6 +2050,12 @@ int drm_dp_mst_topology_mgr_set_mst(struct drm_dp_mst_topology_mgr *mgr, bool ms mgr->mst_primary = mstb; kref_get(&mgr->mst_primary->kref); + ret = drm_dp_dpcd_writeb(mgr->aux, DP_MSTM_CTRL, + DP_MST_EN | DP_UP_REQ_EN | DP_UPSTREAM_IS_SRC); + if (ret < 0) { + goto out_unlock; + } + { struct drm_dp_payload reset_pay; reset_pay.start_slot = 0; @@ -1934,26 +2063,6 @@ int drm_dp_mst_topology_mgr_set_mst(struct drm_dp_mst_topology_mgr *mgr, bool ms drm_dp_dpcd_write_payload(mgr, 0, &reset_pay); } - ret = drm_dp_dpcd_writeb(mgr->aux, DP_MSTM_CTRL, - DP_MST_EN | DP_UP_REQ_EN | DP_UPSTREAM_IS_SRC); - if (ret < 0) { - goto out_unlock; - } - - - /* sort out guid */ - ret = drm_dp_dpcd_read(mgr->aux, DP_GUID, mgr->guid, 16); - if (ret != 16) { - DRM_DEBUG_KMS("failed to read DP GUID %d\n", ret); - goto out_unlock; - } - - mgr->guid_valid = drm_dp_validate_guid(mgr, mgr->guid); - if (!mgr->guid_valid) { - ret = drm_dp_dpcd_write(mgr->aux, DP_GUID, mgr->guid, 16); - mgr->guid_valid = true; - } - queue_work(system_long_wq, &mgr->work); ret = 0; @@ -2015,6 +2124,8 @@ int drm_dp_mst_topology_mgr_resume(struct drm_dp_mst_topology_mgr *mgr) if (mgr->mst_primary) { int sret; + u8 guid[16]; + sret = drm_dp_dpcd_read(mgr->aux, DP_DPCD_REV, mgr->dpcd, DP_RECEIVER_CAP_SIZE); if (sret != DP_RECEIVER_CAP_SIZE) { DRM_DEBUG_KMS("dpcd read failed - undocked during suspend?\n"); @@ -2029,6 +2140,16 @@ int drm_dp_mst_topology_mgr_resume(struct drm_dp_mst_topology_mgr *mgr) ret = -1; goto out_unlock; } + + /* Some hubs forget their guids after they resume */ + sret = drm_dp_dpcd_read(mgr->aux, DP_GUID, guid, 16); + if (sret != 16) { + DRM_DEBUG_KMS("dpcd read failed - undocked during suspend?\n"); + ret = -1; + goto out_unlock; + } + drm_dp_check_mstb_guid(mgr->mst_primary, guid); + ret = 0; } else ret = -1; @@ -2145,28 +2266,51 @@ static int drm_dp_mst_handle_up_req(struct drm_dp_mst_topology_mgr *mgr) if (mgr->up_req_recv.have_eomt) { struct drm_dp_sideband_msg_req_body msg; - struct drm_dp_mst_branch *mstb; + struct drm_dp_mst_branch *mstb = NULL; bool seqno; - mstb = drm_dp_get_mst_branch_device(mgr, - mgr->up_req_recv.initial_hdr.lct, - mgr->up_req_recv.initial_hdr.rad); - if (!mstb) { - DRM_DEBUG_KMS("Got MST reply from unknown device %d\n", mgr->up_req_recv.initial_hdr.lct); - memset(&mgr->up_req_recv, 0, sizeof(struct drm_dp_sideband_msg_rx)); - return 0; + + if (!mgr->up_req_recv.initial_hdr.broadcast) { + mstb = drm_dp_get_mst_branch_device(mgr, + mgr->up_req_recv.initial_hdr.lct, + mgr->up_req_recv.initial_hdr.rad); + if (!mstb) { + DRM_DEBUG_KMS("Got MST reply from unknown device %d\n", mgr->up_req_recv.initial_hdr.lct); + memset(&mgr->up_req_recv, 0, sizeof(struct drm_dp_sideband_msg_rx)); + return 0; + } } seqno = mgr->up_req_recv.initial_hdr.seqno; drm_dp_sideband_parse_req(&mgr->up_req_recv, &msg); if (msg.req_type == DP_CONNECTION_STATUS_NOTIFY) { - drm_dp_send_up_ack_reply(mgr, mstb, msg.req_type, seqno, false); + drm_dp_send_up_ack_reply(mgr, mgr->mst_primary, msg.req_type, seqno, false); + + if (!mstb) + mstb = drm_dp_get_mst_branch_device_by_guid(mgr, msg.u.conn_stat.guid); + + if (!mstb) { + DRM_DEBUG_KMS("Got MST reply from unknown device %d\n", mgr->up_req_recv.initial_hdr.lct); + memset(&mgr->up_req_recv, 0, sizeof(struct drm_dp_sideband_msg_rx)); + return 0; + } + drm_dp_update_port(mstb, &msg.u.conn_stat); + DRM_DEBUG_KMS("Got CSN: pn: %d ldps:%d ddps: %d mcs: %d ip: %d pdt: %d\n", msg.u.conn_stat.port_number, msg.u.conn_stat.legacy_device_plug_status, msg.u.conn_stat.displayport_device_plug_status, msg.u.conn_stat.message_capability_status, msg.u.conn_stat.input_port, msg.u.conn_stat.peer_device_type); (*mgr->cbs->hotplug)(mgr); } else if (msg.req_type == DP_RESOURCE_STATUS_NOTIFY) { - drm_dp_send_up_ack_reply(mgr, mstb, msg.req_type, seqno, false); + drm_dp_send_up_ack_reply(mgr, mgr->mst_primary, msg.req_type, seqno, false); + if (!mstb) + mstb = drm_dp_get_mst_branch_device_by_guid(mgr, msg.u.resource_stat.guid); + + if (!mstb) { + DRM_DEBUG_KMS("Got MST reply from unknown device %d\n", mgr->up_req_recv.initial_hdr.lct); + memset(&mgr->up_req_recv, 0, sizeof(struct drm_dp_sideband_msg_rx)); + return 0; + } + DRM_DEBUG_KMS("Got RSN: pn: %d avail_pbn %d\n", msg.u.resource_stat.port_number, msg.u.resource_stat.available_pbn); } @@ -2346,6 +2490,7 @@ bool drm_dp_mst_allocate_vcpi(struct drm_dp_mst_topology_mgr *mgr, struct drm_dp DRM_DEBUG_KMS("payload: vcpi %d already allocated for pbn %d - requested pbn %d\n", port->vcpi.vcpi, port->vcpi.pbn, pbn); if (pbn == port->vcpi.pbn) { *slots = port->vcpi.num_slots; + drm_dp_put_port(port); return true; } } @@ -2505,32 +2650,31 @@ EXPORT_SYMBOL(drm_dp_check_act_status); */ int drm_dp_calc_pbn_mode(int clock, int bpp) { - fixed20_12 pix_bw; - fixed20_12 fbpp; - fixed20_12 result; - fixed20_12 margin, tmp; - u32 res; + u64 kbps; + s64 peak_kbps; + u32 numerator; + u32 denominator; - pix_bw.full = dfixed_const(clock); - fbpp.full = dfixed_const(bpp); - tmp.full = dfixed_const(8); - fbpp.full = dfixed_div(fbpp, tmp); + kbps = clock * bpp; - result.full = dfixed_mul(pix_bw, fbpp); - margin.full = dfixed_const(54); - tmp.full = dfixed_const(64); - margin.full = dfixed_div(margin, tmp); - result.full = dfixed_div(result, margin); + /* + * margin 5300ppm + 300ppm ~ 0.6% as per spec, factor is 1.006 + * The unit of 54/64Mbytes/sec is an arbitrary unit chosen based on + * common multiplier to render an integer PBN for all link rate/lane + * counts combinations + * calculate + * peak_kbps *= (1006/1000) + * peak_kbps *= (64/54) + * peak_kbps *= 8 convert to bytes + */ - margin.full = dfixed_const(1006); - tmp.full = dfixed_const(1000); - margin.full = dfixed_div(margin, tmp); - result.full = dfixed_mul(result, margin); + numerator = 64 * 1006; + denominator = 54 * 8 * 1000 * 1000; - result.full = dfixed_div(result, tmp); - result.full = dfixed_ceil(result); - res = dfixed_trunc(result); - return res; + kbps *= numerator; + peak_kbps = drm_fixp_from_fraction(kbps, denominator); + + return drm_fixp2int_ceil(peak_kbps); } EXPORT_SYMBOL(drm_dp_calc_pbn_mode); @@ -2538,11 +2682,23 @@ static int test_calc_pbn_mode(void) { int ret; ret = drm_dp_calc_pbn_mode(154000, 30); - if (ret != 689) + if (ret != 689) { + DRM_ERROR("PBN calculation test failed - clock %d, bpp %d, expected PBN %d, actual PBN %d.\n", + 154000, 30, 689, ret); return -EINVAL; + } ret = drm_dp_calc_pbn_mode(234000, 30); - if (ret != 1047) + if (ret != 1047) { + DRM_ERROR("PBN calculation test failed - clock %d, bpp %d, expected PBN %d, actual PBN %d.\n", + 234000, 30, 1047, ret); return -EINVAL; + } + ret = drm_dp_calc_pbn_mode(297000, 24); + if (ret != 1063) { + DRM_ERROR("PBN calculation test failed - clock %d, bpp %d, expected PBN %d, actual PBN %d.\n", + 297000, 24, 1063, ret); + return -EINVAL; + } return 0; } @@ -2683,6 +2839,13 @@ static void drm_dp_tx_work(struct work_struct *work) mutex_unlock(&mgr->qlock); } +static void drm_dp_free_mst_port(struct kref *kref) +{ + struct drm_dp_mst_port *port = container_of(kref, struct drm_dp_mst_port, kref); + kref_put(&port->parent->kref, drm_dp_free_mst_branch_device); + kfree(port); +} + static void drm_dp_destroy_connector_work(struct work_struct *work) { struct drm_dp_mst_topology_mgr *mgr = container_of(work, struct drm_dp_mst_topology_mgr, destroy_connector_work); @@ -2703,13 +2866,20 @@ static void drm_dp_destroy_connector_work(struct work_struct *work) list_del(&port->next); mutex_unlock(&mgr->destroy_connector_lock); + kref_init(&port->kref); + INIT_LIST_HEAD(&port->next); + mgr->cbs->destroy_connector(mgr, port->connector); drm_dp_port_teardown_pdt(port, port->pdt); - if (!port->input && port->vcpi.vcpi > 0) + if (!port->input && port->vcpi.vcpi > 0) { + drm_dp_mst_reset_vcpi_slots(mgr, port); + drm_dp_update_payload_part1(mgr); drm_dp_mst_put_payload_id(mgr, port->vcpi.vcpi); - kfree(port); + } + + kref_put(&port->kref, drm_dp_free_mst_port); send_hotplug = true; } if (send_hotplug) @@ -2736,7 +2906,6 @@ int drm_dp_mst_topology_mgr_init(struct drm_dp_mst_topology_mgr *mgr, mutex_init(&mgr->qlock); mutex_init(&mgr->payload_lock); mutex_init(&mgr->destroy_connector_lock); - INIT_LIST_HEAD(&mgr->tx_msg_upq); INIT_LIST_HEAD(&mgr->tx_msg_downq); INIT_LIST_HEAD(&mgr->destroy_connector_list); INIT_WORK(&mgr->work, drm_dp_mst_link_probe_work); diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index 69cbab5e5c81..5ad036741b99 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -1899,7 +1899,6 @@ static int drm_pick_crtcs(struct drm_fb_helper *fb_helper, int n, int width, int height) { int c, o; - struct drm_device *dev = fb_helper->dev; struct drm_connector *connector; const struct drm_connector_helper_funcs *connector_funcs; struct drm_encoder *encoder; @@ -1918,7 +1917,7 @@ static int drm_pick_crtcs(struct drm_fb_helper *fb_helper, if (modes[n] == NULL) return best_score; - crtcs = kzalloc(dev->mode_config.num_connector * + crtcs = kzalloc(fb_helper->connector_count * sizeof(struct drm_fb_helper_crtc *), GFP_KERNEL); if (!crtcs) return best_score; @@ -1964,7 +1963,7 @@ static int drm_pick_crtcs(struct drm_fb_helper *fb_helper, if (score > best_score) { best_score = score; memcpy(best_crtcs, crtcs, - dev->mode_config.num_connector * + fb_helper->connector_count * sizeof(struct drm_fb_helper_crtc *)); } } diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c index 607f493ae801..8090989185b2 100644 --- a/drivers/gpu/drm/drm_irq.c +++ b/drivers/gpu/drm/drm_irq.c @@ -221,6 +221,64 @@ static void drm_update_vblank_count(struct drm_device *dev, unsigned int pipe, diff = (flags & DRM_CALLED_FROM_VBLIRQ) != 0; } + /* + * Within a drm_vblank_pre_modeset - drm_vblank_post_modeset + * interval? If so then vblank irqs keep running and it will likely + * happen that the hardware vblank counter is not trustworthy as it + * might reset at some point in that interval and vblank timestamps + * are not trustworthy either in that interval. Iow. this can result + * in a bogus diff >> 1 which must be avoided as it would cause + * random large forward jumps of the software vblank counter. + */ + if (diff > 1 && (vblank->inmodeset & 0x2)) { + DRM_DEBUG_VBL("clamping vblank bump to 1 on crtc %u: diffr=%u" + " due to pre-modeset.\n", pipe, diff); + diff = 1; + } + + /* + * FIMXE: Need to replace this hack with proper seqlocks. + * + * Restrict the bump of the software vblank counter to a safe maximum + * value of +1 whenever there is the possibility that concurrent readers + * of vblank timestamps could be active at the moment, as the current + * implementation of the timestamp caching and updating is not safe + * against concurrent readers for calls to store_vblank() with a bump + * of anything but +1. A bump != 1 would very likely return corrupted + * timestamps to userspace, because the same slot in the cache could + * be concurrently written by store_vblank() and read by one of those + * readers without the read-retry logic detecting the collision. + * + * Concurrent readers can exist when we are called from the + * drm_vblank_off() or drm_vblank_on() functions and other non-vblank- + * irq callers. However, all those calls to us are happening with the + * vbl_lock locked to prevent drm_vblank_get(), so the vblank refcount + * can't increase while we are executing. Therefore a zero refcount at + * this point is safe for arbitrary counter bumps if we are called + * outside vblank irq, a non-zero count is not 100% safe. Unfortunately + * we must also accept a refcount of 1, as whenever we are called from + * drm_vblank_get() -> drm_vblank_enable() the refcount will be 1 and + * we must let that one pass through in order to not lose vblank counts + * during vblank irq off - which would completely defeat the whole + * point of this routine. + * + * Whenever we are called from vblank irq, we have to assume concurrent + * readers exist or can show up any time during our execution, even if + * the refcount is currently zero, as vblank irqs are usually only + * enabled due to the presence of readers, and because when we are called + * from vblank irq we can't hold the vbl_lock to protect us from sudden + * bumps in vblank refcount. Therefore also restrict bumps to +1 when + * called from vblank irq. + */ + if ((diff > 1) && (atomic_read(&vblank->refcount) > 1 || + (flags & DRM_CALLED_FROM_VBLIRQ))) { + DRM_DEBUG_VBL("clamping vblank bump to 1 on crtc %u: diffr=%u " + "refcount %u, vblirq %u\n", pipe, diff, + atomic_read(&vblank->refcount), + (flags & DRM_CALLED_FROM_VBLIRQ) != 0); + diff = 1; + } + DRM_DEBUG_VBL("updating vblank count on crtc %u:" " current=%u, diff=%u, hw=%u hw_last=%u\n", pipe, vblank->count, diff, cur_vblank, vblank->last); @@ -1313,7 +1371,13 @@ void drm_vblank_off(struct drm_device *dev, unsigned int pipe) spin_lock_irqsave(&dev->event_lock, irqflags); spin_lock(&dev->vbl_lock); - vblank_disable_and_save(dev, pipe); + DRM_DEBUG_VBL("crtc %d, vblank enabled %d, inmodeset %d\n", + pipe, vblank->enabled, vblank->inmodeset); + + /* Avoid redundant vblank disables without previous drm_vblank_on(). */ + if (drm_core_check_feature(dev, DRIVER_ATOMIC) || !vblank->inmodeset) + vblank_disable_and_save(dev, pipe); + wake_up(&vblank->queue); /* @@ -1415,6 +1479,9 @@ void drm_vblank_on(struct drm_device *dev, unsigned int pipe) return; spin_lock_irqsave(&dev->vbl_lock, irqflags); + DRM_DEBUG_VBL("crtc %d, vblank enabled %d, inmodeset %d\n", + pipe, vblank->enabled, vblank->inmodeset); + /* Drop our private "prevent drm_vblank_get" refcount */ if (vblank->inmodeset) { atomic_dec(&vblank->refcount); @@ -1427,8 +1494,7 @@ void drm_vblank_on(struct drm_device *dev, unsigned int pipe) * re-enable interrupts if there are users left, or the * user wishes vblank interrupts to be enabled all the time. */ - if (atomic_read(&vblank->refcount) != 0 || - (!dev->vblank_disable_immediate && drm_vblank_offdelay == 0)) + if (atomic_read(&vblank->refcount) != 0 || drm_vblank_offdelay == 0) WARN_ON(drm_vblank_enable(dev, pipe)); spin_unlock_irqrestore(&dev->vbl_lock, irqflags); } @@ -1523,6 +1589,7 @@ void drm_vblank_post_modeset(struct drm_device *dev, unsigned int pipe) if (vblank->inmodeset) { spin_lock_irqsave(&dev->vbl_lock, irqflags); dev->vblank_disable_allowed = true; + drm_reset_vblank_timestamp(dev, pipe); spin_unlock_irqrestore(&dev->vbl_lock, irqflags); if (vblank->inmodeset & 0x2) diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c index cd74a0953f42..39e30abddf08 100644 --- a/drivers/gpu/drm/drm_modes.c +++ b/drivers/gpu/drm/drm_modes.c @@ -1487,6 +1487,8 @@ int drm_mode_convert_umode(struct drm_display_mode *out, if (out->status != MODE_OK) goto out; + drm_mode_set_crtcinfo(out, CRTC_INTERLACE_HALVE_V); + ret = 0; out: diff --git a/drivers/gpu/drm/gma500/gem.c b/drivers/gpu/drm/gma500/gem.c index c707fa6fca85..e3bdc8b1c32c 100644 --- a/drivers/gpu/drm/gma500/gem.c +++ b/drivers/gpu/drm/gma500/gem.c @@ -130,7 +130,7 @@ int psb_gem_create(struct drm_file *file, struct drm_device *dev, u64 size, return ret; } /* We have the initial and handle reference but need only one now */ - drm_gem_object_unreference(&r->gem); + drm_gem_object_unreference_unlocked(&r->gem); *handlep = handle; return 0; } diff --git a/drivers/gpu/drm/gma500/mdfld_dsi_pkg_sender.c b/drivers/gpu/drm/gma500/mdfld_dsi_pkg_sender.c index 6b43ae3ffd73..1616af209bfc 100644 --- a/drivers/gpu/drm/gma500/mdfld_dsi_pkg_sender.c +++ b/drivers/gpu/drm/gma500/mdfld_dsi_pkg_sender.c @@ -72,7 +72,7 @@ static const char *const dsi_errors[] = { "RX Prot Violation", "HS Generic Write FIFO Full", "LP Generic Write FIFO Full", - "Generic Read Data Avail" + "Generic Read Data Avail", "Special Packet Sent", "Tearing Effect", }; diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c index b4741d121a74..61fcb3b22297 100644 --- a/drivers/gpu/drm/i915/i915_dma.c +++ b/drivers/gpu/drm/i915/i915_dma.c @@ -402,6 +402,8 @@ static int i915_load_modeset_init(struct drm_device *dev) if (ret) goto cleanup_gem_stolen; + intel_setup_gmbus(dev); + /* Important: The output setup functions called by modeset_init need * working irqs for e.g. gmbus and dp aux transfers. */ intel_modeset_init(dev); @@ -451,6 +453,7 @@ cleanup_gem: cleanup_irq: intel_guc_ucode_fini(dev); drm_irq_uninstall(dev); + intel_teardown_gmbus(dev); cleanup_gem_stolen: i915_gem_cleanup_stolen(dev); cleanup_vga_switcheroo: @@ -1028,7 +1031,6 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags) /* Try to make sure MCHBAR is enabled before poking at it */ intel_setup_mchbar(dev); - intel_setup_gmbus(dev); intel_opregion_setup(dev); i915_gem_load(dev); @@ -1099,7 +1101,6 @@ out_gem_unload: if (dev->pdev->msi_enabled) pci_disable_msi(dev->pdev); - intel_teardown_gmbus(dev); intel_teardown_mchbar(dev); pm_qos_remove_request(&dev_priv->pm_qos); destroy_workqueue(dev_priv->gpu_error.hangcheck_wq); @@ -1198,7 +1199,6 @@ int i915_driver_unload(struct drm_device *dev) intel_csr_ucode_fini(dev); - intel_teardown_gmbus(dev); intel_teardown_mchbar(dev); destroy_workqueue(dev_priv->hotplug.dp_wq); diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 760e0ce4aa26..a6ad938f44a6 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -531,7 +531,10 @@ void intel_detect_pch(struct drm_device *dev) dev_priv->pch_type = PCH_SPT; DRM_DEBUG_KMS("Found SunrisePoint LP PCH\n"); WARN_ON(!IS_SKYLAKE(dev)); - } else if (id == INTEL_PCH_P2X_DEVICE_ID_TYPE) { + } else if ((id == INTEL_PCH_P2X_DEVICE_ID_TYPE) || + ((id == INTEL_PCH_QEMU_DEVICE_ID_TYPE) && + pch->subsystem_vendor == 0x1af4 && + pch->subsystem_device == 0x1100)) { dev_priv->pch_type = intel_virt_detect_pch(dev); } else continue; diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index f4af19a0d569..d3ce4da6a6ad 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -2614,6 +2614,7 @@ struct drm_i915_cmd_table { #define INTEL_PCH_SPT_DEVICE_ID_TYPE 0xA100 #define INTEL_PCH_SPT_LP_DEVICE_ID_TYPE 0x9D00 #define INTEL_PCH_P2X_DEVICE_ID_TYPE 0x7100 +#define INTEL_PCH_QEMU_DEVICE_ID_TYPE 0x2900 /* qemu q35 has 2918 */ #define INTEL_PCH_TYPE(dev) (__I915__(dev)->pch_type) #define HAS_PCH_SPT(dev) (INTEL_PCH_TYPE(dev) == PCH_SPT) diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c index 02ceb7a4b481..0433d25f9d23 100644 --- a/drivers/gpu/drm/i915/i915_gem_context.c +++ b/drivers/gpu/drm/i915/i915_gem_context.c @@ -340,6 +340,10 @@ void i915_gem_context_reset(struct drm_device *dev) i915_gem_context_unreference(lctx); ring->last_context = NULL; } + + /* Force the GPU state to be reinitialised on enabling */ + if (ring->default_context) + ring->default_context->legacy_hw_ctx.initialized = false; } } @@ -708,7 +712,7 @@ static int do_switch(struct drm_i915_gem_request *req) if (ret) goto unpin_out; - if (!to->legacy_hw_ctx.initialized) { + if (!to->legacy_hw_ctx.initialized || i915_gem_context_is_default(to)) { hw_flags |= MI_RESTORE_INHIBIT; /* NB: If we inhibit the restore, the context is not allowed to * die because future work may end up depending on valid address diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c index f7df54a8ee2b..c0a96f1ee18e 100644 --- a/drivers/gpu/drm/i915/i915_gem_shrinker.c +++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c @@ -39,7 +39,7 @@ static bool mutex_is_locked_by(struct mutex *mutex, struct task_struct *task) if (!mutex_is_locked(mutex)) return false; -#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_MUTEXES) +#if defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_MUTEX_SPIN_ON_OWNER) return mutex->owner == task; #else /* Since UP may be pre-empted, we cannot assume that we own the lock */ diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 0d228f909dcb..0f42a2782afc 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -2354,9 +2354,13 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg) spt_irq_handler(dev, pch_iir); else cpt_irq_handler(dev, pch_iir); - } else - DRM_ERROR("The master control interrupt lied (SDE)!\n"); - + } else { + /* + * Like on previous PCH there seems to be something + * fishy going on with forwarding PCH interrupts. + */ + DRM_DEBUG_DRIVER("The master control interrupt lied (SDE)!\n"); + } } I915_WRITE_FW(GEN8_MASTER_IRQ, GEN8_MASTER_IRQ_CONTROL); diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index bc7b8faba84d..9ed9f6dde86f 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -2838,7 +2838,14 @@ enum skl_disp_power_wells { #define GEN6_RP_STATE_CAP (MCHBAR_MIRROR_BASE_SNB + 0x5998) #define BXT_RP_STATE_CAP 0x138170 -#define INTERVAL_1_28_US(us) (((us) * 100) >> 7) +/* + * Make these a multiple of magic 25 to avoid SNB (eg. Dell XPS + * 8300) freezing up around GPU hangs. Looks as if even + * scheduling/timer interrupts start misbehaving if the RPS + * EI/thresholds are "bad", leading to a very sluggish or even + * frozen machine. + */ +#define INTERVAL_1_28_US(us) roundup(((us) * 100) >> 7, 25) #define INTERVAL_1_33_US(us) (((us) * 3) >> 2) #define INTERVAL_0_833_US(us) (((us) * 6) / 5) #define GT_INTERVAL_FROM_US(dev_priv, us) (IS_GEN9(dev_priv) ? \ @@ -7350,6 +7357,8 @@ enum skl_disp_power_wells { #define TRANS_CLK_SEL_DISABLED (0x0<<29) #define TRANS_CLK_SEL_PORT(x) (((x)+1)<<29) +#define CDCLK_FREQ 0x46200 + #define TRANSA_MSA_MISC 0x60410 #define TRANSB_MSA_MISC 0x61410 #define TRANSC_MSA_MISC 0x62410 diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c index 6a2c76e367a5..97d1ed20418b 100644 --- a/drivers/gpu/drm/i915/intel_crt.c +++ b/drivers/gpu/drm/i915/intel_crt.c @@ -248,8 +248,14 @@ static bool intel_crt_compute_config(struct intel_encoder *encoder, pipe_config->has_pch_encoder = true; /* LPT FDI RX only supports 8bpc. */ - if (HAS_PCH_LPT(dev)) + if (HAS_PCH_LPT(dev)) { + if (pipe_config->bw_constrained && pipe_config->pipe_bpp < 24) { + DRM_DEBUG_KMS("LPT only supports 24bpp\n"); + return false; + } + pipe_config->pipe_bpp = 24; + } /* FDI must always be 2.7 GHz */ if (HAS_DDI(dev)) { diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c index 9e530a739354..fc28c512ece3 100644 --- a/drivers/gpu/drm/i915/intel_csr.c +++ b/drivers/gpu/drm/i915/intel_csr.c @@ -180,7 +180,8 @@ struct stepping_info { static const struct stepping_info skl_stepping_info[] = { {'A', '0'}, {'B', '0'}, {'C', '0'}, {'D', '0'}, {'E', '0'}, {'F', '0'}, - {'G', '0'}, {'H', '0'}, {'I', '0'} + {'G', '0'}, {'H', '0'}, {'I', '0'}, + {'J', '0'}, {'K', '0'} }; static struct stepping_info bxt_stepping_info[] = { diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index a6752a61d99f..3c6b07683bd9 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -464,9 +464,17 @@ static void intel_prepare_ddi_buffers(struct drm_device *dev, enum port port, } else if (IS_BROADWELL(dev)) { ddi_translations_fdi = bdw_ddi_translations_fdi; ddi_translations_dp = bdw_ddi_translations_dp; - ddi_translations_edp = bdw_ddi_translations_edp; + + if (dev_priv->edp_low_vswing) { + ddi_translations_edp = bdw_ddi_translations_edp; + n_edp_entries = ARRAY_SIZE(bdw_ddi_translations_edp); + } else { + ddi_translations_edp = bdw_ddi_translations_dp; + n_edp_entries = ARRAY_SIZE(bdw_ddi_translations_dp); + } + ddi_translations_hdmi = bdw_ddi_translations_hdmi; - n_edp_entries = ARRAY_SIZE(bdw_ddi_translations_edp); + n_dp_entries = ARRAY_SIZE(bdw_ddi_translations_dp); n_hdmi_entries = ARRAY_SIZE(bdw_ddi_translations_hdmi); hdmi_default_entry = 7; @@ -1582,7 +1590,8 @@ skl_ddi_pll_select(struct intel_crtc *intel_crtc, DPLL_CFGCR2_KDIV(wrpll_params.kdiv) | DPLL_CFGCR2_PDIV(wrpll_params.pdiv) | wrpll_params.central_freq; - } else if (intel_encoder->type == INTEL_OUTPUT_DISPLAYPORT) { + } else if (intel_encoder->type == INTEL_OUTPUT_DISPLAYPORT || + intel_encoder->type == INTEL_OUTPUT_DP_MST) { switch (crtc_state->port_clock / 2) { case 81000: ctrl1 |= DPLL_CTRL1_LINK_RATE(DPLL_CTRL1_LINK_RATE_810, 0); @@ -3187,12 +3196,6 @@ void intel_ddi_get_config(struct intel_encoder *encoder, intel_ddi_clock_get(encoder, pipe_config); } -static void intel_ddi_destroy(struct drm_encoder *encoder) -{ - /* HDMI has nothing special to destroy, so we can go with this. */ - intel_dp_encoder_destroy(encoder); -} - static bool intel_ddi_compute_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config) { @@ -3211,7 +3214,8 @@ static bool intel_ddi_compute_config(struct intel_encoder *encoder, } static const struct drm_encoder_funcs intel_ddi_funcs = { - .destroy = intel_ddi_destroy, + .reset = intel_dp_encoder_reset, + .destroy = intel_dp_encoder_destroy, }; static struct intel_connector * @@ -3283,6 +3287,7 @@ void intel_ddi_init(struct drm_device *dev, enum port port) intel_encoder->post_disable = intel_ddi_post_disable; intel_encoder->get_hw_state = intel_ddi_get_hw_state; intel_encoder->get_config = intel_ddi_get_config; + intel_encoder->suspend = intel_dp_encoder_suspend; intel_dig_port->port = port; intel_dig_port->saved_port_bits = I915_READ(DDI_BUF_CTL(port)) & diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 32cf97346978..c41bc42b6fa7 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -4447,7 +4447,7 @@ int skl_update_scaler_crtc(struct intel_crtc_state *state) intel_crtc->base.base.id, intel_crtc->pipe, SKL_CRTC_INDEX); return skl_update_scaler(state, !state->base.active, SKL_CRTC_INDEX, - &state->scaler_state.scaler_id, DRM_ROTATE_0, + &state->scaler_state.scaler_id, BIT(DRM_ROTATE_0), state->pipe_src_w, state->pipe_src_h, adjusted_mode->crtc_hdisplay, adjusted_mode->crtc_vdisplay); } @@ -8228,12 +8228,14 @@ static void ironlake_init_pch_refclk(struct drm_device *dev) { struct drm_i915_private *dev_priv = dev->dev_private; struct intel_encoder *encoder; + int i; u32 val, final; bool has_lvds = false; bool has_cpu_edp = false; bool has_panel = false; bool has_ck505 = false; bool can_ssc = false; + bool using_ssc_source = false; /* We need to take the global config into account */ for_each_intel_encoder(dev, encoder) { @@ -8260,8 +8262,22 @@ static void ironlake_init_pch_refclk(struct drm_device *dev) can_ssc = true; } - DRM_DEBUG_KMS("has_panel %d has_lvds %d has_ck505 %d\n", - has_panel, has_lvds, has_ck505); + /* Check if any DPLLs are using the SSC source */ + for (i = 0; i < dev_priv->num_shared_dpll; i++) { + u32 temp = I915_READ(PCH_DPLL(i)); + + if (!(temp & DPLL_VCO_ENABLE)) + continue; + + if ((temp & PLL_REF_INPUT_MASK) == + PLLB_REF_INPUT_SPREADSPECTRUMIN) { + using_ssc_source = true; + break; + } + } + + DRM_DEBUG_KMS("has_panel %d has_lvds %d has_ck505 %d using_ssc_source %d\n", + has_panel, has_lvds, has_ck505, using_ssc_source); /* Ironlake: try to setup display ref clock before DPLL * enabling. This is only under driver's control after @@ -8298,9 +8314,9 @@ static void ironlake_init_pch_refclk(struct drm_device *dev) final |= DREF_CPU_SOURCE_OUTPUT_NONSPREAD; } else final |= DREF_CPU_SOURCE_OUTPUT_DISABLE; - } else { - final |= DREF_SSC_SOURCE_DISABLE; - final |= DREF_CPU_SOURCE_OUTPUT_DISABLE; + } else if (using_ssc_source) { + final |= DREF_SSC_SOURCE_ENABLE; + final |= DREF_SSC1_ENABLE; } if (final == val) @@ -8346,7 +8362,7 @@ static void ironlake_init_pch_refclk(struct drm_device *dev) POSTING_READ(PCH_DREF_CONTROL); udelay(200); } else { - DRM_DEBUG_KMS("Disabling SSC entirely\n"); + DRM_DEBUG_KMS("Disabling CPU source output\n"); val &= ~DREF_CPU_SOURCE_OUTPUT_MASK; @@ -8357,16 +8373,20 @@ static void ironlake_init_pch_refclk(struct drm_device *dev) POSTING_READ(PCH_DREF_CONTROL); udelay(200); - /* Turn off the SSC source */ - val &= ~DREF_SSC_SOURCE_MASK; - val |= DREF_SSC_SOURCE_DISABLE; + if (!using_ssc_source) { + DRM_DEBUG_KMS("Disabling SSC source\n"); - /* Turn off SSC1 */ - val &= ~DREF_SSC1_ENABLE; + /* Turn off the SSC source */ + val &= ~DREF_SSC_SOURCE_MASK; + val |= DREF_SSC_SOURCE_DISABLE; - I915_WRITE(PCH_DREF_CONTROL, val); - POSTING_READ(PCH_DREF_CONTROL); - udelay(200); + /* Turn off SSC1 */ + val &= ~DREF_SSC1_ENABLE; + + I915_WRITE(PCH_DREF_CONTROL, val); + POSTING_READ(PCH_DREF_CONTROL); + udelay(200); + } } BUG_ON(val != final); @@ -9669,6 +9689,8 @@ static void broadwell_set_cdclk(struct drm_device *dev, int cdclk) sandybridge_pcode_write(dev_priv, HSW_PCODE_DE_WRITE_FREQ_REQ, data); mutex_unlock(&dev_priv->rps.hw_lock); + I915_WRITE(CDCLK_FREQ, DIV_ROUND_CLOSEST(cdclk, 1000) - 1); + intel_update_cdclk(dev); WARN(cdclk != dev_priv->cdclk_freq, @@ -11930,11 +11952,21 @@ connected_sink_compute_bpp(struct intel_connector *connector, pipe_config->pipe_bpp = connector->base.display_info.bpc*3; } - /* Clamp bpp to 8 on screens without EDID 1.4 */ - if (connector->base.display_info.bpc == 0 && bpp > 24) { - DRM_DEBUG_KMS("clamping display bpp (was %d) to default limit of 24\n", - bpp); - pipe_config->pipe_bpp = 24; + /* Clamp bpp to default limit on screens without EDID 1.4 */ + if (connector->base.display_info.bpc == 0) { + int type = connector->base.connector_type; + int clamp_bpp = 24; + + /* Fall back to 18 bpp when DP sink capability is unknown. */ + if (type == DRM_MODE_CONNECTOR_DisplayPort || + type == DRM_MODE_CONNECTOR_eDP) + clamp_bpp = 18; + + if (bpp > clamp_bpp) { + DRM_DEBUG_KMS("clamping display bpp (was %d) to default limit of %d\n", + bpp, clamp_bpp); + pipe_config->pipe_bpp = clamp_bpp; + } } } @@ -13537,11 +13569,12 @@ intel_check_primary_plane(struct drm_plane *plane, int max_scale = DRM_PLANE_HELPER_NO_SCALING; bool can_position = false; - /* use scaler when colorkey is not required */ - if (INTEL_INFO(plane->dev)->gen >= 9 && - state->ckey.flags == I915_SET_COLORKEY_NONE) { - min_scale = 1; - max_scale = skl_max_scale(to_intel_crtc(crtc), crtc_state); + if (INTEL_INFO(plane->dev)->gen >= 9) { + /* use scaler when colorkey is not required */ + if (state->ckey.flags == I915_SET_COLORKEY_NONE) { + min_scale = 1; + max_scale = skl_max_scale(to_intel_crtc(crtc), crtc_state); + } can_position = true; } @@ -15565,6 +15598,8 @@ void intel_modeset_cleanup(struct drm_device *dev) mutex_lock(&dev->struct_mutex); intel_cleanup_gt_powersave(dev); mutex_unlock(&dev->struct_mutex); + + intel_teardown_gmbus(dev); } /* diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 78b8ec84d576..8e1d6d74c203 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -3628,8 +3628,7 @@ static bool intel_dp_reset_link_train(struct intel_dp *intel_dp, uint32_t *DP, uint8_t dp_train_pat) { - if (!intel_dp->train_set_valid) - memset(intel_dp->train_set, 0, sizeof(intel_dp->train_set)); + memset(intel_dp->train_set, 0, sizeof(intel_dp->train_set)); intel_dp_set_signal_levels(intel_dp, DP); return intel_dp_set_link_train(intel_dp, DP, dp_train_pat); } @@ -3746,22 +3745,6 @@ intel_dp_link_training_clock_recovery(struct intel_dp *intel_dp) break; } - /* - * if we used previously trained voltage and pre-emphasis values - * and we don't get clock recovery, reset link training values - */ - if (intel_dp->train_set_valid) { - DRM_DEBUG_KMS("clock recovery not ok, reset"); - /* clear the flag as we are not reusing train set */ - intel_dp->train_set_valid = false; - if (!intel_dp_reset_link_train(intel_dp, &DP, - DP_TRAINING_PATTERN_1 | - DP_LINK_SCRAMBLING_DISABLE)) { - DRM_ERROR("failed to enable link training\n"); - return; - } - continue; - } /* Check to see if we've tried the max voltage */ for (i = 0; i < intel_dp->lane_count; i++) @@ -3854,7 +3837,6 @@ intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp) /* Make sure clock is still ok */ if (!drm_dp_clock_recovery_ok(link_status, intel_dp->lane_count)) { - intel_dp->train_set_valid = false; intel_dp_link_training_clock_recovery(intel_dp); intel_dp_set_link_train(intel_dp, &DP, training_pattern | @@ -3871,7 +3853,6 @@ intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp) /* Try 5 times, then try clock recovery if that fails */ if (tries > 5) { - intel_dp->train_set_valid = false; intel_dp_link_training_clock_recovery(intel_dp); intel_dp_set_link_train(intel_dp, &DP, training_pattern | @@ -3893,10 +3874,8 @@ intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp) intel_dp->DP = DP; - if (channel_eq) { - intel_dp->train_set_valid = true; + if (channel_eq) DRM_DEBUG_KMS("Channel EQ done. DP Training successful\n"); - } } void intel_dp_stop_link_train(struct intel_dp *intel_dp) @@ -5035,7 +5014,7 @@ void intel_dp_encoder_destroy(struct drm_encoder *encoder) kfree(intel_dig_port); } -static void intel_dp_encoder_suspend(struct intel_encoder *intel_encoder) +void intel_dp_encoder_suspend(struct intel_encoder *intel_encoder) { struct intel_dp *intel_dp = enc_to_intel_dp(&intel_encoder->base); @@ -5077,15 +5056,17 @@ static void intel_edp_panel_vdd_sanitize(struct intel_dp *intel_dp) edp_panel_vdd_schedule_off(intel_dp); } -static void intel_dp_encoder_reset(struct drm_encoder *encoder) +void intel_dp_encoder_reset(struct drm_encoder *encoder) { - struct intel_dp *intel_dp; + struct drm_i915_private *dev_priv = to_i915(encoder->dev); + struct intel_dp *intel_dp = enc_to_intel_dp(encoder); + + if (!HAS_DDI(dev_priv)) + intel_dp->DP = I915_READ(intel_dp->output_reg); if (to_intel_encoder(encoder)->type != INTEL_OUTPUT_EDP) return; - intel_dp = enc_to_intel_dp(encoder); - pps_lock(intel_dp); /* @@ -5157,9 +5138,6 @@ intel_dp_hpd_pulse(struct intel_digital_port *intel_dig_port, bool long_hpd) intel_display_power_get(dev_priv, power_domain); if (long_hpd) { - /* indicate that we need to restart link training */ - intel_dp->train_set_valid = false; - if (!intel_digital_port_connected(dev_priv, intel_dig_port)) goto mst_fail; diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c index 0639275fc471..06bd9257acdc 100644 --- a/drivers/gpu/drm/i915/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/intel_dp_mst.c @@ -477,6 +477,8 @@ static void intel_dp_destroy_mst_connector(struct drm_dp_mst_topology_mgr *mgr, struct intel_connector *intel_connector = to_intel_connector(connector); struct drm_device *dev = connector->dev; + intel_connector->unregister(intel_connector); + /* need to nuke the connector */ drm_modeset_lock_all(dev); if (connector->state->crtc) { @@ -490,11 +492,7 @@ static void intel_dp_destroy_mst_connector(struct drm_dp_mst_topology_mgr *mgr, WARN(ret, "Disabling mst crtc failed with %i\n", ret); } - drm_modeset_unlock_all(dev); - intel_connector->unregister(intel_connector); - - drm_modeset_lock_all(dev); intel_connector_remove_from_fbdev(intel_connector); drm_connector_cleanup(connector); drm_modeset_unlock_all(dev); diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index 0d00f07b7163..c5f11e0c5d5b 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -783,7 +783,6 @@ struct intel_dp { bool has_aux_irq, int send_bytes, uint32_t aux_clock_divider); - bool train_set_valid; /* Displayport compliance testing */ unsigned long compliance_test_type; @@ -1204,6 +1203,8 @@ void intel_dp_set_link_params(struct intel_dp *intel_dp, void intel_dp_start_link_train(struct intel_dp *intel_dp); void intel_dp_stop_link_train(struct intel_dp *intel_dp); void intel_dp_sink_dpms(struct intel_dp *intel_dp, int mode); +void intel_dp_encoder_reset(struct drm_encoder *encoder); +void intel_dp_encoder_suspend(struct intel_encoder *intel_encoder); void intel_dp_encoder_destroy(struct drm_encoder *encoder); int intel_dp_sink_crc(struct intel_dp *intel_dp, u8 *crc); bool intel_dp_compute_config(struct intel_encoder *encoder, diff --git a/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c b/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c index a5e99ac305da..a8912aecc31f 100644 --- a/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c +++ b/drivers/gpu/drm/i915/intel_dsi_panel_vbt.c @@ -207,7 +207,12 @@ static const u8 *mipi_exec_gpio(struct intel_dsi *intel_dsi, const u8 *data) gpio = *data++; /* pull up/down */ - action = *data++; + action = *data++ & 1; + + if (gpio >= ARRAY_SIZE(gtable)) { + DRM_DEBUG_KMS("unknown gpio %u\n", gpio); + goto out; + } function = gtable[gpio].function_reg; pad = gtable[gpio].pad_reg; @@ -226,6 +231,7 @@ static const u8 *mipi_exec_gpio(struct intel_dsi *intel_dsi, const u8 *data) vlv_gpio_nc_write(dev_priv, pad, val); mutex_unlock(&dev_priv->sb_lock); +out: return data; } diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c index 4fd5fdfef6bd..c0c094d5b822 100644 --- a/drivers/gpu/drm/i915/intel_fbdev.c +++ b/drivers/gpu/drm/i915/intel_fbdev.c @@ -362,12 +362,12 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper, uint64_t conn_configured = 0, mask; int pass = 0; - save_enabled = kcalloc(dev->mode_config.num_connector, sizeof(bool), + save_enabled = kcalloc(fb_helper->connector_count, sizeof(bool), GFP_KERNEL); if (!save_enabled) return false; - memcpy(save_enabled, enabled, dev->mode_config.num_connector); + memcpy(save_enabled, enabled, fb_helper->connector_count); mask = (1 << fb_helper->connector_count) - 1; retry: for (i = 0; i < fb_helper->connector_count; i++) { @@ -501,7 +501,7 @@ retry: if (fallback) { bail: DRM_DEBUG_KMS("Not using firmware configuration\n"); - memcpy(enabled, save_enabled, dev->mode_config.num_connector); + memcpy(enabled, save_enabled, fb_helper->connector_count); kfree(save_enabled); return false; } diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index e6c035b0fc1c..4b8ed9f2dabc 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -1388,8 +1388,16 @@ intel_hdmi_detect(struct drm_connector *connector, bool force) hdmi_to_dig_port(intel_hdmi)); } - if (!live_status) - DRM_DEBUG_KMS("Live status not up!"); + if (!live_status) { + DRM_DEBUG_KMS("HDMI live status down\n"); + /* + * Live status register is not reliable on all intel platforms. + * So consider live_status only for certain platforms, for + * others, read EDID to determine presence of sink. + */ + if (INTEL_INFO(dev_priv)->gen < 7 || IS_IVYBRIDGE(dev_priv)) + live_status = true; + } intel_hdmi_unset_edid(connector); diff --git a/drivers/gpu/drm/i915/intel_hotplug.c b/drivers/gpu/drm/i915/intel_hotplug.c index b17785719598..d7a6437d9da2 100644 --- a/drivers/gpu/drm/i915/intel_hotplug.c +++ b/drivers/gpu/drm/i915/intel_hotplug.c @@ -468,9 +468,14 @@ void intel_hpd_init(struct drm_i915_private *dev_priv) list_for_each_entry(connector, &mode_config->connector_list, head) { struct intel_connector *intel_connector = to_intel_connector(connector); connector->polled = intel_connector->polled; - if (connector->encoder && !connector->polled && I915_HAS_HOTPLUG(dev) && intel_connector->encoder->hpd_pin > HPD_NONE) - connector->polled = DRM_CONNECTOR_POLL_HPD; + + /* MST has a dynamic intel_connector->encoder and it's reprobing + * is all handled by the MST helpers. */ if (intel_connector->mst_port) + continue; + + if (!connector->polled && I915_HAS_HOTPLUG(dev) && + intel_connector->encoder->hpd_pin > HPD_NONE) connector->polled = DRM_CONNECTOR_POLL_HPD; } diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c index 8324654037b6..f3bee54c414f 100644 --- a/drivers/gpu/drm/i915/intel_i2c.c +++ b/drivers/gpu/drm/i915/intel_i2c.c @@ -675,7 +675,7 @@ int intel_setup_gmbus(struct drm_device *dev) return 0; err: - while (--pin) { + while (pin--) { if (!intel_gmbus_is_valid_pin(dev_priv, pin)) continue; diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index 88e12bdf79e2..7058f75c7b42 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -776,11 +776,11 @@ static int logical_ring_prepare(struct drm_i915_gem_request *req, int bytes) if (unlikely(total_bytes > remain_usable)) { /* * The base request will fit but the reserved space - * falls off the end. So only need to to wait for the - * reserved size after flushing out the remainder. + * falls off the end. So don't need an immediate wrap + * and only need to effectively wait for the reserved + * size space from the start of ringbuffer. */ wait_bytes = remain_actual + ringbuf->reserved_size; - need_wrap = true; } else if (total_bytes > ringbuf->space) { /* No wrapping required, just waiting. */ wait_bytes = total_bytes; @@ -1706,6 +1706,7 @@ static int gen8_emit_flush_render(struct drm_i915_gem_request *request, if (flush_domains) { flags |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH; flags |= PIPE_CONTROL_DEPTH_CACHE_FLUSH; + flags |= PIPE_CONTROL_DC_FLUSH_ENABLE; flags |= PIPE_CONTROL_FLUSH_ENABLE; } diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index f091ad12d694..62284e45d531 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -3880,6 +3880,8 @@ static void ilk_pipe_wm_get_hw_state(struct drm_crtc *crtc) if (IS_HASWELL(dev) || IS_BROADWELL(dev)) hw->wm_linetime[pipe] = I915_READ(PIPE_WM_LINETIME(pipe)); + memset(active, 0, sizeof(*active)); + active->pipe_enabled = intel_crtc->active; if (active->pipe_enabled) { @@ -6620,6 +6622,12 @@ static void broadwell_init_clock_gating(struct drm_device *dev) misccpctl = I915_READ(GEN7_MISCCPCTL); I915_WRITE(GEN7_MISCCPCTL, misccpctl & ~GEN7_DOP_CLOCK_GATE_ENABLE); I915_WRITE(GEN8_L3SQCREG1, BDW_WA_L3SQCREG1_DEFAULT); + /* + * Wait at least 100 clocks before re-enabling clock gating. See + * the definition of L3SQCREG1 in BSpec. + */ + POSTING_READ(GEN8_L3SQCREG1); + udelay(1); I915_WRITE(GEN7_MISCCPCTL, misccpctl); /* diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 9461a238f5d5..9d48443bca2e 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -347,6 +347,7 @@ gen7_render_ring_flush(struct drm_i915_gem_request *req, if (flush_domains) { flags |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH; flags |= PIPE_CONTROL_DEPTH_CACHE_FLUSH; + flags |= PIPE_CONTROL_DC_FLUSH_ENABLE; flags |= PIPE_CONTROL_FLUSH_ENABLE; } if (invalidate_domains) { @@ -419,6 +420,7 @@ gen8_render_ring_flush(struct drm_i915_gem_request *req, if (flush_domains) { flags |= PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH; flags |= PIPE_CONTROL_DEPTH_CACHE_FLUSH; + flags |= PIPE_CONTROL_DC_FLUSH_ENABLE; flags |= PIPE_CONTROL_FLUSH_ENABLE; } if (invalidate_domains) { @@ -1920,6 +1922,17 @@ i915_dispatch_execbuffer(struct drm_i915_gem_request *req, return 0; } +static void cleanup_phys_status_page(struct intel_engine_cs *ring) +{ + struct drm_i915_private *dev_priv = to_i915(ring->dev); + + if (!dev_priv->status_page_dmah) + return; + + drm_pci_free(ring->dev, dev_priv->status_page_dmah); + ring->status_page.page_addr = NULL; +} + static void cleanup_status_page(struct intel_engine_cs *ring) { struct drm_i915_gem_object *obj; @@ -1936,9 +1949,9 @@ static void cleanup_status_page(struct intel_engine_cs *ring) static int init_status_page(struct intel_engine_cs *ring) { - struct drm_i915_gem_object *obj; + struct drm_i915_gem_object *obj = ring->status_page.obj; - if ((obj = ring->status_page.obj) == NULL) { + if (obj == NULL) { unsigned flags; int ret; @@ -2132,7 +2145,7 @@ static int intel_init_ring_buffer(struct drm_device *dev, if (ret) goto error; } else { - BUG_ON(ring->id != RCS); + WARN_ON(ring->id != RCS); ret = init_phys_status_page(ring); if (ret) goto error; @@ -2177,7 +2190,12 @@ void intel_cleanup_ring_buffer(struct intel_engine_cs *ring) if (ring->cleanup) ring->cleanup(ring); - cleanup_status_page(ring); + if (I915_NEED_GFX_HWS(ring->dev)) { + cleanup_status_page(ring); + } else { + WARN_ON(ring->id != RCS); + cleanup_phys_status_page(ring); + } i915_cmd_parser_fini_ring(ring); i915_gem_batch_pool_fini(&ring->batch_pool); @@ -2339,11 +2357,11 @@ static int __intel_ring_prepare(struct intel_engine_cs *ring, int bytes) if (unlikely(total_bytes > remain_usable)) { /* * The base request will fit but the reserved space - * falls off the end. So only need to to wait for the - * reserved size after flushing out the remainder. + * falls off the end. So don't need an immediate wrap + * and only need to effectively wait for the reserved + * size space from the start of ringbuffer. */ wait_bytes = remain_actual + ringbuf->reserved_size; - need_wrap = true; } else if (total_bytes > ringbuf->space) { /* No wrapping required, just waiting. */ wait_bytes = total_bytes; diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c index 43cba129a0c0..cc91ae832ffb 100644 --- a/drivers/gpu/drm/i915/intel_uncore.c +++ b/drivers/gpu/drm/i915/intel_uncore.c @@ -1132,7 +1132,11 @@ static void intel_uncore_fw_domains_init(struct drm_device *dev) } else if (IS_HASWELL(dev) || IS_BROADWELL(dev)) { dev_priv->uncore.funcs.force_wake_get = fw_domains_get_with_thread_status; - dev_priv->uncore.funcs.force_wake_put = fw_domains_put; + if (IS_HASWELL(dev)) + dev_priv->uncore.funcs.force_wake_put = + fw_domains_put_with_fifo; + else + dev_priv->uncore.funcs.force_wake_put = fw_domains_put; fw_domain_init(dev_priv, FW_DOMAIN_ID_RENDER, FORCEWAKE_MT, FORCEWAKE_ACK_HSW); } else if (IS_IVYBRIDGE(dev)) { diff --git a/drivers/gpu/drm/imx/imx-drm-core.c b/drivers/gpu/drm/imx/imx-drm-core.c index 7b990b4e96d2..5378bdc3bbf9 100644 --- a/drivers/gpu/drm/imx/imx-drm-core.c +++ b/drivers/gpu/drm/imx/imx-drm-core.c @@ -26,6 +26,7 @@ #include #include #include +#include