diff options
370 files changed, 6248 insertions, 2550 deletions
@@ -82,7 +82,10 @@ Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@gmail.com> Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@imgtec.com> Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@mips.com> <dev.kurt@vandijck-laurijssen.be> <kurt.van.dijck@eia.be> -Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> +Dmitry Baryshkov <dbaryshkov@gmail.com> +Dmitry Baryshkov <dbaryshkov@gmail.com> <[dbaryshkov@gmail.com]> +Dmitry Baryshkov <dbaryshkov@gmail.com> <dmitry_baryshkov@mentor.com> +Dmitry Baryshkov <dbaryshkov@gmail.com> <dmitry_eremin@mentor.com> Dmitry Safonov <0x7f454c46@gmail.com> <dima@arista.com> Dmitry Safonov <0x7f454c46@gmail.com> <d.safonov@partner.samsung.com> Dmitry Safonov <0x7f454c46@gmail.com> <dsafonov@virtuozzo.com> diff --git a/Documentation/devicetree/bindings/clock/imx5-clock.yaml b/Documentation/devicetree/bindings/clock/imx5-clock.yaml index 4d9e7c73dce9..90775c2669b8 100644 --- a/Documentation/devicetree/bindings/clock/imx5-clock.yaml +++ b/Documentation/devicetree/bindings/clock/imx5-clock.yaml @@ -57,7 +57,7 @@ examples: }; can@53fc8000 { - compatible = "fsl,imx53-flexcan", "fsl,p1010-flexcan"; + compatible = "fsl,imx53-flexcan", "fsl,imx25-flexcan"; reg = <0x53fc8000 0x4000>; interrupts = <82>; clocks = <&clks IMX5_CLK_CAN1_IPG_GATE>, <&clks IMX5_CLK_CAN1_SERIAL_GATE>; diff --git a/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml b/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml index 43df15ba8fa4..13875eab2ed6 100644 --- a/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml +++ b/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml @@ -20,8 +20,6 @@ properties: - fsl,imx8qm-flexcan - fsl,imx8mp-flexcan - fsl,imx6q-flexcan - - fsl,imx53-flexcan - - fsl,imx35-flexcan - fsl,imx28-flexcan - fsl,imx25-flexcan - fsl,p1010-flexcan @@ -30,6 +28,11 @@ properties: - fsl,lx2160ar1-flexcan - items: - enum: + - fsl,imx53-flexcan + - fsl,imx35-flexcan + - const: fsl,imx25-flexcan + - items: + - enum: - fsl,imx7d-flexcan - fsl,imx6ul-flexcan - fsl,imx6sx-flexcan @@ -81,11 +84,12 @@ properties: req_bit is the bit offset of CAN stop request. $ref: /schemas/types.yaml#/definitions/phandle-array items: - - description: The 'gpr' is the phandle to general purpose register node. - - description: The 'req_gpr' is the gpr register offset of CAN stop request. - maximum: 0xff - - description: The 'req_bit' is the bit offset of CAN stop request. - maximum: 0x1f + items: + - description: The 'gpr' is the phandle to general purpose register node. + - description: The 'req_gpr' is the gpr register offset of CAN stop request. + maximum: 0xff + - description: The 'req_bit' is the bit offset of CAN stop request. + maximum: 0x1f fsl,clk-source: description: | diff --git a/Documentation/filesystems/ext4/journal.rst b/Documentation/filesystems/ext4/journal.rst index 805a1e9ea3a5..849d5b119eb8 100644 --- a/Documentation/filesystems/ext4/journal.rst +++ b/Documentation/filesystems/ext4/journal.rst @@ -256,6 +256,10 @@ which is 1024 bytes long: - s\_padding2 - * - 0x54 + - \_\_be32 + - s\_num\_fc\_blocks + - Number of fast commit blocks in the journal. + * - 0x58 - \_\_u32 - s\_padding[42] - @@ -310,6 +314,8 @@ The journal incompat features are any combination of the following: - This journal uses v3 of the checksum on-disk format. This is the same as v2, but the journal block tag size is fixed regardless of the size of block numbers. (JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3) + * - 0x20 + - Journal has fast commit blocks. (JBD2\_FEATURE\_INCOMPAT\_FAST\_COMMIT) .. _jbd2_checksum_type: diff --git a/Documentation/filesystems/ext4/super.rst b/Documentation/filesystems/ext4/super.rst index 93e55d7c1d40..2eb1ab20498d 100644 --- a/Documentation/filesystems/ext4/super.rst +++ b/Documentation/filesystems/ext4/super.rst @@ -596,6 +596,13 @@ following: - Sparse Super Block, v2. If this flag is set, the SB field s\_backup\_bgs points to the two block groups that contain backup superblocks (COMPAT\_SPARSE\_SUPER2). + * - 0x400 + - Fast commits supported. Although fast commits blocks are + backward incompatible, fast commit blocks are not always + present in the journal. If fast commit blocks are present in + the journal, JBD2 incompat feature + (JBD2\_FEATURE\_INCOMPAT\_FAST\_COMMIT) gets + set (COMPAT\_FAST\_COMMIT). .. _super_incompat: diff --git a/Documentation/filesystems/journalling.rst b/Documentation/filesystems/journalling.rst index 5a5f70b4063e..e18f90ffc6fd 100644 --- a/Documentation/filesystems/journalling.rst +++ b/Documentation/filesystems/journalling.rst @@ -136,10 +136,8 @@ Fast commits ~~~~~~~~~~~~ JBD2 to also allows you to perform file-system specific delta commits known as -fast commits. In order to use fast commits, you first need to call -:c:func:`jbd2_fc_init` and tell how many blocks at the end of journal -area should be reserved for fast commits. Along with that, you will also need -to set following callbacks that perform correspodning work: +fast commits. In order to use fast commits, you will need to set following +callbacks that perform correspodning work: `journal->j_fc_cleanup_cb`: Cleanup function called after every full commit and fast commit. diff --git a/Documentation/firmware-guide/acpi/acpi-lid.rst b/Documentation/firmware-guide/acpi/acpi-lid.rst index 874ce0ed340d..71b9af13a048 100644 --- a/Documentation/firmware-guide/acpi/acpi-lid.rst +++ b/Documentation/firmware-guide/acpi/acpi-lid.rst @@ -19,9 +19,9 @@ report the "current" state of the lid as either "opened" or "closed". For most platforms, both the _LID method and the lid notifications are reliable. However, there are exceptions. In order to work with these -exceptional buggy platforms, special restrictions and expections should be +exceptional buggy platforms, special restrictions and exceptions should be taken into account. This document describes the restrictions and the -expections of the Linux ACPI lid device driver. +exceptions of the Linux ACPI lid device driver. Restrictions of the returning value of the _LID control method @@ -46,7 +46,7 @@ state is changed to "closed". The "closed" notification is normally used to trigger some system power saving operations on Windows. Since it is fully tested, it is reliable from all AML tables. -Expections for the userspace users of the ACPI lid device driver +Exceptions for the userspace users of the ACPI lid device driver ================================================================ The ACPI button driver exports the lid state to the userspace via the @@ -100,7 +100,7 @@ use the following kernel parameter: C. button.lid_init_state=ignore: When this option is specified, the ACPI button driver never reports the initial lid state and there is a compensation mechanism implemented to - ensure that the reliable "closed" notifications can always be delievered + ensure that the reliable "closed" notifications can always be delivered to the userspace by always pairing "closed" input events with complement "opened" input events. But there is still no guarantee that the "opened" notifications can be delivered to the userspace when the lid is actually diff --git a/Documentation/firmware-guide/acpi/gpio-properties.rst b/Documentation/firmware-guide/acpi/gpio-properties.rst index bb6d74f23ee0..59aad6138b6e 100644 --- a/Documentation/firmware-guide/acpi/gpio-properties.rst +++ b/Documentation/firmware-guide/acpi/gpio-properties.rst @@ -20,9 +20,9 @@ index, like the ASL example below shows:: Name (_CRS, ResourceTemplate () { - GpioIo (Exclusive, PullUp, 0, 0, IoRestrictionInputOnly, + GpioIo (Exclusive, PullUp, 0, 0, IoRestrictionOutputOnly, "\\_SB.GPO0", 0, ResourceConsumer) {15} - GpioIo (Exclusive, PullUp, 0, 0, IoRestrictionInputOnly, + GpioIo (Exclusive, PullUp, 0, 0, IoRestrictionOutputOnly, "\\_SB.GPO0", 0, ResourceConsumer) {27, 31} }) @@ -49,15 +49,41 @@ index pin Pin in the GpioIo()/GpioInt() resource. Typically this is zero. active_low - If 1 the GPIO is marked as active_low. + If 1, the GPIO is marked as active_low. Since ACPI GpioIo() resource does not have a field saying whether it is active low or high, the "active_low" argument can be used here. Setting it to 1 marks the GPIO as active low. +Note, active_low in _DSD does not make sense for GpioInt() resource and +must be 0. GpioInt() resource has its own means of defining it. + In our Bluetooth example the "reset-gpios" refers to the second GpioIo() resource, second pin in that resource with the GPIO number of 31. +The GpioIo() resource unfortunately doesn't explicitly provide an initial +state of the output pin which driver should use during its initialization. + +Linux tries to use common sense here and derives the state from the bias +and polarity settings. The table below shows the expectations: + +========= ============= ============== +Pull Bias Polarity Requested... +========= ============= ============== +Implicit x AS IS (assumed firmware configured for us) +Explicit x (no _DSD) as Pull Bias (Up == High, Down == Low), + assuming non-active (Polarity = !Pull Bias) +Down Low as low, assuming active +Down High as low, assuming non-active +Up Low as high, assuming non-active +Up High as high, assuming active +========= ============= ============== + +That said, for our above example the both GPIOs, since the bias setting +is explicit and _DSD is present, will be treated as active with a high +polarity and Linux will configure the pins in this state until a driver +reprograms them differently. + It is possible to leave holes in the array of GPIOs. This is useful in cases like with SPI host controllers where some chip selects may be implemented as GPIOs and some as native signals. For example a SPI host @@ -112,8 +138,8 @@ Example:: Package () { "gpio-line-names", Package () { - "SPI0_CS_N", "EXP2_INT", "MUX6_IO", "UART0_RXD", "MUX7_IO", - "LVL_C_A1", "MUX0_IO", "SPI1_MISO" + "SPI0_CS_N", "EXP2_INT", "MUX6_IO", "UART0_RXD", + "MUX7_IO", "LVL_C_A1", "MUX0_IO", "SPI1_MISO", } } @@ -137,7 +163,7 @@ to the GPIO lines it is going to use and provide the GPIO subsystem with a mapping between those names and the ACPI GPIO resources corresponding to them. To do that, the driver needs to define a mapping table as a NULL-terminated -array of struct acpi_gpio_mapping objects that each contain a name, a pointer +array of struct acpi_gpio_mapping objects that each contains a name, a pointer to an array of line data (struct acpi_gpio_params) objects and the size of that array. Each struct acpi_gpio_params object consists of three fields, crs_entry_index, line_index, active_low, representing the index of the target @@ -154,13 +180,14 @@ question would look like this:: static const struct acpi_gpio_mapping bluetooth_acpi_gpios[] = { { "reset-gpios", &reset_gpio, 1 }, { "shutdown-gpios", &shutdown_gpio, 1 }, - { }, + { } }; Next, the mapping table needs to be passed as the second argument to -acpi_dev_add_driver_gpios() that will register it with the ACPI device object -pointed to by its first argument. That should be done in the driver's .probe() -routine. On removal, the driver should unregister its GPIO mapping table by +acpi_dev_add_driver_gpios() or its managed analogue that will +register it with the ACPI device object pointed to by its first +argument. That should be done in the driver's .probe() routine. +On removal, the driver should unregister its GPIO mapping table by calling acpi_dev_remove_driver_gpios() on the ACPI device object where that table was previously registered. @@ -191,12 +218,12 @@ The driver might expect to get the right GPIO when it does:: but since there is no way to know the mapping between "reset" and the GpioIo() in _CRS desc will hold ERR_PTR(-ENOENT). -The driver author can solve this by passing the mapping explictly -(the recommended way and documented in the above chapter). +The driver author can solve this by passing the mapping explicitly +(this is the recommended way and it's documented in the above chapter). The ACPI GPIO mapping tables should not contaminate drivers that are not knowing about which exact device they are servicing on. It implies that -the ACPI GPIO mapping tables are hardly linked to ACPI ID and certain +the ACPI GPIO mapping tables are hardly linked to an ACPI ID and certain objects, as listed in the above chapter, of the device in question. Getting GPIO descriptor @@ -229,5 +256,5 @@ Case 2 explicitly tells GPIO core to look for resources in _CRS. Be aware that gpiod_get_index() in cases 1 and 2, assuming that there are two versions of ACPI device description provided and no mapping is present in the driver, will return different resources. That's why a -certain driver has to handle them carefully as explained in previous +certain driver has to handle them carefully as explained in the previous chapter. diff --git a/Documentation/firmware-guide/acpi/method-tracing.rst b/Documentation/firmware-guide/acpi/method-tracing.rst index 0aa7e2c5d32a..6ab6c0964042 100644 --- a/Documentation/firmware-guide/acpi/method-tracing.rst +++ b/Documentation/firmware-guide/acpi/method-tracing.rst @@ -98,7 +98,7 @@ subject to change:: [ 0.188903] exdebug-0398 ex_trace_point : Method End [0xf58394d8:\_SB.PCI0.LPCB.ECOK] execution. Developers can utilize these special log entries to track the AML -interpretion, thus can aid issue debugging and performance tuning. Note +interpretation, thus can aid issue debugging and performance tuning. Note that, as the "AML tracer" logs are implemented via ACPI_DEBUG_PRINT() macro, CONFIG_ACPI_DEBUG is also required to be enabled for enabling "AML tracer" logs. diff --git a/Documentation/networking/netdev-FAQ.rst b/Documentation/networking/netdev-FAQ.rst index d5c9320901c3..21537766be4d 100644 --- a/Documentation/networking/netdev-FAQ.rst +++ b/Documentation/networking/netdev-FAQ.rst @@ -110,7 +110,7 @@ Q: I sent a patch and I'm wondering what happened to it? Q: How can I tell whether it got merged? A: Start by looking at the main patchworks queue for netdev: - http://patchwork.ozlabs.org/project/netdev/list/ + https://patchwork.kernel.org/project/netdevbpf/list/ The "State" field will tell you exactly where things are at with your patch. @@ -152,7 +152,7 @@ networking subsystem, and then hands them off to Greg. There is a patchworks queue that you can see here: - http://patchwork.ozlabs.org/bundle/davem/stable/?state=* + https://patchwork.kernel.org/bundle/netdev/stable/?state=* It contains the patches which Dave has selected, but not yet handed off to Greg. If Greg already has the patch, then it will be here: diff --git a/Documentation/networking/phy.rst b/Documentation/networking/phy.rst index 256106054c8c..b2f7ec794bc8 100644 --- a/Documentation/networking/phy.rst +++ b/Documentation/networking/phy.rst @@ -247,8 +247,8 @@ Some of the interface modes are described below: speeds (see below.) ``PHY_INTERFACE_MODE_2500BASEX`` - This defines a variant of 1000BASE-X which is clocked 2.5 times faster, - than the 802.3 standard giving a fixed bit rate of 3.125Gbaud. + This defines a variant of 1000BASE-X which is clocked 2.5 times as fast + as the 802.3 standard, giving a fixed bit rate of 3.125Gbaud. ``PHY_INTERFACE_MODE_SGMII`` This is used for Cisco SGMII, which is a modification of 1000BASE-X diff --git a/Documentation/process/stable-kernel-rules.rst b/Documentation/process/stable-kernel-rules.rst index 06f743b612c4..3973556250e1 100644 --- a/Documentation/process/stable-kernel-rules.rst +++ b/Documentation/process/stable-kernel-rules.rst @@ -39,7 +39,7 @@ Procedure for submitting patches to the -stable tree submission guidelines as described in :ref:`Documentation/networking/netdev-FAQ.rst <netdev-FAQ>` after first checking the stable networking queue at - https://patchwork.ozlabs.org/bundle/davem/stable/?series=&submitter=&state=*&q=&archive= + https://patchwork.kernel.org/bundle/netdev/stable/?state=* to ensure the requested patch is not already queued up. - Security patches should not be handled (solely) by the -stable review process but should follow the procedures in diff --git a/Documentation/translations/it_IT/process/stable-kernel-rules.rst b/Documentation/translations/it_IT/process/stable-kernel-rules.rst index 4f206cee31a7..283d62541c4f 100644 --- a/Documentation/translations/it_IT/process/stable-kernel-rules.rst +++ b/Documentation/translations/it_IT/process/stable-kernel-rules.rst @@ -46,7 +46,7 @@ Procedura per sottomettere patch per i sorgenti -stable :ref:`Documentation/translations/it_IT/networking/netdev-FAQ.rst <it_netdev-FAQ>`; ma solo dopo aver verificato al seguente indirizzo che la patch non sia già in coda: - https://patchwork.ozlabs.org/bundle/davem/stable/?series=&submitter=&state=*&q=&archive= + https://patchwork.kernel.org/bundle/netdev/stable/?state=* - Una patch di sicurezza non dovrebbero essere gestite (solamente) dal processo di revisione -stable, ma dovrebbe seguire le procedure descritte in :ref:`Documentation/translations/it_IT/admin-guide/security-bugs.rst <it_securitybugs>`. diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 36d5f1f3c6dd..e00a66d72372 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6367,7 +6367,7 @@ accesses that would usually trigger a #GP by KVM into the guest will instead get bounced to user space through the KVM_EXIT_X86_RDMSR and KVM_EXIT_X86_WRMSR exit notifications. -8.25 KVM_X86_SET_MSR_FILTER +8.27 KVM_X86_SET_MSR_FILTER --------------------------- :Architectures: x86 @@ -6381,8 +6381,7 @@ In combination with KVM_CAP_X86_USER_SPACE_MSR, this allows user space to trap and emulate MSRs that are outside of the scope of KVM as well as limit the attack surface on KVM's MSR emulation code. - -8.26 KVM_CAP_ENFORCE_PV_CPUID +8.28 KVM_CAP_ENFORCE_PV_CPUID ----------------------------- Architectures: x86 diff --git a/MAINTAINERS b/MAINTAINERS index e7be8a467fa7..5cc595ac7b28 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1279,7 +1279,7 @@ M: Igor Russkikh <irusskikh@marvell.com> L: netdev@vger.kernel.org S: Supported W: https://www.marvell.com/ -Q: http://patchwork.ozlabs.org/project/netdev/list/ +Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: Documentation/networking/device_drivers/ethernet/aquantia/atlantic.rst F: drivers/net/ethernet/aquantia/atlantic/ @@ -6604,6 +6604,7 @@ Q: http://patchwork.ozlabs.org/project/linux-ext4/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4.git F: Documentation/filesystems/ext4/ F: fs/ext4/ +F: include/trace/events/ext4.h Extended Verification Module (EVM) M: Mimi Zohar <zohar@linux.ibm.com> @@ -8819,8 +8820,8 @@ S: Supported W: http://www.intel.com/support/feedback.htm W: http://e1000.sourceforge.net/ Q: http://patchwork.ozlabs.org/project/intel-wired-lan/list/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net-queue.git -T: git git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/net-queue.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue.git F: Documentation/networking/device_drivers/ethernet/intel/ F: drivers/net/ethernet/intel/ F: drivers/net/ethernet/intel/*/ @@ -11163,7 +11164,7 @@ M: Tariq Toukan <tariqt@nvidia.com> L: netdev@vger.kernel.org S: Supported W: http://www.mellanox.com -Q: http://patchwork.ozlabs.org/project/netdev/list/ +Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: drivers/net/ethernet/mellanox/mlx4/en_* MELLANOX ETHERNET DRIVER (mlx5e) @@ -11171,7 +11172,7 @@ M: Saeed Mahameed <saeedm@nvidia.com> L: netdev@vger.kernel.org S: Supported W: http://www.mellanox.com -Q: http://patchwork.ozlabs.org/project/netdev/list/ +Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: drivers/net/ethernet/mellanox/mlx5/core/en_* MELLANOX ETHERNET INNOVA DRIVERS @@ -11179,7 +11180,7 @@ R: Boris Pismenny <borisp@nvidia.com> L: netdev@vger.kernel.org S: Supported W: http://www.mellanox.com -Q: http://patchwork.ozlabs.org/project/netdev/list/ +Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: drivers/net/ethernet/mellanox/mlx5/core/accel/* F: drivers/net/ethernet/mellanox/mlx5/core/en_accel/* F: drivers/net/ethernet/mellanox/mlx5/core/fpga/* @@ -11191,7 +11192,7 @@ M: Ido Schimmel <idosch@nvidia.com> L: netdev@vger.kernel.org S: Supported W: http://www.mellanox.com -Q: http://patchwork.ozlabs.org/project/netdev/list/ +Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: drivers/net/ethernet/mellanox/mlxsw/ F: tools/testing/selftests/drivers/net/mlxsw/ @@ -11200,7 +11201,7 @@ M: mlxsw@nvidia.com L: netdev@vger.kernel.org S: Supported W: http://www.mellanox.com -Q: http://patchwork.ozlabs.org/project/netdev/list/ +Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: drivers/net/ethernet/mellanox/mlxfw/ MELLANOX HARDWARE PLATFORM SUPPORT @@ -11219,7 +11220,7 @@ L: netdev@vger.kernel.org L: linux-rdma@vger.kernel.org S: Supported W: http://www.mellanox.com -Q: http://patchwork.ozlabs.org/project/netdev/list/ +Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: drivers/net/ethernet/mellanox/mlx4/ F: include/linux/mlx4/ @@ -11240,7 +11241,7 @@ L: netdev@vger.kernel.org L: linux-rdma@vger.kernel.org S: Supported W: http://www.mellanox.com -Q: http://patchwork.ozlabs.org/project/netdev/list/ +Q: https://patchwork.kernel.org/project/netdevbpf/list/ F: Documentation/networking/device_drivers/ethernet/mellanox/ F: drivers/net/ethernet/mellanox/mlx5/core/ F: include/linux/mlx5/ @@ -12120,7 +12121,7 @@ M: Jakub Kicinski <kuba@kernel.org> L: netdev@vger.kernel.org S: Maintained W: http://www.linuxfoundation.org/en/Net -Q: http://patchwork.ozlabs.org/project/netdev/list/ +Q: https://patchwork.kernel.org/project/netdevbpf/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git F: Documentation/devicetree/bindings/net/ @@ -12165,7 +12166,7 @@ M: Jakub Kicinski <kuba@kernel.org> L: netdev@vger.kernel.org S: Maintained W: http://www.linuxfoundation.org/en/Net -Q: http://patchwork.ozlabs.org/project/netdev/list/ +Q: https://patchwork.kernel.org/project/netdevbpf/list/ B: mailto:netdev@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git @@ -15235,7 +15236,6 @@ F: drivers/iommu/s390-iommu.c S390 IUCV NETWORK LAYER M: Julian Wiedmann <jwi@linux.ibm.com> M: Karsten Graul <kgraul@linux.ibm.com> -M: Ursula Braun <ubraun@linux.ibm.com> L: linux-s390@vger.kernel.org S: Supported W: http://www.ibm.com/developerworks/linux/linux390/ @@ -15246,7 +15246,6 @@ F: net/iucv/ S390 NETWORK DRIVERS M: Julian Wiedmann <jwi@linux.ibm.com> M: Karsten Graul <kgraul@linux.ibm.com> -M: Ursula Braun <ubraun@linux.ibm.com> L: linux-s390@vger.kernel.org S: Supported W: http://www.ibm.com/developerworks/linux/linux390/ @@ -15813,7 +15812,6 @@ S: Maintained F: drivers/misc/sgi-xp/ SHARED MEMORY COMMUNICATIONS (SMC) SOCKETS -M: Ursula Braun <ubraun@linux.ibm.com> M: Karsten Graul <kgraul@linux.ibm.com> L: linux-s390@vger.kernel.org S: Supported @@ -18160,6 +18158,14 @@ L: linux-usb@vger.kernel.org S: Supported F: drivers/usb/class/usblp.c +USB RAW GADGET DRIVER +R: Andrey Konovalov <andreyknvl@gmail.com> +L: linux-usb@vger.kernel.org +S: Maintained +F: Documentation/usb/raw-gadget.rst +F: drivers/usb/gadget/legacy/raw_gadget.c +F: include/uapi/linux/usb/raw_gadget.h + USB QMI WWAN NETWORK DRIVER M: Bjørn Mork <bjorn@mork.no> L: netdev@vger.kernel.org @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 10 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc4 NAME = Kleptomaniac Octopus # *DOCUMENTATION* diff --git a/arch/arm/include/asm/kprobes.h b/arch/arm/include/asm/kprobes.h index 213607a1f45c..e26a278d301a 100644 --- a/arch/arm/include/asm/kprobes.h +++ b/arch/arm/include/asm/kprobes.h @@ -44,20 +44,20 @@ int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *data); /* optinsn template addresses */ -extern __visible kprobe_opcode_t optprobe_template_entry; -extern __visible kprobe_opcode_t optprobe_template_val; -extern __visible kprobe_opcode_t optprobe_template_call; -extern __visible kprobe_opcode_t optprobe_template_end; -extern __visible kprobe_opcode_t optprobe_template_sub_sp; -extern __visible kprobe_opcode_t optprobe_template_add_sp; -extern __visible kprobe_opcode_t optprobe_template_restore_begin; -extern __visible kprobe_opcode_t optprobe_template_restore_orig_insn; -extern __visible kprobe_opcode_t optprobe_template_restore_end; +extern __visible kprobe_opcode_t optprobe_template_entry[]; +extern __visible kprobe_opcode_t optprobe_template_val[]; +extern __visible kprobe_opcode_t optprobe_template_call[]; +extern __visible kprobe_opcode_t optprobe_template_end[]; +extern __visible kprobe_opcode_t optprobe_template_sub_sp[]; +extern __visible kprobe_opcode_t optprobe_template_add_sp[]; +extern __visible kprobe_opcode_t optprobe_template_restore_begin[]; +extern __visible kprobe_opcode_t optprobe_template_restore_orig_insn[]; +extern __visible kprobe_opcode_t optprobe_template_restore_end[]; #define MAX_OPTIMIZED_LENGTH 4 #define MAX_OPTINSN_SIZE \ - ((unsigned long)&optprobe_template_end - \ - (unsigned long)&optprobe_template_entry) + ((unsigned long)optprobe_template_end - \ + (unsigned long)optprobe_template_entry) #define RELATIVEJUMP_SIZE 4 struct arch_optimized_insn { diff --git a/arch/arm/kernel/perf_regs.c b/arch/arm/kernel/perf_regs.c index 05fe92aa7d98..0529f90395c9 100644 --- a/arch/arm/kernel/perf_regs.c +++ b/arch/arm/kernel/perf_regs.c @@ -32,8 +32,7 @@ u64 perf_reg_abi(struct task_struct *task) } void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { regs_user->regs = task_pt_regs(current); regs_user->abi = perf_reg_abi(current); diff --git a/arch/arm/probes/kprobes/opt-arm.c b/arch/arm/probes/kprobes/opt-arm.c index 7a449df0b359..c78180172120 100644 --- a/arch/arm/probes/kprobes/opt-arm.c +++ b/arch/arm/probes/kprobes/opt-arm.c @@ -85,21 +85,21 @@ asm ( "optprobe_template_end:\n"); #define TMPL_VAL_IDX \ - ((unsigned long *)&optprobe_template_val - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_val - (unsigned long *)optprobe_template_entry) #define TMPL_CALL_IDX \ - ((unsigned long *)&optprobe_template_call - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_call - (unsigned long *)optprobe_template_entry) #define TMPL_END_IDX \ - ((unsigned long *)&optprobe_template_end - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_end - (unsigned long *)optprobe_template_entry) #define TMPL_ADD_SP \ - ((unsigned long *)&optprobe_template_add_sp - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_add_sp - (unsigned long *)optprobe_template_entry) #define TMPL_SUB_SP \ - ((unsigned long *)&optprobe_template_sub_sp - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_sub_sp - (unsigned long *)optprobe_template_entry) #define TMPL_RESTORE_BEGIN \ - ((unsigned long *)&optprobe_template_restore_begin - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_restore_begin - (unsigned long *)optprobe_template_entry) #define TMPL_RESTORE_ORIGN_INSN \ - ((unsigned long *)&optprobe_template_restore_orig_insn - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_restore_orig_insn - (unsigned long *)optprobe_template_entry) #define TMPL_RESTORE_END \ - ((unsigned long *)&optprobe_template_restore_end - (unsigned long *)&optprobe_template_entry) + ((unsigned long *)optprobe_template_restore_end - (unsigned long *)optprobe_template_entry) /* * ARM can always optimize an instruction when using ARM ISA, except @@ -234,7 +234,7 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, struct kprobe *or } /* Copy arch-dep-instance from template. */ - memcpy(code, (unsigned long *)&optprobe_template_entry, + memcpy(code, (unsigned long *)optprobe_template_entry, TMPL_END_IDX * sizeof(kprobe_opcode_t)); /* Adjust buffer according to instruction. */ diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28.dts b/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28.dts index f46eb47cfa4d..8161dd237971 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28.dts @@ -75,6 +75,7 @@ &enetc_port0 { phy-handle = <&phy0>; phy-connection-type = "sgmii"; + managed = "in-band-status"; status = "okay"; mdio { diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 97244d4feca9..da250e4741bd 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -268,6 +268,8 @@ extern struct arm64_ftr_reg arm64_ftr_reg_ctrel0; /* * CPU feature detected at boot time based on feature of one or more CPUs. * All possible conflicts for a late CPU are ignored. + * NOTE: this means that a late CPU with the feature will *not* cause the + * capability to be advertised by cpus_have_*cap()! */ #define ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE \ (ARM64_CPUCAP_SCOPE_LOCAL_CPU | \ diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 9e2e9a63c7b6..ef5b040dee44 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -86,6 +86,8 @@ #define QCOM_CPU_PART_FALKOR_V1 0x800 #define QCOM_CPU_PART_FALKOR 0xC00 #define QCOM_CPU_PART_KRYO 0x200 +#define QCOM_CPU_PART_KRYO_2XX_GOLD 0x800 +#define QCOM_CPU_PART_KRYO_2XX_SILVER 0x801 #define QCOM_CPU_PART_KRYO_3XX_SILVER 0x803 #define QCOM_CPU_PART_KRYO_4XX_GOLD 0x804 #define QCOM_CPU_PART_KRYO_4XX_SILVER 0x805 @@ -116,6 +118,8 @@ #define MIDR_QCOM_FALKOR_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR_V1) #define MIDR_QCOM_FALKOR MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR) #define MIDR_QCOM_KRYO MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO) +#define MIDR_QCOM_KRYO_2XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_2XX_GOLD) +#define MIDR_QCOM_KRYO_2XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_2XX_SILVER) #define MIDR_QCOM_KRYO_3XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_3XX_SILVER) #define MIDR_QCOM_KRYO_4XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_GOLD) #define MIDR_QCOM_KRYO_4XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_SILVER) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 781d029b8aa8..0cd9f0f75c13 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -118,6 +118,8 @@ struct kvm_arch { */ unsigned long *pmu_filter; unsigned int pmuver; + + u8 pfr0_csv2; }; struct kvm_vcpu_fault_info { diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 174817ba119c..e2ef4c2edf06 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -372,6 +372,8 @@ #define SYS_CONTEXTIDR_EL1 sys_reg(3, 0, 13, 0, 1) #define SYS_TPIDR_EL1 sys_reg(3, 0, 13, 0, 4) +#define SYS_SCXTNUM_EL1 sys_reg(3, 0, 13, 0, 7) + #define SYS_CNTKCTL_EL1 sys_reg(3, 0, 14, 1, 0) #define SYS_CCSIDR_EL1 sys_reg(3, 1, 0, 0, 0) @@ -404,6 +406,8 @@ #define SYS_TPIDR_EL0 sys_reg(3, 3, 13, 0, 2) #define SYS_TPIDRRO_EL0 sys_reg(3, 3, 13, 0, 3) +#define SYS_SCXTNUM_EL0 sys_reg(3, 3, 13, 0, 7) + /* Definitions for system register interface to AMU for ARMv8.4 onwards */ #define SYS_AM_EL0(crm, op2) sys_reg(3, 3, 13, (crm), (op2)) #define SYS_AMCR_EL0 SYS_AM_EL0(2, 0) diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 61314fd70f13..cafaf0da05b7 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -299,6 +299,8 @@ static const struct midr_range erratum_845719_list[] = { MIDR_REV_RANGE(MIDR_CORTEX_A53, 0, 0, 4), /* Brahma-B53 r0p[0] */ MIDR_REV(MIDR_BRAHMA_B53, 0, 0), + /* Kryo2XX Silver rAp4 */ + MIDR_REV(MIDR_QCOM_KRYO_2XX_SILVER, 0xa, 0x4), {}, }; #endif diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index dcc165b3fc04..6f36c4f62f69 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1337,6 +1337,8 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry, MIDR_ALL_VERSIONS(MIDR_CORTEX_A73), MIDR_ALL_VERSIONS(MIDR_HISI_TSV110), MIDR_ALL_VERSIONS(MIDR_NVIDIA_CARMEL), + MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_2XX_GOLD), + MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_2XX_SILVER), MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER), MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER), { /* sentinel */ } diff --git a/arch/arm64/kernel/kexec_image.c b/arch/arm64/kernel/kexec_image.c index 66adee8b5fc8..9ec34690e255 100644 --- a/arch/arm64/kernel/kexec_image.c +++ b/arch/arm64/kernel/kexec_image.c @@ -127,7 +127,7 @@ static void *image_load(struct kimage *image, kernel_segment->mem, kbuf.bufsz, kernel_segment->memsz); - return 0; + return NULL; } #ifdef CONFIG_KEXEC_IMAGE_VERIFY_SIG diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c index 94e8718e7229..f6f58e6265df 100644 --- a/arch/arm64/kernel/perf_regs.c +++ b/arch/arm64/kernel/perf_regs.c @@ -73,8 +73,7 @@ u64 perf_reg_abi(struct task_struct *task) } void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { regs_user->regs = task_pt_regs(current); regs_user->abi = perf_reg_abi(current); diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 4784011cecac..a47a40ec6ad9 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -522,14 +522,13 @@ static void erratum_1418040_thread_switch(struct task_struct *prev, bool prev32, next32; u64 val; - if (!(IS_ENABLED(CONFIG_ARM64_ERRATUM_1418040) && - cpus_have_const_cap(ARM64_WORKAROUND_1418040))) + if (!IS_ENABLED(CONFIG_ARM64_ERRATUM_1418040)) return; prev32 = is_compat_thread(task_thread_info(prev)); next32 = is_compat_thread(task_thread_info(next)); - if (prev32 == next32) + if (prev32 == next32 || !this_cpu_has_cap(ARM64_WORKAROUND_1418040)) return; val = read_sysreg(cntkctl_el1); diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index c18eb7d41274..f6e4e3737405 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -118,6 +118,7 @@ static enum mitigation_state spectre_v2_get_cpu_hw_mitigation_state(void) MIDR_ALL_VERSIONS(MIDR_CORTEX_A55), MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53), MIDR_ALL_VERSIONS(MIDR_HISI_TSV110), + MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_2XX_SILVER), MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER), MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER), { /* sentinel */ } diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c index 43ae4e0c968f..62d2bda7adb8 100644 --- a/arch/arm64/kernel/psci.c +++ b/arch/arm64/kernel/psci.c @@ -66,7 +66,6 @@ static int cpu_psci_cpu_disable(unsigned int cpu) static void cpu_psci_cpu_die(unsigned int cpu) { - int ret; /* * There are no known implementations of PSCI actually using the * power state field, pass a sensible default for now. @@ -74,9 +73,7 @@ static void cpu_psci_cpu_die(unsigned int cpu) u32 state = PSCI_POWER_STATE_TYPE_POWER_DOWN << PSCI_0_2_POWER_STATE_TYPE_SHIFT; - ret = psci_ops.cpu_off(state); - - pr_crit("unable to power off CPU%u (%d)\n", cpu, ret); + psci_ops.cpu_off(state); } static int cpu_psci_cpu_kill(unsigned int cpu) diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 09c96f57818c..18e9727d3f64 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -413,6 +413,7 @@ void cpu_die_early(void) /* Mark this CPU absent */ set_cpu_present(cpu, 0); + rcu_report_dead(cpu); if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) { update_cpu_boot_status(CPU_KILL_ME); diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 5750ec34960e..c0ffb019ca8b 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -102,6 +102,20 @@ static int kvm_arm_default_max_vcpus(void) return vgic_present ? kvm_vgic_get_max_vcpus() : KVM_MAX_VCPUS; } +static void set_default_csv2(struct kvm *kvm) +{ + /* + * The default is to expose CSV2 == 1 if the HW isn't affected. + * Although this is a per-CPU feature, we make it global because + * asymmetric systems are just a nuisance. + * + * Userspace can override this as long as it doesn't promise + * the impossible. + */ + if (arm64_get_spectre_v2_state() == SPECTRE_UNAFFECTED) + kvm->arch.pfr0_csv2 = 1; +} + /** * kvm_arch_init_vm - initializes a VM data structure * @kvm: pointer to the KVM struct @@ -127,6 +141,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) /* The maximum number of VCPUs is limited by the host's GIC model */ kvm->arch.max_vcpus = kvm_arm_default_max_vcpus(); + set_default_csv2(kvm); + return ret; out_free_stage2_pgd: kvm_free_stage2_pgd(&kvm->arch.mmu); diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 57972bdb213a..1a01da9fdc99 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -788,10 +788,12 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, } switch (vma_shift) { +#ifndef __PAGETABLE_PMD_FOLDED case PUD_SHIFT: if (fault_supports_stage2_huge_mapping(memslot, hva, PUD_SIZE)) break; fallthrough; +#endif case CONT_PMD_SHIFT: vma_shift = PMD_SHIFT; fallthrough; diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index fb12d3ef423a..c1fac9836af1 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1038,8 +1038,8 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, { SYS_DESC(SYS_PMEVTYPERn_EL0(n)), \ access_pmu_evtyper, reset_unknown, (PMEVTYPER0_EL0 + n), } -static bool access_amu(struct kvm_vcpu *vcpu, struct sys_reg_params *p, - const struct sys_reg_desc *r) +static bool undef_access(struct kvm_vcpu *vcpu, struct sys_reg_params *p, + const struct sys_reg_desc *r) { kvm_inject_undefined(vcpu); @@ -1047,33 +1047,25 @@ static bool access_amu(struct kvm_vcpu *vcpu, struct sys_reg_params *p, } /* Macro to expand the AMU counter and type registers*/ -#define AMU_AMEVCNTR0_EL0(n) { SYS_DESC(SYS_AMEVCNTR0_EL0(n)), access_amu } -#define AMU_AMEVTYPER0_EL0(n) { SYS_DESC(SYS_AMEVTYPER0_EL0(n)), access_amu } -#define AMU_AMEVCNTR1_EL0(n) { SYS_DESC(SYS_AMEVCNTR1_EL0(n)), access_amu } -#define AMU_AMEVTYPER1_EL0(n) { SYS_DESC(SYS_AMEVTYPER1_EL0(n)), access_amu } - -static bool trap_ptrauth(struct kvm_vcpu *vcpu, - struct sys_reg_params *p, - const struct sys_reg_desc *rd) -{ - /* - * If we land here, that is because we didn't fixup the access on exit - * by allowing the PtrAuth sysregs. The only way this happens is when - * the guest does not have PtrAuth support enabled. - */ - kvm_inject_undefined(vcpu); - - return false; -} +#define AMU_AMEVCNTR0_EL0(n) { SYS_DESC(SYS_AMEVCNTR0_EL0(n)), undef_access } +#define AMU_AMEVTYPER0_EL0(n) { SYS_DESC(SYS_AMEVTYPER0_EL0(n)), undef_access } +#define AMU_AMEVCNTR1_EL0(n) { SYS_DESC(SYS_AMEVCNTR1_EL0(n)), undef_access } +#define AMU_AMEVTYPER1_EL0(n) { SYS_DESC(SYS_AMEVTYPER1_EL0(n)), undef_access } static unsigned int ptrauth_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { - return vcpu_has_ptrauth(vcpu) ? 0 : REG_HIDDEN_USER | REG_HIDDEN_GUEST; + return vcpu_has_ptrauth(vcpu) ? 0 : REG_HIDDEN; } +/* + * If we land here on a PtrAuth access, that is because we didn't + * fixup the access on exit by allowing the PtrAuth sysregs. The only + * way this happens is when the guest does not have PtrAuth support + * enabled. + */ #define __PTRAUTH_KEY(k) \ - { SYS_DESC(SYS_## k), trap_ptrauth, reset_unknown, k, \ + { SYS_DESC(SYS_## k), undef_access, reset_unknown, k, \ .visibility = ptrauth_visibility} #define PTRAUTH_KEY(k) \ @@ -1128,9 +1120,8 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu, if (!vcpu_has_sve(vcpu)) val &= ~(0xfUL << ID_AA64PFR0_SVE_SHIFT); val &= ~(0xfUL << ID_AA64PFR0_AMU_SHIFT); - if (!(val & (0xfUL << ID_AA64PFR0_CSV2_SHIFT)) && - arm64_get_spectre_v2_state() == SPECTRE_UNAFFECTED) - val |= (1UL << ID_AA64PFR0_CSV2_SHIFT); + val &= ~(0xfUL << ID_AA64PFR0_CSV2_SHIFT); + val |= ((u64)vcpu->kvm->arch.pfr0_csv2 << ID_AA64PFR0_CSV2_SHIFT); } else if (id == SYS_ID_AA64PFR1_EL1) { val &= ~(0xfUL << ID_AA64PFR1_MTE_SHIFT); } else if (id == SYS_ID_AA64ISAR1_EL1 && !vcpu_has_ptrauth(vcpu)) { @@ -1153,6 +1144,22 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu, return val; } +static unsigned int id_visibility(const struct kvm_vcpu *vcpu, + const struct sys_reg_desc *r) +{ + u32 id = sys_reg((u32)r->Op0, (u32)r->Op1, + (u32)r->CRn, (u32)r->CRm, (u32)r->Op2); + + switch (id) { + case SYS_ID_AA64ZFR0_EL1: + if (!vcpu_has_sve(vcpu)) + return REG_RAZ; + break; + } + + return 0; +} + /* cpufeature ID register access trap handlers */ static bool __access_id_reg(struct kvm_vcpu *vcpu, @@ -1171,7 +1178,9 @@ static bool access_id_reg(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { - return __access_id_reg(vcpu, p, r, false); + bool raz = sysreg_visible_as_raz(vcpu, r); + + return __access_id_reg(vcpu, p, r, raz); } static bool access_raz_id_reg(struct kvm_vcpu *vcpu, @@ -1192,71 +1201,40 @@ static unsigned int sve_visibility(const struct kvm_vcpu *vcpu, if (vcpu_has_sve(vcpu)) return 0; - return REG_HIDDEN_USER | REG_HIDDEN_GUEST; -} - -/* Visibility overrides for SVE-specific ID registers */ -static unsigned int sve_id_visibility(const struct kvm_vcpu *vcpu, - const struct sys_reg_desc *rd) -{ - if (vcpu_has_sve(vcpu)) - return 0; - - return REG_HIDDEN_USER; + return REG_HIDDEN; } -/* Generate the emulated ID_AA64ZFR0_EL1 value exposed to the guest */ -static u64 guest_id_aa64zfr0_el1(const struct kvm_vcpu *vcpu) -{ - if (!vcpu_has_sve(vcpu)) - return 0; - - return read_sanitised_ftr_reg(SYS_ID_AA64ZFR0_EL1); -} - -static bool access_id_aa64zfr0_el1(struct kvm_vcpu *vcpu, - struct sys_reg_params *p, - const struct sys_reg_desc *rd) -{ - if (p->is_write) - return write_to_read_only(vcpu, p, rd); - - p->regval = guest_id_aa64zfr0_el1(vcpu); - return true; -} - -static int get_id_aa64zfr0_el1(struct kvm_vcpu *vcpu, - const struct sys_reg_desc *rd, - const struct kvm_one_reg *reg, void __user *uaddr) -{ - u64 val; - - if (WARN_ON(!vcpu_has_sve(vcpu))) - return -ENOENT; - - val = guest_id_aa64zfr0_el1(vcpu); - return reg_to_user(uaddr, &val, reg->id); -} - -static int set_id_aa64zfr0_el1(struct kvm_vcpu *vcpu, - const struct sys_reg_desc *rd, - const struct kvm_one_reg *reg, void __user *uaddr) +static int set_id_aa64pfr0_el1(struct kvm_vcpu *vcpu, + const struct sys_reg_desc *rd, + const struct kvm_one_reg *reg, void __user *uaddr) { const u64 id = sys_reg_to_index(rd); int err; u64 val; - - if (WARN_ON(!vcpu_has_sve(vcpu))) - return -ENOENT; + u8 csv2; err = reg_from_user(&val, uaddr, id); if (err) return err; - /* This is what we mean by invariant: you can't change it. */ - if (val != guest_id_aa64zfr0_el1(vcpu)) + /* + * Allow AA64PFR0_EL1.CSV2 to be set from userspace as long as + * it doesn't promise more than what is actually provided (the + * guest could otherwise be covered in ectoplasmic residue). + */ + csv2 = cpuid_feature_extract_unsigned_field(val, ID_AA64PFR0_CSV2_SHIFT); + if (csv2 > 1 || + (csv2 && arm64_get_spectre_v2_state() != SPECTRE_UNAFFECTED)) return -EINVAL; + /* We can only differ with CSV2, and anything else is an error */ + val ^= read_id_reg(vcpu, rd, false); + val &= ~(0xFUL << ID_AA64PFR0_CSV2_SHIFT); + if (val) + return -EINVAL; + + vcpu->kvm->arch.pfr0_csv2 = csv2; + return 0; } @@ -1299,13 +1277,17 @@ static int __set_id_reg(const struct kvm_vcpu *vcpu, static int get_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - return __get_id_reg(vcpu, rd, uaddr, false); + bool raz = sysreg_visible_as_raz(vcpu, rd); + + return __get_id_reg(vcpu, rd, uaddr, raz); } static int set_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - return __set_id_reg(vcpu, rd, uaddr, false); + bool raz = sysreg_visible_as_raz(vcpu, rd); + + return __set_id_reg(vcpu, rd, uaddr, raz); } static int get_raz_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, @@ -1384,19 +1366,13 @@ static bool access_ccsidr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, return true; } -static bool access_mte_regs(struct kvm_vcpu *vcpu, struct sys_reg_params *p, - const struct sys_reg_desc *r) -{ - kvm_inject_undefined(vcpu); - return false; -} - /* sys_reg_desc initialiser for known cpufeature ID registers */ #define ID_SANITISED(name) { \ SYS_DESC(SYS_##name), \ .access = access_id_reg, \ .get_user = get_id_reg, \ .set_user = set_id_reg, \ + .visibility = id_visibility, \ } /* @@ -1514,11 +1490,12 @@ static const struct sys_reg_desc sys_reg_descs[] = { /* AArch64 ID registers */ /* CRm=4 */ - ID_SANITISED(ID_AA64PFR0_EL1), + { SYS_DESC(SYS_ID_AA64PFR0_EL1), .access = access_id_reg, + .get_user = get_id_reg, .set_user = set_id_aa64pfr0_el1, }, ID_SANITISED(ID_AA64PFR1_EL1), ID_UNALLOCATED(4,2), ID_UNALLOCATED(4,3), - { SYS_DESC(SYS_ID_AA64ZFR0_EL1), access_id_aa64zfr0_el1, .get_user = get_id_aa64zfr0_el1, .set_user = set_id_aa64zfr0_el1, .visibility = sve_id_visibility }, + ID_SANITISED(ID_AA64ZFR0_EL1), ID_UNALLOCATED(4,5), ID_UNALLOCATED(4,6), ID_UNALLOCATED(4,7), @@ -1557,8 +1534,8 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_ACTLR_EL1), access_actlr, reset_actlr, ACTLR_EL1 }, { SYS_DESC(SYS_CPACR_EL1), NULL, reset_val, CPACR_EL1, 0 }, - { SYS_DESC(SYS_RGSR_EL1), access_mte_regs }, - { SYS_DESC(SYS_GCR_EL1), access_mte_regs }, + { SYS_DESC(SYS_RGSR_EL1), undef_access }, + { SYS_DESC(SYS_GCR_EL1), undef_access }, { SYS_DESC(SYS_ZCR_EL1), NULL, reset_val, ZCR_EL1, 0, .visibility = sve_visibility }, { SYS_DESC(SYS_TTBR0_EL1), access_vm_reg, reset_unknown, TTBR0_EL1 }, @@ -1584,8 +1561,8 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_ERXMISC0_EL1), trap_raz_wi }, { SYS_DESC(SYS_ERXMISC1_EL1), trap_raz_wi }, - { SYS_DESC(SYS_TFSR_EL1), access_mte_regs }, - { SYS_DESC(SYS_TFSRE0_EL1), access_mte_regs }, + { SYS_DESC(SYS_TFSR_EL1), undef_access }, + { SYS_DESC(SYS_TFSRE0_EL1), undef_access }, { SYS_DESC(SYS_FAR_EL1), access_vm_reg, reset_unknown, FAR_EL1 }, { SYS_DESC(SYS_PAR_EL1), NULL, reset_unknown, PAR_EL1 }, @@ -1621,6 +1598,8 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_CONTEXTIDR_EL1), access_vm_reg, reset_val, CONTEXTIDR_EL1, 0 }, { SYS_DESC(SYS_TPIDR_EL1), NULL, reset_unknown, TPIDR_EL1 }, + { SYS_DESC(SYS_SCXTNUM_EL1), undef_access }, + { SYS_DESC(SYS_CNTKCTL_EL1), NULL, reset_val, CNTKCTL_EL1, 0}, { SYS_DESC(SYS_CCSIDR_EL1), access_ccsidr }, @@ -1649,14 +1628,16 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_TPIDR_EL0), NULL, reset_unknown, TPIDR_EL0 }, { SYS_DESC(SYS_TPIDRRO_EL0), NULL, reset_unknown, TPIDRRO_EL0 }, - { SYS_DESC(SYS_AMCR_EL0), access_amu }, - { SYS_DESC(SYS_AMCFGR_EL0), access_amu }, - { SYS_DESC(SYS_AMCGCR_EL0), access_amu }, - { SYS_DESC(SYS_AMUSERENR_EL0), access_amu }, - { SYS_DESC(SYS_AMCNTENCLR0_EL0), access_amu }, - { SYS_DESC(SYS_AMCNTENSET0_EL0), access_amu }, - { SYS_DESC(SYS_AMCNTENCLR1_EL0), access_amu }, - { SYS_DESC(SYS_AMCNTENSET1_EL0), access_amu }, + { SYS_DESC(SYS_SCXTNUM_EL0), undef_access }, + + { SYS_DESC(SYS_AMCR_EL0), undef_access }, + { SYS_DESC(SYS_AMCFGR_EL0), undef_access }, + { SYS_DESC(SYS_AMCGCR_EL0), undef_access }, + { SYS_DESC(SYS_AMUSERENR_EL0), undef_access }, + { SYS_DESC(SYS_AMCNTENCLR0_EL0), undef_access }, + { SYS_DESC(SYS_AMCNTENSET0_EL0), undef_access }, + { SYS_DESC(SYS_AMCNTENCLR1_EL0), undef_access }, + { SYS_DESC(SYS_AMCNTENSET1_EL0), undef_access }, AMU_AMEVCNTR0_EL0(0), AMU_AMEVCNTR0_EL0(1), AMU_AMEVCNTR0_EL0(2), @@ -2185,7 +2166,7 @@ static void perform_access(struct kvm_vcpu *vcpu, trace_kvm_sys_access(*vcpu_pc(vcpu), params, r); /* Check for regs disabled by runtime config */ - if (sysreg_hidden_from_guest(vcpu, r)) { + if (sysreg_hidden(vcpu, r)) { kvm_inject_undefined(vcpu); return; } @@ -2684,7 +2665,7 @@ int kvm_arm_sys_reg_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg return get_invariant_sys_reg(reg->id, uaddr); /* Check for regs disabled by runtime config */ - if (sysreg_hidden_from_user(vcpu, r)) + if (sysreg_hidden(vcpu, r)) return -ENOENT; if (r->get_user) @@ -2709,7 +2690,7 @@ int kvm_arm_sys_reg_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg return set_invariant_sys_reg(reg->id, uaddr); /* Check for regs disabled by runtime config */ - if (sysreg_hidden_from_user(vcpu, r)) + if (sysreg_hidden(vcpu, r)) return -ENOENT; if (r->set_user) @@ -2780,7 +2761,7 @@ static int walk_one_sys_reg(const struct kvm_vcpu *vcpu, if (!(rd->reg || rd->get_user)) return 0; - if (sysreg_hidden_from_user(vcpu, rd)) + if (sysreg_hidden(vcpu, rd)) return 0; if (!copy_reg_to_user(rd, uind)) diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h index 5a6fc30f5989..0f95964339b1 100644 --- a/arch/arm64/kvm/sys_regs.h +++ b/arch/arm64/kvm/sys_regs.h @@ -59,8 +59,8 @@ struct sys_reg_desc { const struct sys_reg_desc *rd); }; -#define REG_HIDDEN_USER (1 << 0) /* hidden from userspace ioctls */ -#define REG_HIDDEN_GUEST (1 << 1) /* hidden from guest */ +#define REG_HIDDEN (1 << 0) /* hidden from userspace and guest */ +#define REG_RAZ (1 << 1) /* RAZ from userspace and guest */ static __printf(2, 3) inline void print_sys_reg_msg(const struct sys_reg_params *p, @@ -111,22 +111,22 @@ static inline void reset_val(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r __vcpu_sys_reg(vcpu, r->reg) = r->val; } -static inline bool sysreg_hidden_from_guest(const struct kvm_vcpu *vcpu, - const struct sys_reg_desc *r) +static inline bool sysreg_hidden(const struct kvm_vcpu *vcpu, + const struct sys_reg_desc *r) { if (likely(!r->visibility)) return false; - return r->visibility(vcpu, r) & REG_HIDDEN_GUEST; + return r->visibility(vcpu, r) & REG_HIDDEN; } -static inline bool sysreg_hidden_from_user(const struct kvm_vcpu *vcpu, - const struct sys_reg_desc *r) +static inline bool sysreg_visible_as_raz(const struct kvm_vcpu *vcpu, + const struct sys_reg_desc *r) { if (likely(!r->visibility)) return false; - return r->visibility(vcpu, r) & REG_HIDDEN_USER; + return r->visibility(vcpu, r) & REG_RAZ; } static inline int cmp_sys_reg(const struct sys_reg_desc *i1, diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 1c0f3e02f731..ca692a815731 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -1444,11 +1444,28 @@ static void __remove_pgd_mapping(pgd_t *pgdir, unsigned long start, u64 size) free_empty_tables(start, end, PAGE_OFFSET, PAGE_END); } +static bool inside_linear_region(u64 start, u64 size) +{ + /* + * Linear mapping region is the range [PAGE_OFFSET..(PAGE_END - 1)] + * accommodating both its ends but excluding PAGE_END. Max physical + * range which can be mapped inside this linear mapping range, must + * also be derived from its end points. + */ + return start >= __pa(_PAGE_OFFSET(vabits_actual)) && + (start + size - 1) <= __pa(PAGE_END - 1); +} + int arch_add_memory(int nid, u64 start, u64 size, struct mhp_params *params) { int ret, flags = 0; + if (!inside_linear_region(start, size)) { + pr_err("[%llx %llx] is outside linear mapping region\n", start, start + size); + return -EINVAL; + } + if (rodata_full || debug_pagealloc_enabled()) flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS; diff --git a/arch/csky/kernel/perf_regs.c b/arch/csky/kernel/perf_regs.c index eb32838b8210..09b7f88a2d6a 100644 --- a/arch/csky/kernel/perf_regs.c +++ b/arch/csky/kernel/perf_regs.c @@ -32,8 +32,7 @@ u64 perf_reg_abi(struct task_struct *task) } void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { regs_user->regs = task_pt_regs(current); regs_user->abi = perf_reg_abi(current); diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index 9ed4fcccf8a9..7b25548ec42b 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -1336,7 +1336,7 @@ static void dump_trace_imc_data(struct perf_event *event) /* If this is a valid record, create the sample */ struct perf_output_handle handle; - if (perf_output_begin(&handle, event, header.size)) + if (perf_output_begin(&handle, &data, event, header.size)) return; perf_output_sample(&handle, &header, &data, event); diff --git a/arch/powerpc/perf/perf_regs.c b/arch/powerpc/perf/perf_regs.c index 8e53f2fc3fe0..6f681b105eec 100644 --- a/arch/powerpc/perf/perf_regs.c +++ b/arch/powerpc/perf/perf_regs.c @@ -144,8 +144,7 @@ u64 perf_reg_abi(struct task_struct *task) } void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { regs_user->regs = task_pt_regs(current); regs_user->abi = (regs_user->regs) ? perf_reg_abi(current) : diff --git a/arch/riscv/kernel/perf_regs.c b/arch/riscv/kernel/perf_regs.c index 04a38fbeb9c7..fd304a248de6 100644 --- a/arch/riscv/kernel/perf_regs.c +++ b/arch/riscv/kernel/perf_regs.c @@ -36,8 +36,7 @@ u64 perf_reg_abi(struct task_struct *task) } void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { regs_user->regs = task_pt_regs(current); regs_user->abi = perf_reg_abi(current); diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index 4f9e4626df55..00255ae3979d 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -672,7 +672,7 @@ static void cpumsf_output_event_pid(struct perf_event *event, rcu_read_lock(); perf_prepare_sample(&header, data, event, regs); - if (perf_output_begin(&handle, event, header.size)) + if (perf_output_begin(&handle, data, event, header.size)) goto out; /* Update the process ID (see also kernel/events/core.c) */ diff --git a/arch/s390/kernel/perf_regs.c b/arch/s390/kernel/perf_regs.c index 4352a504f235..6e9e5d5e927e 100644 --- a/arch/s390/kernel/perf_regs.c +++ b/arch/s390/kernel/perf_regs.c @@ -53,8 +53,7 @@ u64 perf_reg_abi(struct task_struct *task) } void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { /* * Use the regs from the first interruption and let diff --git a/arch/um/include/asm/pgalloc.h b/arch/um/include/asm/pgalloc.h index 5393e13e07e0..2bbf28cf3aa9 100644 --- a/arch/um/include/asm/pgalloc.h +++ b/arch/um/include/asm/pgalloc.h @@ -33,7 +33,13 @@ do { \ } while (0) #ifdef CONFIG_3_LEVEL_PGTABLES -#define __pmd_free_tlb(tlb,x, address) tlb_remove_page((tlb),virt_to_page(x)) + +#define __pmd_free_tlb(tlb, pmd, address) \ +do { \ + pgtable_pmd_page_dtor(virt_to_page(pmd)); \ + tlb_remove_page((tlb),virt_to_page(pmd)); \ +} while (0) \ + #endif #endif diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index f1926e9f2143..af457f8cb29d 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2630,7 +2630,7 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status) u64 pebs_enabled = cpuc->pebs_enabled; handled++; - x86_pmu.drain_pebs(regs); + x86_pmu.drain_pebs(regs, &data); status &= x86_pmu.intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI; /* @@ -4987,6 +4987,12 @@ __init int intel_pmu_init(void) x86_add_quirk(intel_arch_events_quirk); /* Install first, so it runs last */ + if (version >= 5) { + x86_pmu.intel_cap.anythread_deprecated = edx.split.anythread_deprecated; + if (x86_pmu.intel_cap.anythread_deprecated) + pr_cont(" AnyThread deprecated, "); + } + /* * Install the hw-cache-events table: */ @@ -5512,6 +5518,10 @@ __init int intel_pmu_init(void) x86_pmu.intel_ctrl |= ((1LL << x86_pmu.num_counters_fixed)-1) << INTEL_PMC_IDX_FIXED; + /* AnyThread may be deprecated on arch perfmon v5 or later */ + if (x86_pmu.intel_cap.anythread_deprecated) + x86_pmu.format_attrs = intel_arch_formats_attr; + if (x86_pmu.event_constraints) { /* * event on fixed counter2 (REF_CYCLES) only works on this diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 404315df1e16..b47cc4226934 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -642,8 +642,8 @@ int intel_pmu_drain_bts_buffer(void) rcu_read_lock(); perf_prepare_sample(&header, &data, event, ®s); - if (perf_output_begin(&handle, event, header.size * - (top - base - skip))) + if (perf_output_begin(&handle, &data, event, + header.size * (top - base - skip))) goto unlock; for (at = base; at < top; at++) { @@ -670,7 +670,9 @@ unlock: static inline void intel_pmu_drain_pebs_buffer(void) { - x86_pmu.drain_pebs(NULL); + struct perf_sample_data data; + + x86_pmu.drain_pebs(NULL, &data); } /* @@ -1719,23 +1721,24 @@ intel_pmu_save_and_restart_reload(struct perf_event *event, int count) return 0; } -static void __intel_pmu_pebs_event(struct perf_event *event, - struct pt_regs *iregs, - void *base, void *top, - int bit, int count, - void (*setup_sample)(struct perf_event *, - struct pt_regs *, - void *, - struct perf_sample_data *, - struct pt_regs *)) +static __always_inline void +__intel_pmu_pebs_event(struct perf_event *event, + struct pt_regs *iregs, + struct perf_sample_data *data, + void *base, void *top, + int bit, int count, + void (*setup_sample)(struct perf_event *, + struct pt_regs *, + void *, + struct perf_sample_data *, + struct pt_regs *)) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; - struct perf_sample_data data; struct x86_perf_regs perf_regs; struct pt_regs *regs = &perf_regs.regs; void *at = get_next_pebs_record_by_bit(base, top, bit); - struct pt_regs dummy_iregs; + static struct pt_regs dummy_iregs; if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) { /* @@ -1752,14 +1755,14 @@ static void __intel_pmu_pebs_event(struct perf_event *event, iregs = &dummy_iregs; while (count > 1) { - setup_sample(event, iregs, at, &data, regs); - perf_event_output(event, &data, regs); + setup_sample(event, iregs, at, data, regs); + perf_event_output(event, data, regs); at += cpuc->pebs_record_size; at = get_next_pebs_record_by_bit(at, top, bit); count--; } - setup_sample(event, iregs, at, &data, regs); + setup_sample(event, iregs, at, data, regs); if (iregs == &dummy_iregs) { /* * The PEBS records may be drained in the non-overflow context, @@ -1767,18 +1770,18 @@ static void __intel_pmu_pebs_event(struct perf_event *event, * last record the same as other PEBS records, and doesn't * invoke the generic overflow handler. */ - perf_event_output(event, &data, regs); + perf_event_output(event, data, regs); } else { /* * All but the last records are processed. * The last one is left to be able to call the overflow handler. */ - if (perf_event_overflow(event, &data, regs)) + if (perf_event_overflow(event, data, regs)) x86_pmu_stop(event, 0); } } -static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) +static void intel_pmu_drain_pebs_core(struct pt_regs *iregs, struct perf_sample_data *data) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct debug_store *ds = cpuc->ds; @@ -1812,7 +1815,7 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) return; } - __intel_pmu_pebs_event(event, iregs, at, top, 0, n, + __intel_pmu_pebs_event(event, iregs, data, at, top, 0, n, setup_pebs_fixed_sample_data); } @@ -1835,7 +1838,7 @@ static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, int } } -static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) +static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_data *data) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct debug_store *ds = cpuc->ds; @@ -1942,14 +1945,14 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) } if (counts[bit]) { - __intel_pmu_pebs_event(event, iregs, base, + __intel_pmu_pebs_event(event, iregs, data, base, top, bit, counts[bit], setup_pebs_fixed_sample_data); } } } -static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs) +static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_data *data) { short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {}; struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); @@ -1997,7 +2000,7 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs) if (WARN_ON_ONCE(!event->attr.precise_ip)) continue; - __intel_pmu_pebs_event(event, iregs, base, + __intel_pmu_pebs_event(event, iregs, data, base, top, bit, counts[bit], setup_pebs_adaptive_sample_data); } diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index 39e632ed6ca9..bbd1120ae161 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -475,7 +475,7 @@ enum perf_snb_uncore_imc_freerunning_types { static struct freerunning_counters snb_uncore_imc_freerunning[] = { [SNB_PCI_UNCORE_IMC_DATA_READS] = { SNB_UNCORE_PCI_IMC_DATA_READS_BASE, 0x0, 0x0, 1, 32 }, - [SNB_PCI_UNCORE_IMC_DATA_READS] = { SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE, + [SNB_PCI_UNCORE_IMC_DATA_WRITES] = { SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE, 0x0, 0x0, 1, 32 }, [SNB_PCI_UNCORE_IMC_GT_REQUESTS] = { SNB_UNCORE_PCI_IMC_GT_REQUESTS_BASE, 0x0, 0x0, 1, 32 }, diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index ee2b9b9fc2a5..6a8edfe59b09 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -585,6 +585,7 @@ union perf_capabilities { u64 pebs_baseline:1; u64 perf_metrics:1; u64 pebs_output_pt_available:1; + u64 anythread_deprecated:1; }; u64 capabilities; }; @@ -727,7 +728,7 @@ struct x86_pmu { int pebs_record_size; int pebs_buffer_size; int max_pebs_events; - void (*drain_pebs)(struct pt_regs *regs); + void (*drain_pebs)(struct pt_regs *regs, struct perf_sample_data *data); struct event_constraint *pebs_constraints; void (*pebs_aliases)(struct perf_event *event); unsigned long large_pebs_flags; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index d44858b69353..324ddd7fd0aa 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -639,6 +639,7 @@ struct kvm_vcpu_arch { int cpuid_nent; struct kvm_cpuid_entry2 *cpuid_entries; + unsigned long cr3_lm_rsvd_bits; int maxphyaddr; int max_tdp_level; diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 6960cd6d1f23..b9a7fd0a27e2 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -137,7 +137,9 @@ union cpuid10_edx { struct { unsigned int num_counters_fixed:5; unsigned int bit_width_fixed:8; - unsigned int reserved:19; + unsigned int reserved1:2; + unsigned int anythread_deprecated:1; + unsigned int reserved2:16; } split; unsigned int full; }; diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h index 172d3e4a9e4b..648eb23fe7f0 100644 --- a/arch/x86/include/asm/uv/uv.h +++ b/arch/x86/include/asm/uv/uv.h @@ -2,14 +2,8 @@ #ifndef _ASM_X86_UV_UV_H #define _ASM_X86_UV_UV_H -#include <asm/tlbflush.h> - enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC}; -struct cpumask; -struct mm_struct; -struct flush_tlb_info; - #ifdef CONFIG_X86_UV #include <linux/efi.h> @@ -44,10 +38,6 @@ static inline int is_uv_system(void) { return 0; } static inline int is_uv_hubbed(int uv) { return 0; } static inline void uv_cpu_init(void) { } static inline void uv_system_init(void) { } -static inline const struct cpumask * -uv_flush_tlb_others(const struct cpumask *cpumask, - const struct flush_tlb_info *info) -{ return cpumask; } #endif /* X86_UV */ diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 3115caa7d7d0..1b98f8c12b96 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -33,7 +33,7 @@ static union uvh_apicid uvh_apicid; static int uv_node_id; /* Unpack AT/OEM/TABLE ID's to be NULL terminated strings */ -static u8 uv_archtype[UV_AT_SIZE]; +static u8 uv_archtype[UV_AT_SIZE + 1]; static u8 oem_id[ACPI_OEM_ID_SIZE + 1]; static u8 oem_table_id[ACPI_OEM_TABLE_ID_SIZE + 1]; @@ -320,7 +320,7 @@ static int __init decode_arch_type(unsigned long ptr) if (n > 0 && n < sizeof(uv_ate->archtype)) { pr_info("UV: UVarchtype received from BIOS\n"); - uv_stringify(UV_AT_SIZE, uv_archtype, uv_ate->archtype); + uv_stringify(sizeof(uv_archtype), uv_archtype, uv_ate->archtype); return 1; } return 0; @@ -378,7 +378,7 @@ static int __init uv_set_system_type(char *_oem_id, char *_oem_table_id) if (!early_get_arch_type()) /* If not use OEM ID for UVarchtype */ - uv_stringify(UV_AT_SIZE, uv_archtype, _oem_id); + uv_stringify(sizeof(uv_archtype), uv_archtype, oem_id); /* Check if not hubbed */ if (strncmp(uv_archtype, "SGI", 3) != 0) { diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c index bb7e1132290b..f9e5352b3bef 100644 --- a/arch/x86/kernel/perf_regs.c +++ b/arch/x86/kernel/perf_regs.c @@ -101,8 +101,7 @@ u64 perf_reg_abi(struct task_struct *task) } void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { regs_user->regs = task_pt_regs(current); regs_user->abi = perf_reg_abi(current); @@ -129,12 +128,20 @@ u64 perf_reg_abi(struct task_struct *task) return PERF_SAMPLE_REGS_ABI_64; } +static DEFINE_PER_CPU(struct pt_regs, nmi_user_regs); + void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { + struct pt_regs *regs_user_copy = this_cpu_ptr(&nmi_user_regs); struct pt_regs *user_regs = task_pt_regs(current); + if (!in_nmi()) { + regs_user->regs = user_regs; + regs_user->abi = perf_reg_abi(current); + return; + } + /* * If we're in an NMI that interrupted task_pt_regs setup, then * we can't sample user regs at all. This check isn't really diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 06a278b3701d..83637a2ff605 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -90,6 +90,20 @@ static int kvm_check_cpuid(struct kvm_cpuid_entry2 *entries, int nent) return 0; } +void kvm_update_pv_runtime(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, KVM_CPUID_FEATURES, 0); + + /* + * save the feature bitmap to avoid cpuid lookup for every PV + * operation + */ + if (best) + vcpu->arch.pv_cpuid.features = best->eax; +} + void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; @@ -124,13 +138,6 @@ void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu) (best->eax & (1 << KVM_FEATURE_PV_UNHALT))) best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT); - /* - * save the feature bitmap to avoid cpuid lookup for every PV - * operation - */ - if (best) - vcpu->arch.pv_cpuid.features = best->eax; - if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT)) { best = kvm_find_cpuid_entry(vcpu, 0x1, 0); if (best) @@ -162,6 +169,8 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) vcpu->arch.guest_supported_xcr0 = (best->eax | ((u64)best->edx << 32)) & supported_xcr0; + kvm_update_pv_runtime(vcpu); + vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); kvm_mmu_reset_context(vcpu); @@ -169,6 +178,8 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) vcpu->arch.cr4_guest_rsvd_bits = __cr4_reserved_bits(guest_cpuid_has, vcpu); + vcpu->arch.cr3_lm_rsvd_bits = rsvd_bits(cpuid_maxphyaddr(vcpu), 63); + /* Invoke the vendor callback only after the above state is updated. */ kvm_x86_ops.vcpu_after_set_cpuid(vcpu); } @@ -672,7 +683,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) edx.split.num_counters_fixed = min(cap.num_counters_fixed, MAX_FIXED_COUNTERS); edx.split.bit_width_fixed = cap.bit_width_fixed; - edx.split.reserved = 0; + edx.split.anythread_deprecated = 1; + edx.split.reserved1 = 0; + edx.split.reserved2 = 0; entry->eax = eax.full; entry->ebx = cap.events_mask; diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index bf8577947ed2..f7a6e8f83783 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -11,6 +11,7 @@ extern u32 kvm_cpu_caps[NCAPINTS] __read_mostly; void kvm_set_cpu_caps(void); void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu); +void kvm_update_pv_runtime(struct kvm_vcpu *vcpu); struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, u32 function, u32 index); int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid, diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 0d917eb70319..56cae1ff9e3f 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -4046,6 +4046,12 @@ static int em_clflush(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } +static int em_clflushopt(struct x86_emulate_ctxt *ctxt) +{ + /* emulating clflushopt regardless of cpuid */ + return X86EMUL_CONTINUE; +} + static int em_movsxd(struct x86_emulate_ctxt *ctxt) { ctxt->dst.val = (s32) ctxt->src.val; @@ -4585,7 +4591,7 @@ static const struct opcode group11[] = { }; static const struct gprefix pfx_0f_ae_7 = { - I(SrcMem | ByteOp, em_clflush), N, N, N, + I(SrcMem | ByteOp, em_clflush), I(SrcMem | ByteOp, em_clflushopt), N, N, }; static const struct group_dual group15 = { { diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 1f96adff8dc4..5bb1939b65d8 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -856,12 +856,14 @@ static int pte_list_add(struct kvm_vcpu *vcpu, u64 *spte, } else { rmap_printk("pte_list_add: %p %llx many->many\n", spte, *spte); desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); - while (desc->sptes[PTE_LIST_EXT-1] && desc->more) { - desc = desc->more; + while (desc->sptes[PTE_LIST_EXT-1]) { count += PTE_LIST_EXT; - } - if (desc->sptes[PTE_LIST_EXT-1]) { - desc->more = mmu_alloc_pte_list_desc(vcpu); + + if (!desc->more) { + desc->more = mmu_alloc_pte_list_desc(vcpu); + desc = desc->more; + break; + } desc = desc->more; } for (i = 0; desc->sptes[i]; ++i) diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 27e381c9da6c..ff28a5c6abd6 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -49,7 +49,14 @@ bool is_tdp_mmu_root(struct kvm *kvm, hpa_t hpa) { struct kvm_mmu_page *sp; + if (!kvm->arch.tdp_mmu_enabled) + return false; + if (WARN_ON(!VALID_PAGE(hpa))) + return false; + sp = to_shadow_page(hpa); + if (WARN_ON(!sp)) + return false; return sp->tdp_mmu_page && sp->root_count; } diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 2f32fd09e259..1e81cfebd491 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3741,6 +3741,7 @@ static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + struct kvm_cpuid_entry2 *best; vcpu->arch.xsaves_enabled = guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && boot_cpu_has(X86_FEATURE_XSAVE) && @@ -3753,6 +3754,13 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) /* Check again if INVPCID interception if required */ svm_check_invpcid(svm); + /* For sev guests, the memory encryption bit is not reserved in CR3. */ + if (sev_guest(vcpu->kvm)) { + best = kvm_find_cpuid_entry(vcpu, 0x8000001F, 0); + if (best) + vcpu->arch.cr3_lm_rsvd_bits &= ~(1UL << (best->ebx & 0x3f)); + } + if (!kvm_vcpu_apicv_active(vcpu)) return; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index f5ede41bf9e6..078a39d489fe 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -255,11 +255,10 @@ static struct kmem_cache *x86_emulator_cache; /* * When called, it means the previous get/set msr reached an invalid msr. - * Return 0 if we want to ignore/silent this failed msr access, or 1 if we want - * to fail the caller. + * Return true if we want to ignore/silent this failed msr access. */ -static int kvm_msr_ignored_check(struct kvm_vcpu *vcpu, u32 msr, - u64 data, bool write) +static bool kvm_msr_ignored_check(struct kvm_vcpu *vcpu, u32 msr, + u64 data, bool write) { const char *op = write ? "wrmsr" : "rdmsr"; @@ -268,11 +267,11 @@ static int kvm_msr_ignored_check(struct kvm_vcpu *vcpu, u32 msr, kvm_pr_unimpl("ignored %s: 0x%x data 0x%llx\n", op, msr, data); /* Mask the error */ - return 0; + return true; } else { kvm_debug_ratelimited("unhandled %s: 0x%x data 0x%llx\n", op, msr, data); - return -ENOENT; + return false; } } @@ -1042,7 +1041,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) } if (is_long_mode(vcpu) && - (cr3 & rsvd_bits(cpuid_maxphyaddr(vcpu), 63))) + (cr3 & vcpu->arch.cr3_lm_rsvd_bits)) return 1; else if (is_pae_paging(vcpu) && !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) @@ -1416,7 +1415,8 @@ static int do_get_msr_feature(struct kvm_vcpu *vcpu, unsigned index, u64 *data) if (r == KVM_MSR_RET_INVALID) { /* Unconditionally clear the output for simplicity */ *data = 0; - r = kvm_msr_ignored_check(vcpu, index, 0, false); + if (kvm_msr_ignored_check(vcpu, index, 0, false)) + r = 0; } if (r) @@ -1540,7 +1540,7 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data, struct msr_data msr; if (!host_initiated && !kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_WRITE)) - return -EPERM; + return KVM_MSR_RET_FILTERED; switch (index) { case MSR_FS_BASE: @@ -1581,7 +1581,8 @@ static int kvm_set_msr_ignored_check(struct kvm_vcpu *vcpu, int ret = __kvm_set_msr(vcpu, index, data, host_initiated); if (ret == KVM_MSR_RET_INVALID) - ret = kvm_msr_ignored_check(vcpu, index, data, true); + if (kvm_msr_ignored_check(vcpu, index, data, true)) + ret = 0; return ret; } @@ -1599,7 +1600,7 @@ int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, int ret; if (!host_initiated && !kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_READ)) - return -EPERM; + return KVM_MSR_RET_FILTERED; msr.index = index; msr.host_initiated = host_initiated; @@ -1618,7 +1619,8 @@ static int kvm_get_msr_ignored_check(struct kvm_vcpu *vcpu, if (ret == KVM_MSR_RET_INVALID) { /* Unconditionally clear *data for simplicity */ *data = 0; - ret = kvm_msr_ignored_check(vcpu, index, 0, false); + if (kvm_msr_ignored_check(vcpu, index, 0, false)) + ret = 0; } return ret; @@ -1662,9 +1664,9 @@ static int complete_emulated_wrmsr(struct kvm_vcpu *vcpu) static u64 kvm_msr_reason(int r) { switch (r) { - case -ENOENT: + case KVM_MSR_RET_INVALID: return KVM_MSR_EXIT_REASON_UNKNOWN; - case -EPERM: + case KVM_MSR_RET_FILTERED: return KVM_MSR_EXIT_REASON_FILTER; default: return KVM_MSR_EXIT_REASON_INVAL; @@ -1965,7 +1967,7 @@ static void kvm_write_system_time(struct kvm_vcpu *vcpu, gpa_t system_time, struct kvm_arch *ka = &vcpu->kvm->arch; if (vcpu->vcpu_id == 0 && !host_initiated) { - if (ka->boot_vcpu_runs_old_kvmclock && old_msr) + if (ka->boot_vcpu_runs_old_kvmclock != old_msr) kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu); ka->boot_vcpu_runs_old_kvmclock = old_msr; @@ -3063,9 +3065,9 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) /* Values other than LBR and BTF are vendor-specific, thus reserved and should throw a #GP */ return 1; - } - vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n", - __func__, data); + } else if (report_ignored_msrs) + vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n", + __func__, data); break; case 0x200 ... 0x2ff: return kvm_mtrr_set_msr(vcpu, msr, data); @@ -3463,29 +3465,63 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vcpu->arch.efer; break; case MSR_KVM_WALL_CLOCK: + if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE)) + return 1; + + msr_info->data = vcpu->kvm->arch.wall_clock; + break; case MSR_KVM_WALL_CLOCK_NEW: + if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2)) + return 1; + msr_info->data = vcpu->kvm->arch.wall_clock; break; case MSR_KVM_SYSTEM_TIME: + if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE)) + return 1; + + msr_info->data = vcpu->arch.time; + break; case MSR_KVM_SYSTEM_TIME_NEW: + if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2)) + return 1; + msr_info->data = vcpu->arch.time; break; case MSR_KVM_ASYNC_PF_EN: + if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF)) + return 1; + msr_info->data = vcpu->arch.apf.msr_en_val; break; case MSR_KVM_ASYNC_PF_INT: + if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT)) + return 1; + msr_info->data = vcpu->arch.apf.msr_int_val; break; case MSR_KVM_ASYNC_PF_ACK: + if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF)) + return 1; + msr_info->data = 0; break; case MSR_KVM_STEAL_TIME: + if (!guest_pv_has(vcpu, KVM_FEATURE_STEAL_TIME)) + return 1; + msr_info->data = vcpu->arch.st.msr_val; break; case MSR_KVM_PV_EOI_EN: + if (!guest_pv_has(vcpu, KVM_FEATURE_PV_EOI)) + return 1; + msr_info->data = vcpu->arch.pv_eoi.msr_val; break; case MSR_KVM_POLL_CONTROL: + if (!guest_pv_has(vcpu, KVM_FEATURE_POLL_CONTROL)) + return 1; + msr_info->data = vcpu->arch.msr_kvm_poll_control; break; case MSR_IA32_P5_MC_ADDR: @@ -4575,6 +4611,8 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, case KVM_CAP_ENFORCE_PV_FEATURE_CPUID: vcpu->arch.pv_cpuid.enforce = cap->args[0]; + if (vcpu->arch.pv_cpuid.enforce) + kvm_update_pv_runtime(vcpu); return 0; diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 3900ab0c6004..e7ca622a468f 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -376,7 +376,13 @@ int kvm_handle_memory_failure(struct kvm_vcpu *vcpu, int r, int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva); bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type); -#define KVM_MSR_RET_INVALID 2 +/* + * Internal error codes that are used to indicate that MSR emulation encountered + * an error that should result in #GP in the guest, unless userspace + * handles it. + */ +#define KVM_MSR_RET_INVALID 2 /* in-kernel MSR emulation #GP condition */ +#define KVM_MSR_RET_FILTERED 3 /* #GP due to userspace MSR filter */ #define __cr4_reserved_bits(__cpu_has, __c) \ ({ \ diff --git a/block/genhd.c b/block/genhd.c index 0a273211fec2..9387f050c248 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -49,7 +49,7 @@ static void disk_release_events(struct gendisk *disk); * Set disk capacity and notify if the size is not currently * zero and will not be set to zero */ -void set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size, +bool set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size, bool update_bdev) { sector_t capacity = get_capacity(disk); @@ -62,7 +62,10 @@ void set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size, char *envp[] = { "RESIZE=1", NULL }; kobject_uevent_env(&disk_to_dev(disk)->kobj, KOBJ_CHANGE, envp); + return true; } + + return false; } EXPORT_SYMBOL_GPL(set_capacity_revalidate_and_notify); diff --git a/drivers/accessibility/speakup/main.c b/drivers/accessibility/speakup/main.c index be79b2135fac..48019660a096 100644 --- a/drivers/accessibility/speakup/main.c +++ b/drivers/accessibility/speakup/main.c @@ -357,7 +357,6 @@ static void speakup_cut(struct vc_data *vc) mark_cut_flag = 0; synth_printf("%s\n", spk_msg_get(MSG_CUT)); - speakup_clear_selection(); ret = speakup_set_selection(tty); switch (ret) { diff --git a/drivers/accessibility/speakup/selection.c b/drivers/accessibility/speakup/selection.c index 032f3264fba1..7df7afad5ab4 100644 --- a/drivers/accessibility/speakup/selection.c +++ b/drivers/accessibility/speakup/selection.c @@ -22,13 +22,6 @@ struct speakup_selection_work { struct tty_struct *tty; }; -void speakup_clear_selection(void) -{ - console_lock(); - clear_selection(); - console_unlock(); -} - static void __speakup_set_selection(struct work_struct *work) { struct speakup_selection_work *ssw = @@ -51,6 +44,10 @@ static void __speakup_set_selection(struct work_struct *work) goto unref; } + console_lock(); + clear_selection(); + console_unlock(); + set_selection_kernel(&sel, tty); unref: diff --git a/drivers/accessibility/speakup/speakup.h b/drivers/accessibility/speakup/speakup.h index 74fe49c2c511..33594f5a7983 100644 --- a/drivers/accessibility/speakup/speakup.h +++ b/drivers/accessibility/speakup/speakup.h @@ -70,7 +70,6 @@ void spk_do_flush(void); void speakup_start_ttys(void); void synth_buffer_add(u16 ch); void synth_buffer_clear(void); -void speakup_clear_selection(void); int speakup_set_selection(struct tty_struct *tty); void speakup_cancel_selection(void); int speakup_paste_selection(struct tty_struct *tty); diff --git a/drivers/accessibility/speakup/spk_ttyio.c b/drivers/accessibility/speakup/spk_ttyio.c index a831ff64f8ba..ecc39983e946 100644 --- a/drivers/accessibility/speakup/spk_ttyio.c +++ b/drivers/accessibility/speakup/spk_ttyio.c @@ -298,11 +298,13 @@ static unsigned char ttyio_in(int timeout) struct spk_ldisc_data *ldisc_data = speakup_tty->disc_data; char rv; - if (wait_for_completion_timeout(&ldisc_data->completion, + if (!timeout) { + if (!try_wait_for_completion(&ldisc_data->completion)) + return 0xff; + } else if (wait_for_completion_timeout(&ldisc_data->completion, usecs_to_jiffies(timeout)) == 0) { - if (timeout) - pr_warn("spk_ttyio: timeout (%d) while waiting for input\n", - timeout); + pr_warn("spk_ttyio: timeout (%d) while waiting for input\n", + timeout); return 0xff; } diff --git a/drivers/accessibility/speakup/spk_types.h b/drivers/accessibility/speakup/spk_types.h index 7398f1196e10..91fca3033a45 100644 --- a/drivers/accessibility/speakup/spk_types.h +++ b/drivers/accessibility/speakup/spk_types.h @@ -32,6 +32,10 @@ enum { E_NEW_DEFAULT, }; +/* + * Note: add new members at the end, speakupmap.h depends on the values of the + * enum starting from SPELL_DELAY (see inc_dec_var) + */ enum var_id_t { VERSION = 0, SYNTH, SILENT, SYNTH_DIRECT, KEYMAP, CHARS, @@ -42,9 +46,9 @@ enum var_id_t { SAY_CONTROL, SAY_WORD_CTL, NO_INTERRUPT, KEY_ECHO, SPELL_DELAY, PUNC_LEVEL, READING_PUNC, ATTRIB_BLEEP, BLEEPS, - RATE, PITCH, INFLECTION, VOL, TONE, PUNCT, VOICE, FREQUENCY, LANG, + RATE, PITCH, VOL, TONE, PUNCT, VOICE, FREQUENCY, LANG, DIRECT, PAUSE, - CAPS_START, CAPS_STOP, CHARTAB, + CAPS_START, CAPS_STOP, CHARTAB, INFLECTION, MAXVARS }; diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c index bc96457c9e25..a322a7bd286b 100644 --- a/drivers/acpi/acpi_video.c +++ b/drivers/acpi/acpi_video.c @@ -578,7 +578,7 @@ acpi_video_bqc_value_to_level(struct acpi_video_device *device, ACPI_VIDEO_FIRST_LEVEL - 1 - bqc_value; level = device->brightness->levels[bqc_value + - ACPI_VIDEO_FIRST_LEVEL]; + ACPI_VIDEO_FIRST_LEVEL]; } else { level = bqc_value; } @@ -990,8 +990,8 @@ set_level: goto out_free_levels; ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "found %d brightness levels\n", - br->count - ACPI_VIDEO_FIRST_LEVEL)); + "found %d brightness levels\n", + br->count - ACPI_VIDEO_FIRST_LEVEL)); return 0; out_free_levels: diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c index cab4af532f36..08ee1c7b12e0 100644 --- a/drivers/acpi/battery.c +++ b/drivers/acpi/battery.c @@ -987,7 +987,7 @@ static int acpi_battery_update(struct acpi_battery *battery, bool resume) */ if ((battery->state & ACPI_BATTERY_STATE_CRITICAL) || (test_bit(ACPI_BATTERY_ALARM_PRESENT, &battery->flags) && - (battery->capacity_now <= battery->alarm))) + (battery->capacity_now <= battery->alarm))) acpi_pm_wakeup_event(&battery->device->dev); return result; diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c index 0761529cac05..0d93a5ef4d07 100644 --- a/drivers/acpi/button.c +++ b/drivers/acpi/button.c @@ -89,7 +89,18 @@ static const struct dmi_system_id dmi_lid_quirks[] = { */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "MEDION"), - DMI_MATCH(DMI_PRODUCT_NAME, "E2215T MD60198"), + DMI_MATCH(DMI_PRODUCT_NAME, "E2215T"), + }, + .driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_OPEN, + }, + { + /* + * Medion Akoya E2228T, notification of the LID device only + * happens on close, not on open and _LID always returns closed. + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "MEDION"), + DMI_MATCH(DMI_PRODUCT_NAME, "E2228T"), }, .driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_OPEN, }, diff --git a/drivers/acpi/dptf/dptf_pch_fivr.c b/drivers/acpi/dptf/dptf_pch_fivr.c index 4c1992fce150..5fca18296bf6 100644 --- a/drivers/acpi/dptf/dptf_pch_fivr.c +++ b/drivers/acpi/dptf/dptf_pch_fivr.c @@ -106,6 +106,7 @@ static int pch_fivr_remove(struct platform_device *pdev) static const struct acpi_device_id pch_fivr_device_ids[] = { {"INTC1045", 0}, + {"INTC1049", 0}, {"", 0}, }; MODULE_DEVICE_TABLE(acpi, pch_fivr_device_ids); diff --git a/drivers/acpi/dptf/dptf_power.c b/drivers/acpi/dptf/dptf_power.c index 06741305fc77..a24d5d7aa117 100644 --- a/drivers/acpi/dptf/dptf_power.c +++ b/drivers/acpi/dptf/dptf_power.c @@ -229,6 +229,8 @@ static const struct acpi_device_id int3407_device_ids[] = { {"INT3532", 0}, {"INTC1047", 0}, {"INTC1050", 0}, + {"INTC1060", 0}, + {"INTC1061", 0}, {"", 0}, }; MODULE_DEVICE_TABLE(acpi, int3407_device_ids); diff --git a/drivers/acpi/dptf/int340x_thermal.c b/drivers/acpi/dptf/int340x_thermal.c index 8d420c7e7178..d14025a85ce8 100644 --- a/drivers/acpi/dptf/int340x_thermal.c +++ b/drivers/acpi/dptf/int340x_thermal.c @@ -25,10 +25,16 @@ static const struct acpi_device_id int340x_thermal_device_ids[] = { {"INT340A"}, {"INT340B"}, {"INTC1040"}, + {"INTC1041"}, {"INTC1043"}, {"INTC1044"}, {"INTC1045"}, + {"INTC1046"}, {"INTC1047"}, + {"INTC1048"}, + {"INTC1049"}, + {"INTC1060"}, + {"INTC1061"}, {""}, }; diff --git a/drivers/acpi/event.c b/drivers/acpi/event.c index 170643927044..92e59f45329b 100644 --- a/drivers/acpi/event.c +++ b/drivers/acpi/event.c @@ -31,7 +31,7 @@ int acpi_notifier_call_chain(struct acpi_device *dev, u32 type, u32 data) event.type = type; event.data = data; return (blocking_notifier_call_chain(&acpi_chain_head, 0, (void *)&event) - == NOTIFY_BAD) ? -EINVAL : 0; + == NOTIFY_BAD) ? -EINVAL : 0; } EXPORT_SYMBOL(acpi_notifier_call_chain); diff --git a/drivers/acpi/evged.c b/drivers/acpi/evged.c index b1a7f8d6965e..fe6b6792c8bb 100644 --- a/drivers/acpi/evged.c +++ b/drivers/acpi/evged.c @@ -101,7 +101,7 @@ static acpi_status acpi_ged_request_interrupt(struct acpi_resource *ares, switch (gsi) { case 0 ... 255: - sprintf(ev_name, "_%c%02hhX", + sprintf(ev_name, "_%c%02X", trigger == ACPI_EDGE_SENSITIVE ? 'E' : 'L', gsi); if (ACPI_SUCCESS(acpi_get_handle(handle, ev_name, &evt_handle))) diff --git a/drivers/acpi/fan.c b/drivers/acpi/fan.c index 62873388b24f..48354f82fba6 100644 --- a/drivers/acpi/fan.c +++ b/drivers/acpi/fan.c @@ -27,6 +27,7 @@ static const struct acpi_device_id fan_device_ids[] = { {"PNP0C0B", 0}, {"INT3404", 0}, {"INTC1044", 0}, + {"INTC1048", 0}, {"", 0}, }; MODULE_DEVICE_TABLE(acpi, fan_device_ids); diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h index 43411a7457cd..e3638bafb941 100644 --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -134,7 +134,7 @@ int acpi_add_power_resource(acpi_handle handle); void acpi_power_add_remove_device(struct acpi_device *adev, bool add); int acpi_power_wakeup_list_init(struct list_head *list, int *system_level); int acpi_device_sleep_wake(struct acpi_device *dev, - int enable, int sleep_state, int dev_state); + int enable, int sleep_state, int dev_state); int acpi_power_get_inferred_state(struct acpi_device *device, int *state); int acpi_power_on_resources(struct acpi_device *device, int state); int acpi_power_transition(struct acpi_device *device, int state); diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 3a3c209ed3d3..442608220b5c 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -2175,10 +2175,10 @@ static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc) * these commands. */ enum nfit_aux_cmds { - NFIT_CMD_TRANSLATE_SPA = 5, - NFIT_CMD_ARS_INJECT_SET = 7, - NFIT_CMD_ARS_INJECT_CLEAR = 8, - NFIT_CMD_ARS_INJECT_GET = 9, + NFIT_CMD_TRANSLATE_SPA = 5, + NFIT_CMD_ARS_INJECT_SET = 7, + NFIT_CMD_ARS_INJECT_CLEAR = 8, + NFIT_CMD_ARS_INJECT_GET = 9, }; static void acpi_nfit_init_dsms(struct acpi_nfit_desc *acpi_desc) @@ -2632,7 +2632,7 @@ static int acpi_nfit_blk_region_enable(struct nvdimm_bus *nvdimm_bus, nfit_blk->bdw_offset = nfit_mem->bdw->offset; mmio = &nfit_blk->mmio[BDW]; mmio->addr.base = devm_nvdimm_memremap(dev, nfit_mem->spa_bdw->address, - nfit_mem->spa_bdw->length, nd_blk_memremap_flags(ndbr)); + nfit_mem->spa_bdw->length, nd_blk_memremap_flags(ndbr)); if (!mmio->addr.base) { dev_dbg(dev, "%s failed to map bdw\n", nvdimm_name(nvdimm)); diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c index dea8a60e18a4..14ee631cb7cf 100644 --- a/drivers/acpi/pci_irq.c +++ b/drivers/acpi/pci_irq.c @@ -175,7 +175,7 @@ static int acpi_pci_irq_check_entry(acpi_handle handle, struct pci_dev *dev, * configure the IRQ assigned to this slot|dev|pin. The 'source_index' * indicates which resource descriptor in the resource template (of * the link device) this interrupt is allocated from. - * + * * NOTE: Don't query the Link Device for IRQ information at this time * because Link Device enumeration may not have occurred yet * (e.g. exists somewhere 'below' this _PRT entry in the ACPI diff --git a/drivers/acpi/pci_link.c b/drivers/acpi/pci_link.c index 606da5d77ad3..fb4c5632a232 100644 --- a/drivers/acpi/pci_link.c +++ b/drivers/acpi/pci_link.c @@ -6,8 +6,8 @@ * Copyright (C) 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com> * Copyright (C) 2002 Dominik Brodowski <devel@brodo.de> * - * TBD: - * 1. Support more than one IRQ resource entry per link device (index). + * TBD: + * 1. Support more than one IRQ resource entry per link device (index). * 2. Implement start/stop mechanism and use ACPI Bus Driver facilities * for IRQ management (e.g. start()->_SRS). */ @@ -249,8 +249,8 @@ static int acpi_pci_link_get_current(struct acpi_pci_link *link) } } - /* - * Query and parse _CRS to get the current IRQ assignment. + /* + * Query and parse _CRS to get the current IRQ assignment. */ status = acpi_walk_resources(link->device->handle, METHOD_NAME__CRS, @@ -396,7 +396,7 @@ static int acpi_pci_link_set(struct acpi_pci_link *link, int irq) /* * "acpi_irq_balance" (default in APIC mode) enables ACPI to use PIC Interrupt * Link Devices to move the PIRQs around to minimize sharing. - * + * * "acpi_irq_nobalance" (default in PIC mode) tells ACPI not to move any PIC IRQs * that the BIOS has already set to active. This is necessary because * ACPI has no automatic means of knowing what ISA IRQs are used. Note that @@ -414,7 +414,7 @@ static int acpi_pci_link_set(struct acpi_pci_link *link, int irq) * * Note that PCI IRQ routers have a list of possible IRQs, * which may not include the IRQs this table says are available. - * + * * Since this heuristic can't tell the difference between a link * that no device will attach to, vs. a link which may be shared * by multiple active devices -- it is not optimal. diff --git a/drivers/acpi/pci_mcfg.c b/drivers/acpi/pci_mcfg.c index 7ddd57abadd1..95f23acd5b80 100644 --- a/drivers/acpi/pci_mcfg.c +++ b/drivers/acpi/pci_mcfg.c @@ -173,7 +173,7 @@ static int pci_mcfg_quirk_matches(struct mcfg_fixup *f, u16 segment, { if (!memcmp(f->oem_id, mcfg_oem_id, ACPI_OEM_ID_SIZE) && !memcmp(f->oem_table_id, mcfg_oem_table_id, - ACPI_OEM_TABLE_ID_SIZE) && + ACPI_OEM_TABLE_ID_SIZE) && f->oem_revision == mcfg_oem_revision && f->segment == segment && resource_contains(&f->bus_range, bus_range)) diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c index 837b875d075e..8048da85b7e0 100644 --- a/drivers/acpi/power.c +++ b/drivers/acpi/power.c @@ -13,7 +13,7 @@ * 1. via "Device Specific (D-State) Control" * 2. via "Power Resource Control". * The code below deals with ACPI Power Resources control. - * + * * An ACPI "power resource object" represents a software controllable power * plane, clock plane, or other resource depended on by a device. * @@ -645,7 +645,7 @@ int acpi_power_wakeup_list_init(struct list_head *list, int *system_level_p) * -ENODEV if the execution of either _DSW or _PSW has failed */ int acpi_device_sleep_wake(struct acpi_device *dev, - int enable, int sleep_state, int dev_state) + int enable, int sleep_state, int dev_state) { union acpi_object in_arg[3]; struct acpi_object_list arg_list = { 3, in_arg }; @@ -690,7 +690,7 @@ int acpi_device_sleep_wake(struct acpi_device *dev, /* * Prepare a wakeup device, two steps (Ref ACPI 2.0:P229): - * 1. Power on the power resources required for the wakeup device + * 1. Power on the power resources required for the wakeup device * 2. Execute _DSW (Device Sleep Wake) or (deprecated in ACPI 3.0) _PSW (Power * State Wake) for the device, if present */ diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c index 5909e8fa4013..b04a68950ff1 100644 --- a/drivers/acpi/processor_perflib.c +++ b/drivers/acpi/processor_perflib.c @@ -354,7 +354,7 @@ static int acpi_processor_get_performance_states(struct acpi_processor *pr) (u32) px->control, (u32) px->status)); /* - * Check that ACPI's u64 MHz will be valid as u32 KHz in cpufreq + * Check that ACPI's u64 MHz will be valid as u32 KHz in cpufreq */ if (!px->core_frequency || ((u32)(px->core_frequency * 1000) != @@ -627,7 +627,7 @@ int acpi_processor_preregister_performance( goto err_ret; /* - * Now that we have _PSD data from all CPUs, lets setup P-state + * Now that we have _PSD data from all CPUs, lets setup P-state * domain info. */ for_each_possible_cpu(i) { @@ -693,7 +693,7 @@ int acpi_processor_preregister_performance( if (match_pdomain->domain != pdomain->domain) continue; - match_pr->performance->shared_type = + match_pr->performance->shared_type = pr->performance->shared_type; cpumask_copy(match_pr->performance->shared_cpu_map, pr->performance->shared_cpu_map); diff --git a/drivers/acpi/sbs.c b/drivers/acpi/sbs.c index f158b8c30113..e6d9f4de2800 100644 --- a/drivers/acpi/sbs.c +++ b/drivers/acpi/sbs.c @@ -366,7 +366,7 @@ static int acpi_battery_get_state(struct acpi_battery *battery) state_readers[i].mode, ACPI_SBS_BATTERY, state_readers[i].command, - (u8 *)battery + + (u8 *)battery + state_readers[i].offset); if (result) goto end; diff --git a/drivers/acpi/sbshc.c b/drivers/acpi/sbshc.c index 87b74e9015e5..53c2862c4c75 100644 --- a/drivers/acpi/sbshc.c +++ b/drivers/acpi/sbshc.c @@ -176,7 +176,7 @@ int acpi_smbus_write(struct acpi_smb_hc *hc, u8 protocol, u8 address, EXPORT_SYMBOL_GPL(acpi_smbus_write); int acpi_smbus_register_callback(struct acpi_smb_hc *hc, - smbus_alarm_callback callback, void *context) + smbus_alarm_callback callback, void *context) { mutex_lock(&hc->lock); hc->callback = callback; diff --git a/drivers/acpi/sbshc.h b/drivers/acpi/sbshc.h index c3522bb82792..695c390e2884 100644 --- a/drivers/acpi/sbshc.h +++ b/drivers/acpi/sbshc.h @@ -24,9 +24,9 @@ enum acpi_sbs_device_addr { typedef void (*smbus_alarm_callback)(void *context); extern int acpi_smbus_read(struct acpi_smb_hc *hc, u8 protocol, u8 address, - u8 command, u8 * data); + u8 command, u8 *data); extern int acpi_smbus_write(struct acpi_smb_hc *hc, u8 protocol, u8 slave_address, - u8 command, u8 * data, u8 length); + u8 command, u8 *data, u8 length); extern int acpi_smbus_register_callback(struct acpi_smb_hc *hc, - smbus_alarm_callback callback, void *context); + smbus_alarm_callback callback, void *context); extern int acpi_smbus_unregister_callback(struct acpi_smb_hc *hc); diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index a896e5e87c93..bc6a79e33220 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -1453,7 +1453,7 @@ int acpi_dma_get_range(struct device *dev, u64 *dma_addr, u64 *offset, } /** - * acpi_dma_configure - Set-up DMA configuration for the device. + * acpi_dma_configure_id - Set-up DMA configuration for the device. * @dev: The pointer to the device * @attr: device dma attributes * @input_id: input device id const value pointer diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index 3a032afd9d05..4f5463b2a217 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -178,14 +178,14 @@ static const struct dmi_system_id video_detect_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X201s"), }, }, - { - .callback = video_detect_force_video, - .ident = "ThinkPad X201T", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X201T"), - }, - }, + { + .callback = video_detect_force_video, + .ident = "ThinkPad X201T", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X201T"), + }, + }, /* The native backlight controls do not work on some older machines */ { diff --git a/drivers/acpi/wakeup.c b/drivers/acpi/wakeup.c index f89dd9a99e6e..b02bf770aead 100644 --- a/drivers/acpi/wakeup.c +++ b/drivers/acpi/wakeup.c @@ -44,7 +44,7 @@ void acpi_enable_wakeup_devices(u8 sleep_state) if (!dev->wakeup.flags.valid || sleep_state > (u32) dev->wakeup.sleep_state || !(device_may_wakeup(&dev->dev) - || dev->wakeup.prepare_count)) + || dev->wakeup.prepare_count)) continue; if (device_may_wakeup(&dev->dev)) @@ -69,7 +69,7 @@ void acpi_disable_wakeup_devices(u8 sleep_state) if (!dev->wakeup.flags.valid || sleep_state > (u32) dev->wakeup.sleep_state || !(device_may_wakeup(&dev->dev) - || dev->wakeup.prepare_count)) + || dev->wakeup.prepare_count)) continue; acpi_set_gpe_wake_mask(dev->wakeup.gpe_device, dev->wakeup.gpe_number, diff --git a/drivers/block/loop.c b/drivers/block/loop.c index cb1191d6e945..a58084c2ed7c 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -255,7 +255,8 @@ static void loop_set_size(struct loop_device *lo, loff_t size) bd_set_nr_sectors(bdev, size); - set_capacity_revalidate_and_notify(lo->lo_disk, size, false); + if (!set_capacity_revalidate_and_notify(lo->lo_disk, size, false)) + kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE); } static inline int diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index c4f9ccf5cc2a..aaae9220f3a0 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1518,6 +1518,7 @@ static void nbd_release(struct gendisk *disk, fmode_t mode) if (test_bit(NBD_RT_DISCONNECT_ON_CLOSE, &nbd->config->runtime_flags) && bdev->bd_openers == 0) nbd_disconnect_and_put(nbd); + bdput(bdev); nbd_config_put(nbd); nbd_put(nbd); diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index a2da8f768b94..1836cc56e357 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -435,12 +435,12 @@ static struct port_buffer *alloc_buf(struct virtio_device *vdev, size_t buf_size /* * Allocate DMA memory from ancestor. When a virtio * device is created by remoteproc, the DMA memory is - * associated with the grandparent device: - * vdev => rproc => platform-dev. + * associated with the parent device: + * virtioY => remoteprocX#vdevYbuffer. */ - if (!vdev->dev.parent || !vdev->dev.parent->parent) + buf->dev = vdev->dev.parent; + if (!buf->dev) goto free_buf; - buf->dev = vdev->dev.parent->parent; /* Increase device refcnt to avoid freeing it */ get_device(buf->dev); diff --git a/drivers/clk/imx/clk-imx8mm.c b/drivers/clk/imx/clk-imx8mm.c index 0de0be0cf548..f358ad907299 100644 --- a/drivers/clk/imx/clk-imx8mm.c +++ b/drivers/clk/imx/clk-imx8mm.c @@ -443,9 +443,9 @@ static int imx8mm_clocks_probe(struct platform_device *pdev) hws[IMX8MM_CLK_A53_CORE] = imx_clk_hw_mux2("arm_a53_core", base + 0x9880, 24, 1, imx8mm_a53_core_sels, ARRAY_SIZE(imx8mm_a53_core_sels)); /* BUS */ - hws[IMX8MM_CLK_MAIN_AXI] = imx8m_clk_hw_composite_critical("main_axi", imx8mm_main_axi_sels, base + 0x8800); + hws[IMX8MM_CLK_MAIN_AXI] = imx8m_clk_hw_composite_bus_critical("main_axi", imx8mm_main_axi_sels, base + 0x8800); hws[IMX8MM_CLK_ENET_AXI] = imx8m_clk_hw_composite_bus("enet_axi", imx8mm_enet_axi_sels, base + 0x8880); - hws[IMX8MM_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_critical("nand_usdhc_bus", imx8mm_nand_usdhc_sels, base + 0x8900); + hws[IMX8MM_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_bus_critical("nand_usdhc_bus", imx8mm_nand_usdhc_sels, base + 0x8900); hws[IMX8MM_CLK_VPU_BUS] = imx8m_clk_hw_composite_bus("vpu_bus", imx8mm_vpu_bus_sels, base + 0x8980); hws[IMX8MM_CLK_DISP_AXI] = imx8m_clk_hw_composite_bus("disp_axi", imx8mm_disp_axi_sels, base + 0x8a00); hws[IMX8MM_CLK_DISP_APB] = imx8m_clk_hw_composite_bus("disp_apb", imx8mm_disp_apb_sels, base + 0x8a80); @@ -453,11 +453,11 @@ static int imx8mm_clocks_probe(struct platform_device *pdev) hws[IMX8MM_CLK_USB_BUS] = imx8m_clk_hw_composite_bus("usb_bus", imx8mm_usb_bus_sels, base + 0x8b80); hws[IMX8MM_CLK_GPU_AXI] = imx8m_clk_hw_composite_bus("gpu_axi", imx8mm_gpu_axi_sels, base + 0x8c00); hws[IMX8MM_CLK_GPU_AHB] = imx8m_clk_hw_composite_bus("gpu_ahb", imx8mm_gpu_ahb_sels, base + 0x8c80); - hws[IMX8MM_CLK_NOC] = imx8m_clk_hw_composite_critical("noc", imx8mm_noc_sels, base + 0x8d00); - hws[IMX8MM_CLK_NOC_APB] = imx8m_clk_hw_composite_critical("noc_apb", imx8mm_noc_apb_sels, base + 0x8d80); + hws[IMX8MM_CLK_NOC] = imx8m_clk_hw_composite_bus_critical("noc", imx8mm_noc_sels, base + 0x8d00); + hws[IMX8MM_CLK_NOC_APB] = imx8m_clk_hw_composite_bus_critical("noc_apb", imx8mm_noc_apb_sels, base + 0x8d80); /* AHB */ - hws[IMX8MM_CLK_AHB] = imx8m_clk_hw_composite_critical("ahb", imx8mm_ahb_sels, base + 0x9000); + hws[IMX8MM_CLK_AHB] = imx8m_clk_hw_composite_bus_critical("ahb", imx8mm_ahb_sels, base + 0x9000); hws[IMX8MM_CLK_AUDIO_AHB] = imx8m_clk_hw_composite_bus("audio_ahb", imx8mm_audio_ahb_sels, base + 0x9100); /* IPG */ diff --git a/drivers/clk/imx/clk-imx8mn.c b/drivers/clk/imx/clk-imx8mn.c index e984de543f0b..f3c5e6cf55dd 100644 --- a/drivers/clk/imx/clk-imx8mn.c +++ b/drivers/clk/imx/clk-imx8mn.c @@ -431,7 +431,7 @@ static int imx8mn_clocks_probe(struct platform_device *pdev) hws[IMX8MN_CLK_A53_CORE] = imx_clk_hw_mux2("arm_a53_core", base + 0x9880, 24, 1, imx8mn_a53_core_sels, ARRAY_SIZE(imx8mn_a53_core_sels)); /* BUS */ - hws[IMX8MN_CLK_MAIN_AXI] = imx8m_clk_hw_composite_critical("main_axi", imx8mn_main_axi_sels, base + 0x8800); + hws[IMX8MN_CLK_MAIN_AXI] = imx8m_clk_hw_composite_bus_critical("main_axi", imx8mn_main_axi_sels, base + 0x8800); hws[IMX8MN_CLK_ENET_AXI] = imx8m_clk_hw_composite_bus("enet_axi", imx8mn_enet_axi_sels, base + 0x8880); hws[IMX8MN_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_bus("nand_usdhc_bus", imx8mn_nand_usdhc_sels, base + 0x8900); hws[IMX8MN_CLK_DISP_AXI] = imx8m_clk_hw_composite_bus("disp_axi", imx8mn_disp_axi_sels, base + 0x8a00); @@ -439,9 +439,9 @@ static int imx8mn_clocks_probe(struct platform_device *pdev) hws[IMX8MN_CLK_USB_BUS] = imx8m_clk_hw_composite_bus("usb_bus", imx8mn_usb_bus_sels, base + 0x8b80); hws[IMX8MN_CLK_GPU_AXI] = imx8m_clk_hw_composite_bus("gpu_axi", imx8mn_gpu_axi_sels, base + 0x8c00); hws[IMX8MN_CLK_GPU_AHB] = imx8m_clk_hw_composite_bus("gpu_ahb", imx8mn_gpu_ahb_sels, base + 0x8c80); - hws[IMX8MN_CLK_NOC] = imx8m_clk_hw_composite_critical("noc", imx8mn_noc_sels, base + 0x8d00); + hws[IMX8MN_CLK_NOC] = imx8m_clk_hw_composite_bus_critical("noc", imx8mn_noc_sels, base + 0x8d00); - hws[IMX8MN_CLK_AHB] = imx8m_clk_hw_composite_critical("ahb", imx8mn_ahb_sels, base + 0x9000); + hws[IMX8MN_CLK_AHB] = imx8m_clk_hw_composite_bus_critical("ahb", imx8mn_ahb_sels, base + 0x9000); hws[IMX8MN_CLK_AUDIO_AHB] = imx8m_clk_hw_composite_bus("audio_ahb", imx8mn_audio_ahb_sels, base + 0x9100); hws[IMX8MN_CLK_IPG_ROOT] = imx_clk_hw_divider2("ipg_root", "ahb", base + 0x9080, 0, 1); hws[IMX8MN_CLK_IPG_AUDIO_ROOT] = imx_clk_hw_divider2("ipg_audio_root", "audio_ahb", base + 0x9180, 0, 1); diff --git a/drivers/clk/imx/clk-imx8mp.c b/drivers/clk/imx/clk-imx8mp.c index 12ce4770f702..48e212477f52 100644 --- a/drivers/clk/imx/clk-imx8mp.c +++ b/drivers/clk/imx/clk-imx8mp.c @@ -557,9 +557,9 @@ static int imx8mp_clocks_probe(struct platform_device *pdev) /* CORE SEL */ hws[IMX8MP_CLK_A53_CORE] = imx_clk_hw_mux2("arm_a53_core", ccm_base + 0x9880, 24, 1, imx8mp_a53_core_sels, ARRAY_SIZE(imx8mp_a53_core_sels)); - hws[IMX8MP_CLK_MAIN_AXI] = imx8m_clk_hw_composite_critical("main_axi", imx8mp_main_axi_sels, ccm_base + 0x8800); + hws[IMX8MP_CLK_MAIN_AXI] = imx8m_clk_hw_composite_bus_critical("main_axi", imx8mp_main_axi_sels, ccm_base + 0x8800); hws[IMX8MP_CLK_ENET_AXI] = imx8m_clk_hw_composite_bus("enet_axi", imx8mp_enet_axi_sels, ccm_base + 0x8880); - hws[IMX8MP_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_critical("nand_usdhc_bus", imx8mp_nand_usdhc_sels, ccm_base + 0x8900); + hws[IMX8MP_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_bus_critical("nand_usdhc_bus", imx8mp_nand_usdhc_sels, ccm_base + 0x8900); hws[IMX8MP_CLK_VPU_BUS] = imx8m_clk_hw_composite_bus("vpu_bus", imx8mp_vpu_bus_sels, ccm_base + 0x8980); hws[IMX8MP_CLK_MEDIA_AXI] = imx8m_clk_hw_composite_bus("media_axi", imx8mp_media_axi_sels, ccm_base + 0x8a00); hws[IMX8MP_CLK_MEDIA_APB] = imx8m_clk_hw_composite_bus("media_apb", imx8mp_media_apb_sels, ccm_base + 0x8a80); @@ -567,12 +567,12 @@ static int imx8mp_clocks_probe(struct platform_device *pdev) hws[IMX8MP_CLK_HDMI_AXI] = imx8m_clk_hw_composite_bus("hdmi_axi", imx8mp_media_axi_sels, ccm_base + 0x8b80); hws[IMX8MP_CLK_GPU_AXI] = imx8m_clk_hw_composite_bus("gpu_axi", imx8mp_gpu_axi_sels, ccm_base + 0x8c00); hws[IMX8MP_CLK_GPU_AHB] = imx8m_clk_hw_composite_bus("gpu_ahb", imx8mp_gpu_ahb_sels, ccm_base + 0x8c80); - hws[IMX8MP_CLK_NOC] = imx8m_clk_hw_composite_critical("noc", imx8mp_noc_sels, ccm_base + 0x8d00); - hws[IMX8MP_CLK_NOC_IO] = imx8m_clk_hw_composite_critical("noc_io", imx8mp_noc_io_sels, ccm_base + 0x8d80); + hws[IMX8MP_CLK_NOC] = imx8m_clk_hw_composite_bus_critical("noc", imx8mp_noc_sels, ccm_base + 0x8d00); + hws[IMX8MP_CLK_NOC_IO] = imx8m_clk_hw_composite_bus_critical("noc_io", imx8mp_noc_io_sels, ccm_base + 0x8d80); hws[IMX8MP_CLK_ML_AXI] = imx8m_clk_hw_composite_bus("ml_axi", imx8mp_ml_axi_sels, ccm_base + 0x8e00); hws[IMX8MP_CLK_ML_AHB] = imx8m_clk_hw_composite_bus("ml_ahb", imx8mp_ml_ahb_sels, ccm_base + 0x8e80); - hws[IMX8MP_CLK_AHB] = imx8m_clk_hw_composite_critical("ahb_root", imx8mp_ahb_sels, ccm_base + 0x9000); + hws[IMX8MP_CLK_AHB] = imx8m_clk_hw_composite_bus_critical("ahb_root", imx8mp_ahb_sels, ccm_base + 0x9000); hws[IMX8MP_CLK_AUDIO_AHB] = imx8m_clk_hw_composite_bus("audio_ahb", imx8mp_audio_ahb_sels, ccm_base + 0x9100); hws[IMX8MP_CLK_MIPI_DSI_ESC_RX] = imx8m_clk_hw_composite_bus("mipi_dsi_esc_rx", imx8mp_mipi_dsi_esc_rx_sels, ccm_base + 0x9200); diff --git a/drivers/clk/imx/clk-imx8mq.c b/drivers/clk/imx/clk-imx8mq.c index 8265d1d48af4..06292d4a98ff 100644 --- a/drivers/clk/imx/clk-imx8mq.c +++ b/drivers/clk/imx/clk-imx8mq.c @@ -431,7 +431,7 @@ static int imx8mq_clocks_probe(struct platform_device *pdev) hws[IMX8MQ_CLK_A53_CORE] = imx_clk_hw_mux2("arm_a53_core", base + 0x9880, 24, 1, imx8mq_a53_core_sels, ARRAY_SIZE(imx8mq_a53_core_sels)); /* BUS */ - hws[IMX8MQ_CLK_MAIN_AXI] = imx8m_clk_hw_composite_critical("main_axi", imx8mq_main_axi_sels, base + 0x8800); + hws[IMX8MQ_CLK_MAIN_AXI] = imx8m_clk_hw_composite_bus_critical("main_axi", imx8mq_main_axi_sels, base + 0x8800); hws[IMX8MQ_CLK_ENET_AXI] = imx8m_clk_hw_composite_bus("enet_axi", imx8mq_enet_axi_sels, base + 0x8880); hws[IMX8MQ_CLK_NAND_USDHC_BUS] = imx8m_clk_hw_composite_bus("nand_usdhc_bus", imx8mq_nand_usdhc_sels, base + 0x8900); hws[IMX8MQ_CLK_VPU_BUS] = imx8m_clk_hw_composite_bus("vpu_bus", imx8mq_vpu_bus_sels, base + 0x8980); @@ -441,12 +441,12 @@ static int imx8mq_clocks_probe(struct platform_device *pdev) hws[IMX8MQ_CLK_USB_BUS] = imx8m_clk_hw_composite_bus("usb_bus", imx8mq_usb_bus_sels, base + 0x8b80); hws[IMX8MQ_CLK_GPU_AXI] = imx8m_clk_hw_composite_bus("gpu_axi", imx8mq_gpu_axi_sels, base + 0x8c00); hws[IMX8MQ_CLK_GPU_AHB] = imx8m_clk_hw_composite_bus("gpu_ahb", imx8mq_gpu_ahb_sels, base + 0x8c80); - hws[IMX8MQ_CLK_NOC] = imx8m_clk_hw_composite_critical("noc", imx8mq_noc_sels, base + 0x8d00); - hws[IMX8MQ_CLK_NOC_APB] = imx8m_clk_hw_composite_critical("noc_apb", imx8mq_noc_apb_sels, base + 0x8d80); + hws[IMX8MQ_CLK_NOC] = imx8m_clk_hw_composite_bus_critical("noc", imx8mq_noc_sels, base + 0x8d00); + hws[IMX8MQ_CLK_NOC_APB] = imx8m_clk_hw_composite_bus_critical("noc_apb", imx8mq_noc_apb_sels, base + 0x8d80); /* AHB */ /* AHB clock is used by the AHB bus therefore marked as critical */ - hws[IMX8MQ_CLK_AHB] = imx8m_clk_hw_composite_critical("ahb", imx8mq_ahb_sels, base + 0x9000); + hws[IMX8MQ_CLK_AHB] = imx8m_clk_hw_composite_bus_critical("ahb", imx8mq_ahb_sels, base + 0x9000); hws[IMX8MQ_CLK_AUDIO_AHB] = imx8m_clk_hw_composite_bus("audio_ahb", imx8mq_audio_ahb_sels, base + 0x9100); /* IPG */ diff --git a/drivers/clk/imx/clk.h b/drivers/clk/imx/clk.h index 3b796b3da249..1d7be0c86538 100644 --- a/drivers/clk/imx/clk.h +++ b/drivers/clk/imx/clk.h @@ -549,6 +549,11 @@ struct clk_hw *imx8m_clk_hw_composite_flags(const char *name, IMX_COMPOSITE_BUS, \ CLK_SET_RATE_NO_REPARENT | CLK_OPS_PARENT_ENABLE) +#define imx8m_clk_hw_composite_bus_critical(name, parent_names, reg) \ + imx8m_clk_hw_composite_flags(name, parent_names, ARRAY_SIZE(parent_names), reg, \ + IMX_COMPOSITE_BUS, \ + CLK_SET_RATE_NO_REPARENT | CLK_OPS_PARENT_ENABLE | CLK_IS_CRITICAL) + #define imx8m_clk_hw_composite_core(name, parent_names, reg) \ imx8m_clk_hw_composite_flags(name, parent_names, \ ARRAY_SIZE(parent_names), reg, \ diff --git a/drivers/clk/meson/clk-regmap.h b/drivers/clk/meson/clk-regmap.h index c4a39604cffd..e365312da54e 100644 --- a/drivers/clk/meson/clk-regmap.h +++ b/drivers/clk/meson/clk-regmap.h @@ -26,7 +26,10 @@ struct clk_regmap { void *data; }; -#define to_clk_regmap(_hw) container_of(_hw, struct clk_regmap, hw) +static inline struct clk_regmap *to_clk_regmap(struct clk_hw *hw) +{ + return container_of(hw, struct clk_regmap, hw); +} /** * struct clk_regmap_gate_data - regmap backed gate specific data diff --git a/drivers/clk/qcom/clk-regmap.h b/drivers/clk/qcom/clk-regmap.h index 6cfc1bccb255..14ec659a3a77 100644 --- a/drivers/clk/qcom/clk-regmap.h +++ b/drivers/clk/qcom/clk-regmap.h @@ -24,7 +24,11 @@ struct clk_regmap { unsigned int enable_mask; bool enable_is_inverted; }; -#define to_clk_regmap(_hw) container_of(_hw, struct clk_regmap, hw) + +static inline struct clk_regmap *to_clk_regmap(struct clk_hw *hw) +{ + return container_of(hw, struct clk_regmap, hw); +} int clk_is_enabled_regmap(struct clk_hw *hw); int clk_enable_regmap(struct clk_hw *hw); diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 336b5e94cbc8..1e7e3f2ff09f 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -2254,7 +2254,7 @@ static int cpufreq_init_governor(struct cpufreq_policy *policy) return -EINVAL; /* Platform doesn't want dynamic frequency switching ? */ - if (policy->governor->dynamic_switching && + if (policy->governor->flags & CPUFREQ_GOV_DYNAMIC_SWITCHING && cpufreq_driver->flags & CPUFREQ_NO_AUTO_DYNAMIC_SWITCHING) { struct cpufreq_governor *gov = cpufreq_fallback_governor(); @@ -2280,6 +2280,8 @@ static int cpufreq_init_governor(struct cpufreq_policy *policy) } } + policy->strict_target = !!(policy->governor->flags & CPUFREQ_GOV_STRICT_TARGET); + return 0; } diff --git a/drivers/cpufreq/cpufreq_governor.h b/drivers/cpufreq/cpufreq_governor.h index c56773c25757..bab8e6140377 100644 --- a/drivers/cpufreq/cpufreq_governor.h +++ b/drivers/cpufreq/cpufreq_governor.h @@ -156,7 +156,7 @@ void cpufreq_dbs_governor_limits(struct cpufreq_policy *policy); #define CPUFREQ_DBS_GOVERNOR_INITIALIZER(_name_) \ { \ .name = _name_, \ - .dynamic_switching = true, \ + .flags = CPUFREQ_GOV_DYNAMIC_SWITCHING, \ .owner = THIS_MODULE, \ .init = cpufreq_dbs_governor_init, \ .exit = cpufreq_dbs_governor_exit, \ diff --git a/drivers/cpufreq/cpufreq_performance.c b/drivers/cpufreq/cpufreq_performance.c index 71c1d9aba772..addd93f2a420 100644 --- a/drivers/cpufreq/cpufreq_performance.c +++ b/drivers/cpufreq/cpufreq_performance.c @@ -20,6 +20,7 @@ static void cpufreq_gov_performance_limits(struct cpufreq_policy *policy) static struct cpufreq_governor cpufreq_gov_performance = { .name = "performance", .owner = THIS_MODULE, + .flags = CPUFREQ_GOV_STRICT_TARGET, .limits = cpufreq_gov_performance_limits, }; diff --git a/drivers/cpufreq/cpufreq_powersave.c b/drivers/cpufreq/cpufreq_powersave.c index 7749522355b5..8d830d860e91 100644 --- a/drivers/cpufreq/cpufreq_powersave.c +++ b/drivers/cpufreq/cpufreq_powersave.c @@ -21,6 +21,7 @@ static struct cpufreq_governor cpufreq_gov_powersave = { .name = "powersave", .limits = cpufreq_gov_powersave_limits, .owner = THIS_MODULE, + .flags = CPUFREQ_GOV_STRICT_TARGET, }; MODULE_AUTHOR("Dominik Brodowski <linux@brodo.de>"); diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index b7a9779250aa..36a3ccfe6d3d 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -2527,7 +2527,7 @@ static void intel_cpufreq_trace(struct cpudata *cpu, unsigned int trace_type, in } static void intel_cpufreq_adjust_hwp(struct cpudata *cpu, u32 target_pstate, - bool fast_switch) + bool strict, bool fast_switch) { u64 prev = READ_ONCE(cpu->hwp_req_cached), value = prev; @@ -2539,7 +2539,7 @@ static void intel_cpufreq_adjust_hwp(struct cpudata *cpu, u32 target_pstate, * field in it, so opportunistically update the max too if needed. */ value &= ~HWP_MAX_PERF(~0L); - value |= HWP_MAX_PERF(cpu->max_perf_ratio); + value |= HWP_MAX_PERF(strict ? target_pstate : cpu->max_perf_ratio); if (value == prev) return; @@ -2562,14 +2562,16 @@ static void intel_cpufreq_adjust_perf_ctl(struct cpudata *cpu, pstate_funcs.get_val(cpu, target_pstate)); } -static int intel_cpufreq_update_pstate(struct cpudata *cpu, int target_pstate, - bool fast_switch) +static int intel_cpufreq_update_pstate(struct cpufreq_policy *policy, + int target_pstate, bool fast_switch) { + struct cpudata *cpu = all_cpu_data[policy->cpu]; int old_pstate = cpu->pstate.current_pstate; target_pstate = intel_pstate_prepare_request(cpu, target_pstate); if (hwp_active) { - intel_cpufreq_adjust_hwp(cpu, target_pstate, fast_switch); + intel_cpufreq_adjust_hwp(cpu, target_pstate, + policy->strict_target, fast_switch); cpu->pstate.current_pstate = target_pstate; } else if (target_pstate != old_pstate) { intel_cpufreq_adjust_perf_ctl(cpu, target_pstate, fast_switch); @@ -2609,7 +2611,7 @@ static int intel_cpufreq_target(struct cpufreq_policy *policy, break; } - target_pstate = intel_cpufreq_update_pstate(cpu, target_pstate, false); + target_pstate = intel_cpufreq_update_pstate(policy, target_pstate, false); freqs.new = target_pstate * cpu->pstate.scaling; @@ -2628,7 +2630,7 @@ static unsigned int intel_cpufreq_fast_switch(struct cpufreq_policy *policy, target_pstate = DIV_ROUND_UP(target_freq, cpu->pstate.scaling); - target_pstate = intel_cpufreq_update_pstate(cpu, target_pstate, true); + target_pstate = intel_cpufreq_update_pstate(policy, target_pstate, true); return target_pstate * cpu->pstate.scaling; } diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c index 8d1ff2454e2e..efb8a66efc68 100644 --- a/drivers/firmware/xilinx/zynqmp.c +++ b/drivers/firmware/xilinx/zynqmp.c @@ -147,6 +147,9 @@ static int zynqmp_pm_feature(u32 api_id) return 0; /* Return value if feature is already checked */ + if (api_id > ARRAY_SIZE(zynqmp_pm_features)) + return PM_FEATURE_INVALID; + if (zynqmp_pm_features[api_id] != PM_FEATURE_UNCHECKED) return zynqmp_pm_features[api_id]; diff --git a/drivers/gpio/gpio-aspeed.c b/drivers/gpio/gpio-aspeed.c index e44d5de2a120..b966f5e28ebf 100644 --- a/drivers/gpio/gpio-aspeed.c +++ b/drivers/gpio/gpio-aspeed.c @@ -1114,6 +1114,7 @@ static const struct aspeed_gpio_config ast2500_config = static const struct aspeed_bank_props ast2600_bank_props[] = { /* input output */ + {4, 0xffffffff, 0x00ffffff}, /* Q/R/S/T */ {5, 0xffffffff, 0xffffff00}, /* U/V/W/X */ {6, 0x0000ffff, 0x0000ffff}, /* Y/Z */ { }, diff --git a/drivers/gpio/gpio-dwapb.c b/drivers/gpio/gpio-dwapb.c index a5b326754124..2a9046c0fb16 100644 --- a/drivers/gpio/gpio-dwapb.c +++ b/drivers/gpio/gpio-dwapb.c @@ -343,8 +343,8 @@ static int dwapb_irq_set_type(struct irq_data *d, u32 type) #ifdef CONFIG_PM_SLEEP static int dwapb_irq_set_wake(struct irq_data *d, unsigned int enable) { - struct irq_chip_generic *igc = irq_data_get_irq_chip_data(d); - struct dwapb_gpio *gpio = igc->private; + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct dwapb_gpio *gpio = to_dwapb_gpio(gc); struct dwapb_context *ctx = gpio->ports[0].ctx; irq_hw_number_t bit = irqd_to_hwirq(d); diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c index 6d59e3a43761..f7ceb2b11afc 100644 --- a/drivers/gpio/gpio-omap.c +++ b/drivers/gpio/gpio-omap.c @@ -1114,13 +1114,23 @@ static void omap_gpio_idle(struct gpio_bank *bank, bool may_lose_context) { struct device *dev = bank->chip.parent; void __iomem *base = bank->base; - u32 nowake; + u32 mask, nowake; bank->saved_datain = readl_relaxed(base + bank->regs->datain); if (!bank->enabled_non_wakeup_gpios) goto update_gpio_context_count; + /* Check for pending EDGE_FALLING, ignore EDGE_BOTH */ + mask = bank->enabled_non_wakeup_gpios & bank->context.fallingdetect; + mask &= ~bank->context.risingdetect; + bank->saved_datain |= mask; + + /* Check for pending EDGE_RISING, ignore EDGE_BOTH */ + mask = bank->enabled_non_wakeup_gpios & bank->context.risingdetect; + mask &= ~bank->context.fallingdetect; + bank->saved_datain &= ~mask; + if (!may_lose_context) goto update_gpio_context_count; diff --git a/drivers/gpio/gpio-pcie-idio-24.c b/drivers/gpio/gpio-pcie-idio-24.c index a68941d19ac6..2a07fd96707e 100644 --- a/drivers/gpio/gpio-pcie-idio-24.c +++ b/drivers/gpio/gpio-pcie-idio-24.c @@ -28,6 +28,47 @@ #include <linux/spinlock.h> #include <linux/types.h> +/* + * PLX PEX8311 PCI LCS_INTCSR Interrupt Control/Status + * + * Bit: Description + * 0: Enable Interrupt Sources (Bit 0) + * 1: Enable Interrupt Sources (Bit 1) + * 2: Generate Internal PCI Bus Internal SERR# Interrupt + * 3: Mailbox Interrupt Enable + * 4: Power Management Interrupt Enable + * 5: Power Management Interrupt + * 6: Slave Read Local Data Parity Check Error Enable + * 7: Slave Read Local Data Parity Check Error Status + * 8: Internal PCI Wire Interrupt Enable + * 9: PCI Express Doorbell Interrupt Enable + * 10: PCI Abort Interrupt Enable + * 11: Local Interrupt Input Enable + * 12: Retry Abort Enable + * 13: PCI Express Doorbell Interrupt Active + * 14: PCI Abort Interrupt Active + * 15: Local Interrupt Input Active + * 16: Local Interrupt Output Enable + * 17: Local Doorbell Interrupt Enable + * 18: DMA Channel 0 Interrupt Enable + * 19: DMA Channel 1 Interrupt Enable + * 20: Local Doorbell Interrupt Active + * 21: DMA Channel 0 Interrupt Active + * 22: DMA Channel 1 Interrupt Active + * 23: Built-In Self-Test (BIST) Interrupt Active + * 24: Direct Master was the Bus Master during a Master or Target Abort + * 25: DMA Channel 0 was the Bus Master during a Master or Target Abort + * 26: DMA Channel 1 was the Bus Master during a Master or Target Abort + * 27: Target Abort after internal 256 consecutive Master Retrys + * 28: PCI Bus wrote data to LCS_MBOX0 + * 29: PCI Bus wrote data to LCS_MBOX1 + * 30: PCI Bus wrote data to LCS_MBOX2 + * 31: PCI Bus wrote data to LCS_MBOX3 + */ +#define PLX_PEX8311_PCI_LCS_INTCSR 0x68 +#define INTCSR_INTERNAL_PCI_WIRE BIT(8) +#define INTCSR_LOCAL_INPUT BIT(11) + /** * struct idio_24_gpio_reg - GPIO device registers structure * @out0_7: Read: FET Outputs 0-7 @@ -92,6 +133,7 @@ struct idio_24_gpio_reg { struct idio_24_gpio { struct gpio_chip chip; raw_spinlock_t lock; + __u8 __iomem *plx; struct idio_24_gpio_reg __iomem *reg; unsigned long irq_mask; }; @@ -334,13 +376,13 @@ static void idio_24_irq_mask(struct irq_data *data) unsigned long flags; const unsigned long bit_offset = irqd_to_hwirq(data) - 24; unsigned char new_irq_mask; - const unsigned long bank_offset = bit_offset/8 * 8; + const unsigned long bank_offset = bit_offset / 8; unsigned char cos_enable_state; raw_spin_lock_irqsave(&idio24gpio->lock, flags); - idio24gpio->irq_mask &= BIT(bit_offset); - new_irq_mask = idio24gpio->irq_mask >> bank_offset; + idio24gpio->irq_mask &= ~BIT(bit_offset); + new_irq_mask = idio24gpio->irq_mask >> bank_offset * 8; if (!new_irq_mask) { cos_enable_state = ioread8(&idio24gpio->reg->cos_enable); @@ -363,12 +405,12 @@ static void idio_24_irq_unmask(struct irq_data *data) unsigned long flags; unsigned char prev_irq_mask; const unsigned long bit_offset = irqd_to_hwirq(data) - 24; - const unsigned long bank_offset = bit_offset/8 * 8; + const unsigned long bank_offset = bit_offset / 8; unsigned char cos_enable_state; raw_spin_lock_irqsave(&idio24gpio->lock, flags); - prev_irq_mask = idio24gpio->irq_mask >> bank_offset; + prev_irq_mask = idio24gpio->irq_mask >> bank_offset * 8; idio24gpio->irq_mask |= BIT(bit_offset); if (!prev_irq_mask) { @@ -455,6 +497,7 @@ static int idio_24_probe(struct pci_dev *pdev, const struct pci_device_id *id) struct device *const dev = &pdev->dev; struct idio_24_gpio *idio24gpio; int err; + const size_t pci_plx_bar_index = 1; const size_t pci_bar_index = 2; const char *const name = pci_name(pdev); struct gpio_irq_chip *girq; @@ -469,12 +512,13 @@ static int idio_24_probe(struct pci_dev *pdev, const struct pci_device_id *id) return err; } - err = pcim_iomap_regions(pdev, BIT(pci_bar_index), name); + err = pcim_iomap_regions(pdev, BIT(pci_plx_bar_index) | BIT(pci_bar_index), name); if (err) { dev_err(dev, "Unable to map PCI I/O addresses (%d)\n", err); return err; } + idio24gpio->plx = pcim_iomap_table(pdev)[pci_plx_bar_index]; idio24gpio->reg = pcim_iomap_table(pdev)[pci_bar_index]; idio24gpio->chip.label = name; @@ -504,6 +548,12 @@ static int idio_24_probe(struct pci_dev *pdev, const struct pci_device_id *id) /* Software board reset */ iowrite8(0, &idio24gpio->reg->soft_reset); + /* + * enable PLX PEX8311 internal PCI wire interrupt and local interrupt + * input + */ + iowrite8((INTCSR_INTERNAL_PCI_WIRE | INTCSR_LOCAL_INPUT) >> 8, + idio24gpio->plx + PLX_PEX8311_PCI_LCS_INTCSR + 1); err = devm_gpiochip_add_data(dev, &idio24gpio->chip, idio24gpio); if (err) { diff --git a/drivers/gpio/gpio-sifive.c b/drivers/gpio/gpio-sifive.c index c54dd08f2cbf..d5eb9ca11901 100644 --- a/drivers/gpio/gpio-sifive.c +++ b/drivers/gpio/gpio-sifive.c @@ -183,7 +183,7 @@ static int sifive_gpio_probe(struct platform_device *pdev) return PTR_ERR(chip->regs); ngpio = of_irq_count(node); - if (ngpio >= SIFIVE_GPIO_MAX) { + if (ngpio > SIFIVE_GPIO_MAX) { dev_err(dev, "Too many GPIO interrupts (max=%d)\n", SIFIVE_GPIO_MAX); return -ENXIO; diff --git a/drivers/gpio/gpiolib-cdev.h b/drivers/gpio/gpiolib-cdev.h index cb41dd757338..b42644cbffb8 100644 --- a/drivers/gpio/gpiolib-cdev.h +++ b/drivers/gpio/gpiolib-cdev.h @@ -7,22 +7,7 @@ struct gpio_device; -#ifdef CONFIG_GPIO_CDEV - int gpiolib_cdev_register(struct gpio_device *gdev, dev_t devt); void gpiolib_cdev_unregister(struct gpio_device *gdev); -#else - -static inline int gpiolib_cdev_register(struct gpio_device *gdev, dev_t devt) -{ - return 0; -} - -static inline void gpiolib_cdev_unregister(struct gpio_device *gdev) -{ -} - -#endif /* CONFIG_GPIO_CDEV */ - #endif /* GPIOLIB_CDEV_H */ diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 3cdf9effc13a..089ddcaa9bc6 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -480,11 +480,23 @@ static void gpiodevice_release(struct device *dev) kfree(gdev); } +#ifdef CONFIG_GPIO_CDEV +#define gcdev_register(gdev, devt) gpiolib_cdev_register((gdev), (devt)) +#define gcdev_unregister(gdev) gpiolib_cdev_unregister((gdev)) +#else +/* + * gpiolib_cdev_register() indirectly calls device_add(), which is still + * required even when cdev is not selected. + */ +#define gcdev_register(gdev, devt) device_add(&(gdev)->dev) +#define gcdev_unregister(gdev) device_del(&(gdev)->dev) +#endif + static int gpiochip_setup_dev(struct gpio_device *gdev) { int ret; - ret = gpiolib_cdev_register(gdev, gpio_devt); + ret = gcdev_register(gdev, gpio_devt); if (ret) return ret; @@ -500,7 +512,7 @@ static int gpiochip_setup_dev(struct gpio_device *gdev) return 0; err_remove_device: - gpiolib_cdev_unregister(gdev); + gcdev_unregister(gdev); return ret; } @@ -825,7 +837,7 @@ void gpiochip_remove(struct gpio_chip *gc) * be removed, else it will be dangling until the last user is * gone. */ - gpiolib_cdev_unregister(gdev); + gcdev_unregister(gdev); put_device(&gdev->dev); } EXPORT_SYMBOL_GPL(gpiochip_remove); diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c index d5715c1d177b..8eeba8096493 100644 --- a/drivers/gpu/drm/amd/amdgpu/nv.c +++ b/drivers/gpu/drm/amd/amdgpu/nv.c @@ -492,8 +492,7 @@ int nv_set_ip_blocks(struct amdgpu_device *adev) if (adev->enable_virtual_display || amdgpu_sriov_vf(adev)) amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block); #if defined(CONFIG_DRM_AMD_DC) - else if (amdgpu_device_has_dc_support(adev) && - !nv_is_headless_sku(adev->pdev)) + else if (amdgpu_device_has_dc_support(adev)) amdgpu_device_ip_block_add(adev, &dm_ip_block); #endif amdgpu_device_ip_block_add(adev, &gfx_v10_0_ip_block); diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c index dff5c15b4858..c4828bd3264b 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c @@ -40,6 +40,7 @@ MODULE_FIRMWARE("amdgpu/renoir_asd.bin"); MODULE_FIRMWARE("amdgpu/renoir_ta.bin"); MODULE_FIRMWARE("amdgpu/green_sardine_asd.bin"); +MODULE_FIRMWARE("amdgpu/green_sardine_ta.bin"); /* address block */ #define smnMP1_FIRMWARE_FLAGS 0x3010024 diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn30/irq_service_dcn30.c b/drivers/gpu/drm/amd/display/dc/irq/dcn30/irq_service_dcn30.c index 49689f71f4f1..0effbb2bd74a 100644 --- a/drivers/gpu/drm/amd/display/dc/irq/dcn30/irq_service_dcn30.c +++ b/drivers/gpu/drm/amd/display/dc/irq/dcn30/irq_service_dcn30.c @@ -306,8 +306,8 @@ irq_source_info_dcn30[DAL_IRQ_SOURCES_NUMBER] = { pflip_int_entry(1), pflip_int_entry(2), pflip_int_entry(3), - [DC_IRQ_SOURCE_PFLIP5] = dummy_irq_entry(), - [DC_IRQ_SOURCE_PFLIP6] = dummy_irq_entry(), + pflip_int_entry(4), + pflip_int_entry(5), [DC_IRQ_SOURCE_PFLIP_UNDERLAY0] = dummy_irq_entry(), gpio_pad_int_entry(0), gpio_pad_int_entry(1), diff --git a/drivers/gpu/drm/bridge/cadence/Kconfig b/drivers/gpu/drm/bridge/cadence/Kconfig index 511d67b16d14..ef8c230e0f62 100644 --- a/drivers/gpu/drm/bridge/cadence/Kconfig +++ b/drivers/gpu/drm/bridge/cadence/Kconfig @@ -13,7 +13,7 @@ config DRM_CDNS_MHDP8546 if DRM_CDNS_MHDP8546 config DRM_CDNS_MHDP8546_J721E - depends on ARCH_K3_J721E_SOC || COMPILE_TEST + depends on ARCH_K3 || COMPILE_TEST bool "J721E Cadence DPI/DP wrapper support" default y help diff --git a/drivers/gpu/drm/gma500/psb_irq.c b/drivers/gpu/drm/gma500/psb_irq.c index 15eb3770d817..361e3a0c5ab6 100644 --- a/drivers/gpu/drm/gma500/psb_irq.c +++ b/drivers/gpu/drm/gma500/psb_irq.c @@ -347,6 +347,7 @@ int psb_irq_postinstall(struct drm_device *dev) { struct drm_psb_private *dev_priv = dev->dev_private; unsigned long irqflags; + unsigned int i; spin_lock_irqsave(&dev_priv->irqmask_lock, irqflags); @@ -359,20 +360,12 @@ int psb_irq_postinstall(struct drm_device *dev) PSB_WVDC32(dev_priv->vdc_irq_mask, PSB_INT_ENABLE_R); PSB_WVDC32(0xFFFFFFFF, PSB_HWSTAM); - if (dev->vblank[0].enabled) - psb_enable_pipestat(dev_priv, 0, PIPE_VBLANK_INTERRUPT_ENABLE); - else - psb_disable_pipestat(dev_priv, 0, PIPE_VBLANK_INTERRUPT_ENABLE); - - if (dev->vblank[1].enabled) - psb_enable_pipestat(dev_priv, 1, PIPE_VBLANK_INTERRUPT_ENABLE); - else - psb_disable_pipestat(dev_priv, 1, PIPE_VBLANK_INTERRUPT_ENABLE); - - if (dev->vblank[2].enabled) - psb_enable_pipestat(dev_priv, 2, PIPE_VBLANK_INTERRUPT_ENABLE); - else - psb_disable_pipestat(dev_priv, 2, PIPE_VBLANK_INTERRUPT_ENABLE); + for (i = 0; i < dev->num_crtcs; ++i) { + if (dev->vblank[i].enabled) + psb_enable_pipestat(dev_priv, i, PIPE_VBLANK_INTERRUPT_ENABLE); + else + psb_disable_pipestat(dev_priv, i, PIPE_VBLANK_INTERRUPT_ENABLE); + } if (dev_priv->ops->hotplug_enable) dev_priv->ops->hotplug_enable(dev, true); @@ -385,6 +378,7 @@ void psb_irq_uninstall(struct drm_device *dev) { struct drm_psb_private *dev_priv = dev->dev_private; unsigned long irqflags; + unsigned int i; spin_lock_irqsave(&dev_priv->irqmask_lock, irqflags); @@ -393,14 +387,10 @@ void psb_irq_uninstall(struct drm_device *dev) PSB_WVDC32(0xFFFFFFFF, PSB_HWSTAM); - if (dev->vblank[0].enabled) - psb_disable_pipestat(dev_priv, 0, PIPE_VBLANK_INTERRUPT_ENABLE); - - if (dev->vblank[1].enabled) - psb_disable_pipestat(dev_priv, 1, PIPE_VBLANK_INTERRUPT_ENABLE); - - if (dev->vblank[2].enabled) - psb_disable_pipestat(dev_priv, 2, PIPE_VBLANK_INTERRUPT_ENABLE); + for (i = 0; i < dev->num_crtcs; ++i) { + if (dev->vblank[i].enabled) + psb_disable_pipestat(dev_priv, i, PIPE_VBLANK_INTERRUPT_ENABLE); + } dev_priv->vdc_irq_mask &= _PSB_IRQ_SGX_FLAG | _PSB_IRQ_MSVDX_FLAG | diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h index b5c15557cc87..d6711caa7f39 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h @@ -56,6 +56,8 @@ struct drm_i915_gem_object_ops { void (*truncate)(struct drm_i915_gem_object *obj); void (*writeback)(struct drm_i915_gem_object *obj); + int (*pread)(struct drm_i915_gem_object *obj, + const struct drm_i915_gem_pread *arg); int (*pwrite)(struct drm_i915_gem_object *obj, const struct drm_i915_gem_pwrite *arg); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_phys.c b/drivers/gpu/drm/i915/gem/i915_gem_phys.c index 28147aab47b9..3a4dfe2ef1da 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_phys.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_phys.c @@ -134,6 +134,58 @@ i915_gem_object_put_pages_phys(struct drm_i915_gem_object *obj, vaddr, dma); } +static int +phys_pwrite(struct drm_i915_gem_object *obj, + const struct drm_i915_gem_pwrite *args) +{ + void *vaddr = sg_page(obj->mm.pages->sgl) + args->offset; + char __user *user_data = u64_to_user_ptr(args->data_ptr); + int err; + + err = i915_gem_object_wait(obj, + I915_WAIT_INTERRUPTIBLE | + I915_WAIT_ALL, + MAX_SCHEDULE_TIMEOUT); + if (err) + return err; + + /* + * We manually control the domain here and pretend that it + * remains coherent i.e. in the GTT domain, like shmem_pwrite. + */ + i915_gem_object_invalidate_frontbuffer(obj, ORIGIN_CPU); + + if (copy_from_user(vaddr, user_data, args->size)) + return -EFAULT; + + drm_clflush_virt_range(vaddr, args->size); + intel_gt_chipset_flush(&to_i915(obj->base.dev)->gt); + + i915_gem_object_flush_frontbuffer(obj, ORIGIN_CPU); + return 0; +} + +static int +phys_pread(struct drm_i915_gem_object *obj, + const struct drm_i915_gem_pread *args) +{ + void *vaddr = sg_page(obj->mm.pages->sgl) + args->offset; + char __user *user_data = u64_to_user_ptr(args->data_ptr); + int err; + + err = i915_gem_object_wait(obj, + I915_WAIT_INTERRUPTIBLE, + MAX_SCHEDULE_TIMEOUT); + if (err) + return err; + + drm_clflush_virt_range(vaddr, args->size); + if (copy_to_user(user_data, vaddr, args->size)) + return -EFAULT; + + return 0; +} + static void phys_release(struct drm_i915_gem_object *obj) { fput(obj->base.filp); @@ -144,6 +196,9 @@ static const struct drm_i915_gem_object_ops i915_gem_phys_ops = { .get_pages = i915_gem_object_get_pages_phys, .put_pages = i915_gem_object_put_pages_phys, + .pread = phys_pread, + .pwrite = phys_pwrite, + .release = phys_release, }; diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index 5bfb5f7ed02c..efdeb7b7b2a0 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -371,7 +371,8 @@ static void __setup_engine_capabilities(struct intel_engine_cs *engine) * instances. */ if ((INTEL_GEN(i915) >= 11 && - engine->gt->info.vdbox_sfc_access & engine->mask) || + (engine->gt->info.vdbox_sfc_access & + BIT(engine->instance))) || (INTEL_GEN(i915) >= 9 && engine->instance == 0)) engine->uabi_capabilities |= I915_VIDEO_AND_ENHANCE_CLASS_CAPABILITY_SFC; diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index bb0c12975f38..58276694c848 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -180,30 +180,6 @@ try_again: } static int -i915_gem_phys_pwrite(struct drm_i915_gem_object *obj, - struct drm_i915_gem_pwrite *args, - struct drm_file *file) -{ - void *vaddr = sg_page(obj->mm.pages->sgl) + args->offset; - char __user *user_data = u64_to_user_ptr(args->data_ptr); - - /* - * We manually control the domain here and pretend that it - * remains coherent i.e. in the GTT domain, like shmem_pwrite. - */ - i915_gem_object_invalidate_frontbuffer(obj, ORIGIN_CPU); - - if (copy_from_user(vaddr, user_data, args->size)) - return -EFAULT; - - drm_clflush_virt_range(vaddr, args->size); - intel_gt_chipset_flush(&to_i915(obj->base.dev)->gt); - - i915_gem_object_flush_frontbuffer(obj, ORIGIN_CPU); - return 0; -} - -static int i915_gem_create(struct drm_file *file, struct intel_memory_region *mr, u64 *size_p, @@ -527,6 +503,12 @@ i915_gem_pread_ioctl(struct drm_device *dev, void *data, trace_i915_gem_object_pread(obj, args->offset, args->size); + ret = -ENODEV; + if (obj->ops->pread) + ret = obj->ops->pread(obj, args); + if (ret != -ENODEV) + goto out; + ret = i915_gem_object_wait(obj, I915_WAIT_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); @@ -866,8 +848,6 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data, if (ret == -EFAULT || ret == -ENOSPC) { if (i915_gem_object_has_struct_page(obj)) ret = i915_gem_shmem_pwrite(obj, args); - else - ret = i915_gem_phys_pwrite(obj, args, file); } i915_gem_object_unpin_pages(obj); diff --git a/drivers/gpu/drm/mcde/mcde_drv.c b/drivers/gpu/drm/mcde/mcde_drv.c index c592957ed07f..92f8bd907193 100644 --- a/drivers/gpu/drm/mcde/mcde_drv.c +++ b/drivers/gpu/drm/mcde/mcde_drv.c @@ -413,7 +413,13 @@ static int mcde_probe(struct platform_device *pdev) match); if (ret) { dev_err(dev, "failed to add component master\n"); - goto clk_disable; + /* + * The EPOD regulator is already disabled at this point so some + * special errorpath code is needed + */ + clk_disable_unprepare(mcde->mcde_clk); + regulator_disable(mcde->vana); + return ret; } return 0; diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index b111fe24a06b..36d6b6093d16 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -455,7 +455,7 @@ nv50_outp_get_old_connector(struct nouveau_encoder *outp, * DAC *****************************************************************************/ static void -nv50_dac_disable(struct drm_encoder *encoder) +nv50_dac_disable(struct drm_encoder *encoder, struct drm_atomic_state *state) { struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); struct nv50_core *core = nv50_disp(encoder->dev)->core; @@ -467,7 +467,7 @@ nv50_dac_disable(struct drm_encoder *encoder) } static void -nv50_dac_enable(struct drm_encoder *encoder) +nv50_dac_enable(struct drm_encoder *encoder, struct drm_atomic_state *state) { struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); struct nouveau_crtc *nv_crtc = nouveau_crtc(encoder->crtc); @@ -525,8 +525,8 @@ nv50_dac_detect(struct drm_encoder *encoder, struct drm_connector *connector) static const struct drm_encoder_helper_funcs nv50_dac_help = { .atomic_check = nv50_outp_atomic_check, - .enable = nv50_dac_enable, - .disable = nv50_dac_disable, + .atomic_enable = nv50_dac_enable, + .atomic_disable = nv50_dac_disable, .detect = nv50_dac_detect }; @@ -1055,7 +1055,7 @@ nv50_dp_bpc_to_depth(unsigned int bpc) } static void -nv50_msto_enable(struct drm_encoder *encoder) +nv50_msto_enable(struct drm_encoder *encoder, struct drm_atomic_state *state) { struct nv50_head *head = nv50_head(encoder->crtc); struct nv50_head_atom *armh = nv50_head_atom(head->base.base.state); @@ -1101,7 +1101,7 @@ nv50_msto_enable(struct drm_encoder *encoder) } static void -nv50_msto_disable(struct drm_encoder *encoder) +nv50_msto_disable(struct drm_encoder *encoder, struct drm_atomic_state *state) { struct nv50_msto *msto = nv50_msto(encoder); struct nv50_mstc *mstc = msto->mstc; @@ -1118,8 +1118,8 @@ nv50_msto_disable(struct drm_encoder *encoder) static const struct drm_encoder_helper_funcs nv50_msto_help = { - .disable = nv50_msto_disable, - .enable = nv50_msto_enable, + .atomic_disable = nv50_msto_disable, + .atomic_enable = nv50_msto_enable, .atomic_check = nv50_msto_atomic_check, }; @@ -1645,8 +1645,7 @@ nv50_sor_disable(struct drm_encoder *encoder, } static void -nv50_sor_enable(struct drm_encoder *encoder, - struct drm_atomic_state *state) +nv50_sor_enable(struct drm_encoder *encoder, struct drm_atomic_state *state) { struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); struct nouveau_crtc *nv_crtc = nouveau_crtc(encoder->crtc); @@ -1873,7 +1872,7 @@ nv50_pior_atomic_check(struct drm_encoder *encoder, } static void -nv50_pior_disable(struct drm_encoder *encoder) +nv50_pior_disable(struct drm_encoder *encoder, struct drm_atomic_state *state) { struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); struct nv50_core *core = nv50_disp(encoder->dev)->core; @@ -1885,7 +1884,7 @@ nv50_pior_disable(struct drm_encoder *encoder) } static void -nv50_pior_enable(struct drm_encoder *encoder) +nv50_pior_enable(struct drm_encoder *encoder, struct drm_atomic_state *state) { struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); struct nouveau_crtc *nv_crtc = nouveau_crtc(encoder->crtc); @@ -1921,14 +1920,14 @@ nv50_pior_enable(struct drm_encoder *encoder) } core->func->pior->ctrl(core, nv_encoder->or, ctrl, asyh); - nv_encoder->crtc = encoder->crtc; + nv_encoder->crtc = &nv_crtc->base; } static const struct drm_encoder_helper_funcs nv50_pior_help = { .atomic_check = nv50_pior_atomic_check, - .enable = nv50_pior_enable, - .disable = nv50_pior_disable, + .atomic_enable = nv50_pior_enable, + .atomic_disable = nv50_pior_disable, }; static void diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 2ee75646ad6f..56b335a55966 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -350,14 +350,13 @@ set_placement_list(struct nouveau_drm *drm, struct ttm_place *pl, unsigned *n, if (domain & NOUVEAU_GEM_DOMAIN_VRAM) { struct nvif_mmu *mmu = &drm->client.mmu; - const u8 type = mmu->type[drm->ttm.type_vram].type; pl[*n].mem_type = TTM_PL_VRAM; pl[*n].flags = flags & ~TTM_PL_FLAG_CACHED; /* Some BARs do not support being ioremapped WC */ if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_TESLA && - type & NVIF_MEM_UNCACHED) + mmu->type[drm->ttm.type_vram].type & NVIF_MEM_UNCACHED) pl[*n].flags &= ~TTM_PL_FLAG_WC; (*n)++; diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c index 6f21f36719fc..8b4b3688c7ae 100644 --- a/drivers/gpu/drm/nouveau/nouveau_connector.c +++ b/drivers/gpu/drm/nouveau/nouveau_connector.c @@ -532,11 +532,13 @@ static void nouveau_connector_set_edid(struct nouveau_connector *nv_connector, struct edid *edid) { - struct edid *old_edid = nv_connector->edid; + if (nv_connector->edid != edid) { + struct edid *old_edid = nv_connector->edid; - drm_connector_update_edid_property(&nv_connector->base, edid); - kfree(old_edid); - nv_connector->edid = edid; + drm_connector_update_edid_property(&nv_connector->base, edid); + kfree(old_edid); + nv_connector->edid = edid; + } } static enum drm_connector_status @@ -669,8 +671,10 @@ nouveau_connector_detect_lvds(struct drm_connector *connector, bool force) /* Try retrieving EDID via DDC */ if (!drm->vbios.fp_no_ddc) { status = nouveau_connector_detect(connector, force); - if (status == connector_status_connected) + if (status == connector_status_connected) { + edid = nv_connector->edid; goto out; + } } /* On some laptops (Sony, i'm looking at you) there appears to diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c index 0cde10fe0e71..f202ac7f4b3d 100644 --- a/drivers/hv/hv.c +++ b/drivers/hv/hv.c @@ -244,9 +244,13 @@ int hv_synic_cleanup(unsigned int cpu) /* * Hyper-V does not provide a way to change the connect CPU once - * it is set; we must prevent the connect CPU from going offline. + * it is set; we must prevent the connect CPU from going offline + * while the VM is running normally. But in the panic or kexec() + * path where the vmbus is already disconnected, the CPU must be + * allowed to shut down. */ - if (cpu == VMBUS_CONNECT_CPU) + if (cpu == VMBUS_CONNECT_CPU && + vmbus_connection.conn_state == CONNECTED) return -EBUSY; /* diff --git a/drivers/hwmon/amd_energy.c b/drivers/hwmon/amd_energy.c index d06597303d5a..3197cda7bcd9 100644 --- a/drivers/hwmon/amd_energy.c +++ b/drivers/hwmon/amd_energy.c @@ -171,7 +171,7 @@ static umode_t amd_energy_is_visible(const void *_data, enum hwmon_sensor_types type, u32 attr, int channel) { - return 0444; + return 0440; } static int energy_accumulator(void *p) diff --git a/drivers/hwmon/applesmc.c b/drivers/hwmon/applesmc.c index a18887990f4a..79b498f816fe 100644 --- a/drivers/hwmon/applesmc.c +++ b/drivers/hwmon/applesmc.c @@ -32,6 +32,7 @@ #include <linux/hwmon.h> #include <linux/workqueue.h> #include <linux/err.h> +#include <linux/bits.h> /* data port used by Apple SMC */ #define APPLESMC_DATA_PORT 0x300 @@ -42,10 +43,13 @@ #define APPLESMC_MAX_DATA_LENGTH 32 -/* wait up to 128 ms for a status change. */ -#define APPLESMC_MIN_WAIT 0x0010 -#define APPLESMC_RETRY_WAIT 0x0100 -#define APPLESMC_MAX_WAIT 0x20000 +/* Apple SMC status bits */ +#define SMC_STATUS_AWAITING_DATA BIT(0) /* SMC has data waiting to be read */ +#define SMC_STATUS_IB_CLOSED BIT(1) /* Will ignore any input */ +#define SMC_STATUS_BUSY BIT(2) /* Command in progress */ + +/* Initial wait is 8us */ +#define APPLESMC_MIN_WAIT 0x0008 #define APPLESMC_READ_CMD 0x10 #define APPLESMC_WRITE_CMD 0x11 @@ -151,65 +155,84 @@ static unsigned int key_at_index; static struct workqueue_struct *applesmc_led_wq; /* - * wait_read - Wait for a byte to appear on SMC port. Callers must - * hold applesmc_lock. + * Wait for specific status bits with a mask on the SMC. + * Used before all transactions. + * This does 10 fast loops of 8us then exponentially backs off for a + * minimum total wait of 262ms. Depending on usleep_range this could + * run out past 500ms. */ -static int wait_read(void) + +static int wait_status(u8 val, u8 mask) { - unsigned long end = jiffies + (APPLESMC_MAX_WAIT * HZ) / USEC_PER_SEC; u8 status; int us; + int i; - for (us = APPLESMC_MIN_WAIT; us < APPLESMC_MAX_WAIT; us <<= 1) { - usleep_range(us, us * 16); + us = APPLESMC_MIN_WAIT; + for (i = 0; i < 24 ; i++) { status = inb(APPLESMC_CMD_PORT); - /* read: wait for smc to settle */ - if (status & 0x01) + if ((status & mask) == val) return 0; - /* timeout: give up */ - if (time_after(jiffies, end)) - break; + usleep_range(us, us * 2); + if (i > 9) + us <<= 1; } - - pr_warn("wait_read() fail: 0x%02x\n", status); return -EIO; } -/* - * send_byte - Write to SMC port, retrying when necessary. Callers - * must hold applesmc_lock. - */ +/* send_byte - Write to SMC data port. Callers must hold applesmc_lock. */ + static int send_byte(u8 cmd, u16 port) { - u8 status; - int us; - unsigned long end = jiffies + (APPLESMC_MAX_WAIT * HZ) / USEC_PER_SEC; + int status; + + status = wait_status(0, SMC_STATUS_IB_CLOSED); + if (status) + return status; + /* + * This needs to be a separate read looking for bit 0x04 + * after bit 0x02 falls. If consolidated with the wait above + * this extra read may not happen if status returns both + * simultaneously and this would appear to be required. + */ + status = wait_status(SMC_STATUS_BUSY, SMC_STATUS_BUSY); + if (status) + return status; outb(cmd, port); - for (us = APPLESMC_MIN_WAIT; us < APPLESMC_MAX_WAIT; us <<= 1) { - usleep_range(us, us * 16); - status = inb(APPLESMC_CMD_PORT); - /* write: wait for smc to settle */ - if (status & 0x02) - continue; - /* ready: cmd accepted, return */ - if (status & 0x04) - return 0; - /* timeout: give up */ - if (time_after(jiffies, end)) - break; - /* busy: long wait and resend */ - udelay(APPLESMC_RETRY_WAIT); - outb(cmd, port); - } - - pr_warn("send_byte(0x%02x, 0x%04x) fail: 0x%02x\n", cmd, port, status); - return -EIO; + return 0; } +/* send_command - Write a command to the SMC. Callers must hold applesmc_lock. */ + static int send_command(u8 cmd) { - return send_byte(cmd, APPLESMC_CMD_PORT); + int ret; + + ret = wait_status(0, SMC_STATUS_IB_CLOSED); + if (ret) + return ret; + outb(cmd, APPLESMC_CMD_PORT); + return 0; +} + +/* + * Based on logic from the Apple driver. This is issued before any interaction + * If busy is stuck high, issue a read command to reset the SMC state machine. + * If busy is stuck high after the command then the SMC is jammed. + */ + +static int smc_sane(void) +{ + int ret; + + ret = wait_status(0, SMC_STATUS_BUSY); + if (!ret) + return ret; + ret = send_command(APPLESMC_READ_CMD); + if (ret) + return ret; + return wait_status(0, SMC_STATUS_BUSY); } static int send_argument(const char *key) @@ -226,6 +249,11 @@ static int read_smc(u8 cmd, const char *key, u8 *buffer, u8 len) { u8 status, data = 0; int i; + int ret; + + ret = smc_sane(); + if (ret) + return ret; if (send_command(cmd) || send_argument(key)) { pr_warn("%.4s: read arg fail\n", key); @@ -239,7 +267,8 @@ static int read_smc(u8 cmd, const char *key, u8 *buffer, u8 len) } for (i = 0; i < len; i++) { - if (wait_read()) { + if (wait_status(SMC_STATUS_AWAITING_DATA | SMC_STATUS_BUSY, + SMC_STATUS_AWAITING_DATA | SMC_STATUS_BUSY)) { pr_warn("%.4s: read data[%d] fail\n", key, i); return -EIO; } @@ -250,19 +279,24 @@ static int read_smc(u8 cmd, const char *key, u8 *buffer, u8 len) for (i = 0; i < 16; i++) { udelay(APPLESMC_MIN_WAIT); status = inb(APPLESMC_CMD_PORT); - if (!(status & 0x01)) + if (!(status & SMC_STATUS_AWAITING_DATA)) break; data = inb(APPLESMC_DATA_PORT); } if (i) pr_warn("flushed %d bytes, last value is: %d\n", i, data); - return 0; + return wait_status(0, SMC_STATUS_BUSY); } static int write_smc(u8 cmd, const char *key, const u8 *buffer, u8 len) { int i; + int ret; + + ret = smc_sane(); + if (ret) + return ret; if (send_command(cmd) || send_argument(key)) { pr_warn("%s: write arg fail\n", key); @@ -281,7 +315,7 @@ static int write_smc(u8 cmd, const char *key, const u8 *buffer, u8 len) } } - return 0; + return wait_status(0, SMC_STATUS_BUSY); } static int read_register_count(unsigned int *count) diff --git a/drivers/hwmon/pmbus/max20730.c b/drivers/hwmon/pmbus/max20730.c index 57923d72490c..be83b98411c7 100644 --- a/drivers/hwmon/pmbus/max20730.c +++ b/drivers/hwmon/pmbus/max20730.c @@ -122,8 +122,8 @@ static ssize_t max20730_debugfs_read(struct file *file, char __user *buf, switch (idx) { case MAX20730_DEBUGFS_VOUT_MIN: ret = VOLT_FROM_REG(data->mfr_voutmin * 10000); - len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d.%d\n", - ret / 10000, ret % 10000); + len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d.%d\n", + ret / 10000, ret % 10000); break; case MAX20730_DEBUGFS_FREQUENCY: val = (data->mfr_devset1 & MAX20730_MFR_DEVSET1_FSW_MASK) @@ -141,7 +141,7 @@ static ssize_t max20730_debugfs_read(struct file *file, char __user *buf, ret = 800; else ret = 900; - len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); + len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); break; case MAX20730_DEBUGFS_PG_DELAY: val = (data->mfr_devset1 & MAX20730_MFR_DEVSET1_TSTAT_MASK) @@ -223,7 +223,7 @@ static ssize_t max20730_debugfs_read(struct file *file, char __user *buf, case MAX20730_DEBUGFS_OC_PROTECT_MODE: ret = (data->mfr_devset2 & MAX20730_MFR_DEVSET2_OCPM_MASK) >> MAX20730_MFR_DEVSET2_OCPM_BIT_POS; - len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); + len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); break; case MAX20730_DEBUGFS_SS_TIMING: val = (data->mfr_devset2 & MAX20730_MFR_DEVSET2_SS_MASK) @@ -241,32 +241,32 @@ static ssize_t max20730_debugfs_read(struct file *file, char __user *buf, case MAX20730_DEBUGFS_IMAX: ret = (data->mfr_devset2 & MAX20730_MFR_DEVSET2_IMAX_MASK) >> MAX20730_MFR_DEVSET2_IMAX_BIT_POS; - len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); + len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); break; case MAX20730_DEBUGFS_OPERATION: ret = i2c_smbus_read_byte_data(psu->client, PMBUS_OPERATION); if (ret < 0) return ret; - len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); + len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); break; case MAX20730_DEBUGFS_ON_OFF_CONFIG: ret = i2c_smbus_read_byte_data(psu->client, PMBUS_ON_OFF_CONFIG); if (ret < 0) return ret; - len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); + len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); break; case MAX20730_DEBUGFS_SMBALERT_MASK: ret = i2c_smbus_read_word_data(psu->client, PMBUS_SMB_ALERT_MASK); if (ret < 0) return ret; - len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); + len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); break; case MAX20730_DEBUGFS_VOUT_MODE: ret = i2c_smbus_read_byte_data(psu->client, PMBUS_VOUT_MODE); if (ret < 0) return ret; - len = snprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); + len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, "%d\n", ret); break; case MAX20730_DEBUGFS_VOUT_COMMAND: ret = i2c_smbus_read_word_data(psu->client, PMBUS_VOUT_COMMAND); @@ -274,8 +274,8 @@ static ssize_t max20730_debugfs_read(struct file *file, char __user *buf, return ret; ret = VOLT_FROM_REG(ret * 10000); - len = snprintf(tbuf, DEBUG_FS_DATA_MAX, - "%d.%d\n", ret / 10000, ret % 10000); + len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, + "%d.%d\n", ret / 10000, ret % 10000); break; case MAX20730_DEBUGFS_VOUT_MAX: ret = i2c_smbus_read_word_data(psu->client, PMBUS_VOUT_MAX); @@ -283,8 +283,8 @@ static ssize_t max20730_debugfs_read(struct file *file, char __user *buf, return ret; ret = VOLT_FROM_REG(ret * 10000); - len = snprintf(tbuf, DEBUG_FS_DATA_MAX, - "%d.%d\n", ret / 10000, ret % 10000); + len = scnprintf(tbuf, DEBUG_FS_DATA_MAX, + "%d.%d\n", ret / 10000, ret % 10000); break; default: len = strlcpy(tbuf, "Invalid\n", DEBUG_FS_DATA_MAX); diff --git a/drivers/hwmon/pmbus/pmbus_core.c b/drivers/hwmon/pmbus/pmbus_core.c index 170a9f82ca61..b0e2820a2d57 100644 --- a/drivers/hwmon/pmbus/pmbus_core.c +++ b/drivers/hwmon/pmbus/pmbus_core.c @@ -941,12 +941,16 @@ static ssize_t pmbus_show_sensor(struct device *dev, struct i2c_client *client = to_i2c_client(dev->parent); struct pmbus_sensor *sensor = to_pmbus_sensor(devattr); struct pmbus_data *data = i2c_get_clientdata(client); + ssize_t ret; + mutex_lock(&data->update_lock); pmbus_update_sensor_data(client, sensor); if (sensor->data < 0) - return sensor->data; - - return snprintf(buf, PAGE_SIZE, "%lld\n", pmbus_reg2data(data, sensor)); + ret = sensor->data; + else + ret = snprintf(buf, PAGE_SIZE, "%lld\n", pmbus_reg2data(data, sensor)); + mutex_unlock(&data->update_lock); + return ret; } static ssize_t pmbus_set_sensor(struct device *dev, @@ -2012,8 +2016,11 @@ static ssize_t pmbus_show_samples(struct device *dev, int val; struct i2c_client *client = to_i2c_client(dev->parent); struct pmbus_samples_reg *reg = to_samples_reg(devattr); + struct pmbus_data *data = i2c_get_clientdata(client); + mutex_lock(&data->update_lock); val = _pmbus_read_word_data(client, reg->page, 0xff, reg->attr->reg); + mutex_unlock(&data->update_lock); if (val < 0) return val; diff --git a/drivers/hwmon/pwm-fan.c b/drivers/hwmon/pwm-fan.c index bdba2143021a..1f63807c0399 100644 --- a/drivers/hwmon/pwm-fan.c +++ b/drivers/hwmon/pwm-fan.c @@ -54,16 +54,18 @@ static irqreturn_t pulse_handler(int irq, void *dev_id) static void sample_timer(struct timer_list *t) { struct pwm_fan_ctx *ctx = from_timer(ctx, t, rpm_timer); + unsigned int delta = ktime_ms_delta(ktime_get(), ctx->sample_start); int pulses; - u64 tmp; - pulses = atomic_read(&ctx->pulses); - atomic_sub(pulses, &ctx->pulses); - tmp = (u64)pulses * ktime_ms_delta(ktime_get(), ctx->sample_start) * 60; - do_div(tmp, ctx->pulses_per_revolution * 1000); - ctx->rpm = tmp; + if (delta) { + pulses = atomic_read(&ctx->pulses); + atomic_sub(pulses, &ctx->pulses); + ctx->rpm = (unsigned int)(pulses * 1000 * 60) / + (ctx->pulses_per_revolution * delta); + + ctx->sample_start = ktime_get(); + } - ctx->sample_start = ktime_get(); mod_timer(&ctx->rpm_timer, jiffies + HZ); } diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index 404b40af31cb..b2e804473209 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -333,6 +333,11 @@ static void dmar_pci_bus_del_dev(struct dmar_pci_notify_info *info) dmar_iommu_notify_scope_dev(info); } +static inline void vf_inherit_msi_domain(struct pci_dev *pdev) +{ + dev_set_msi_domain(&pdev->dev, dev_get_msi_domain(&pdev->physfn->dev)); +} + static int dmar_pci_bus_notifier(struct notifier_block *nb, unsigned long action, void *data) { @@ -342,8 +347,20 @@ static int dmar_pci_bus_notifier(struct notifier_block *nb, /* Only care about add/remove events for physical functions. * For VFs we actually do the lookup based on the corresponding * PF in device_to_iommu() anyway. */ - if (pdev->is_virtfn) + if (pdev->is_virtfn) { + /* + * Ensure that the VF device inherits the irq domain of the + * PF device. Ideally the device would inherit the domain + * from the bus, but DMAR can have multiple units per bus + * which makes this impossible. The VF 'bus' could inherit + * from the PF device, but that's yet another x86'sism to + * inflict on everybody else. + */ + if (action == BUS_NOTIFY_ADD_DEVICE) + vf_inherit_msi_domain(pdev); return NOTIFY_DONE; + } + if (action != BUS_NOTIFY_ADD_DEVICE && action != BUS_NOTIFY_REMOVED_DEVICE) return NOTIFY_DONE; diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 1b1ca63e6bbe..c6622011d493 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -3818,9 +3818,8 @@ bounce_map_single(struct device *dev, phys_addr_t paddr, size_t size, * page aligned, we don't need to use a bounce page. */ if (!IS_ALIGNED(paddr | size, VTD_PAGE_SIZE)) { - tlb_addr = swiotlb_tbl_map_single(dev, - phys_to_dma_unencrypted(dev, io_tlb_start), - paddr, size, aligned_size, dir, attrs); + tlb_addr = swiotlb_tbl_map_single(dev, paddr, size, + aligned_size, dir, attrs); if (tlb_addr == DMA_MAPPING_ERROR) { goto swiotlb_error; } else { diff --git a/drivers/misc/habanalabs/common/command_buffer.c b/drivers/misc/habanalabs/common/command_buffer.c index 901e213daf40..ada570f35a41 100644 --- a/drivers/misc/habanalabs/common/command_buffer.c +++ b/drivers/misc/habanalabs/common/command_buffer.c @@ -142,11 +142,10 @@ static void cb_fini(struct hl_device *hdev, struct hl_cb *cb) { if (cb->is_internal) gen_pool_free(hdev->internal_cb_pool, - cb->kernel_address, cb->size); + (uintptr_t)cb->kernel_address, cb->size); else hdev->asic_funcs->asic_dma_free_coherent(hdev, cb->size, - (void *) (uintptr_t) cb->kernel_address, - cb->bus_address); + cb->kernel_address, cb->bus_address); kfree(cb); } @@ -230,7 +229,7 @@ static struct hl_cb *hl_cb_alloc(struct hl_device *hdev, u32 cb_size, return NULL; } - cb->kernel_address = (u64) (uintptr_t) p; + cb->kernel_address = p; cb->size = cb_size; return cb; @@ -509,7 +508,7 @@ int hl_cb_mmap(struct hl_fpriv *hpriv, struct vm_area_struct *vma) vma->vm_private_data = cb; - rc = hdev->asic_funcs->cb_mmap(hdev, vma, (void *) cb->kernel_address, + rc = hdev->asic_funcs->cb_mmap(hdev, vma, cb->kernel_address, cb->bus_address, cb->size); if (rc) { spin_lock(&cb->lock); diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h index 80d4d7385ffe..6ed974d2def0 100644 --- a/drivers/misc/habanalabs/common/habanalabs.h +++ b/drivers/misc/habanalabs/common/habanalabs.h @@ -452,7 +452,7 @@ struct hl_cb { struct list_head pool_list; struct list_head va_block_list; u64 id; - u64 kernel_address; + void *kernel_address; dma_addr_t bus_address; u32 mmap_size; u32 size; @@ -515,7 +515,7 @@ struct hl_hw_queue { struct hl_hw_sob hw_sob[HL_RSVD_SOBS]; struct hl_cs_job **shadow_queue; enum hl_queue_type queue_type; - u64 kernel_address; + void *kernel_address; dma_addr_t bus_address; u32 pi; atomic_t ci; @@ -544,7 +544,7 @@ struct hl_hw_queue { */ struct hl_cq { struct hl_device *hdev; - u64 kernel_address; + void *kernel_address; dma_addr_t bus_address; u32 cq_idx; u32 hw_queue_id; @@ -562,7 +562,7 @@ struct hl_cq { */ struct hl_eq { struct hl_device *hdev; - u64 kernel_address; + void *kernel_address; dma_addr_t bus_address; u32 ci; }; @@ -757,7 +757,7 @@ struct hl_asic_funcs { u32 (*get_dma_desc_list_size)(struct hl_device *hdev, struct sg_table *sgt); void (*add_end_of_cb_packets)(struct hl_device *hdev, - u64 kernel_address, u32 len, + void *kernel_address, u32 len, u64 cq_addr, u32 cq_val, u32 msix_num, bool eb); void (*update_eq_ci)(struct hl_device *hdev, u32 val); @@ -1382,13 +1382,13 @@ void hl_wreg(struct hl_device *hdev, u32 reg, u32 val); for (;;) { \ /* Verify we read updates done by other cores or by device */ \ mb(); \ - (val) = *((u32 *) (uintptr_t) (addr)); \ + (val) = *((u32 *)(addr)); \ if (mem_written_by_device) \ (val) = le32_to_cpu(*(__le32 *) &(val)); \ if (cond) \ break; \ if (timeout_us && ktime_compare(ktime_get(), __timeout) > 0) { \ - (val) = *((u32 *) (uintptr_t) (addr)); \ + (val) = *((u32 *)(addr)); \ if (mem_written_by_device) \ (val) = le32_to_cpu(*(__le32 *) &(val)); \ break; \ diff --git a/drivers/misc/habanalabs/common/hw_queue.c b/drivers/misc/habanalabs/common/hw_queue.c index 5e66c98fb0d3..250cf9cefc06 100644 --- a/drivers/misc/habanalabs/common/hw_queue.c +++ b/drivers/misc/habanalabs/common/hw_queue.c @@ -75,7 +75,7 @@ static void ext_and_hw_queue_submit_bd(struct hl_device *hdev, { struct hl_bd *bd; - bd = (struct hl_bd *) (uintptr_t) q->kernel_address; + bd = q->kernel_address; bd += hl_pi_2_offset(q->pi); bd->ctl = cpu_to_le32(ctl); bd->len = cpu_to_le32(len); @@ -335,8 +335,7 @@ static void int_queue_schedule_job(struct hl_cs_job *job) bd.len = cpu_to_le32(job->job_cb_size); bd.ptr = cpu_to_le64((u64) (uintptr_t) job->user_cb); - pi = (__le64 *) (uintptr_t) (q->kernel_address + - ((q->pi & (q->int_queue_len - 1)) * sizeof(bd))); + pi = q->kernel_address + (q->pi & (q->int_queue_len - 1)) * sizeof(bd); q->pi++; q->pi &= ((q->int_queue_len << 1) - 1); @@ -630,7 +629,7 @@ static int ext_and_cpu_queue_init(struct hl_device *hdev, struct hl_hw_queue *q, if (!p) return -ENOMEM; - q->kernel_address = (u64) (uintptr_t) p; + q->kernel_address = p; q->shadow_queue = kmalloc_array(HL_QUEUE_LENGTH, sizeof(*q->shadow_queue), @@ -653,11 +652,11 @@ free_queue: if (is_cpu_queue) hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev, HL_QUEUE_SIZE_IN_BYTES, - (void *) (uintptr_t) q->kernel_address); + q->kernel_address); else hdev->asic_funcs->asic_dma_free_coherent(hdev, HL_QUEUE_SIZE_IN_BYTES, - (void *) (uintptr_t) q->kernel_address, + q->kernel_address, q->bus_address); return rc; @@ -676,7 +675,7 @@ static int int_queue_init(struct hl_device *hdev, struct hl_hw_queue *q) return -EFAULT; } - q->kernel_address = (u64) (uintptr_t) p; + q->kernel_address = p; q->pi = 0; atomic_set(&q->ci, 0); @@ -704,7 +703,7 @@ static int hw_queue_init(struct hl_device *hdev, struct hl_hw_queue *q) if (!p) return -ENOMEM; - q->kernel_address = (u64) (uintptr_t) p; + q->kernel_address = p; /* Make sure read/write pointers are initialized to start of queue */ atomic_set(&q->ci, 0); @@ -839,11 +838,11 @@ static void queue_fini(struct hl_device *hdev, struct hl_hw_queue *q) if (q->queue_type == QUEUE_TYPE_CPU) hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev, HL_QUEUE_SIZE_IN_BYTES, - (void *) (uintptr_t) q->kernel_address); + q->kernel_address); else hdev->asic_funcs->asic_dma_free_coherent(hdev, HL_QUEUE_SIZE_IN_BYTES, - (void *) (uintptr_t) q->kernel_address, + q->kernel_address, q->bus_address); } diff --git a/drivers/misc/habanalabs/common/irq.c b/drivers/misc/habanalabs/common/irq.c index d20e40a53d70..de53fb5f978a 100644 --- a/drivers/misc/habanalabs/common/irq.c +++ b/drivers/misc/habanalabs/common/irq.c @@ -90,7 +90,7 @@ irqreturn_t hl_irq_handler_cq(int irq, void *arg) return IRQ_HANDLED; } - cq_base = (struct hl_cq_entry *) (uintptr_t) cq->kernel_address; + cq_base = cq->kernel_address; while (1) { bool entry_ready = ((le32_to_cpu(cq_base[cq->ci].data) & @@ -152,7 +152,7 @@ irqreturn_t hl_irq_handler_eq(int irq, void *arg) struct hl_eq_entry *eq_base; struct hl_eqe_work *handle_eqe_work; - eq_base = (struct hl_eq_entry *) (uintptr_t) eq->kernel_address; + eq_base = eq->kernel_address; while (1) { bool entry_ready = @@ -221,7 +221,7 @@ int hl_cq_init(struct hl_device *hdev, struct hl_cq *q, u32 hw_queue_id) return -ENOMEM; q->hdev = hdev; - q->kernel_address = (u64) (uintptr_t) p; + q->kernel_address = p; q->hw_queue_id = hw_queue_id; q->ci = 0; q->pi = 0; @@ -242,7 +242,8 @@ int hl_cq_init(struct hl_device *hdev, struct hl_cq *q, u32 hw_queue_id) void hl_cq_fini(struct hl_device *hdev, struct hl_cq *q) { hdev->asic_funcs->asic_dma_free_coherent(hdev, HL_CQ_SIZE_IN_BYTES, - (void *) (uintptr_t) q->kernel_address, q->bus_address); + q->kernel_address, + q->bus_address); } void hl_cq_reset(struct hl_device *hdev, struct hl_cq *q) @@ -259,7 +260,7 @@ void hl_cq_reset(struct hl_device *hdev, struct hl_cq *q) * when the device is operational again */ - memset((void *) (uintptr_t) q->kernel_address, 0, HL_CQ_SIZE_IN_BYTES); + memset(q->kernel_address, 0, HL_CQ_SIZE_IN_BYTES); } /** @@ -282,7 +283,7 @@ int hl_eq_init(struct hl_device *hdev, struct hl_eq *q) return -ENOMEM; q->hdev = hdev; - q->kernel_address = (u64) (uintptr_t) p; + q->kernel_address = p; q->ci = 0; return 0; @@ -302,7 +303,7 @@ void hl_eq_fini(struct hl_device *hdev, struct hl_eq *q) hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev, HL_EQ_SIZE_IN_BYTES, - (void *) (uintptr_t) q->kernel_address); + q->kernel_address); } void hl_eq_reset(struct hl_device *hdev, struct hl_eq *q) @@ -316,5 +317,5 @@ void hl_eq_reset(struct hl_device *hdev, struct hl_eq *q) * when the device is operational again */ - memset((void *) (uintptr_t) q->kernel_address, 0, HL_EQ_SIZE_IN_BYTES); + memset(q->kernel_address, 0, HL_EQ_SIZE_IN_BYTES); } diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c index 5f65a1691551..2519a34e25b7 100644 --- a/drivers/misc/habanalabs/gaudi/gaudi.c +++ b/drivers/misc/habanalabs/gaudi/gaudi.c @@ -680,8 +680,7 @@ static int _gaudi_init_tpc_mem(struct hl_device *hdev, if (!cb) return -EFAULT; - init_tpc_mem_pkt = (struct packet_lin_dma *) (uintptr_t) - cb->kernel_address; + init_tpc_mem_pkt = cb->kernel_address; cb_size = sizeof(*init_tpc_mem_pkt); memset(init_tpc_mem_pkt, 0, cb_size); @@ -3811,8 +3810,7 @@ static int gaudi_validate_cb(struct hl_device *hdev, u16 pkt_size; struct gaudi_packet *user_pkt; - user_pkt = (struct gaudi_packet *) (uintptr_t) - (parser->user_cb->kernel_address + cb_parsed_length); + user_pkt = parser->user_cb->kernel_address + cb_parsed_length; pkt_id = (enum packet_id) ( (le64_to_cpu(user_pkt->header) & @@ -4035,11 +4033,9 @@ static int gaudi_patch_cb(struct hl_device *hdev, u32 new_pkt_size = 0; struct gaudi_packet *user_pkt, *kernel_pkt; - user_pkt = (struct gaudi_packet *) (uintptr_t) - (parser->user_cb->kernel_address + cb_parsed_length); - kernel_pkt = (struct gaudi_packet *) (uintptr_t) - (parser->patched_cb->kernel_address + - cb_patched_cur_length); + user_pkt = parser->user_cb->kernel_address + cb_parsed_length; + kernel_pkt = parser->patched_cb->kernel_address + + cb_patched_cur_length; pkt_id = (enum packet_id) ( (le64_to_cpu(user_pkt->header) & @@ -4155,8 +4151,8 @@ static int gaudi_parse_cb_mmu(struct hl_device *hdev, * The check that parser->user_cb_size <= parser->user_cb->size was done * in validate_queue_index(). */ - memcpy((void *) (uintptr_t) parser->patched_cb->kernel_address, - (void *) (uintptr_t) parser->user_cb->kernel_address, + memcpy(parser->patched_cb->kernel_address, + parser->user_cb->kernel_address, parser->user_cb_size); patched_cb_size = parser->patched_cb_size; @@ -4290,7 +4286,7 @@ static int gaudi_cs_parser(struct hl_device *hdev, struct hl_cs_parser *parser) } static void gaudi_add_end_of_cb_packets(struct hl_device *hdev, - u64 kernel_address, u32 len, + void *kernel_address, u32 len, u64 cq_addr, u32 cq_val, u32 msi_vec, bool eb) { @@ -4298,8 +4294,7 @@ static void gaudi_add_end_of_cb_packets(struct hl_device *hdev, struct packet_msg_prot *cq_pkt; u32 tmp; - cq_pkt = (struct packet_msg_prot *) (uintptr_t) - (kernel_address + len - (sizeof(struct packet_msg_prot) * 2)); + cq_pkt = kernel_address + len - (sizeof(struct packet_msg_prot) * 2); tmp = FIELD_PREP(GAUDI_PKT_CTL_OPCODE_MASK, PACKET_MSG_PROT); tmp |= FIELD_PREP(GAUDI_PKT_CTL_MB_MASK, 1); @@ -4342,7 +4337,7 @@ static int gaudi_memset_device_memory(struct hl_device *hdev, u64 addr, if (!cb) return -EFAULT; - lin_dma_pkt = (struct packet_lin_dma *) (uintptr_t) cb->kernel_address; + lin_dma_pkt = cb->kernel_address; memset(lin_dma_pkt, 0, sizeof(*lin_dma_pkt)); cb_size = sizeof(*lin_dma_pkt); @@ -4747,7 +4742,7 @@ static void gaudi_write_pte(struct hl_device *hdev, u64 addr, u64 val) (addr - gaudi->hbm_bar_cur_addr)); } -static void gaudi_mmu_prepare_reg(struct hl_device *hdev, u64 reg, u32 asid) +void gaudi_mmu_prepare_reg(struct hl_device *hdev, u64 reg, u32 asid) { /* mask to zero the MMBP and ASID bits */ WREG32_AND(reg, ~0x7FF); @@ -4915,9 +4910,6 @@ static void gaudi_mmu_prepare(struct hl_device *hdev, u32 asid) gaudi_mmu_prepare_reg(hdev, mmMME2_ACC_WBC, asid); gaudi_mmu_prepare_reg(hdev, mmMME3_ACC_WBC, asid); - gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_ARUSER, asid); - gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_AWUSER, asid); - hdev->asic_funcs->set_clock_gating(hdev); mutex_unlock(&gaudi->clk_gate_mutex); @@ -4954,8 +4946,8 @@ static int gaudi_send_job_on_qman0(struct hl_device *hdev, cb = job->patched_cb; - fence_pkt = (struct packet_msg_prot *) (uintptr_t) (cb->kernel_address + - job->job_cb_size - sizeof(struct packet_msg_prot)); + fence_pkt = cb->kernel_address + + job->job_cb_size - sizeof(struct packet_msg_prot); tmp = FIELD_PREP(GAUDI_PKT_CTL_OPCODE_MASK, PACKET_MSG_PROT); tmp |= FIELD_PREP(GAUDI_PKT_CTL_EB_MASK, 1); @@ -6386,7 +6378,7 @@ static void gaudi_gen_signal_cb(struct hl_device *hdev, void *data, u16 sob_id) struct packet_msg_short *pkt; u32 value, ctl; - pkt = (struct packet_msg_short *) (uintptr_t) cb->kernel_address; + pkt = cb->kernel_address; memset(pkt, 0, sizeof(*pkt)); /* Inc by 1, Mode ADD */ @@ -6478,7 +6470,7 @@ static void gaudi_gen_wait_cb(struct hl_device *hdev, void *data, u16 sob_id, u16 sob_val, u16 mon_id, u32 q_idx) { struct hl_cb *cb = (struct hl_cb *) data; - void *buf = (void *) (uintptr_t) cb->kernel_address; + void *buf = cb->kernel_address; u64 monitor_base, fence_addr = 0; u32 size = 0; u16 msg_addr_offset; diff --git a/drivers/misc/habanalabs/gaudi/gaudiP.h b/drivers/misc/habanalabs/gaudi/gaudiP.h index 83ad2b0a3a61..8eb598db81b2 100644 --- a/drivers/misc/habanalabs/gaudi/gaudiP.h +++ b/drivers/misc/habanalabs/gaudi/gaudiP.h @@ -271,5 +271,6 @@ void gaudi_set_pll_profile(struct hl_device *hdev, enum hl_pll_frequency freq); int gaudi_debug_coresight(struct hl_device *hdev, void *data); void gaudi_halt_coresight(struct hl_device *hdev); int gaudi_get_clk_rate(struct hl_device *hdev, u32 *cur_clk, u32 *max_clk); +void gaudi_mmu_prepare_reg(struct hl_device *hdev, u64 reg, u32 asid); #endif /* GAUDIP_H_ */ diff --git a/drivers/misc/habanalabs/gaudi/gaudi_coresight.c b/drivers/misc/habanalabs/gaudi/gaudi_coresight.c index 881531d4d9da..3d2b0f0f4650 100644 --- a/drivers/misc/habanalabs/gaudi/gaudi_coresight.c +++ b/drivers/misc/habanalabs/gaudi/gaudi_coresight.c @@ -623,6 +623,11 @@ static int gaudi_config_etr(struct hl_device *hdev, return -EINVAL; } + gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_ARUSER, + hdev->compute_ctx->asid); + gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_AWUSER, + hdev->compute_ctx->asid); + msb = upper_32_bits(input->buffer_address) >> 8; msb &= PSOC_GLOBAL_CONF_TRACE_ADDR_MSB_MASK; WREG32(mmPSOC_GLOBAL_CONF_TRACE_ADDR, msb); diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 5db52064ed9e..235d47b2420f 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -2882,8 +2882,8 @@ static int goya_send_job_on_qman0(struct hl_device *hdev, struct hl_cs_job *job) cb = job->patched_cb; - fence_pkt = (struct packet_msg_prot *) (uintptr_t) (cb->kernel_address + - job->job_cb_size - sizeof(struct packet_msg_prot)); + fence_pkt = cb->kernel_address + + job->job_cb_size - sizeof(struct packet_msg_prot); tmp = (PACKET_MSG_PROT << GOYA_PKT_CTL_OPCODE_SHIFT) | (1 << GOYA_PKT_CTL_EB_SHIFT) | @@ -3475,8 +3475,7 @@ static int goya_validate_cb(struct hl_device *hdev, u16 pkt_size; struct goya_packet *user_pkt; - user_pkt = (struct goya_packet *) (uintptr_t) - (parser->user_cb->kernel_address + cb_parsed_length); + user_pkt = parser->user_cb->kernel_address + cb_parsed_length; pkt_id = (enum packet_id) ( (le64_to_cpu(user_pkt->header) & @@ -3713,11 +3712,9 @@ static int goya_patch_cb(struct hl_device *hdev, u32 new_pkt_size = 0; struct goya_packet *user_pkt, *kernel_pkt; - user_pkt = (struct goya_packet *) (uintptr_t) - (parser->user_cb->kernel_address + cb_parsed_length); - kernel_pkt = (struct goya_packet *) (uintptr_t) - (parser->patched_cb->kernel_address + - cb_patched_cur_length); + user_pkt = parser->user_cb->kernel_address + cb_parsed_length; + kernel_pkt = parser->patched_cb->kernel_address + + cb_patched_cur_length; pkt_id = (enum packet_id) ( (le64_to_cpu(user_pkt->header) & @@ -3841,8 +3838,8 @@ static int goya_parse_cb_mmu(struct hl_device *hdev, * The check that parser->user_cb_size <= parser->user_cb->size was done * in validate_queue_index(). */ - memcpy((void *) (uintptr_t) parser->patched_cb->kernel_address, - (void *) (uintptr_t) parser->user_cb->kernel_address, + memcpy(parser->patched_cb->kernel_address, + parser->user_cb->kernel_address, parser->user_cb_size); patched_cb_size = parser->patched_cb_size; @@ -3974,15 +3971,14 @@ int goya_cs_parser(struct hl_device *hdev, struct hl_cs_parser *parser) return goya_parse_cb_no_mmu(hdev, parser); } -void goya_add_end_of_cb_packets(struct hl_device *hdev, u64 kernel_address, +void goya_add_end_of_cb_packets(struct hl_device *hdev, void *kernel_address, u32 len, u64 cq_addr, u32 cq_val, u32 msix_vec, bool eb) { struct packet_msg_prot *cq_pkt; u32 tmp; - cq_pkt = (struct packet_msg_prot *) (uintptr_t) - (kernel_address + len - (sizeof(struct packet_msg_prot) * 2)); + cq_pkt = kernel_address + len - (sizeof(struct packet_msg_prot) * 2); tmp = (PACKET_MSG_PROT << GOYA_PKT_CTL_OPCODE_SHIFT) | (1 << GOYA_PKT_CTL_EB_SHIFT) | @@ -4746,7 +4742,7 @@ static int goya_memset_device_memory(struct hl_device *hdev, u64 addr, u64 size, if (!cb) return -ENOMEM; - lin_dma_pkt = (struct packet_lin_dma *) (uintptr_t) cb->kernel_address; + lin_dma_pkt = cb->kernel_address; do { memset(lin_dma_pkt, 0, sizeof(*lin_dma_pkt)); diff --git a/drivers/misc/habanalabs/goya/goyaP.h b/drivers/misc/habanalabs/goya/goyaP.h index 09b4006d4dc3..def86c75e035 100644 --- a/drivers/misc/habanalabs/goya/goyaP.h +++ b/drivers/misc/habanalabs/goya/goyaP.h @@ -217,7 +217,7 @@ int goya_resume(struct hl_device *hdev); void goya_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_entry); void *goya_get_events_stat(struct hl_device *hdev, bool aggregate, u32 *size); -void goya_add_end_of_cb_packets(struct hl_device *hdev, u64 kernel_address, +void goya_add_end_of_cb_packets(struct hl_device *hdev, void *kernel_address, u32 len, u64 cq_addr, u32 cq_val, u32 msix_vec, bool eb); int goya_cs_parser(struct hl_device *hdev, struct hl_cs_parser *parser); diff --git a/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h b/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h index f395721060bd..46aed13f16b1 100644 --- a/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h +++ b/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h @@ -421,7 +421,6 @@ enum axi_id { #define QM_ARB_ERR_MSG_EN_MASK (\ QM_ARB_ERR_MSG_EN_CHOISE_OVF_MASK |\ - QM_ARB_ERR_MSG_EN_CHOISE_WDT_MASK |\ QM_ARB_ERR_MSG_EN_AXI_LBW_ERR_MASK) #define PCIE_AUX_FLR_CTRL_HW_CTRL_MASK 0x1 diff --git a/drivers/misc/mei/client.h b/drivers/misc/mei/client.h index 64143d4ec758..9e08a9843bba 100644 --- a/drivers/misc/mei/client.h +++ b/drivers/misc/mei/client.h @@ -182,11 +182,11 @@ static inline u8 mei_cl_me_id(const struct mei_cl *cl) * * @cl: host client * - * Return: mtu + * Return: mtu or 0 if client is not connected */ static inline size_t mei_cl_mtu(const struct mei_cl *cl) { - return cl->me_cl->props.max_msg_length; + return cl->me_cl ? cl->me_cl->props.max_msg_length : 0; } /** diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c index 414314151d0a..acb9c81a4e45 100644 --- a/drivers/mmc/host/renesas_sdhi_core.c +++ b/drivers/mmc/host/renesas_sdhi_core.c @@ -572,17 +572,6 @@ static void renesas_sdhi_reset(struct tmio_mmc_host *host) TMIO_MASK_INIT_RCAR2); } -/* - * This is a temporary workaround! This driver used 'hw_reset' wrongly and the - * fix for that showed a regression. So, we mimic the old behaviour until the - * proper solution is found. - */ -static void renesas_sdhi_hw_reset(struct mmc_host *mmc) -{ - struct tmio_mmc_host *host = mmc_priv(mmc); - renesas_sdhi_reset(host); -} - #define SH_MOBILE_SDHI_MIN_TAP_ROW 3 static int renesas_sdhi_select_tuning(struct tmio_mmc_host *host) @@ -1020,8 +1009,6 @@ int renesas_sdhi_probe(struct platform_device *pdev, if (of_data && of_data->scc_offset) { priv->scc_ctl = host->ctl + of_data->scc_offset; host->reset = renesas_sdhi_reset; - host->ops.hw_reset = renesas_sdhi_hw_reset; - host->mmc->caps |= MMC_CAP_HW_RESET; } } @@ -1160,6 +1147,7 @@ int renesas_sdhi_remove(struct platform_device *pdev) tmio_mmc_host_remove(host); renesas_sdhi_clk_disable(host); + tmio_mmc_host_free(host); return 0; } diff --git a/drivers/mmc/host/sdhci-of-esdhc.c b/drivers/mmc/host/sdhci-of-esdhc.c index bb094459196a..ab5ab969f711 100644 --- a/drivers/mmc/host/sdhci-of-esdhc.c +++ b/drivers/mmc/host/sdhci-of-esdhc.c @@ -1324,6 +1324,8 @@ static struct soc_device_attribute soc_fixup_sdhc_clkdivs[] = { static struct soc_device_attribute soc_unreliable_pulse_detection[] = { { .family = "QorIQ LX2160A", .revision = "1.0", }, + { .family = "QorIQ LX2160A", .revision = "2.0", }, + { .family = "QorIQ LS1028A", .revision = "1.0", }, { }, }; diff --git a/drivers/mmc/host/tmio_mmc_core.c b/drivers/mmc/host/tmio_mmc_core.c index 2fce0518632d..cb4149fd12e0 100644 --- a/drivers/mmc/host/tmio_mmc_core.c +++ b/drivers/mmc/host/tmio_mmc_core.c @@ -175,6 +175,8 @@ static void tmio_mmc_reset(struct tmio_mmc_host *host) if (host->reset) host->reset(host); + tmio_mmc_abort_dma(host); + if (host->pdata->flags & TMIO_MMC_SDIO_IRQ) { sd_ctrl_write16(host, CTL_SDIO_IRQ_MASK, host->sdio_irq_mask); sd_ctrl_write16(host, CTL_TRANSACTION_CTL, 0x0001); @@ -223,8 +225,6 @@ static void tmio_mmc_reset_work(struct work_struct *work) /* Ready for new calls */ host->mrq = NULL; - - tmio_mmc_abort_dma(host); mmc_request_done(host->mmc, mrq); } @@ -927,6 +927,9 @@ static void tmio_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) switch (ios->power_mode) { case MMC_POWER_OFF: tmio_mmc_power_off(host); + /* Downgrade ensures a sane state for tuning HW (e.g. SCC) */ + if (host->mmc->ops->hs400_downgrade) + host->mmc->ops->hs400_downgrade(host->mmc); host->set_clock(host, 0); break; case MMC_POWER_UP: diff --git a/drivers/net/dsa/mv88e6xxx/devlink.c b/drivers/net/dsa/mv88e6xxx/devlink.c index 10cd1bfd81a0..ade04c036fd9 100644 --- a/drivers/net/dsa/mv88e6xxx/devlink.c +++ b/drivers/net/dsa/mv88e6xxx/devlink.c @@ -393,8 +393,10 @@ static int mv88e6xxx_region_atu_snapshot(struct devlink *dl, mv88e6xxx_reg_lock(chip); err = mv88e6xxx_fid_map(chip, fid_bitmap); - if (err) + if (err) { + kfree(table); goto out; + } while (1) { fid = find_next_bit(fid_bitmap, MV88E6XXX_N_FID, fid + 1); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index 3352dad6ca99..27308600da15 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -2124,6 +2124,9 @@ void cxgb4_inline_tx_skb(const struct sk_buff *skb, const struct sge_txq *q, void cxgb4_write_sgl(const struct sk_buff *skb, struct sge_txq *q, struct ulptx_sgl *sgl, u64 *end, unsigned int start, const dma_addr_t *addr); +void cxgb4_write_partial_sgl(const struct sk_buff *skb, struct sge_txq *q, + struct ulptx_sgl *sgl, u64 *end, + const dma_addr_t *addr, u32 start, u32 send_len); void cxgb4_ring_tx_db(struct adapter *adap, struct sge_txq *q, int n); int t4_set_vlan_acl(struct adapter *adap, unsigned int mbox, unsigned int vf, u16 vlan); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c index 0273f40b85f7..17410fe86626 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c @@ -3573,6 +3573,8 @@ static int chcr_stats_show(struct seq_file *seq, void *v) atomic64_read(&adap->ch_ktls_stats.ktls_tx_complete_pkts)); seq_printf(seq, "TX trim pkts : %20llu\n", atomic64_read(&adap->ch_ktls_stats.ktls_tx_trimmed_pkts)); + seq_printf(seq, "TX sw fallback : %20llu\n", + atomic64_read(&adap->ch_ktls_stats.ktls_tx_fallback)); while (i < MAX_NPORTS) { ktls_port = &adap->ch_ktls_stats.ktls_port[i]; seq_printf(seq, "Port %d\n", i); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index a952fe198eb9..7fd264a6d085 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -1176,6 +1176,7 @@ static u16 cxgb_select_queue(struct net_device *dev, struct sk_buff *skb, txq = netdev_pick_tx(dev, skb, sb_dev); if (xfrm_offload(skb) || is_ptp_enabled(skb, dev) || skb->encapsulation || + cxgb4_is_ktls_skb(skb) || (proto != IPPROTO_TCP && proto != IPPROTO_UDP)) txq = txq % pi->nqsets; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h index b169776ab484..1b49f2fa9b18 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h @@ -388,6 +388,7 @@ struct ch_ktls_stats_debug { atomic64_t ktls_tx_retransmit_pkts; atomic64_t ktls_tx_complete_pkts; atomic64_t ktls_tx_trimmed_pkts; + atomic64_t ktls_tx_fallback; }; #endif @@ -493,6 +494,11 @@ struct cxgb4_uld_info { #endif }; +static inline bool cxgb4_is_ktls_skb(struct sk_buff *skb) +{ + return skb->sk && tls_is_sk_tx_device_offloaded(skb->sk); +} + void cxgb4_uld_enable(struct adapter *adap); void cxgb4_register_uld(enum cxgb4_uld type, const struct cxgb4_uld_info *p); int cxgb4_unregister_uld(enum cxgb4_uld type); diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index a9e9c7ae565d..196652a114c5 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -890,6 +890,114 @@ void cxgb4_write_sgl(const struct sk_buff *skb, struct sge_txq *q, } EXPORT_SYMBOL(cxgb4_write_sgl); +/* cxgb4_write_partial_sgl - populate SGL for partial packet + * @skb: the packet + * @q: the Tx queue we are writing into + * @sgl: starting location for writing the SGL + * @end: points right after the end of the SGL + * @addr: the list of bus addresses for the SGL elements + * @start: start offset in the SKB where partial data starts + * @len: length of data from @start to send out + * + * This API will handle sending out partial data of a skb if required. + * Unlike cxgb4_write_sgl, @start can be any offset into the skb data, + * and @len will decide how much data after @start offset to send out. + */ +void cxgb4_write_partial_sgl(const struct sk_buff *skb, struct sge_txq *q, + struct ulptx_sgl *sgl, u64 *end, + const dma_addr_t *addr, u32 start, u32 len) +{ + struct ulptx_sge_pair buf[MAX_SKB_FRAGS / 2 + 1] = {0}, *to; + u32 frag_size, skb_linear_data_len = skb_headlen(skb); + struct skb_shared_info *si = skb_shinfo(skb); + u8 i = 0, frag_idx = 0, nfrags = 0; + skb_frag_t *frag; + + /* Fill the first SGL either from linear data or from partial + * frag based on @start. + */ + if (unlikely(start < skb_linear_data_len)) { + frag_size = min(len, skb_linear_data_len - start); + sgl->len0 = htonl(frag_size); + sgl->addr0 = cpu_to_be64(addr[0] + start); + len -= frag_size; + nfrags++; + } else { + start -= skb_linear_data_len; + frag = &si->frags[frag_idx]; + frag_size = skb_frag_size(frag); + /* find the first frag */ + while (start >= frag_size) { + start -= frag_size; + frag_idx++; + frag = &si->frags[frag_idx]; + frag_size = skb_frag_size(frag); + } + + frag_size = min(len, skb_frag_size(frag) - start); + sgl->len0 = cpu_to_be32(frag_size); + sgl->addr0 = cpu_to_be64(addr[frag_idx + 1] + start); + len -= frag_size; + nfrags++; + frag_idx++; + } + + /* If the entire partial data fit in one SGL, then send it out + * now. + */ + if (!len) + goto done; + + /* Most of the complexity below deals with the possibility we hit the + * end of the queue in the middle of writing the SGL. For this case + * only we create the SGL in a temporary buffer and then copy it. + */ + to = (u8 *)end > (u8 *)q->stat ? buf : sgl->sge; + + /* If the skb couldn't fit in first SGL completely, fill the + * rest of the frags in subsequent SGLs. Note that each SGL + * pair can store 2 frags. + */ + while (len) { + frag_size = min(len, skb_frag_size(&si->frags[frag_idx])); + to->len[i & 1] = cpu_to_be32(frag_size); + to->addr[i & 1] = cpu_to_be64(addr[frag_idx + 1]); + if (i && (i & 1)) + to++; + nfrags++; + frag_idx++; + i++; + len -= frag_size; + } + + /* If we ended in an odd boundary, then set the second SGL's + * length in the pair to 0. + */ + if (i & 1) + to->len[1] = cpu_to_be32(0); + + /* Copy from temporary buffer to Tx ring, in case we hit the + * end of the queue in the middle of writing the SGL. + */ + if (unlikely((u8 *)end > (u8 *)q->stat)) { + u32 part0 = (u8 *)q->stat - (u8 *)sgl->sge, part1; + + if (likely(part0)) + memcpy(sgl->sge, buf, part0); + part1 = (u8 *)end - (u8 *)q->stat; + memcpy(q->desc, (u8 *)buf + part0, part1); + end = (void *)q->desc + part1; + } + + /* 0-pad to multiple of 16 */ + if ((uintptr_t)end & 8) + *end = 0; +done: + sgl->cmd_nsge = htonl(ULPTX_CMD_V(ULP_TX_SC_DSGL) | + ULPTX_NSGE_V(nfrags)); +} +EXPORT_SYMBOL(cxgb4_write_partial_sgl); + /* This function copies 64 byte coalesced work request to * memory mapped BAR2 space. For coalesced WR SGE fetches * data from the FIFO instead of from Host. @@ -1422,7 +1530,8 @@ static netdev_tx_t cxgb4_eth_xmit(struct sk_buff *skb, struct net_device *dev) #endif /* CHELSIO_IPSEC_INLINE */ #if IS_ENABLED(CONFIG_CHELSIO_TLS_DEVICE) - if (skb->decrypted) + if (cxgb4_is_ktls_skb(skb) && + (skb->len - (skb_transport_offset(skb) + tcp_hdrlen(skb)))) return adap->uld[CXGB4_ULD_KTLS].tx_handler(skb, dev); #endif /* CHELSIO_TLS_DEVICE */ diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c index 5195f692f14d..c24485c0d512 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c @@ -14,6 +14,50 @@ static LIST_HEAD(uld_ctx_list); static DEFINE_MUTEX(dev_mutex); +/* chcr_get_nfrags_to_send: get the remaining nfrags after start offset + * @skb: skb + * @start: start offset. + * @len: how much data to send after @start + */ +static int chcr_get_nfrags_to_send(struct sk_buff *skb, u32 start, u32 len) +{ + struct skb_shared_info *si = skb_shinfo(skb); + u32 frag_size, skb_linear_data_len = skb_headlen(skb); + u8 nfrags = 0, frag_idx = 0; + skb_frag_t *frag; + + /* if its a linear skb then return 1 */ + if (!skb_is_nonlinear(skb)) + return 1; + + if (unlikely(start < skb_linear_data_len)) { + frag_size = min(len, skb_linear_data_len - start); + start = 0; + } else { + start -= skb_linear_data_len; + + frag = &si->frags[frag_idx]; + frag_size = skb_frag_size(frag); + while (start >= frag_size) { + start -= frag_size; + frag_idx++; + frag = &si->frags[frag_idx]; + frag_size = skb_frag_size(frag); + } + frag_size = min(len, skb_frag_size(frag) - start); + } + len -= frag_size; + nfrags++; + + while (len) { + frag_size = min(len, skb_frag_size(&si->frags[frag_idx])); + len -= frag_size; + nfrags++; + frag_idx++; + } + return nfrags; +} + static int chcr_init_tcb_fields(struct chcr_ktls_info *tx_info); /* * chcr_ktls_save_keys: calculate and save crypto keys. @@ -689,7 +733,8 @@ static int chcr_ktls_cpl_set_tcb_rpl(struct adapter *adap, unsigned char *input) } static void *__chcr_write_cpl_set_tcb_ulp(struct chcr_ktls_info *tx_info, - u32 tid, void *pos, u16 word, u64 mask, + u32 tid, void *pos, u16 word, + struct sge_eth_txq *q, u64 mask, u64 val, u32 reply) { struct cpl_set_tcb_field_core *cpl; @@ -698,7 +743,10 @@ static void *__chcr_write_cpl_set_tcb_ulp(struct chcr_ktls_info *tx_info, /* ULP_TXPKT */ txpkt = pos; - txpkt->cmd_dest = htonl(ULPTX_CMD_V(ULP_TX_PKT) | ULP_TXPKT_DEST_V(0)); + txpkt->cmd_dest = htonl(ULPTX_CMD_V(ULP_TX_PKT) | + ULP_TXPKT_CHANNELID_V(tx_info->port_id) | + ULP_TXPKT_FID_V(q->q.cntxt_id) | + ULP_TXPKT_RO_F); txpkt->len = htonl(DIV_ROUND_UP(CHCR_SET_TCB_FIELD_LEN, 16)); /* ULPTX_IDATA sub-command */ @@ -753,7 +801,7 @@ static void *chcr_write_cpl_set_tcb_ulp(struct chcr_ktls_info *tx_info, } else { u8 buf[48] = {0}; - __chcr_write_cpl_set_tcb_ulp(tx_info, tid, buf, word, + __chcr_write_cpl_set_tcb_ulp(tx_info, tid, buf, word, q, mask, val, reply); return chcr_copy_to_txd(buf, &q->q, pos, @@ -761,7 +809,7 @@ static void *chcr_write_cpl_set_tcb_ulp(struct chcr_ktls_info *tx_info, } } - pos = __chcr_write_cpl_set_tcb_ulp(tx_info, tid, pos, word, + pos = __chcr_write_cpl_set_tcb_ulp(tx_info, tid, pos, word, q, mask, val, reply); /* check again if we are at the end of the queue */ @@ -783,11 +831,11 @@ static void *chcr_write_cpl_set_tcb_ulp(struct chcr_ktls_info *tx_info, */ static int chcr_ktls_xmit_tcb_cpls(struct chcr_ktls_info *tx_info, struct sge_eth_txq *q, u64 tcp_seq, - u64 tcp_ack, u64 tcp_win) + u64 tcp_ack, u64 tcp_win, bool offset) { bool first_wr = ((tx_info->prev_ack == 0) && (tx_info->prev_win == 0)); struct ch_ktls_port_stats_debug *port_stats; - u32 len, cpl = 0, ndesc, wr_len; + u32 len, cpl = 0, ndesc, wr_len, wr_mid = 0; struct fw_ulptx_wr *wr; int credits; void *pos; @@ -803,6 +851,11 @@ static int chcr_ktls_xmit_tcb_cpls(struct chcr_ktls_info *tx_info, return NETDEV_TX_BUSY; } + if (unlikely(credits < ETHTXQ_STOP_THRES)) { + chcr_eth_txq_stop(q); + wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F; + } + pos = &q->q.desc[q->q.pidx]; /* make space for WR, we'll fill it later when we know all the cpls * being sent out and have complete length. @@ -818,7 +871,7 @@ static int chcr_ktls_xmit_tcb_cpls(struct chcr_ktls_info *tx_info, cpl++; } /* reset snd una if it's a re-transmit pkt */ - if (tcp_seq != tx_info->prev_seq) { + if (tcp_seq != tx_info->prev_seq || offset) { /* reset snd_una */ port_stats = &tx_info->adap->ch_ktls_stats.ktls_port[tx_info->port_id]; @@ -827,7 +880,8 @@ static int chcr_ktls_xmit_tcb_cpls(struct chcr_ktls_info *tx_info, TCB_SND_UNA_RAW_V (TCB_SND_UNA_RAW_M), TCB_SND_UNA_RAW_V(0), 0); - atomic64_inc(&port_stats->ktls_tx_ooo); + if (tcp_seq != tx_info->prev_seq) + atomic64_inc(&port_stats->ktls_tx_ooo); cpl++; } /* update ack */ @@ -856,7 +910,8 @@ static int chcr_ktls_xmit_tcb_cpls(struct chcr_ktls_info *tx_info, wr->op_to_compl = htonl(FW_WR_OP_V(FW_ULPTX_WR)); wr->cookie = 0; /* fill len in wr field */ - wr->flowid_len16 = htonl(FW_WR_LEN16_V(DIV_ROUND_UP(len, 16))); + wr->flowid_len16 = htonl(wr_mid | + FW_WR_LEN16_V(DIV_ROUND_UP(len, 16))); ndesc = DIV_ROUND_UP(len, 64); chcr_txq_advance(&q->q, ndesc); @@ -866,34 +921,14 @@ static int chcr_ktls_xmit_tcb_cpls(struct chcr_ktls_info *tx_info, } /* - * chcr_ktls_skb_copy - * @nskb - new skb where the frags to be added. - * @skb - old skb from which frags will be copied. - */ -static void chcr_ktls_skb_copy(struct sk_buff *skb, struct sk_buff *nskb) -{ - int i; - - for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - skb_shinfo(nskb)->frags[i] = skb_shinfo(skb)->frags[i]; - __skb_frag_ref(&skb_shinfo(nskb)->frags[i]); - } - - skb_shinfo(nskb)->nr_frags = skb_shinfo(skb)->nr_frags; - nskb->len += skb->data_len; - nskb->data_len = skb->data_len; - nskb->truesize += skb->data_len; -} - -/* * chcr_ktls_get_tx_flits * returns number of flits to be sent out, it includes key context length, WR * size and skb fragments. */ static unsigned int -chcr_ktls_get_tx_flits(const struct sk_buff *skb, unsigned int key_ctx_len) +chcr_ktls_get_tx_flits(u32 nr_frags, unsigned int key_ctx_len) { - return chcr_sgl_len(skb_shinfo(skb)->nr_frags) + + return chcr_sgl_len(nr_frags) + DIV_ROUND_UP(key_ctx_len + CHCR_KTLS_WR_SIZE, 8); } @@ -957,8 +992,10 @@ chcr_ktls_write_tcp_options(struct chcr_ktls_info *tx_info, struct sk_buff *skb, struct tcphdr *tcp; int len16, pktlen; struct iphdr *ip; + u32 wr_mid = 0; int credits; u8 buf[150]; + u64 cntrl1; void *pos; iplen = skb_network_header_len(skb); @@ -967,7 +1004,7 @@ chcr_ktls_write_tcp_options(struct chcr_ktls_info *tx_info, struct sk_buff *skb, /* packet length = eth hdr len + ip hdr len + tcp hdr len * (including options). */ - pktlen = skb->len - skb->data_len; + pktlen = skb_transport_offset(skb) + tcp_hdrlen(skb); ctrl = sizeof(*cpl) + pktlen; len16 = DIV_ROUND_UP(sizeof(*wr) + ctrl, 16); @@ -980,6 +1017,11 @@ chcr_ktls_write_tcp_options(struct chcr_ktls_info *tx_info, struct sk_buff *skb, return NETDEV_TX_BUSY; } + if (unlikely(credits < ETHTXQ_STOP_THRES)) { + chcr_eth_txq_stop(q); + wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F; + } + pos = &q->q.desc[q->q.pidx]; wr = pos; @@ -987,7 +1029,7 @@ chcr_ktls_write_tcp_options(struct chcr_ktls_info *tx_info, struct sk_buff *skb, wr->op_immdlen = htonl(FW_WR_OP_V(FW_ETH_TX_PKT_WR) | FW_WR_IMMDLEN_V(ctrl)); - wr->equiq_to_len16 = htonl(FW_WR_LEN16_V(len16)); + wr->equiq_to_len16 = htonl(wr_mid | FW_WR_LEN16_V(len16)); wr->r3 = 0; cpl = (void *)(wr + 1); @@ -997,22 +1039,28 @@ chcr_ktls_write_tcp_options(struct chcr_ktls_info *tx_info, struct sk_buff *skb, TXPKT_PF_V(tx_info->adap->pf)); cpl->pack = 0; cpl->len = htons(pktlen); - /* checksum offload */ - cpl->ctrl1 = 0; - - pos = cpl + 1; memcpy(buf, skb->data, pktlen); if (tx_info->ip_family == AF_INET) { /* we need to correct ip header len */ ip = (struct iphdr *)(buf + maclen); ip->tot_len = htons(pktlen - maclen); + cntrl1 = TXPKT_CSUM_TYPE_V(TX_CSUM_TCPIP); #if IS_ENABLED(CONFIG_IPV6) } else { ip6 = (struct ipv6hdr *)(buf + maclen); ip6->payload_len = htons(pktlen - maclen - iplen); + cntrl1 = TXPKT_CSUM_TYPE_V(TX_CSUM_TCPIP6); #endif } + + cntrl1 |= T6_TXPKT_ETHHDR_LEN_V(maclen - ETH_HLEN) | + TXPKT_IPHDR_LEN_V(iplen); + /* checksum offload */ + cpl->ctrl1 = cpu_to_be64(cntrl1); + + pos = cpl + 1; + /* now take care of the tcp header, if fin is not set then clear push * bit as well, and if fin is set, it will be sent at the last so we * need to update the tcp sequence number as per the last packet. @@ -1031,71 +1079,6 @@ chcr_ktls_write_tcp_options(struct chcr_ktls_info *tx_info, struct sk_buff *skb, return 0; } -/* chcr_ktls_skb_shift - Shifts request length paged data from skb to another. - * @tgt- buffer into which tail data gets added - * @skb- buffer from which the paged data comes from - * @shiftlen- shift up to this many bytes - */ -static int chcr_ktls_skb_shift(struct sk_buff *tgt, struct sk_buff *skb, - int shiftlen) -{ - skb_frag_t *fragfrom, *fragto; - int from, to, todo; - - WARN_ON(shiftlen > skb->data_len); - - todo = shiftlen; - from = 0; - to = 0; - fragfrom = &skb_shinfo(skb)->frags[from]; - - while ((todo > 0) && (from < skb_shinfo(skb)->nr_frags)) { - fragfrom = &skb_shinfo(skb)->frags[from]; - fragto = &skb_shinfo(tgt)->frags[to]; - - if (todo >= skb_frag_size(fragfrom)) { - *fragto = *fragfrom; - todo -= skb_frag_size(fragfrom); - from++; - to++; - - } else { - __skb_frag_ref(fragfrom); - skb_frag_page_copy(fragto, fragfrom); - skb_frag_off_copy(fragto, fragfrom); - skb_frag_size_set(fragto, todo); - - skb_frag_off_add(fragfrom, todo); - skb_frag_size_sub(fragfrom, todo); - todo = 0; - - to++; - break; - } - } - - /* Ready to "commit" this state change to tgt */ - skb_shinfo(tgt)->nr_frags = to; - - /* Reposition in the original skb */ - to = 0; - while (from < skb_shinfo(skb)->nr_frags) - skb_shinfo(skb)->frags[to++] = skb_shinfo(skb)->frags[from++]; - - skb_shinfo(skb)->nr_frags = to; - - WARN_ON(todo > 0 && !skb_shinfo(skb)->nr_frags); - - skb->len -= shiftlen; - skb->data_len -= shiftlen; - skb->truesize -= shiftlen; - tgt->len += shiftlen; - tgt->data_len += shiftlen; - tgt->truesize += shiftlen; - - return shiftlen; -} - /* * chcr_ktls_xmit_wr_complete: This sends out the complete record. If an skb * received has partial end part of the record, send out the complete record, so @@ -1111,6 +1094,8 @@ static int chcr_ktls_skb_shift(struct sk_buff *tgt, struct sk_buff *skb, static int chcr_ktls_xmit_wr_complete(struct sk_buff *skb, struct chcr_ktls_info *tx_info, struct sge_eth_txq *q, u32 tcp_seq, + bool is_last_wr, u32 data_len, + u32 skb_offset, u32 nfrags, bool tcp_push, u32 mss) { u32 len16, wr_mid = 0, flits = 0, ndesc, cipher_start; @@ -1126,7 +1111,7 @@ static int chcr_ktls_xmit_wr_complete(struct sk_buff *skb, u64 *end; /* get the number of flits required */ - flits = chcr_ktls_get_tx_flits(skb, tx_info->key_ctx_len); + flits = chcr_ktls_get_tx_flits(nfrags, tx_info->key_ctx_len); /* number of descriptors */ ndesc = chcr_flits_to_desc(flits); /* check if enough credits available */ @@ -1155,6 +1140,9 @@ static int chcr_ktls_xmit_wr_complete(struct sk_buff *skb, return NETDEV_TX_BUSY; } + if (!is_last_wr) + skb_get(skb); + pos = &q->q.desc[q->q.pidx]; end = (u64 *)pos + flits; /* FW_ULPTX_WR */ @@ -1187,7 +1175,7 @@ static int chcr_ktls_xmit_wr_complete(struct sk_buff *skb, CPL_TX_SEC_PDU_CPLLEN_V(CHCR_CPL_TX_SEC_PDU_LEN_64BIT) | CPL_TX_SEC_PDU_PLACEHOLDER_V(1) | CPL_TX_SEC_PDU_IVINSRTOFST_V(TLS_HEADER_SIZE + 1)); - cpl->pldlen = htonl(skb->data_len); + cpl->pldlen = htonl(data_len); /* encryption should start after tls header size + iv size */ cipher_start = TLS_HEADER_SIZE + tx_info->iv_size + 1; @@ -1229,7 +1217,7 @@ static int chcr_ktls_xmit_wr_complete(struct sk_buff *skb, /* CPL_TX_DATA */ tx_data = (void *)pos; OPCODE_TID(tx_data) = htonl(MK_OPCODE_TID(CPL_TX_DATA, tx_info->tid)); - tx_data->len = htonl(TX_DATA_MSS_V(mss) | TX_LENGTH_V(skb->data_len)); + tx_data->len = htonl(TX_DATA_MSS_V(mss) | TX_LENGTH_V(data_len)); tx_data->rsvd = htonl(tcp_seq); @@ -1249,8 +1237,8 @@ static int chcr_ktls_xmit_wr_complete(struct sk_buff *skb, } /* send the complete packet except the header */ - cxgb4_write_sgl(skb, &q->q, pos, end, skb->len - skb->data_len, - sgl_sdesc->addr); + cxgb4_write_partial_sgl(skb, &q->q, pos, end, sgl_sdesc->addr, + skb_offset, data_len); sgl_sdesc->skb = skb; chcr_txq_advance(&q->q, ndesc); @@ -1282,10 +1270,11 @@ static int chcr_ktls_xmit_wr_short(struct sk_buff *skb, struct sge_eth_txq *q, u32 tcp_seq, bool tcp_push, u32 mss, u32 tls_rec_offset, u8 *prior_data, - u32 prior_data_len) + u32 prior_data_len, u32 data_len, + u32 skb_offset) { + u32 len16, wr_mid = 0, cipher_start, nfrags; struct adapter *adap = tx_info->adap; - u32 len16, wr_mid = 0, cipher_start; unsigned int flits = 0, ndesc; int credits, left, last_desc; struct tx_sw_desc *sgl_sdesc; @@ -1298,10 +1287,11 @@ static int chcr_ktls_xmit_wr_short(struct sk_buff *skb, void *pos; u64 *end; + nfrags = chcr_get_nfrags_to_send(skb, skb_offset, data_len); /* get the number of flits required, it's a partial record so 2 flits * (AES_BLOCK_SIZE) will be added. */ - flits = chcr_ktls_get_tx_flits(skb, tx_info->key_ctx_len) + 2; + flits = chcr_ktls_get_tx_flits(nfrags, tx_info->key_ctx_len) + 2; /* get the correct 8 byte IV of this record */ iv_record = cpu_to_be64(tx_info->iv + tx_info->record_no); /* If it's a middle record and not 16 byte aligned to run AES CTR, need @@ -1373,7 +1363,7 @@ static int chcr_ktls_xmit_wr_short(struct sk_buff *skb, htonl(CPL_TX_SEC_PDU_OPCODE_V(CPL_TX_SEC_PDU) | CPL_TX_SEC_PDU_CPLLEN_V(CHCR_CPL_TX_SEC_PDU_LEN_64BIT) | CPL_TX_SEC_PDU_IVINSRTOFST_V(1)); - cpl->pldlen = htonl(skb->data_len + AES_BLOCK_LEN + prior_data_len); + cpl->pldlen = htonl(data_len + AES_BLOCK_LEN + prior_data_len); cpl->aadstart_cipherstop_hi = htonl(CPL_TX_SEC_PDU_CIPHERSTART_V(cipher_start)); cpl->cipherstop_lo_authinsert = 0; @@ -1404,7 +1394,7 @@ static int chcr_ktls_xmit_wr_short(struct sk_buff *skb, tx_data = (void *)pos; OPCODE_TID(tx_data) = htonl(MK_OPCODE_TID(CPL_TX_DATA, tx_info->tid)); tx_data->len = htonl(TX_DATA_MSS_V(mss) | - TX_LENGTH_V(skb->data_len + prior_data_len)); + TX_LENGTH_V(data_len + prior_data_len)); tx_data->rsvd = htonl(tcp_seq); tx_data->flags = htonl(TX_BYPASS_F); if (tcp_push) @@ -1437,8 +1427,8 @@ static int chcr_ktls_xmit_wr_short(struct sk_buff *skb, if (prior_data_len) pos = chcr_copy_to_txd(prior_data, &q->q, pos, 16); /* send the complete packet except the header */ - cxgb4_write_sgl(skb, &q->q, pos, end, skb->len - skb->data_len, - sgl_sdesc->addr); + cxgb4_write_partial_sgl(skb, &q->q, pos, end, sgl_sdesc->addr, + skb_offset, data_len); sgl_sdesc->skb = skb; chcr_txq_advance(&q->q, ndesc); @@ -1466,6 +1456,7 @@ static int chcr_ktls_tx_plaintxt(struct chcr_ktls_info *tx_info, struct sk_buff *skb, u32 tcp_seq, u32 mss, bool tcp_push, struct sge_eth_txq *q, u32 port_id, u8 *prior_data, + u32 data_len, u32 skb_offset, u32 prior_data_len) { int credits, left, len16, last_desc; @@ -1475,14 +1466,16 @@ static int chcr_ktls_tx_plaintxt(struct chcr_ktls_info *tx_info, struct ulptx_idata *idata; struct ulp_txpkt *ulptx; struct fw_ulptx_wr *wr; - u32 wr_mid = 0; + u32 wr_mid = 0, nfrags; void *pos; u64 *end; flits = DIV_ROUND_UP(CHCR_PLAIN_TX_DATA_LEN, 8); - flits += chcr_sgl_len(skb_shinfo(skb)->nr_frags); + nfrags = chcr_get_nfrags_to_send(skb, skb_offset, data_len); + flits += chcr_sgl_len(nfrags); if (prior_data_len) flits += 2; + /* WR will need len16 */ len16 = DIV_ROUND_UP(flits, 2); /* check how many descriptors needed */ @@ -1535,7 +1528,7 @@ static int chcr_ktls_tx_plaintxt(struct chcr_ktls_info *tx_info, tx_data = (struct cpl_tx_data *)(idata + 1); OPCODE_TID(tx_data) = htonl(MK_OPCODE_TID(CPL_TX_DATA, tx_info->tid)); tx_data->len = htonl(TX_DATA_MSS_V(mss) | - TX_LENGTH_V(skb->data_len + prior_data_len)); + TX_LENGTH_V(data_len + prior_data_len)); /* set tcp seq number */ tx_data->rsvd = htonl(tcp_seq); tx_data->flags = htonl(TX_BYPASS_F); @@ -1559,8 +1552,8 @@ static int chcr_ktls_tx_plaintxt(struct chcr_ktls_info *tx_info, end = pos + left; } /* send the complete packet including the header */ - cxgb4_write_sgl(skb, &q->q, pos, end, skb->len - skb->data_len, - sgl_sdesc->addr); + cxgb4_write_partial_sgl(skb, &q->q, pos, end, sgl_sdesc->addr, + skb_offset, data_len); sgl_sdesc->skb = skb; chcr_txq_advance(&q->q, ndesc); @@ -1568,12 +1561,96 @@ static int chcr_ktls_tx_plaintxt(struct chcr_ktls_info *tx_info, return 0; } +static int chcr_ktls_tunnel_pkt(struct chcr_ktls_info *tx_info, + struct sk_buff *skb, + struct sge_eth_txq *q) +{ + u32 ctrl, iplen, maclen, wr_mid = 0, len16; + struct tx_sw_desc *sgl_sdesc; + struct fw_eth_tx_pkt_wr *wr; + struct cpl_tx_pkt_core *cpl; + unsigned int flits, ndesc; + int credits, last_desc; + u64 cntrl1, *end; + void *pos; + + ctrl = sizeof(*cpl); + flits = DIV_ROUND_UP(sizeof(*wr) + ctrl, 8); + + flits += chcr_sgl_len(skb_shinfo(skb)->nr_frags + 1); + len16 = DIV_ROUND_UP(flits, 2); + /* check how many descriptors needed */ + ndesc = DIV_ROUND_UP(flits, 8); + + credits = chcr_txq_avail(&q->q) - ndesc; + if (unlikely(credits < 0)) { + chcr_eth_txq_stop(q); + return -ENOMEM; + } + + if (unlikely(credits < ETHTXQ_STOP_THRES)) { + chcr_eth_txq_stop(q); + wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F; + } + + last_desc = q->q.pidx + ndesc - 1; + if (last_desc >= q->q.size) + last_desc -= q->q.size; + sgl_sdesc = &q->q.sdesc[last_desc]; + + if (unlikely(cxgb4_map_skb(tx_info->adap->pdev_dev, skb, + sgl_sdesc->addr) < 0)) { + memset(sgl_sdesc->addr, 0, sizeof(sgl_sdesc->addr)); + q->mapping_err++; + return -ENOMEM; + } + + iplen = skb_network_header_len(skb); + maclen = skb_mac_header_len(skb); + + pos = &q->q.desc[q->q.pidx]; + end = (u64 *)pos + flits; + wr = pos; + + /* Firmware work request header */ + wr->op_immdlen = htonl(FW_WR_OP_V(FW_ETH_TX_PKT_WR) | + FW_WR_IMMDLEN_V(ctrl)); + + wr->equiq_to_len16 = htonl(wr_mid | FW_WR_LEN16_V(len16)); + wr->r3 = 0; + + cpl = (void *)(wr + 1); + + /* CPL header */ + cpl->ctrl0 = htonl(TXPKT_OPCODE_V(CPL_TX_PKT) | + TXPKT_INTF_V(tx_info->tx_chan) | + TXPKT_PF_V(tx_info->adap->pf)); + cpl->pack = 0; + cntrl1 = TXPKT_CSUM_TYPE_V(tx_info->ip_family == AF_INET ? + TX_CSUM_TCPIP : TX_CSUM_TCPIP6); + cntrl1 |= T6_TXPKT_ETHHDR_LEN_V(maclen - ETH_HLEN) | + TXPKT_IPHDR_LEN_V(iplen); + /* checksum offload */ + cpl->ctrl1 = cpu_to_be64(cntrl1); + cpl->len = htons(skb->len); + + pos = cpl + 1; + + cxgb4_write_sgl(skb, &q->q, pos, end, 0, sgl_sdesc->addr); + sgl_sdesc->skb = skb; + chcr_txq_advance(&q->q, ndesc); + cxgb4_ring_tx_db(tx_info->adap, &q->q, ndesc); + return 0; +} + /* * chcr_ktls_copy_record_in_skb * @nskb - new skb where the frags to be added. + * @skb - old skb, to copy socket and destructor details. * @record - specific record which has complete 16k record in frags. */ static void chcr_ktls_copy_record_in_skb(struct sk_buff *nskb, + struct sk_buff *skb, struct tls_record_info *record) { int i = 0; @@ -1588,6 +1665,9 @@ static void chcr_ktls_copy_record_in_skb(struct sk_buff *nskb, nskb->data_len = record->len; nskb->len += record->len; nskb->truesize += record->len; + nskb->sk = skb->sk; + nskb->destructor = skb->destructor; + refcount_add(nskb->truesize, &nskb->sk->sk_wmem_alloc); } /* @@ -1659,7 +1739,7 @@ static int chcr_end_part_handler(struct chcr_ktls_info *tx_info, struct sk_buff *skb, struct tls_record_info *record, u32 tcp_seq, int mss, bool tcp_push_no_fin, - struct sge_eth_txq *q, + struct sge_eth_txq *q, u32 skb_offset, u32 tls_end_offset, bool last_wr) { struct sk_buff *nskb = NULL; @@ -1668,30 +1748,37 @@ static int chcr_end_part_handler(struct chcr_ktls_info *tx_info, nskb = skb; atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_complete_pkts); } else { - dev_kfree_skb_any(skb); - - nskb = alloc_skb(0, GFP_KERNEL); - if (!nskb) + nskb = alloc_skb(0, GFP_ATOMIC); + if (!nskb) { + dev_kfree_skb_any(skb); return NETDEV_TX_BUSY; + } + /* copy complete record in skb */ - chcr_ktls_copy_record_in_skb(nskb, record); + chcr_ktls_copy_record_in_skb(nskb, skb, record); /* packet is being sent from the beginning, update the tcp_seq * accordingly. */ tcp_seq = tls_record_start_seq(record); - /* reset snd una, so the middle record won't send the already - * sent part. - */ - if (chcr_ktls_update_snd_una(tx_info, q)) - goto out; + /* reset skb offset */ + skb_offset = 0; + + if (last_wr) + dev_kfree_skb_any(skb); + + last_wr = true; + atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_end_pkts); } if (chcr_ktls_xmit_wr_complete(nskb, tx_info, q, tcp_seq, + last_wr, record->len, skb_offset, + record->num_frags, (last_wr && tcp_push_no_fin), mss)) { goto out; } + tx_info->prev_seq = record->end_seq; return 0; out: dev_kfree_skb_any(nskb); @@ -1723,41 +1810,47 @@ static int chcr_short_record_handler(struct chcr_ktls_info *tx_info, struct sk_buff *skb, struct tls_record_info *record, u32 tcp_seq, int mss, bool tcp_push_no_fin, + u32 data_len, u32 skb_offset, struct sge_eth_txq *q, u32 tls_end_offset) { u32 tls_rec_offset = tcp_seq - tls_record_start_seq(record); u8 prior_data[16] = {0}; u32 prior_data_len = 0; - u32 data_len; /* check if the skb is ending in middle of tag/HASH, its a big * trouble, send the packet before the HASH. */ - int remaining_record = tls_end_offset - skb->data_len; + int remaining_record = tls_end_offset - data_len; if (remaining_record > 0 && remaining_record < TLS_CIPHER_AES_GCM_128_TAG_SIZE) { - int trimmed_len = skb->data_len - - (TLS_CIPHER_AES_GCM_128_TAG_SIZE - remaining_record); - struct sk_buff *tmp_skb = NULL; - /* don't process the pkt if it is only a partial tag */ - if (skb->data_len < TLS_CIPHER_AES_GCM_128_TAG_SIZE) - goto out; + int trimmed_len = 0; - WARN_ON(trimmed_len > skb->data_len); + if (tls_end_offset > TLS_CIPHER_AES_GCM_128_TAG_SIZE) + trimmed_len = data_len - + (TLS_CIPHER_AES_GCM_128_TAG_SIZE - + remaining_record); + if (!trimmed_len) + return FALLBACK; - /* shift to those many bytes */ - tmp_skb = alloc_skb(0, GFP_KERNEL); - if (unlikely(!tmp_skb)) - goto out; + WARN_ON(trimmed_len > data_len); - chcr_ktls_skb_shift(tmp_skb, skb, trimmed_len); - /* free the last trimmed portion */ - dev_kfree_skb_any(skb); - skb = tmp_skb; + data_len = trimmed_len; atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_trimmed_pkts); } - data_len = skb->data_len; + + /* check if it is only the header part. */ + if (tls_rec_offset + data_len <= (TLS_HEADER_SIZE + tx_info->iv_size)) { + if (chcr_ktls_tx_plaintxt(tx_info, skb, tcp_seq, mss, + tcp_push_no_fin, q, + tx_info->port_id, prior_data, + data_len, skb_offset, prior_data_len)) + goto out; + + tx_info->prev_seq = tcp_seq + data_len; + return 0; + } + /* check if the middle record's start point is 16 byte aligned. CTR * needs 16 byte aligned start point to start encryption. */ @@ -1818,9 +1911,6 @@ static int chcr_short_record_handler(struct chcr_ktls_info *tx_info, } /* reset tcp_seq as per the prior_data_required len */ tcp_seq -= prior_data_len; - /* include prio_data_len for further calculation. - */ - data_len += prior_data_len; } /* reset snd una, so the middle record won't send the already * sent part. @@ -1829,37 +1919,54 @@ static int chcr_short_record_handler(struct chcr_ktls_info *tx_info, goto out; atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_middle_pkts); } else { - /* Else means, its a partial first part of the record. Check if - * its only the header, don't need to send for encryption then. - */ - if (data_len <= TLS_HEADER_SIZE + tx_info->iv_size) { - if (chcr_ktls_tx_plaintxt(tx_info, skb, tcp_seq, mss, - tcp_push_no_fin, q, - tx_info->port_id, - prior_data, - prior_data_len)) { - goto out; - } - return 0; - } atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_start_pkts); } if (chcr_ktls_xmit_wr_short(skb, tx_info, q, tcp_seq, tcp_push_no_fin, mss, tls_rec_offset, prior_data, - prior_data_len)) { + prior_data_len, data_len, skb_offset)) { goto out; } + tx_info->prev_seq = tcp_seq + data_len + prior_data_len; return 0; out: dev_kfree_skb_any(skb); return NETDEV_TX_BUSY; } +static int chcr_ktls_sw_fallback(struct sk_buff *skb, + struct chcr_ktls_info *tx_info, + struct sge_eth_txq *q) +{ + u32 data_len, skb_offset; + struct sk_buff *nskb; + struct tcphdr *th; + + nskb = tls_encrypt_skb(skb); + + if (!nskb) + return 0; + + th = tcp_hdr(nskb); + skb_offset = skb_transport_offset(nskb) + tcp_hdrlen(nskb); + data_len = nskb->len - skb_offset; + skb_tx_timestamp(nskb); + + if (chcr_ktls_tunnel_pkt(tx_info, nskb, q)) + goto out; + + tx_info->prev_seq = ntohl(th->seq) + data_len; + atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_fallback); + return 0; +out: + dev_kfree_skb_any(nskb); + return 0; +} /* nic tls TX handler */ static int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev) { + u32 tls_end_offset, tcp_seq, skb_data_len, skb_offset; struct ch_ktls_port_stats_debug *port_stats; struct chcr_ktls_ofld_ctx_tx *tx_ctx; struct ch_ktls_stats_debug *stats; @@ -1867,20 +1974,17 @@ static int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev) int data_len, qidx, ret = 0, mss; struct tls_record_info *record; struct chcr_ktls_info *tx_info; - u32 tls_end_offset, tcp_seq; struct tls_context *tls_ctx; - struct sk_buff *local_skb; struct sge_eth_txq *q; struct adapter *adap; unsigned long flags; tcp_seq = ntohl(th->seq); + skb_offset = skb_transport_offset(skb) + tcp_hdrlen(skb); + skb_data_len = skb->len - skb_offset; + data_len = skb_data_len; - mss = skb_is_gso(skb) ? skb_shinfo(skb)->gso_size : skb->data_len; - - /* check if we haven't set it for ktls offload */ - if (!skb->sk || !tls_is_sk_tx_device_offloaded(skb->sk)) - goto out; + mss = skb_is_gso(skb) ? skb_shinfo(skb)->gso_size : data_len; tls_ctx = tls_get_ctx(skb->sk); if (unlikely(tls_ctx->netdev != dev)) @@ -1892,14 +1996,6 @@ static int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev) if (unlikely(!tx_info)) goto out; - /* don't touch the original skb, make a new skb to extract each records - * and send them separately. - */ - local_skb = alloc_skb(0, GFP_KERNEL); - - if (unlikely(!local_skb)) - return NETDEV_TX_BUSY; - adap = tx_info->adap; stats = &adap->ch_ktls_stats; port_stats = &stats->ktls_port[tx_info->port_id]; @@ -1914,20 +2010,7 @@ static int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev) if (ret) return NETDEV_TX_BUSY; } - /* update tcb */ - ret = chcr_ktls_xmit_tcb_cpls(tx_info, q, ntohl(th->seq), - ntohl(th->ack_seq), - ntohs(th->window)); - if (ret) { - dev_kfree_skb_any(local_skb); - return NETDEV_TX_BUSY; - } - /* copy skb contents into local skb */ - chcr_ktls_skb_copy(skb, local_skb); - - /* go through the skb and send only one record at a time. */ - data_len = skb->data_len; /* TCP segments can be in received either complete or partial. * chcr_end_part_handler will handle cases if complete record or end * part of the record is received. Incase of partial end part of record, @@ -1952,10 +2035,64 @@ static int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev) goto out; } + tls_end_offset = record->end_seq - tcp_seq; + + pr_debug("seq 0x%x, end_seq 0x%x prev_seq 0x%x, datalen 0x%x\n", + tcp_seq, record->end_seq, tx_info->prev_seq, data_len); + /* update tcb for the skb */ + if (skb_data_len == data_len) { + u32 tx_max = tcp_seq; + + if (!tls_record_is_start_marker(record) && + tls_end_offset < TLS_CIPHER_AES_GCM_128_TAG_SIZE) + tx_max = record->end_seq - + TLS_CIPHER_AES_GCM_128_TAG_SIZE; + + ret = chcr_ktls_xmit_tcb_cpls(tx_info, q, tx_max, + ntohl(th->ack_seq), + ntohs(th->window), + tls_end_offset != + record->len); + if (ret) { + spin_unlock_irqrestore(&tx_ctx->base.lock, + flags); + goto out; + } + + if (th->fin) + skb_get(skb); + } + if (unlikely(tls_record_is_start_marker(record))) { - spin_unlock_irqrestore(&tx_ctx->base.lock, flags); atomic64_inc(&port_stats->ktls_tx_skip_no_sync_data); - goto out; + /* If tls_end_offset < data_len, means there is some + * data after start marker, which needs encryption, send + * plaintext first and take skb refcount. else send out + * complete pkt as plaintext. + */ + if (tls_end_offset < data_len) + skb_get(skb); + else + tls_end_offset = data_len; + + ret = chcr_ktls_tx_plaintxt(tx_info, skb, tcp_seq, mss, + (!th->fin && th->psh), q, + tx_info->port_id, NULL, + tls_end_offset, skb_offset, + 0); + + spin_unlock_irqrestore(&tx_ctx->base.lock, flags); + if (ret) { + /* free the refcount taken earlier */ + if (tls_end_offset < data_len) + dev_kfree_skb_any(skb); + goto out; + } + + data_len -= tls_end_offset; + tcp_seq = record->end_seq; + skb_offset += tls_end_offset; + continue; } /* increase page reference count of the record, so that there @@ -1967,73 +2104,64 @@ static int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev) /* lock cleared */ spin_unlock_irqrestore(&tx_ctx->base.lock, flags); - tls_end_offset = record->end_seq - tcp_seq; - pr_debug("seq 0x%x, end_seq 0x%x prev_seq 0x%x, datalen 0x%x\n", - tcp_seq, record->end_seq, tx_info->prev_seq, data_len); /* if a tls record is finishing in this SKB */ if (tls_end_offset <= data_len) { - struct sk_buff *nskb = NULL; - - if (tls_end_offset < data_len) { - nskb = alloc_skb(0, GFP_KERNEL); - if (unlikely(!nskb)) { - ret = -ENOMEM; - goto clear_ref; - } - - chcr_ktls_skb_shift(nskb, local_skb, - tls_end_offset); - } else { - /* its the only record in this skb, directly - * point it. - */ - nskb = local_skb; - } - ret = chcr_end_part_handler(tx_info, nskb, record, + ret = chcr_end_part_handler(tx_info, skb, record, tcp_seq, mss, (!th->fin && th->psh), q, + skb_offset, tls_end_offset, - (nskb == local_skb)); - - if (ret && nskb != local_skb) - dev_kfree_skb_any(local_skb); + skb_offset + + tls_end_offset == skb->len); data_len -= tls_end_offset; /* tcp_seq increment is required to handle next record. */ tcp_seq += tls_end_offset; + skb_offset += tls_end_offset; } else { - ret = chcr_short_record_handler(tx_info, local_skb, + ret = chcr_short_record_handler(tx_info, skb, record, tcp_seq, mss, (!th->fin && th->psh), + data_len, skb_offset, q, tls_end_offset); data_len = 0; } -clear_ref: + /* clear the frag ref count which increased locally before */ for (i = 0; i < record->num_frags; i++) { /* clear the frag ref count */ __skb_frag_unref(&record->frags[i]); } /* if any failure, come out from the loop. */ - if (ret) - goto out; + if (ret) { + if (th->fin) + dev_kfree_skb_any(skb); + + if (ret == FALLBACK) + return chcr_ktls_sw_fallback(skb, tx_info, q); + + return NETDEV_TX_OK; + } + /* length should never be less than 0 */ WARN_ON(data_len < 0); } while (data_len > 0); - tx_info->prev_seq = ntohl(th->seq) + skb->data_len; atomic64_inc(&port_stats->ktls_tx_encrypted_packets); - atomic64_add(skb->data_len, &port_stats->ktls_tx_encrypted_bytes); + atomic64_add(skb_data_len, &port_stats->ktls_tx_encrypted_bytes); /* tcp finish is set, send a separate tcp msg including all the options * as well. */ - if (th->fin) + if (th->fin) { chcr_ktls_write_tcp_options(tx_info, skb, q, tx_info->tx_chan); + dev_kfree_skb_any(skb); + } + return NETDEV_TX_OK; out: dev_kfree_skb_any(skb); return NETDEV_TX_OK; diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.h b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.h index c1651b1431a0..18b3b1f02415 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.h +++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.h @@ -26,6 +26,7 @@ #define CHCR_KTLS_WR_SIZE (CHCR_PLAIN_TX_DATA_LEN +\ sizeof(struct cpl_tx_sec_pdu)) +#define FALLBACK 35 enum ch_ktls_open_state { CH_KTLS_OPEN_SUCCESS = 0, diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index c96e2f2d4cba..4919d22d7b6b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -2713,6 +2713,10 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg) spin_unlock_bh(&vsi->mac_filter_hash_lock); goto error_param; } + if (is_valid_ether_addr(al->list[i].addr) && + is_zero_ether_addr(vf->default_lan_addr.addr)) + ether_addr_copy(vf->default_lan_addr.addr, + al->list[i].addr); } } spin_unlock_bh(&vsi->mac_filter_hash_lock); @@ -2740,6 +2744,7 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg) { struct virtchnl_ether_addr_list *al = (struct virtchnl_ether_addr_list *)msg; + bool was_unimac_deleted = false; struct i40e_pf *pf = vf->pf; struct i40e_vsi *vsi = NULL; i40e_status ret = 0; @@ -2759,6 +2764,8 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg) ret = I40E_ERR_INVALID_MAC_ADDR; goto error_param; } + if (ether_addr_equal(al->list[i].addr, vf->default_lan_addr.addr)) + was_unimac_deleted = true; } vsi = pf->vsi[vf->lan_vsi_idx]; @@ -2779,10 +2786,25 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg) dev_err(&pf->pdev->dev, "Unable to program VF %d MAC filters, error %d\n", vf->vf_id, ret); + if (vf->trusted && was_unimac_deleted) { + struct i40e_mac_filter *f; + struct hlist_node *h; + u8 *macaddr = NULL; + int bkt; + + /* set last unicast mac address as default */ + spin_lock_bh(&vsi->mac_filter_hash_lock); + hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) { + if (is_valid_ether_addr(f->macaddr)) + macaddr = f->macaddr; + } + if (macaddr) + ether_addr_copy(vf->default_lan_addr.addr, macaddr); + spin_unlock_bh(&vsi->mac_filter_hash_lock); + } error_param: /* send the response to the VF */ - return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_DEL_ETH_ADDR, - ret); + return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_DEL_ETH_ADDR, ret); } /** diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 6acede0acdca..567fd67e900e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -281,8 +281,8 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) unsigned int total_rx_bytes = 0, total_rx_packets = 0; u16 cleaned_count = I40E_DESC_UNUSED(rx_ring); unsigned int xdp_res, xdp_xmit = 0; + bool failure = false; struct sk_buff *skb; - bool failure; while (likely(total_rx_packets < (unsigned int)budget)) { union i40e_rx_desc *rx_desc; diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 9112dff075cf..b673ac1199bb 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -3891,21 +3891,23 @@ static int igc_change_mtu(struct net_device *netdev, int new_mtu) } /** - * igc_get_stats - Get System Network Statistics + * igc_get_stats64 - Get System Network Statistics * @netdev: network interface device structure + * @stats: rtnl_link_stats64 pointer * * Returns the address of the device statistics structure. * The statistics are updated here and also from the timer callback. */ -static struct net_device_stats *igc_get_stats(struct net_device *netdev) +static void igc_get_stats64(struct net_device *netdev, + struct rtnl_link_stats64 *stats) { struct igc_adapter *adapter = netdev_priv(netdev); + spin_lock(&adapter->stats64_lock); if (!test_bit(__IGC_RESETTING, &adapter->state)) igc_update_stats(adapter); - - /* only return the current stats */ - return &netdev->stats; + memcpy(stats, &adapter->stats64, sizeof(*stats)); + spin_unlock(&adapter->stats64_lock); } static netdev_features_t igc_fix_features(struct net_device *netdev, @@ -4855,7 +4857,7 @@ static const struct net_device_ops igc_netdev_ops = { .ndo_set_rx_mode = igc_set_rx_mode, .ndo_set_mac_address = igc_set_mac, .ndo_change_mtu = igc_change_mtu, - .ndo_get_stats = igc_get_stats, + .ndo_get_stats64 = igc_get_stats64, .ndo_fix_features = igc_fix_features, .ndo_set_features = igc_set_features, .ndo_features_check = igc_features_check, diff --git a/drivers/net/ethernet/marvell/prestera/Kconfig b/drivers/net/ethernet/marvell/prestera/Kconfig index b1fcc44f566a..b6f20e2034c6 100644 --- a/drivers/net/ethernet/marvell/prestera/Kconfig +++ b/drivers/net/ethernet/marvell/prestera/Kconfig @@ -6,6 +6,7 @@ config PRESTERA tristate "Marvell Prestera Switch ASICs support" depends on NET_SWITCHDEV && VLAN_8021Q + depends on BRIDGE || BRIDGE=n select NET_DEVLINK help This driver supports Marvell Prestera Switch ASICs family. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c index e36e505d38ad..d29af7b9c695 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c @@ -107,12 +107,16 @@ void mlx5e_rep_update_flows(struct mlx5e_priv *priv, mlx5e_tc_encap_flows_del(priv, e, &flow_list); if (neigh_connected && !(e->flags & MLX5_ENCAP_ENTRY_VALID)) { + struct net_device *route_dev; + ether_addr_copy(e->h_dest, ha); ether_addr_copy(eth->h_dest, ha); /* Update the encap source mac, in case that we delete * the flows when encap source mac changed. */ - ether_addr_copy(eth->h_source, e->route_dev->dev_addr); + route_dev = __dev_get_by_index(dev_net(priv->netdev), e->route_dev_ifindex); + if (route_dev) + ether_addr_copy(eth->h_source, route_dev->dev_addr); mlx5e_tc_encap_flows_add(priv, e, &flow_list); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index 7cce85faa16f..90930e54b6f2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -77,13 +77,13 @@ static int get_route_and_out_devs(struct mlx5e_priv *priv, return 0; } -static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv, - struct net_device *mirred_dev, - struct net_device **out_dev, - struct net_device **route_dev, - struct flowi4 *fl4, - struct neighbour **out_n, - u8 *out_ttl) +static int mlx5e_route_lookup_ipv4_get(struct mlx5e_priv *priv, + struct net_device *mirred_dev, + struct net_device **out_dev, + struct net_device **route_dev, + struct flowi4 *fl4, + struct neighbour **out_n, + u8 *out_ttl) { struct neighbour *n; struct rtable *rt; @@ -117,18 +117,28 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv, ip_rt_put(rt); return ret; } + dev_hold(*route_dev); if (!(*out_ttl)) *out_ttl = ip4_dst_hoplimit(&rt->dst); n = dst_neigh_lookup(&rt->dst, &fl4->daddr); ip_rt_put(rt); - if (!n) + if (!n) { + dev_put(*route_dev); return -ENOMEM; + } *out_n = n; return 0; } +static void mlx5e_route_lookup_ipv4_put(struct net_device *route_dev, + struct neighbour *n) +{ + neigh_release(n); + dev_put(route_dev); +} + static const char *mlx5e_netdev_kind(struct net_device *dev) { if (dev->rtnl_link_ops) @@ -193,8 +203,8 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, fl4.saddr = tun_key->u.ipv4.src; ttl = tun_key->ttl; - err = mlx5e_route_lookup_ipv4(priv, mirred_dev, &out_dev, &route_dev, - &fl4, &n, &ttl); + err = mlx5e_route_lookup_ipv4_get(priv, mirred_dev, &out_dev, &route_dev, + &fl4, &n, &ttl); if (err) return err; @@ -223,7 +233,7 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, e->m_neigh.family = n->ops->family; memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len); e->out_dev = out_dev; - e->route_dev = route_dev; + e->route_dev_ifindex = route_dev->ifindex; /* It's important to add the neigh to the hash table before checking * the neigh validity state. So if we'll get a notification, in case the @@ -278,7 +288,7 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, e->flags |= MLX5_ENCAP_ENTRY_VALID; mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev)); - neigh_release(n); + mlx5e_route_lookup_ipv4_put(route_dev, n); return err; destroy_neigh_entry: @@ -286,18 +296,18 @@ destroy_neigh_entry: free_encap: kfree(encap_header); release_neigh: - neigh_release(n); + mlx5e_route_lookup_ipv4_put(route_dev, n); return err; } #if IS_ENABLED(CONFIG_INET) && IS_ENABLED(CONFIG_IPV6) -static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv, - struct net_device *mirred_dev, - struct net_device **out_dev, - struct net_device **route_dev, - struct flowi6 *fl6, - struct neighbour **out_n, - u8 *out_ttl) +static int mlx5e_route_lookup_ipv6_get(struct mlx5e_priv *priv, + struct net_device *mirred_dev, + struct net_device **out_dev, + struct net_device **route_dev, + struct flowi6 *fl6, + struct neighbour **out_n, + u8 *out_ttl) { struct dst_entry *dst; struct neighbour *n; @@ -318,15 +328,25 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv, return ret; } + dev_hold(*route_dev); n = dst_neigh_lookup(dst, &fl6->daddr); dst_release(dst); - if (!n) + if (!n) { + dev_put(*route_dev); return -ENOMEM; + } *out_n = n; return 0; } +static void mlx5e_route_lookup_ipv6_put(struct net_device *route_dev, + struct neighbour *n) +{ + neigh_release(n); + dev_put(route_dev); +} + int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, struct net_device *mirred_dev, struct mlx5e_encap_entry *e) @@ -348,8 +368,8 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, fl6.daddr = tun_key->u.ipv6.dst; fl6.saddr = tun_key->u.ipv6.src; - err = mlx5e_route_lookup_ipv6(priv, mirred_dev, &out_dev, &route_dev, - &fl6, &n, &ttl); + err = mlx5e_route_lookup_ipv6_get(priv, mirred_dev, &out_dev, &route_dev, + &fl6, &n, &ttl); if (err) return err; @@ -378,7 +398,7 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, e->m_neigh.family = n->ops->family; memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len); e->out_dev = out_dev; - e->route_dev = route_dev; + e->route_dev_ifindex = route_dev->ifindex; /* It's importent to add the neigh to the hash table before checking * the neigh validity state. So if we'll get a notification, in case the @@ -433,7 +453,7 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, e->flags |= MLX5_ENCAP_ENTRY_VALID; mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev)); - neigh_release(n); + mlx5e_route_lookup_ipv6_put(route_dev, n); return err; destroy_neigh_entry: @@ -441,7 +461,7 @@ destroy_neigh_entry: free_encap: kfree(encap_header); release_neigh: - neigh_release(n); + mlx5e_route_lookup_ipv6_put(route_dev, n); return err; } #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c index 4e574ac73019..be3465ba38ca 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c @@ -122,9 +122,9 @@ void mlx5e_activate_xsk(struct mlx5e_channel *c) set_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state); /* TX queue is created active. */ - spin_lock(&c->async_icosq_lock); + spin_lock_bh(&c->async_icosq_lock); mlx5e_trigger_irq(&c->async_icosq); - spin_unlock(&c->async_icosq_lock); + spin_unlock_bh(&c->async_icosq_lock); } void mlx5e_deactivate_xsk(struct mlx5e_channel *c) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c index fb671a457129..8e96260fce1d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c @@ -36,9 +36,9 @@ int mlx5e_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags) if (test_and_set_bit(MLX5E_SQ_STATE_PENDING_XSK_TX, &c->async_icosq.state)) return 0; - spin_lock(&c->async_icosq_lock); + spin_lock_bh(&c->async_icosq_lock); mlx5e_trigger_irq(&c->async_icosq); - spin_unlock(&c->async_icosq_lock); + spin_unlock_bh(&c->async_icosq_lock); } return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c index ccaccb9fc2f7..7f6221b8b1f7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c @@ -188,7 +188,7 @@ static int post_rx_param_wqes(struct mlx5e_channel *c, err = 0; sq = &c->async_icosq; - spin_lock(&c->async_icosq_lock); + spin_lock_bh(&c->async_icosq_lock); cseg = post_static_params(sq, priv_rx); if (IS_ERR(cseg)) @@ -199,7 +199,7 @@ static int post_rx_param_wqes(struct mlx5e_channel *c, mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, cseg); unlock: - spin_unlock(&c->async_icosq_lock); + spin_unlock_bh(&c->async_icosq_lock); return err; @@ -265,10 +265,10 @@ resync_post_get_progress_params(struct mlx5e_icosq *sq, BUILD_BUG_ON(MLX5E_KTLS_GET_PROGRESS_WQEBBS != 1); - spin_lock(&sq->channel->async_icosq_lock); + spin_lock_bh(&sq->channel->async_icosq_lock); if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, 1))) { - spin_unlock(&sq->channel->async_icosq_lock); + spin_unlock_bh(&sq->channel->async_icosq_lock); err = -ENOSPC; goto err_dma_unmap; } @@ -299,7 +299,7 @@ resync_post_get_progress_params(struct mlx5e_icosq *sq, icosq_fill_wi(sq, pi, &wi); sq->pc++; mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, cseg); - spin_unlock(&sq->channel->async_icosq_lock); + spin_unlock_bh(&sq->channel->async_icosq_lock); return 0; @@ -360,7 +360,7 @@ static int resync_handle_seq_match(struct mlx5e_ktls_offload_context_rx *priv_rx err = 0; sq = &c->async_icosq; - spin_lock(&c->async_icosq_lock); + spin_lock_bh(&c->async_icosq_lock); cseg = post_static_params(sq, priv_rx); if (IS_ERR(cseg)) { @@ -372,7 +372,7 @@ static int resync_handle_seq_match(struct mlx5e_ktls_offload_context_rx *priv_rx mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, cseg); priv_rx->stats->tls_resync_res_ok++; unlock: - spin_unlock(&c->async_icosq_lock); + spin_unlock_bh(&c->async_icosq_lock); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index b3f02aac7f26..ebce97921e03 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -5253,6 +5253,7 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv) mlx5e_disable_async_events(priv); mlx5_lag_remove(mdev); + mlx5_vxlan_reset_to_default(mdev->vxlan); } int mlx5e_update_nic_rx(struct mlx5e_priv *priv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h index 9020d1419bcf..8932c387d46a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h @@ -186,7 +186,7 @@ struct mlx5e_encap_entry { unsigned char h_dest[ETH_ALEN]; /* destination eth addr */ struct net_device *out_dev; - struct net_device *route_dev; + int route_dev_ifindex; struct mlx5e_tc_tunnel *tunnel; int reformat_type; u8 flags; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 599f5b5ebc97..6628a0197b4e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -1584,7 +1584,7 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) } while ((++work_done < budget) && (cqe = mlx5_cqwq_get_cqe(cqwq))); out: - if (rq->xdp_prog) + if (rcu_access_pointer(rq->xdp_prog)) mlx5e_xdp_rx_poll_complete(rq); mlx5_cqwq_update_db_record(cqwq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index e3a968e9e2a0..2e2fa0440032 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -4658,6 +4658,7 @@ __mlx5e_add_fdb_flow(struct mlx5e_priv *priv, return flow; err_free: + dealloc_mod_hdr_actions(&parse_attr->mod_hdr_acts); mlx5e_flow_put(priv, flow); out: return ERR_PTR(err); @@ -4802,6 +4803,7 @@ mlx5e_add_nic_flow(struct mlx5e_priv *priv, return 0; err_free: + dealloc_mod_hdr_actions(&parse_attr->mod_hdr_acts); mlx5e_flow_put(priv, flow); out: return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 6e6a9a563992..e8e6294c7cca 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1902,8 +1902,6 @@ int mlx5_devlink_port_function_hw_addr_get(struct devlink *devlink, ether_addr_copy(hw_addr, vport->info.mac); *hw_addr_len = ETH_ALEN; err = 0; - } else { - NL_SET_ERR_MSG_MOD(extack, "Eswitch vport is disabled"); } mutex_unlock(&esw->state_lock); return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 16091838bfcf..325a5b0d6829 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -2010,10 +2010,11 @@ void mlx5_del_flow_rules(struct mlx5_flow_handle *handle) down_write_ref_node(&fte->node, false); for (i = handle->num_rules - 1; i >= 0; i--) tree_remove_node(&handle->rule[i]->node, true); - if (fte->modify_mask && fte->dests_size) { - modify_fte(fte); + if (fte->dests_size) { + if (fte->modify_mask) + modify_fte(fte); up_write_ref_node(&fte->node, false); - } else { + } else if (list_empty(&fte->node.children)) { del_hw_fte(&fte->node); /* Avoid double call to del_hw_fte */ fte->node.del_hw_func = NULL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c index 3315afe2f8dc..38084400ee8f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c @@ -168,6 +168,17 @@ struct mlx5_vxlan *mlx5_vxlan_create(struct mlx5_core_dev *mdev) void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan) { + if (!mlx5_vxlan_allowed(vxlan)) + return; + + mlx5_vxlan_del_port(vxlan, IANA_VXLAN_UDP_PORT); + WARN_ON(!hash_empty(vxlan->htable)); + + kfree(vxlan); +} + +void mlx5_vxlan_reset_to_default(struct mlx5_vxlan *vxlan) +{ struct mlx5_vxlan_port *vxlanp; struct hlist_node *tmp; int bkt; @@ -175,12 +186,12 @@ void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan) if (!mlx5_vxlan_allowed(vxlan)) return; - /* Lockless since we are the only hash table consumers*/ hash_for_each_safe(vxlan->htable, bkt, tmp, vxlanp, hlist) { - hash_del(&vxlanp->hlist); - mlx5_vxlan_core_del_port_cmd(vxlan->mdev, vxlanp->udp_port); - kfree(vxlanp); + /* Don't delete default UDP port added by the HW. + * Remove only user configured ports + */ + if (vxlanp->udp_port == IANA_VXLAN_UDP_PORT) + continue; + mlx5_vxlan_del_port(vxlan, vxlanp->udp_port); } - - kfree(vxlan); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h index ec766529f49b..34ef662da35e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h @@ -56,6 +56,7 @@ void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan); int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port); int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port); bool mlx5_vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 port); +void mlx5_vxlan_reset_to_default(struct mlx5_vxlan *vxlan); #else static inline struct mlx5_vxlan* mlx5_vxlan_create(struct mlx5_core_dev *mdev) { return ERR_PTR(-EOPNOTSUPP); } @@ -63,6 +64,7 @@ static inline void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan) { return; } static inline int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port) { return -EOPNOTSUPP; } static inline int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port) { return -EOPNOTSUPP; } static inline bool mlx5_vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 port) { return false; } +static inline void mlx5_vxlan_reset_to_default(struct mlx5_vxlan *vxlan) { return; } #endif #endif /* __MLX5_VXLAN_H__ */ diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index a1938842f828..e2c99d909247 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -674,14 +674,12 @@ clean_up: static int lan743x_dp_write(struct lan743x_adapter *adapter, u32 select, u32 addr, u32 length, u32 *buf) { - int ret = -EIO; u32 dp_sel; int i; - mutex_lock(&adapter->dp_lock); if (lan743x_csr_wait_for_bit(adapter, DP_SEL, DP_SEL_DPRDY_, 1, 40, 100, 100)) - goto unlock; + return -EIO; dp_sel = lan743x_csr_read(adapter, DP_SEL); dp_sel &= ~DP_SEL_MASK_; dp_sel |= select; @@ -693,13 +691,10 @@ static int lan743x_dp_write(struct lan743x_adapter *adapter, lan743x_csr_write(adapter, DP_CMD, DP_CMD_WRITE_); if (lan743x_csr_wait_for_bit(adapter, DP_SEL, DP_SEL_DPRDY_, 1, 40, 100, 100)) - goto unlock; + return -EIO; } - ret = 0; -unlock: - mutex_unlock(&adapter->dp_lock); - return ret; + return 0; } static u32 lan743x_mac_mii_access(u16 id, u16 index, int read) @@ -1019,16 +1014,16 @@ static void lan743x_phy_close(struct lan743x_adapter *adapter) static int lan743x_phy_open(struct lan743x_adapter *adapter) { struct lan743x_phy *phy = &adapter->phy; + struct phy_device *phydev = NULL; struct device_node *phynode; - struct phy_device *phydev; struct net_device *netdev; int ret = -EIO; netdev = adapter->netdev; phynode = of_node_get(adapter->pdev->dev.of_node); - adapter->phy_mode = PHY_INTERFACE_MODE_GMII; if (phynode) { + /* try devicetree phy, or fixed link */ of_get_phy_mode(phynode, &adapter->phy_mode); if (of_phy_is_fixed_link(phynode)) { @@ -1044,13 +1039,15 @@ static int lan743x_phy_open(struct lan743x_adapter *adapter) lan743x_phy_link_status_change, 0, adapter->phy_mode); of_node_put(phynode); - if (!phydev) - goto return_error; - } else { + } + + if (!phydev) { + /* try internal phy */ phydev = phy_find_first(adapter->mdiobus); if (!phydev) goto return_error; + adapter->phy_mode = PHY_INTERFACE_MODE_GMII; ret = phy_connect_direct(netdev, phydev, lan743x_phy_link_status_change, adapter->phy_mode); @@ -2733,7 +2730,6 @@ static int lan743x_hardware_init(struct lan743x_adapter *adapter, adapter->intr.irq = adapter->pdev->irq; lan743x_csr_write(adapter, INT_EN_CLR, 0xFFFFFFFF); - mutex_init(&adapter->dp_lock); ret = lan743x_gpio_init(adapter); if (ret) diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h index c61a40411317..a536f4a4994d 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.h +++ b/drivers/net/ethernet/microchip/lan743x_main.h @@ -712,9 +712,6 @@ struct lan743x_adapter { struct lan743x_csr csr; struct lan743x_intr intr; - /* lock, used to prevent concurrent access to data port */ - struct mutex dp_lock; - struct lan743x_gpio gpio; struct lan743x_ptp ptp; diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 7766d73823eb..85d9c3e30c69 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -4163,7 +4163,8 @@ static bool rtl8169_tso_csum_v2(struct rtl8169_private *tp, opts[1] |= transport_offset << TCPHO_SHIFT; } else { if (unlikely(skb->len < ETH_ZLEN && rtl_test_hw_pad_bug(tp))) - return !eth_skb_pad(skb); + /* eth_skb_pad would free the skb on error */ + return !__skb_put_padto(skb, ETH_ZLEN, false); } return true; @@ -4342,18 +4343,9 @@ static netdev_features_t rtl8169_features_check(struct sk_buff *skb, rtl_chip_supports_csum_v2(tp)) features &= ~NETIF_F_ALL_TSO; } else if (skb->ip_summed == CHECKSUM_PARTIAL) { - if (skb->len < ETH_ZLEN) { - switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_11: - case RTL_GIGA_MAC_VER_12: - case RTL_GIGA_MAC_VER_17: - case RTL_GIGA_MAC_VER_34: - features &= ~NETIF_F_CSUM_MASK; - break; - default: - break; - } - } + /* work around hw bug on some chip versions */ + if (skb->len < ETH_ZLEN) + features &= ~NETIF_F_CSUM_MASK; if (transport_offset > TCPHO_MAX && rtl_chip_supports_csum_v2(tp)) diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index fb1db713b7fb..575580d3ffe0 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -551,6 +551,8 @@ static struct phy_driver realtek_drvs[] = { { PHY_ID_MATCH_EXACT(0x00008201), .name = "RTL8201CP Ethernet", + .read_page = rtl821x_read_page, + .write_page = rtl821x_write_page, }, { PHY_ID_MATCH_EXACT(0x001cc816), .name = "RTL8201F Fast Ethernet", diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 60c1aadece89..f2793ffde191 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -608,8 +608,7 @@ static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev) return ret; } -static int vrf_finish_direct(struct net *net, struct sock *sk, - struct sk_buff *skb) +static void vrf_finish_direct(struct sk_buff *skb) { struct net_device *vrf_dev = skb->dev; @@ -628,7 +627,8 @@ static int vrf_finish_direct(struct net *net, struct sock *sk, skb_pull(skb, ETH_HLEN); } - return 1; + /* reset skb device */ + nf_reset_ct(skb); } #if IS_ENABLED(CONFIG_IPV6) @@ -707,15 +707,41 @@ static struct sk_buff *vrf_ip6_out_redirect(struct net_device *vrf_dev, return skb; } +static int vrf_output6_direct_finish(struct net *net, struct sock *sk, + struct sk_buff *skb) +{ + vrf_finish_direct(skb); + + return vrf_ip6_local_out(net, sk, skb); +} + static int vrf_output6_direct(struct net *net, struct sock *sk, struct sk_buff *skb) { + int err = 1; + skb->protocol = htons(ETH_P_IPV6); - return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, - net, sk, skb, NULL, skb->dev, - vrf_finish_direct, - !(IPCB(skb)->flags & IPSKB_REROUTED)); + if (!(IPCB(skb)->flags & IPSKB_REROUTED)) + err = nf_hook(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, sk, skb, + NULL, skb->dev, vrf_output6_direct_finish); + + if (likely(err == 1)) + vrf_finish_direct(skb); + + return err; +} + +static int vrf_ip6_out_direct_finish(struct net *net, struct sock *sk, + struct sk_buff *skb) +{ + int err; + + err = vrf_output6_direct(net, sk, skb); + if (likely(err == 1)) + err = vrf_ip6_local_out(net, sk, skb); + + return err; } static struct sk_buff *vrf_ip6_out_direct(struct net_device *vrf_dev, @@ -728,18 +754,15 @@ static struct sk_buff *vrf_ip6_out_direct(struct net_device *vrf_dev, skb->dev = vrf_dev; err = nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, - skb, NULL, vrf_dev, vrf_output6_direct); + skb, NULL, vrf_dev, vrf_ip6_out_direct_finish); if (likely(err == 1)) err = vrf_output6_direct(net, sk, skb); - /* reset skb device */ if (likely(err == 1)) - nf_reset_ct(skb); - else - skb = NULL; + return skb; - return skb; + return NULL; } static struct sk_buff *vrf_ip6_out(struct net_device *vrf_dev, @@ -919,15 +942,41 @@ static struct sk_buff *vrf_ip_out_redirect(struct net_device *vrf_dev, return skb; } +static int vrf_output_direct_finish(struct net *net, struct sock *sk, + struct sk_buff *skb) +{ + vrf_finish_direct(skb); + + return vrf_ip_local_out(net, sk, skb); +} + static int vrf_output_direct(struct net *net, struct sock *sk, struct sk_buff *skb) { + int err = 1; + skb->protocol = htons(ETH_P_IP); - return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, - net, sk, skb, NULL, skb->dev, - vrf_finish_direct, - !(IPCB(skb)->flags & IPSKB_REROUTED)); + if (!(IPCB(skb)->flags & IPSKB_REROUTED)) + err = nf_hook(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, skb, + NULL, skb->dev, vrf_output_direct_finish); + + if (likely(err == 1)) + vrf_finish_direct(skb); + + return err; +} + +static int vrf_ip_out_direct_finish(struct net *net, struct sock *sk, + struct sk_buff *skb) +{ + int err; + + err = vrf_output_direct(net, sk, skb); + if (likely(err == 1)) + err = vrf_ip_local_out(net, sk, skb); + + return err; } static struct sk_buff *vrf_ip_out_direct(struct net_device *vrf_dev, @@ -940,18 +989,15 @@ static struct sk_buff *vrf_ip_out_direct(struct net_device *vrf_dev, skb->dev = vrf_dev; err = nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk, - skb, NULL, vrf_dev, vrf_output_direct); + skb, NULL, vrf_dev, vrf_ip_out_direct_finish); if (likely(err == 1)) err = vrf_output_direct(net, sk, skb); - /* reset skb device */ if (likely(err == 1)) - nf_reset_ct(skb); - else - skb = NULL; + return skb; - return skb; + return NULL; } static struct sk_buff *vrf_ip_out(struct net_device *vrf_dev, diff --git a/drivers/net/wan/cosa.c b/drivers/net/wan/cosa.c index f8aed0696d77..2369ca250cd6 100644 --- a/drivers/net/wan/cosa.c +++ b/drivers/net/wan/cosa.c @@ -889,6 +889,7 @@ static ssize_t cosa_write(struct file *file, chan->tx_status = 1; spin_unlock_irqrestore(&cosa->lock, flags); up(&chan->wsem); + kfree(kbuf); return -ERESTARTSYS; } } diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 40ca71b29bb9..9b01afcb7777 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2060,8 +2060,6 @@ static void nvme_update_disk_info(struct gendisk *disk, if (id->nsattr & NVME_NS_ATTR_RO) set_disk_ro(disk, true); - else - set_disk_ro(disk, false); } static inline bool nvme_first_scan(struct gendisk *disk) diff --git a/drivers/of/address.c b/drivers/of/address.c index eb9ab4f1e80b..1c3257a2d4e3 100644 --- a/drivers/of/address.c +++ b/drivers/of/address.c @@ -1034,11 +1034,13 @@ out: */ bool of_dma_is_coherent(struct device_node *np) { - struct device_node *node = of_node_get(np); + struct device_node *node; if (IS_ENABLED(CONFIG_OF_DMA_DEFAULT_COHERENT)) return true; + node = of_node_get(np); + while (node) { if (of_property_read_bool(node, "dma-coherent")) { of_node_put(node); diff --git a/drivers/pinctrl/aspeed/pinctrl-aspeed.c b/drivers/pinctrl/aspeed/pinctrl-aspeed.c index 6a94eaecf638..d6b849552a1e 100644 --- a/drivers/pinctrl/aspeed/pinctrl-aspeed.c +++ b/drivers/pinctrl/aspeed/pinctrl-aspeed.c @@ -286,13 +286,14 @@ int aspeed_pinmux_set_mux(struct pinctrl_dev *pctldev, unsigned int function, static bool aspeed_expr_is_gpio(const struct aspeed_sig_expr *expr) { /* - * The signal type is GPIO if the signal name has "GPIO" as a prefix. + * The signal type is GPIO if the signal name has "GPI" as a prefix. * strncmp (rather than strcmp) is used to implement the prefix * requirement. * - * expr->signal might look like "GPIOT3" in the GPIO case. + * expr->signal might look like "GPIOB1" in the GPIO case. + * expr->signal might look like "GPIT0" in the GPI case. */ - return strncmp(expr->signal, "GPIO", 4) == 0; + return strncmp(expr->signal, "GPI", 3) == 0; } static bool aspeed_gpio_in_exprs(const struct aspeed_sig_expr **exprs) diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c index 154ce3f908cd..1c10ab184783 100644 --- a/drivers/pinctrl/intel/pinctrl-intel.c +++ b/drivers/pinctrl/intel/pinctrl-intel.c @@ -62,10 +62,10 @@ #define PADCFG1_TERM_UP BIT(13) #define PADCFG1_TERM_SHIFT 10 #define PADCFG1_TERM_MASK GENMASK(12, 10) -#define PADCFG1_TERM_20K 4 -#define PADCFG1_TERM_2K 3 -#define PADCFG1_TERM_5K 2 -#define PADCFG1_TERM_1K 1 +#define PADCFG1_TERM_20K BIT(2) +#define PADCFG1_TERM_5K BIT(1) +#define PADCFG1_TERM_1K BIT(0) +#define PADCFG1_TERM_833 (BIT(1) | BIT(0)) #define PADCFG2 0x008 #define PADCFG2_DEBEN BIT(0) @@ -549,12 +549,12 @@ static int intel_config_get_pull(struct intel_pinctrl *pctrl, unsigned int pin, return -EINVAL; switch (term) { + case PADCFG1_TERM_833: + *arg = 833; + break; case PADCFG1_TERM_1K: *arg = 1000; break; - case PADCFG1_TERM_2K: - *arg = 2000; - break; case PADCFG1_TERM_5K: *arg = 5000; break; @@ -570,6 +570,11 @@ static int intel_config_get_pull(struct intel_pinctrl *pctrl, unsigned int pin, return -EINVAL; switch (term) { + case PADCFG1_TERM_833: + if (!(community->features & PINCTRL_FEATURE_1K_PD)) + return -EINVAL; + *arg = 833; + break; case PADCFG1_TERM_1K: if (!(community->features & PINCTRL_FEATURE_1K_PD)) return -EINVAL; @@ -678,6 +683,10 @@ static int intel_config_set_pull(struct intel_pinctrl *pctrl, unsigned int pin, value |= PADCFG1_TERM_UP; + /* Set default strength value in case none is given */ + if (arg == 1) + arg = 5000; + switch (arg) { case 20000: value |= PADCFG1_TERM_20K << PADCFG1_TERM_SHIFT; @@ -685,12 +694,12 @@ static int intel_config_set_pull(struct intel_pinctrl *pctrl, unsigned int pin, case 5000: value |= PADCFG1_TERM_5K << PADCFG1_TERM_SHIFT; break; - case 2000: - value |= PADCFG1_TERM_2K << PADCFG1_TERM_SHIFT; - break; case 1000: value |= PADCFG1_TERM_1K << PADCFG1_TERM_SHIFT; break; + case 833: + value |= PADCFG1_TERM_833 << PADCFG1_TERM_SHIFT; + break; default: ret = -EINVAL; } @@ -700,6 +709,10 @@ static int intel_config_set_pull(struct intel_pinctrl *pctrl, unsigned int pin, case PIN_CONFIG_BIAS_PULL_DOWN: value &= ~(PADCFG1_TERM_UP | PADCFG1_TERM_MASK); + /* Set default strength value in case none is given */ + if (arg == 1) + arg = 5000; + switch (arg) { case 20000: value |= PADCFG1_TERM_20K << PADCFG1_TERM_SHIFT; @@ -714,6 +727,13 @@ static int intel_config_set_pull(struct intel_pinctrl *pctrl, unsigned int pin, } value |= PADCFG1_TERM_1K << PADCFG1_TERM_SHIFT; break; + case 833: + if (!(community->features & PINCTRL_FEATURE_1K_PD)) { + ret = -EINVAL; + break; + } + value |= PADCFG1_TERM_833 << PADCFG1_TERM_SHIFT; + break; default: ret = -EINVAL; } diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index 9a760f5cd7ed..4aea3e05e8c6 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -156,7 +156,7 @@ static int amd_gpio_set_debounce(struct gpio_chip *gc, unsigned offset, pin_reg |= BIT(DB_TMR_OUT_UNIT_OFF); pin_reg &= ~BIT(DB_TMR_LARGE_OFF); } else if (debounce < 250000) { - time = debounce / 15600; + time = debounce / 15625; pin_reg |= time & DB_TMR_OUT_MASK; pin_reg &= ~BIT(DB_TMR_OUT_UNIT_OFF); pin_reg |= BIT(DB_TMR_LARGE_OFF); @@ -166,14 +166,14 @@ static int amd_gpio_set_debounce(struct gpio_chip *gc, unsigned offset, pin_reg |= BIT(DB_TMR_OUT_UNIT_OFF); pin_reg |= BIT(DB_TMR_LARGE_OFF); } else { - pin_reg &= ~DB_CNTRl_MASK; + pin_reg &= ~(DB_CNTRl_MASK << DB_CNTRL_OFF); ret = -EINVAL; } } else { pin_reg &= ~BIT(DB_TMR_OUT_UNIT_OFF); pin_reg &= ~BIT(DB_TMR_LARGE_OFF); pin_reg &= ~DB_TMR_OUT_MASK; - pin_reg &= ~DB_CNTRl_MASK; + pin_reg &= ~(DB_CNTRl_MASK << DB_CNTRL_OFF); } writel(pin_reg, gpio_dev->base + offset * 4); raw_spin_unlock_irqrestore(&gpio_dev->lock, flags); diff --git a/drivers/pinctrl/pinctrl-ingenic.c b/drivers/pinctrl/pinctrl-ingenic.c index c8e50a58a5e5..621909b01deb 100644 --- a/drivers/pinctrl/pinctrl-ingenic.c +++ b/drivers/pinctrl/pinctrl-ingenic.c @@ -635,44 +635,44 @@ static int jz4770_uart3_data_pins[] = { 0x6c, 0x85, }; static int jz4770_uart3_hwflow_pins[] = { 0x88, 0x89, }; static int jz4770_ssi0_dt_a_pins[] = { 0x15, }; static int jz4770_ssi0_dt_b_pins[] = { 0x35, }; -static int jz4770_ssi0_dt_d_pins[] = { 0x55, }; -static int jz4770_ssi0_dt_e_pins[] = { 0x71, }; +static int jz4770_ssi0_dt_d_pins[] = { 0x75, }; +static int jz4770_ssi0_dt_e_pins[] = { 0x91, }; static int jz4770_ssi0_dr_a_pins[] = { 0x14, }; static int jz4770_ssi0_dr_b_pins[] = { 0x34, }; -static int jz4770_ssi0_dr_d_pins[] = { 0x54, }; -static int jz4770_ssi0_dr_e_pins[] = { 0x6e, }; +static int jz4770_ssi0_dr_d_pins[] = { 0x74, }; +static int jz4770_ssi0_dr_e_pins[] = { 0x8e, }; static int jz4770_ssi0_clk_a_pins[] = { 0x12, }; static int jz4770_ssi0_clk_b_pins[] = { 0x3c, }; -static int jz4770_ssi0_clk_d_pins[] = { 0x58, }; -static int jz4770_ssi0_clk_e_pins[] = { 0x6f, }; +static int jz4770_ssi0_clk_d_pins[] = { 0x78, }; +static int jz4770_ssi0_clk_e_pins[] = { 0x8f, }; static int jz4770_ssi0_gpc_b_pins[] = { 0x3e, }; -static int jz4770_ssi0_gpc_d_pins[] = { 0x56, }; -static int jz4770_ssi0_gpc_e_pins[] = { 0x73, }; +static int jz4770_ssi0_gpc_d_pins[] = { 0x76, }; +static int jz4770_ssi0_gpc_e_pins[] = { 0x93, }; static int jz4770_ssi0_ce0_a_pins[] = { 0x13, }; static int jz4770_ssi0_ce0_b_pins[] = { 0x3d, }; -static int jz4770_ssi0_ce0_d_pins[] = { 0x59, }; -static int jz4770_ssi0_ce0_e_pins[] = { 0x70, }; +static int jz4770_ssi0_ce0_d_pins[] = { 0x79, }; +static int jz4770_ssi0_ce0_e_pins[] = { 0x90, }; static int jz4770_ssi0_ce1_b_pins[] = { 0x3f, }; -static int jz4770_ssi0_ce1_d_pins[] = { 0x57, }; -static int jz4770_ssi0_ce1_e_pins[] = { 0x72, }; +static int jz4770_ssi0_ce1_d_pins[] = { 0x77, }; +static int jz4770_ssi0_ce1_e_pins[] = { 0x92, }; static int jz4770_ssi1_dt_b_pins[] = { 0x35, }; -static int jz4770_ssi1_dt_d_pins[] = { 0x55, }; -static int jz4770_ssi1_dt_e_pins[] = { 0x71, }; +static int jz4770_ssi1_dt_d_pins[] = { 0x75, }; +static int jz4770_ssi1_dt_e_pins[] = { 0x91, }; static int jz4770_ssi1_dr_b_pins[] = { 0x34, }; -static int jz4770_ssi1_dr_d_pins[] = { 0x54, }; -static int jz4770_ssi1_dr_e_pins[] = { 0x6e, }; +static int jz4770_ssi1_dr_d_pins[] = { 0x74, }; +static int jz4770_ssi1_dr_e_pins[] = { 0x8e, }; static int jz4770_ssi1_clk_b_pins[] = { 0x3c, }; -static int jz4770_ssi1_clk_d_pins[] = { 0x58, }; -static int jz4770_ssi1_clk_e_pins[] = { 0x6f, }; +static int jz4770_ssi1_clk_d_pins[] = { 0x78, }; +static int jz4770_ssi1_clk_e_pins[] = { 0x8f, }; static int jz4770_ssi1_gpc_b_pins[] = { 0x3e, }; -static int jz4770_ssi1_gpc_d_pins[] = { 0x56, }; -static int jz4770_ssi1_gpc_e_pins[] = { 0x73, }; +static int jz4770_ssi1_gpc_d_pins[] = { 0x76, }; +static int jz4770_ssi1_gpc_e_pins[] = { 0x93, }; static int jz4770_ssi1_ce0_b_pins[] = { 0x3d, }; -static int jz4770_ssi1_ce0_d_pins[] = { 0x59, }; -static int jz4770_ssi1_ce0_e_pins[] = { 0x70, }; +static int jz4770_ssi1_ce0_d_pins[] = { 0x79, }; +static int jz4770_ssi1_ce0_e_pins[] = { 0x90, }; static int jz4770_ssi1_ce1_b_pins[] = { 0x3f, }; -static int jz4770_ssi1_ce1_d_pins[] = { 0x57, }; -static int jz4770_ssi1_ce1_e_pins[] = { 0x72, }; +static int jz4770_ssi1_ce1_d_pins[] = { 0x77, }; +static int jz4770_ssi1_ce1_e_pins[] = { 0x92, }; static int jz4770_mmc0_1bit_a_pins[] = { 0x12, 0x13, 0x14, }; static int jz4770_mmc0_4bit_a_pins[] = { 0x15, 0x16, 0x17, }; static int jz4770_mmc0_1bit_e_pins[] = { 0x9c, 0x9d, 0x94, }; @@ -1050,35 +1050,35 @@ static int jz4780_ssi0_dt_a_19_pins[] = { 0x13, }; static int jz4780_ssi0_dt_a_21_pins[] = { 0x15, }; static int jz4780_ssi0_dt_a_28_pins[] = { 0x1c, }; static int jz4780_ssi0_dt_b_pins[] = { 0x3d, }; -static int jz4780_ssi0_dt_d_pins[] = { 0x59, }; +static int jz4780_ssi0_dt_d_pins[] = { 0x79, }; static int jz4780_ssi0_dr_a_20_pins[] = { 0x14, }; static int jz4780_ssi0_dr_a_27_pins[] = { 0x1b, }; static int jz4780_ssi0_dr_b_pins[] = { 0x34, }; -static int jz4780_ssi0_dr_d_pins[] = { 0x54, }; +static int jz4780_ssi0_dr_d_pins[] = { 0x74, }; static int jz4780_ssi0_clk_a_pins[] = { 0x12, }; static int jz4780_ssi0_clk_b_5_pins[] = { 0x25, }; static int jz4780_ssi0_clk_b_28_pins[] = { 0x3c, }; -static int jz4780_ssi0_clk_d_pins[] = { 0x58, }; +static int jz4780_ssi0_clk_d_pins[] = { 0x78, }; static int jz4780_ssi0_gpc_b_pins[] = { 0x3e, }; -static int jz4780_ssi0_gpc_d_pins[] = { 0x56, }; +static int jz4780_ssi0_gpc_d_pins[] = { 0x76, }; static int jz4780_ssi0_ce0_a_23_pins[] = { 0x17, }; static int jz4780_ssi0_ce0_a_25_pins[] = { 0x19, }; static int jz4780_ssi0_ce0_b_pins[] = { 0x3f, }; -static int jz4780_ssi0_ce0_d_pins[] = { 0x57, }; +static int jz4780_ssi0_ce0_d_pins[] = { 0x77, }; static int jz4780_ssi0_ce1_b_pins[] = { 0x35, }; -static int jz4780_ssi0_ce1_d_pins[] = { 0x55, }; +static int jz4780_ssi0_ce1_d_pins[] = { 0x75, }; static int jz4780_ssi1_dt_b_pins[] = { 0x3d, }; -static int jz4780_ssi1_dt_d_pins[] = { 0x59, }; +static int jz4780_ssi1_dt_d_pins[] = { 0x79, }; static int jz4780_ssi1_dr_b_pins[] = { 0x34, }; -static int jz4780_ssi1_dr_d_pins[] = { 0x54, }; +static int jz4780_ssi1_dr_d_pins[] = { 0x74, }; static int jz4780_ssi1_clk_b_pins[] = { 0x3c, }; -static int jz4780_ssi1_clk_d_pins[] = { 0x58, }; +static int jz4780_ssi1_clk_d_pins[] = { 0x78, }; static int jz4780_ssi1_gpc_b_pins[] = { 0x3e, }; -static int jz4780_ssi1_gpc_d_pins[] = { 0x56, }; +static int jz4780_ssi1_gpc_d_pins[] = { 0x76, }; static int jz4780_ssi1_ce0_b_pins[] = { 0x3f, }; -static int jz4780_ssi1_ce0_d_pins[] = { 0x57, }; +static int jz4780_ssi1_ce0_d_pins[] = { 0x77, }; static int jz4780_ssi1_ce1_b_pins[] = { 0x35, }; -static int jz4780_ssi1_ce1_d_pins[] = { 0x55, }; +static int jz4780_ssi1_ce1_d_pins[] = { 0x75, }; static int jz4780_mmc0_8bit_a_pins[] = { 0x04, 0x05, 0x06, 0x07, 0x18, }; static int jz4780_i2c3_pins[] = { 0x6a, 0x6b, }; static int jz4780_i2c4_e_pins[] = { 0x8c, 0x8d, }; diff --git a/drivers/pinctrl/pinctrl-mcp23s08_spi.c b/drivers/pinctrl/pinctrl-mcp23s08_spi.c index 1f47a661b0a7..9ae10318f6f3 100644 --- a/drivers/pinctrl/pinctrl-mcp23s08_spi.c +++ b/drivers/pinctrl/pinctrl-mcp23s08_spi.c @@ -119,13 +119,15 @@ static int mcp23s08_spi_regmap_init(struct mcp23s08 *mcp, struct device *dev, return -EINVAL; } - copy = devm_kmemdup(dev, &config, sizeof(config), GFP_KERNEL); + copy = devm_kmemdup(dev, config, sizeof(*config), GFP_KERNEL); if (!copy) return -ENOMEM; copy->name = name; mcp->regmap = devm_regmap_init(dev, &mcp23sxx_spi_regmap, mcp, copy); + if (IS_ERR(mcp->regmap)) + dev_err(dev, "regmap init failed for %s\n", mcp->chip.label); return PTR_ERR_OR_ZERO(mcp->regmap); } diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c index 0401c1da79dd..aa1a1c850d05 100644 --- a/drivers/pinctrl/pinctrl-rockchip.c +++ b/drivers/pinctrl/pinctrl-rockchip.c @@ -3155,7 +3155,9 @@ static int rockchip_gpio_to_irq(struct gpio_chip *gc, unsigned offset) if (!bank->domain) return -ENXIO; + clk_enable(bank->clk); virq = irq_create_mapping(bank->domain, offset); + clk_disable(bank->clk); return (virq) ? : -ENXIO; } @@ -3194,7 +3196,7 @@ static void rockchip_irq_demux(struct irq_desc *desc) irq = __ffs(pend); pend &= ~BIT(irq); - virq = irq_linear_revmap(bank->domain, irq); + virq = irq_find_mapping(bank->domain, irq); if (!virq) { dev_err(bank->drvdata->dev, "unmapped irq %d\n", irq); @@ -3373,7 +3375,7 @@ static int rockchip_interrupts_register(struct platform_device *pdev, unsigned int clr = IRQ_NOREQUEST | IRQ_NOPROBE | IRQ_NOAUTOEN; struct irq_chip_generic *gc; int ret; - int i, j; + int i; for (i = 0; i < ctrl->nr_banks; ++i, ++bank) { if (!bank->valid) { @@ -3400,7 +3402,7 @@ static int rockchip_interrupts_register(struct platform_device *pdev, ret = irq_alloc_domain_generic_chips(bank->domain, 32, 1, "rockchip_gpio_irq", handle_level_irq, - clr, 0, IRQ_GC_INIT_MASK_CACHE); + clr, 0, 0); if (ret) { dev_err(&pdev->dev, "could not alloc generic chips for bank %s\n", bank->name); @@ -3409,14 +3411,6 @@ static int rockchip_interrupts_register(struct platform_device *pdev, continue; } - /* - * Linux assumes that all interrupts start out disabled/masked. - * Our driver only uses the concept of masked and always keeps - * things enabled, so for us that's all masked and all enabled. - */ - writel_relaxed(0xffffffff, bank->reg_base + GPIO_INTMASK); - writel_relaxed(0xffffffff, bank->reg_base + GPIO_INTEN); - gc = irq_get_domain_generic_chip(bank->domain, 0); gc->reg_base = bank->reg_base; gc->private = bank; @@ -3433,13 +3427,17 @@ static int rockchip_interrupts_register(struct platform_device *pdev, gc->chip_types[0].chip.irq_set_type = rockchip_irq_set_type; gc->wake_enabled = IRQ_MSK(bank->nr_pins); + /* + * Linux assumes that all interrupts start out disabled/masked. + * Our driver only uses the concept of masked and always keeps + * things enabled, so for us that's all masked and all enabled. + */ + writel_relaxed(0xffffffff, bank->reg_base + GPIO_INTMASK); + writel_relaxed(0xffffffff, bank->reg_base + GPIO_INTEN); + gc->mask_cache = 0xffffffff; + irq_set_chained_handler_and_data(bank->irq, rockchip_irq_demux, bank); - - /* map the gpio irqs here, when the clock is still running */ - for (j = 0 ; j < 32 ; j++) - irq_create_mapping(bank->domain, j); - clk_disable(bank->clk); } diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c index c4bcda90aac4..77a25bdf0da7 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.c +++ b/drivers/pinctrl/qcom/pinctrl-msm.c @@ -815,21 +815,14 @@ static void msm_gpio_irq_clear_unmask(struct irq_data *d, bool status_clear) static void msm_gpio_irq_enable(struct irq_data *d) { - /* - * Clear the interrupt that may be pending before we enable - * the line. - * This is especially a problem with the GPIOs routed to the - * PDC. These GPIOs are direct-connect interrupts to the GIC. - * Disabling the interrupt line at the PDC does not prevent - * the interrupt from being latched at the GIC. The state at - * GIC needs to be cleared before enabling. - */ - if (d->parent_data) { - irq_chip_set_parent_state(d, IRQCHIP_STATE_PENDING, 0); + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct msm_pinctrl *pctrl = gpiochip_get_data(gc); + + if (d->parent_data) irq_chip_enable_parent(d); - } - msm_gpio_irq_clear_unmask(d, true); + if (!test_bit(d->hwirq, pctrl->skip_wake_irqs)) + msm_gpio_irq_clear_unmask(d, true); } static void msm_gpio_irq_disable(struct irq_data *d) @@ -1104,6 +1097,19 @@ static int msm_gpio_irq_reqres(struct irq_data *d) ret = -EINVAL; goto out; } + + /* + * Clear the interrupt that may be pending before we enable + * the line. + * This is especially a problem with the GPIOs routed to the + * PDC. These GPIOs are direct-connect interrupts to the GIC. + * Disabling the interrupt line at the PDC does not prevent + * the interrupt from being latched at the GIC. The state at + * GIC needs to be cleared before enabling. + */ + if (d->parent_data && test_bit(d->hwirq, pctrl->skip_wake_irqs)) + irq_chip_set_parent_state(d, IRQCHIP_STATE_PENDING, 0); + return 0; out: module_put(gc->owner); diff --git a/drivers/pinctrl/qcom/pinctrl-sm8250.c b/drivers/pinctrl/qcom/pinctrl-sm8250.c index 826df0d637ea..af144e724bd9 100644 --- a/drivers/pinctrl/qcom/pinctrl-sm8250.c +++ b/drivers/pinctrl/qcom/pinctrl-sm8250.c @@ -1313,6 +1313,22 @@ static const struct msm_pingroup sm8250_groups[] = { [183] = SDC_PINGROUP(sdc2_data, 0xb7000, 9, 0), }; +static const struct msm_gpio_wakeirq_map sm8250_pdc_map[] = { + { 0, 79 }, { 1, 84 }, { 2, 80 }, { 3, 82 }, { 4, 107 }, { 7, 43 }, + { 11, 42 }, { 14, 44 }, { 15, 52 }, { 19, 67 }, { 23, 68 }, { 24, 105 }, + { 27, 92 }, { 28, 106 }, { 31, 69 }, { 35, 70 }, { 39, 37 }, + { 40, 108 }, { 43, 71 }, { 45, 72 }, { 47, 83 }, { 51, 74 }, { 55, 77 }, + { 59, 78 }, { 63, 75 }, { 64, 81 }, { 65, 87 }, { 66, 88 }, { 67, 89 }, + { 68, 54 }, { 70, 85 }, { 77, 46 }, { 80, 90 }, { 81, 91 }, { 83, 97 }, + { 84, 98 }, { 86, 99 }, { 87, 100 }, { 88, 101 }, { 89, 102 }, + { 92, 103 }, { 93, 104 }, { 100, 53 }, { 103, 47 }, { 104, 48 }, + { 108, 49 }, { 109, 94 }, { 110, 95 }, { 111, 96 }, { 112, 55 }, + { 113, 56 }, { 118, 50 }, { 121, 51 }, { 122, 57 }, { 123, 58 }, + { 124, 45 }, { 126, 59 }, { 128, 76 }, { 129, 86 }, { 132, 93 }, + { 133, 65 }, { 134, 66 }, { 136, 62 }, { 137, 63 }, { 138, 64 }, + { 142, 60 }, { 143, 61 } +}; + static const struct msm_pinctrl_soc_data sm8250_pinctrl = { .pins = sm8250_pins, .npins = ARRAY_SIZE(sm8250_pins), @@ -1323,6 +1339,8 @@ static const struct msm_pinctrl_soc_data sm8250_pinctrl = { .ngpios = 181, .tiles = sm8250_tiles, .ntiles = ARRAY_SIZE(sm8250_tiles), + .wakeirq_map = sm8250_pdc_map, + .nwakeirq_map = ARRAY_SIZE(sm8250_pdc_map), }; static int sm8250_pinctrl_probe(struct platform_device *pdev) diff --git a/drivers/powercap/powercap_sys.c b/drivers/powercap/powercap_sys.c index f808c5fa9838..3f0b8e2ef3d4 100644 --- a/drivers/powercap/powercap_sys.c +++ b/drivers/powercap/powercap_sys.c @@ -367,9 +367,9 @@ static void create_power_zone_common_attributes( &dev_attr_max_energy_range_uj.attr; if (power_zone->ops->get_energy_uj) { if (power_zone->ops->reset_energy_uj) - dev_attr_energy_uj.attr.mode = S_IWUSR | S_IRUGO; + dev_attr_energy_uj.attr.mode = S_IWUSR | S_IRUSR; else - dev_attr_energy_uj.attr.mode = S_IRUGO; + dev_attr_energy_uj.attr.mode = S_IRUSR; power_zone->zone_dev_attrs[count++] = &dev_attr_energy_uj.attr; } diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index b8f573a02713..7a160b86adc6 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -1627,12 +1627,12 @@ start: */ fallthrough; case CLKS_OFF: - ufshcd_scsi_block_requests(hba); hba->clk_gating.state = REQ_CLKS_ON; trace_ufshcd_clk_gating(dev_name(hba->dev), hba->clk_gating.state); - queue_work(hba->clk_gating.clk_gating_workq, - &hba->clk_gating.ungate_work); + if (queue_work(hba->clk_gating.clk_gating_workq, + &hba->clk_gating.ungate_work)) + ufshcd_scsi_block_requests(hba); /* * fall through to check if we should wait for this * work to be done or not. @@ -2115,10 +2115,20 @@ ufshcd_wait_for_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd) unsigned long flags; if (wait_for_completion_timeout(&uic_cmd->done, - msecs_to_jiffies(UIC_CMD_TIMEOUT))) + msecs_to_jiffies(UIC_CMD_TIMEOUT))) { ret = uic_cmd->argument2 & MASK_UIC_COMMAND_RESULT; - else + } else { ret = -ETIMEDOUT; + dev_err(hba->dev, + "uic cmd 0x%x with arg3 0x%x completion timeout\n", + uic_cmd->command, uic_cmd->argument3); + + if (!uic_cmd->cmd_active) { + dev_err(hba->dev, "%s: UIC cmd has been completed, return the result\n", + __func__); + ret = uic_cmd->argument2 & MASK_UIC_COMMAND_RESULT; + } + } spin_lock_irqsave(hba->host->host_lock, flags); hba->active_uic_cmd = NULL; @@ -2150,6 +2160,7 @@ __ufshcd_send_uic_cmd(struct ufs_hba *hba, struct uic_command *uic_cmd, if (completion) init_completion(&uic_cmd->done); + uic_cmd->cmd_active = 1; ufshcd_dispatch_uic_cmd(hba, uic_cmd); return 0; @@ -3807,10 +3818,18 @@ static int ufshcd_uic_pwr_ctrl(struct ufs_hba *hba, struct uic_command *cmd) dev_err(hba->dev, "pwr ctrl cmd 0x%x with mode 0x%x completion timeout\n", cmd->command, cmd->argument3); + + if (!cmd->cmd_active) { + dev_err(hba->dev, "%s: Power Mode Change operation has been completed, go check UPMCRS\n", + __func__); + goto check_upmcrs; + } + ret = -ETIMEDOUT; goto out; } +check_upmcrs: status = ufshcd_get_upmcrs(hba); if (status != PWR_LOCAL) { dev_err(hba->dev, @@ -4902,11 +4921,14 @@ static irqreturn_t ufshcd_uic_cmd_compl(struct ufs_hba *hba, u32 intr_status) ufshcd_get_uic_cmd_result(hba); hba->active_uic_cmd->argument3 = ufshcd_get_dme_attr_val(hba); + if (!hba->uic_async_done) + hba->active_uic_cmd->cmd_active = 0; complete(&hba->active_uic_cmd->done); retval = IRQ_HANDLED; } if ((intr_status & UFSHCD_UIC_PWR_MASK) && hba->uic_async_done) { + hba->active_uic_cmd->cmd_active = 0; complete(hba->uic_async_done); retval = IRQ_HANDLED; } @@ -8906,6 +8928,7 @@ void ufshcd_remove(struct ufs_hba *hba) blk_mq_free_tag_set(&hba->tmf_tag_set); blk_cleanup_queue(hba->cmd_queue); scsi_remove_host(hba->host); + destroy_workqueue(hba->eh_wq); /* disable interrupts */ ufshcd_disable_intr(hba, hba->intr_mask); ufshcd_hba_stop(hba); @@ -9206,6 +9229,7 @@ out_remove_scsi_host: exit_gating: ufshcd_exit_clk_scaling(hba); ufshcd_exit_clk_gating(hba); + destroy_workqueue(hba->eh_wq); out_disable: hba->is_irq_enabled = false; ufshcd_hba_exit(hba); diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h index 47eb1430274c..e0f00a42371c 100644 --- a/drivers/scsi/ufs/ufshcd.h +++ b/drivers/scsi/ufs/ufshcd.h @@ -64,6 +64,7 @@ enum dev_cmd_type { * @argument1: UIC command argument 1 * @argument2: UIC command argument 2 * @argument3: UIC command argument 3 + * @cmd_active: Indicate if UIC command is outstanding * @done: UIC command completion */ struct uic_command { @@ -71,6 +72,7 @@ struct uic_command { u32 argument1; u32 argument2; u32 argument3; + int cmd_active; struct completion done; }; diff --git a/drivers/thunderbolt/debugfs.c b/drivers/thunderbolt/debugfs.c index 3680b2784ea1..ed65d2b13964 100644 --- a/drivers/thunderbolt/debugfs.c +++ b/drivers/thunderbolt/debugfs.c @@ -9,6 +9,7 @@ #include <linux/debugfs.h> #include <linux/pm_runtime.h> +#include <linux/uaccess.h> #include "tb.h" diff --git a/drivers/thunderbolt/icm.c b/drivers/thunderbolt/icm.c index b51fc3f62b1f..977ba91f4d0e 100644 --- a/drivers/thunderbolt/icm.c +++ b/drivers/thunderbolt/icm.c @@ -2284,6 +2284,8 @@ struct tb *icm_probe(struct tb_nhi *nhi) case PCI_DEVICE_ID_INTEL_TGL_NHI0: case PCI_DEVICE_ID_INTEL_TGL_NHI1: + case PCI_DEVICE_ID_INTEL_TGL_H_NHI0: + case PCI_DEVICE_ID_INTEL_TGL_H_NHI1: icm->is_supported = icm_tgl_is_supported; icm->driver_ready = icm_icl_driver_ready; icm->set_uuid = icm_icl_set_uuid; diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c index 3f79baa54829..db80dc5dfeba 100644 --- a/drivers/thunderbolt/nhi.c +++ b/drivers/thunderbolt/nhi.c @@ -406,12 +406,23 @@ static int ring_request_msix(struct tb_ring *ring, bool no_suspend) ring->vector = ret; - ring->irq = pci_irq_vector(ring->nhi->pdev, ring->vector); - if (ring->irq < 0) - return ring->irq; + ret = pci_irq_vector(ring->nhi->pdev, ring->vector); + if (ret < 0) + goto err_ida_remove; + + ring->irq = ret; irqflags = no_suspend ? IRQF_NO_SUSPEND : 0; - return request_irq(ring->irq, ring_msix, irqflags, "thunderbolt", ring); + ret = request_irq(ring->irq, ring_msix, irqflags, "thunderbolt", ring); + if (ret) + goto err_ida_remove; + + return 0; + +err_ida_remove: + ida_simple_remove(&nhi->msix_ida, ring->vector); + + return ret; } static void ring_release_msix(struct tb_ring *ring) @@ -1334,6 +1345,10 @@ static struct pci_device_id nhi_ids[] = { .driver_data = (kernel_ulong_t)&icl_nhi_ops }, { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_TGL_NHI1), .driver_data = (kernel_ulong_t)&icl_nhi_ops }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_TGL_H_NHI0), + .driver_data = (kernel_ulong_t)&icl_nhi_ops }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_TGL_H_NHI1), + .driver_data = (kernel_ulong_t)&icl_nhi_ops }, /* Any USB4 compliant host */ { PCI_DEVICE_CLASS(PCI_CLASS_SERIAL_USB_USB4, ~0) }, diff --git a/drivers/thunderbolt/nhi.h b/drivers/thunderbolt/nhi.h index 80162e4b013f..4e0861d75072 100644 --- a/drivers/thunderbolt/nhi.h +++ b/drivers/thunderbolt/nhi.h @@ -75,6 +75,8 @@ extern const struct tb_nhi_ops icl_nhi_ops; #define PCI_DEVICE_ID_INTEL_ICL_NHI0 0x8a17 #define PCI_DEVICE_ID_INTEL_TGL_NHI0 0x9a1b #define PCI_DEVICE_ID_INTEL_TGL_NHI1 0x9a1d +#define PCI_DEVICE_ID_INTEL_TGL_H_NHI0 0x9a1f +#define PCI_DEVICE_ID_INTEL_TGL_H_NHI1 0x9a21 #define PCI_CLASS_SERIAL_USB_USB4 0x0c0340 diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index a9995e21b916..8ea360b0ff77 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -784,6 +784,8 @@ static inline bool tb_switch_is_tiger_lake(const struct tb_switch *sw) switch (sw->config.device_id) { case PCI_DEVICE_ID_INTEL_TGL_NHI0: case PCI_DEVICE_ID_INTEL_TGL_NHI1: + case PCI_DEVICE_ID_INTEL_TGL_H_NHI0: + case PCI_DEVICE_ID_INTEL_TGL_H_NHI1: return true; } } diff --git a/drivers/thunderbolt/usb4.c b/drivers/thunderbolt/usb4.c index 40f13579a3fe..f2583b4053e4 100644 --- a/drivers/thunderbolt/usb4.c +++ b/drivers/thunderbolt/usb4.c @@ -421,8 +421,12 @@ int usb4_switch_set_wake(struct tb_switch *sw, unsigned int flags) * upstream USB4 port. */ tb_switch_for_each_port(sw, port) { + if (!tb_port_is_null(port)) + continue; if (!route && tb_is_upstream_port(port)) continue; + if (!port->cap_usb4) + continue; ret = tb_port_read(port, &val, TB_CFG_PORT, port->cap_usb4 + PORT_CS_19, 1); diff --git a/drivers/thunderbolt/xdomain.c b/drivers/thunderbolt/xdomain.c index 48907853732a..c00ad817042e 100644 --- a/drivers/thunderbolt/xdomain.c +++ b/drivers/thunderbolt/xdomain.c @@ -881,6 +881,7 @@ static void enumerate_services(struct tb_xdomain *xd) id = ida_simple_get(&xd->service_ids, 0, 0, GFP_KERNEL); if (id < 0) { + kfree(svc->key); kfree(svc); break; } diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c index 6dca744e39e9..be06f1a961c2 100644 --- a/drivers/uio/uio.c +++ b/drivers/uio/uio.c @@ -413,10 +413,10 @@ static int uio_get_minor(struct uio_device *idev) return retval; } -static void uio_free_minor(struct uio_device *idev) +static void uio_free_minor(unsigned long minor) { mutex_lock(&minor_lock); - idr_remove(&uio_idr, idev->minor); + idr_remove(&uio_idr, minor); mutex_unlock(&minor_lock); } @@ -990,7 +990,7 @@ err_request_irq: err_uio_dev_add_attributes: device_del(&idev->dev); err_device_create: - uio_free_minor(idev); + uio_free_minor(idev->minor); put_device(&idev->dev); return ret; } @@ -1042,11 +1042,13 @@ EXPORT_SYMBOL_GPL(__devm_uio_register_device); void uio_unregister_device(struct uio_info *info) { struct uio_device *idev; + unsigned long minor; if (!info || !info->uio_dev) return; idev = info->uio_dev; + minor = idev->minor; mutex_lock(&idev->info_lock); uio_dev_del_attributes(idev); @@ -1062,7 +1064,7 @@ void uio_unregister_device(struct uio_info *info) device_unregister(&idev->dev); - uio_free_minor(idev); + uio_free_minor(minor); return; } diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 1e7568867910..f52f1bc0559f 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -1693,6 +1693,15 @@ static const struct usb_device_id acm_ids[] = { { USB_DEVICE(0x0870, 0x0001), /* Metricom GS Modem */ .driver_info = NO_UNION_NORMAL, /* has no union descriptor */ }, + { USB_DEVICE(0x045b, 0x023c), /* Renesas USB Download mode */ + .driver_info = DISABLE_ECHO, /* Don't echo banner */ + }, + { USB_DEVICE(0x045b, 0x0248), /* Renesas USB Download mode */ + .driver_info = DISABLE_ECHO, /* Don't echo banner */ + }, + { USB_DEVICE(0x045b, 0x024D), /* Renesas USB Download mode */ + .driver_info = DISABLE_ECHO, /* Don't echo banner */ + }, { USB_DEVICE(0x0e8d, 0x0003), /* FIREFLY, MediaTek Inc; andrey.arapov@gmail.com */ .driver_info = NO_UNION_NORMAL, /* has no union descriptor */ }, diff --git a/drivers/usb/host/xhci-histb.c b/drivers/usb/host/xhci-histb.c index 5546e7e013a8..08369857686e 100644 --- a/drivers/usb/host/xhci-histb.c +++ b/drivers/usb/host/xhci-histb.c @@ -240,7 +240,7 @@ static int xhci_histb_probe(struct platform_device *pdev) /* Initialize dma_mask and coherent_dma_mask to 32-bits */ ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32)); if (ret) - return ret; + goto disable_pm; hcd = usb_create_hcd(driver, dev, dev_name(dev)); if (!hcd) { diff --git a/drivers/usb/musb/musb_dsps.c b/drivers/usb/musb/musb_dsps.c index 30085b2be7b9..5892f3ce0cdc 100644 --- a/drivers/usb/musb/musb_dsps.c +++ b/drivers/usb/musb/musb_dsps.c @@ -429,10 +429,12 @@ static int dsps_musb_init(struct musb *musb) struct platform_device *parent = to_platform_device(dev->parent); const struct dsps_musb_wrapper *wrp = glue->wrp; void __iomem *reg_base; + struct resource *r; u32 rev, val; int ret; - reg_base = devm_platform_ioremap_resource_byname(parent, "control"); + r = platform_get_resource_byname(parent, IORESOURCE_MEM, "control"); + reg_base = devm_ioremap_resource(dev, r); if (IS_ERR(reg_base)) return PTR_ERR(reg_base); musb->ctrl_base = reg_base; diff --git a/drivers/usb/typec/ucsi/psy.c b/drivers/usb/typec/ucsi/psy.c index 26ed0b520749..571a51e16234 100644 --- a/drivers/usb/typec/ucsi/psy.c +++ b/drivers/usb/typec/ucsi/psy.c @@ -238,4 +238,13 @@ void ucsi_unregister_port_psy(struct ucsi_connector *con) return; power_supply_unregister(con->psy); + con->psy = NULL; +} + +void ucsi_port_psy_changed(struct ucsi_connector *con) +{ + if (IS_ERR_OR_NULL(con->psy)) + return; + + power_supply_changed(con->psy); } diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index 758b988ac518..51a570d40a42 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -643,8 +643,10 @@ static void ucsi_handle_connector_change(struct work_struct *work) role = !!(con->status.flags & UCSI_CONSTAT_PWR_DIR); if (con->status.change & UCSI_CONSTAT_POWER_OPMODE_CHANGE || - con->status.change & UCSI_CONSTAT_POWER_LEVEL_CHANGE) + con->status.change & UCSI_CONSTAT_POWER_LEVEL_CHANGE) { ucsi_pwr_opmode_change(con); + ucsi_port_psy_changed(con); + } if (con->status.change & UCSI_CONSTAT_POWER_DIR_CHANGE) { typec_set_pwr_role(con->port, role); @@ -674,6 +676,8 @@ static void ucsi_handle_connector_change(struct work_struct *work) ucsi_register_partner(con); else ucsi_unregister_partner(con); + + ucsi_port_psy_changed(con); } if (con->status.change & UCSI_CONSTAT_CAM_CHANGE) { @@ -994,6 +998,7 @@ static int ucsi_register_port(struct ucsi *ucsi, int index) !!(con->status.flags & UCSI_CONSTAT_PWR_DIR)); ucsi_pwr_opmode_change(con); ucsi_register_partner(con); + ucsi_port_psy_changed(con); } if (con->partner) { diff --git a/drivers/usb/typec/ucsi/ucsi.h b/drivers/usb/typec/ucsi/ucsi.h index cba6f77bea61..b7a92f246050 100644 --- a/drivers/usb/typec/ucsi/ucsi.h +++ b/drivers/usb/typec/ucsi/ucsi.h @@ -340,9 +340,11 @@ int ucsi_resume(struct ucsi *ucsi); #if IS_ENABLED(CONFIG_POWER_SUPPLY) int ucsi_register_port_psy(struct ucsi_connector *con); void ucsi_unregister_port_psy(struct ucsi_connector *con); +void ucsi_port_psy_changed(struct ucsi_connector *con); #else static inline int ucsi_register_port_psy(struct ucsi_connector *con) { return 0; } static inline void ucsi_unregister_port_psy(struct ucsi_connector *con) { } +static inline void ucsi_port_psy_changed(struct ucsi_connector *con) { } #endif /* CONFIG_POWER_SUPPLY */ #if IS_ENABLED(CONFIG_TYPEC_DP_ALTMODE) diff --git a/drivers/vdpa/Kconfig b/drivers/vdpa/Kconfig index d7d32b656102..358f6048dd3c 100644 --- a/drivers/vdpa/Kconfig +++ b/drivers/vdpa/Kconfig @@ -13,6 +13,7 @@ config VDPA_SIM depends on RUNTIME_TESTING_MENU && HAS_DMA select DMA_OPS select VHOST_RING + select GENERIC_NET_UTILS default n help vDPA networking device simulator which loop TX traffic back diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index b22adf03f584..f22fce549862 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -52,7 +52,6 @@ #define VHOST_SCSI_VERSION "v0.1" #define VHOST_SCSI_NAMELEN 256 #define VHOST_SCSI_MAX_CDB_SIZE 32 -#define VHOST_SCSI_DEFAULT_TAGS 256 #define VHOST_SCSI_PREALLOC_SGLS 2048 #define VHOST_SCSI_PREALLOC_UPAGES 2048 #define VHOST_SCSI_PREALLOC_PROT_SGLS 2048 @@ -140,6 +139,7 @@ struct vhost_scsi_tpg { struct se_portal_group se_tpg; /* Pointer back to vhost_scsi, protected by tv_tpg_mutex */ struct vhost_scsi *vhost_scsi; + struct list_head tmf_queue; }; struct vhost_scsi_tport { @@ -189,6 +189,9 @@ struct vhost_scsi_virtqueue { * Writers must also take dev mutex and flush under it. */ int inflight_idx; + struct vhost_scsi_cmd *scsi_cmds; + struct sbitmap scsi_tags; + int max_cmds; }; struct vhost_scsi { @@ -209,6 +212,20 @@ struct vhost_scsi { int vs_events_nr; /* num of pending events, protected by vq->mutex */ }; +struct vhost_scsi_tmf { + struct vhost_work vwork; + struct vhost_scsi_tpg *tpg; + struct vhost_scsi *vhost; + struct vhost_scsi_virtqueue *svq; + struct list_head queue_entry; + + struct se_cmd se_cmd; + struct vhost_scsi_inflight *inflight; + struct iovec resp_iov; + int in_iovs; + int vq_desc; +}; + /* * Context for processing request and control queue operations. */ @@ -320,11 +337,13 @@ static u32 vhost_scsi_tpg_get_inst_index(struct se_portal_group *se_tpg) return 1; } -static void vhost_scsi_release_cmd(struct se_cmd *se_cmd) +static void vhost_scsi_release_cmd_res(struct se_cmd *se_cmd) { struct vhost_scsi_cmd *tv_cmd = container_of(se_cmd, struct vhost_scsi_cmd, tvc_se_cmd); - struct se_session *se_sess = tv_cmd->tvc_nexus->tvn_se_sess; + struct vhost_scsi_virtqueue *svq = container_of(tv_cmd->tvc_vq, + struct vhost_scsi_virtqueue, vq); + struct vhost_scsi_inflight *inflight = tv_cmd->inflight; int i; if (tv_cmd->tvc_sgl_count) { @@ -336,8 +355,36 @@ static void vhost_scsi_release_cmd(struct se_cmd *se_cmd) put_page(sg_page(&tv_cmd->tvc_prot_sgl[i])); } - vhost_scsi_put_inflight(tv_cmd->inflight); - target_free_tag(se_sess, se_cmd); + sbitmap_clear_bit(&svq->scsi_tags, se_cmd->map_tag); + vhost_scsi_put_inflight(inflight); +} + +static void vhost_scsi_release_tmf_res(struct vhost_scsi_tmf *tmf) +{ + struct vhost_scsi_tpg *tpg = tmf->tpg; + struct vhost_scsi_inflight *inflight = tmf->inflight; + + mutex_lock(&tpg->tv_tpg_mutex); + list_add_tail(&tpg->tmf_queue, &tmf->queue_entry); + mutex_unlock(&tpg->tv_tpg_mutex); + vhost_scsi_put_inflight(inflight); +} + +static void vhost_scsi_release_cmd(struct se_cmd *se_cmd) +{ + if (se_cmd->se_cmd_flags & SCF_SCSI_TMR_CDB) { + struct vhost_scsi_tmf *tmf = container_of(se_cmd, + struct vhost_scsi_tmf, se_cmd); + + vhost_work_queue(&tmf->vhost->dev, &tmf->vwork); + } else { + struct vhost_scsi_cmd *cmd = container_of(se_cmd, + struct vhost_scsi_cmd, tvc_se_cmd); + struct vhost_scsi *vs = cmd->tvc_vhost; + + llist_add(&cmd->tvc_completion_list, &vs->vs_completion_list); + vhost_work_queue(&vs->dev, &vs->vs_completion_work); + } } static u32 vhost_scsi_sess_get_index(struct se_session *se_sess) @@ -362,34 +409,24 @@ static int vhost_scsi_get_cmd_state(struct se_cmd *se_cmd) return 0; } -static void vhost_scsi_complete_cmd(struct vhost_scsi_cmd *cmd) -{ - struct vhost_scsi *vs = cmd->tvc_vhost; - - llist_add(&cmd->tvc_completion_list, &vs->vs_completion_list); - - vhost_work_queue(&vs->dev, &vs->vs_completion_work); -} - static int vhost_scsi_queue_data_in(struct se_cmd *se_cmd) { - struct vhost_scsi_cmd *cmd = container_of(se_cmd, - struct vhost_scsi_cmd, tvc_se_cmd); - vhost_scsi_complete_cmd(cmd); + transport_generic_free_cmd(se_cmd, 0); return 0; } static int vhost_scsi_queue_status(struct se_cmd *se_cmd) { - struct vhost_scsi_cmd *cmd = container_of(se_cmd, - struct vhost_scsi_cmd, tvc_se_cmd); - vhost_scsi_complete_cmd(cmd); + transport_generic_free_cmd(se_cmd, 0); return 0; } static void vhost_scsi_queue_tm_rsp(struct se_cmd *se_cmd) { - return; + struct vhost_scsi_tmf *tmf = container_of(se_cmd, struct vhost_scsi_tmf, + se_cmd); + + transport_generic_free_cmd(&tmf->se_cmd, 0); } static void vhost_scsi_aborted_task(struct se_cmd *se_cmd) @@ -429,15 +466,6 @@ vhost_scsi_allocate_evt(struct vhost_scsi *vs, return evt; } -static void vhost_scsi_free_cmd(struct vhost_scsi_cmd *cmd) -{ - struct se_cmd *se_cmd = &cmd->tvc_se_cmd; - - /* TODO locking against target/backend threads? */ - transport_generic_free_cmd(se_cmd, 0); - -} - static int vhost_scsi_check_stop_free(struct se_cmd *se_cmd) { return target_put_sess_cmd(se_cmd); @@ -556,7 +584,7 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work) } else pr_err("Faulted on virtio_scsi_cmd_resp\n"); - vhost_scsi_free_cmd(cmd); + vhost_scsi_release_cmd_res(se_cmd); } vq = -1; @@ -566,31 +594,31 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work) } static struct vhost_scsi_cmd * -vhost_scsi_get_tag(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg, +vhost_scsi_get_cmd(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg, unsigned char *cdb, u64 scsi_tag, u16 lun, u8 task_attr, u32 exp_data_len, int data_direction) { + struct vhost_scsi_virtqueue *svq = container_of(vq, + struct vhost_scsi_virtqueue, vq); struct vhost_scsi_cmd *cmd; struct vhost_scsi_nexus *tv_nexus; - struct se_session *se_sess; struct scatterlist *sg, *prot_sg; struct page **pages; - int tag, cpu; + int tag; tv_nexus = tpg->tpg_nexus; if (!tv_nexus) { pr_err("Unable to locate active struct vhost_scsi_nexus\n"); return ERR_PTR(-EIO); } - se_sess = tv_nexus->tvn_se_sess; - tag = sbitmap_queue_get(&se_sess->sess_tag_pool, &cpu); + tag = sbitmap_get(&svq->scsi_tags, 0, false); if (tag < 0) { pr_err("Unable to obtain tag for vhost_scsi_cmd\n"); return ERR_PTR(-ENOMEM); } - cmd = &((struct vhost_scsi_cmd *)se_sess->sess_cmd_map)[tag]; + cmd = &svq->scsi_cmds[tag]; sg = cmd->tvc_sgl; prot_sg = cmd->tvc_prot_sgl; pages = cmd->tvc_upages; @@ -599,7 +627,6 @@ vhost_scsi_get_tag(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg, cmd->tvc_prot_sgl = prot_sg; cmd->tvc_upages = pages; cmd->tvc_se_cmd.map_tag = tag; - cmd->tvc_se_cmd.map_cpu = cpu; cmd->tvc_tag = scsi_tag; cmd->tvc_lun = lun; cmd->tvc_task_attr = task_attr; @@ -907,6 +934,11 @@ vhost_scsi_get_req(struct vhost_virtqueue *vq, struct vhost_scsi_ctx *vc, return ret; } +static u16 vhost_buf_to_lun(u8 *lun_buf) +{ + return ((lun_buf[2] << 8) | lun_buf[3]) & 0x3FFF; +} + static void vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) { @@ -1045,12 +1077,12 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) tag = vhost64_to_cpu(vq, v_req_pi.tag); task_attr = v_req_pi.task_attr; cdb = &v_req_pi.cdb[0]; - lun = ((v_req_pi.lun[2] << 8) | v_req_pi.lun[3]) & 0x3FFF; + lun = vhost_buf_to_lun(v_req_pi.lun); } else { tag = vhost64_to_cpu(vq, v_req.tag); task_attr = v_req.task_attr; cdb = &v_req.cdb[0]; - lun = ((v_req.lun[2] << 8) | v_req.lun[3]) & 0x3FFF; + lun = vhost_buf_to_lun(v_req.lun); } /* * Check that the received CDB size does not exceeded our @@ -1065,11 +1097,11 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) scsi_command_size(cdb), VHOST_SCSI_MAX_CDB_SIZE); goto err; } - cmd = vhost_scsi_get_tag(vq, tpg, cdb, tag, lun, task_attr, + cmd = vhost_scsi_get_cmd(vq, tpg, cdb, tag, lun, task_attr, exp_data_len + prot_bytes, data_direction); if (IS_ERR(cmd)) { - vq_err(vq, "vhost_scsi_get_tag failed %ld\n", + vq_err(vq, "vhost_scsi_get_cmd failed %ld\n", PTR_ERR(cmd)); goto err; } @@ -1088,7 +1120,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) &prot_iter, exp_data_len, &data_iter))) { vq_err(vq, "Failed to map iov to sgl\n"); - vhost_scsi_release_cmd(&cmd->tvc_se_cmd); + vhost_scsi_release_cmd_res(&cmd->tvc_se_cmd); goto err; } } @@ -1124,9 +1156,9 @@ out: } static void -vhost_scsi_send_tmf_reject(struct vhost_scsi *vs, - struct vhost_virtqueue *vq, - struct vhost_scsi_ctx *vc) +vhost_scsi_send_tmf_resp(struct vhost_scsi *vs, struct vhost_virtqueue *vq, + int in_iovs, int vq_desc, struct iovec *resp_iov, + int tmf_resp_code) { struct virtio_scsi_ctrl_tmf_resp rsp; struct iov_iter iov_iter; @@ -1134,17 +1166,87 @@ vhost_scsi_send_tmf_reject(struct vhost_scsi *vs, pr_debug("%s\n", __func__); memset(&rsp, 0, sizeof(rsp)); - rsp.response = VIRTIO_SCSI_S_FUNCTION_REJECTED; + rsp.response = tmf_resp_code; - iov_iter_init(&iov_iter, READ, &vq->iov[vc->out], vc->in, sizeof(rsp)); + iov_iter_init(&iov_iter, READ, resp_iov, in_iovs, sizeof(rsp)); ret = copy_to_iter(&rsp, sizeof(rsp), &iov_iter); if (likely(ret == sizeof(rsp))) - vhost_add_used_and_signal(&vs->dev, vq, vc->head, 0); + vhost_add_used_and_signal(&vs->dev, vq, vq_desc, 0); else pr_err("Faulted on virtio_scsi_ctrl_tmf_resp\n"); } +static void vhost_scsi_tmf_resp_work(struct vhost_work *work) +{ + struct vhost_scsi_tmf *tmf = container_of(work, struct vhost_scsi_tmf, + vwork); + int resp_code; + + if (tmf->se_cmd.se_tmr_req->response == TMR_FUNCTION_COMPLETE) + resp_code = VIRTIO_SCSI_S_FUNCTION_SUCCEEDED; + else + resp_code = VIRTIO_SCSI_S_FUNCTION_REJECTED; + + vhost_scsi_send_tmf_resp(tmf->vhost, &tmf->svq->vq, tmf->in_iovs, + tmf->vq_desc, &tmf->resp_iov, resp_code); + vhost_scsi_release_tmf_res(tmf); +} + +static void +vhost_scsi_handle_tmf(struct vhost_scsi *vs, struct vhost_scsi_tpg *tpg, + struct vhost_virtqueue *vq, + struct virtio_scsi_ctrl_tmf_req *vtmf, + struct vhost_scsi_ctx *vc) +{ + struct vhost_scsi_virtqueue *svq = container_of(vq, + struct vhost_scsi_virtqueue, vq); + struct vhost_scsi_tmf *tmf; + + if (vhost32_to_cpu(vq, vtmf->subtype) != + VIRTIO_SCSI_T_TMF_LOGICAL_UNIT_RESET) + goto send_reject; + + if (!tpg->tpg_nexus || !tpg->tpg_nexus->tvn_se_sess) { + pr_err("Unable to locate active struct vhost_scsi_nexus for LUN RESET.\n"); + goto send_reject; + } + + mutex_lock(&tpg->tv_tpg_mutex); + if (list_empty(&tpg->tmf_queue)) { + pr_err("Missing reserve TMF. Could not handle LUN RESET.\n"); + mutex_unlock(&tpg->tv_tpg_mutex); + goto send_reject; + } + + tmf = list_first_entry(&tpg->tmf_queue, struct vhost_scsi_tmf, + queue_entry); + list_del_init(&tmf->queue_entry); + mutex_unlock(&tpg->tv_tpg_mutex); + + tmf->tpg = tpg; + tmf->vhost = vs; + tmf->svq = svq; + tmf->resp_iov = vq->iov[vc->out]; + tmf->vq_desc = vc->head; + tmf->in_iovs = vc->in; + tmf->inflight = vhost_scsi_get_inflight(vq); + + if (target_submit_tmr(&tmf->se_cmd, tpg->tpg_nexus->tvn_se_sess, NULL, + vhost_buf_to_lun(vtmf->lun), NULL, + TMR_LUN_RESET, GFP_KERNEL, 0, + TARGET_SCF_ACK_KREF) < 0) { + vhost_scsi_release_tmf_res(tmf); + goto send_reject; + } + + return; + +send_reject: + vhost_scsi_send_tmf_resp(vs, vq, vc->in, vc->head, &vq->iov[vc->out], + VIRTIO_SCSI_S_FUNCTION_REJECTED); +} + static void vhost_scsi_send_an_resp(struct vhost_scsi *vs, struct vhost_virtqueue *vq, @@ -1170,6 +1272,7 @@ vhost_scsi_send_an_resp(struct vhost_scsi *vs, static void vhost_scsi_ctl_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) { + struct vhost_scsi_tpg *tpg; union { __virtio32 type; struct virtio_scsi_ctrl_an_req an; @@ -1251,12 +1354,12 @@ vhost_scsi_ctl_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) vc.req += typ_size; vc.req_size -= typ_size; - ret = vhost_scsi_get_req(vq, &vc, NULL); + ret = vhost_scsi_get_req(vq, &vc, &tpg); if (ret) goto err; if (v_req.type == VIRTIO_SCSI_T_TMF) - vhost_scsi_send_tmf_reject(vs, vq, &vc); + vhost_scsi_handle_tmf(vs, tpg, vq, &v_req.tmf, &vc); else vhost_scsi_send_an_resp(vs, vq, &vc); err: @@ -1373,6 +1476,83 @@ static void vhost_scsi_flush(struct vhost_scsi *vs) wait_for_completion(&old_inflight[i]->comp); } +static void vhost_scsi_destroy_vq_cmds(struct vhost_virtqueue *vq) +{ + struct vhost_scsi_virtqueue *svq = container_of(vq, + struct vhost_scsi_virtqueue, vq); + struct vhost_scsi_cmd *tv_cmd; + unsigned int i; + + if (!svq->scsi_cmds) + return; + + for (i = 0; i < svq->max_cmds; i++) { + tv_cmd = &svq->scsi_cmds[i]; + + kfree(tv_cmd->tvc_sgl); + kfree(tv_cmd->tvc_prot_sgl); + kfree(tv_cmd->tvc_upages); + } + + sbitmap_free(&svq->scsi_tags); + kfree(svq->scsi_cmds); + svq->scsi_cmds = NULL; +} + +static int vhost_scsi_setup_vq_cmds(struct vhost_virtqueue *vq, int max_cmds) +{ + struct vhost_scsi_virtqueue *svq = container_of(vq, + struct vhost_scsi_virtqueue, vq); + struct vhost_scsi_cmd *tv_cmd; + unsigned int i; + + if (svq->scsi_cmds) + return 0; + + if (sbitmap_init_node(&svq->scsi_tags, max_cmds, -1, GFP_KERNEL, + NUMA_NO_NODE)) + return -ENOMEM; + svq->max_cmds = max_cmds; + + svq->scsi_cmds = kcalloc(max_cmds, sizeof(*tv_cmd), GFP_KERNEL); + if (!svq->scsi_cmds) { + sbitmap_free(&svq->scsi_tags); + return -ENOMEM; + } + + for (i = 0; i < max_cmds; i++) { + tv_cmd = &svq->scsi_cmds[i]; + + tv_cmd->tvc_sgl = kcalloc(VHOST_SCSI_PREALLOC_SGLS, + sizeof(struct scatterlist), + GFP_KERNEL); + if (!tv_cmd->tvc_sgl) { + pr_err("Unable to allocate tv_cmd->tvc_sgl\n"); + goto out; + } + + tv_cmd->tvc_upages = kcalloc(VHOST_SCSI_PREALLOC_UPAGES, + sizeof(struct page *), + GFP_KERNEL); + if (!tv_cmd->tvc_upages) { + pr_err("Unable to allocate tv_cmd->tvc_upages\n"); + goto out; + } + + tv_cmd->tvc_prot_sgl = kcalloc(VHOST_SCSI_PREALLOC_PROT_SGLS, + sizeof(struct scatterlist), + GFP_KERNEL); + if (!tv_cmd->tvc_prot_sgl) { + pr_err("Unable to allocate tv_cmd->tvc_prot_sgl\n"); + goto out; + } + } + return 0; +out: + vhost_scsi_destroy_vq_cmds(vq); + return -ENOMEM; +} + /* * Called from vhost_scsi_ioctl() context to walk the list of available * vhost_scsi_tpg with an active struct vhost_scsi_nexus @@ -1427,10 +1607,9 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs, if (!strcmp(tv_tport->tport_name, t->vhost_wwpn)) { if (vs->vs_tpg && vs->vs_tpg[tpg->tport_tpgt]) { - kfree(vs_tpg); mutex_unlock(&tpg->tv_tpg_mutex); ret = -EEXIST; - goto out; + goto undepend; } /* * In order to ensure individual vhost-scsi configfs @@ -1442,9 +1621,8 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs, ret = target_depend_item(&se_tpg->tpg_group.cg_item); if (ret) { pr_warn("target_depend_item() failed: %d\n", ret); - kfree(vs_tpg); mutex_unlock(&tpg->tv_tpg_mutex); - goto out; + goto undepend; } tpg->tv_tpg_vhost_count++; tpg->vhost_scsi = vs; @@ -1457,6 +1635,16 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs, if (match) { memcpy(vs->vs_vhost_wwpn, t->vhost_wwpn, sizeof(vs->vs_vhost_wwpn)); + + for (i = VHOST_SCSI_VQ_IO; i < VHOST_SCSI_MAX_VQ; i++) { + vq = &vs->vqs[i].vq; + if (!vhost_vq_is_setup(vq)) + continue; + + if (vhost_scsi_setup_vq_cmds(vq, vq->num)) + goto destroy_vq_cmds; + } + for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) { vq = &vs->vqs[i].vq; mutex_lock(&vq->mutex); @@ -1476,7 +1664,22 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs, vhost_scsi_flush(vs); kfree(vs->vs_tpg); vs->vs_tpg = vs_tpg; + goto out; +destroy_vq_cmds: + for (i--; i >= VHOST_SCSI_VQ_IO; i--) { + if (!vhost_vq_get_backend(&vs->vqs[i].vq)) + vhost_scsi_destroy_vq_cmds(&vs->vqs[i].vq); + } +undepend: + for (i = 0; i < VHOST_SCSI_MAX_TARGET; i++) { + tpg = vs_tpg[i]; + if (tpg) { + tpg->tv_tpg_vhost_count--; + target_undepend_item(&tpg->se_tpg.tpg_group.cg_item); + } + } + kfree(vs_tpg); out: mutex_unlock(&vs->dev.mutex); mutex_unlock(&vhost_scsi_mutex); @@ -1549,6 +1752,12 @@ vhost_scsi_clear_endpoint(struct vhost_scsi *vs, mutex_lock(&vq->mutex); vhost_vq_set_backend(vq, NULL); mutex_unlock(&vq->mutex); + /* + * Make sure cmds are not running before tearing them + * down. + */ + vhost_scsi_flush(vs); + vhost_scsi_destroy_vq_cmds(vq); } } /* @@ -1811,11 +2020,19 @@ static int vhost_scsi_port_link(struct se_portal_group *se_tpg, { struct vhost_scsi_tpg *tpg = container_of(se_tpg, struct vhost_scsi_tpg, se_tpg); + struct vhost_scsi_tmf *tmf; + + tmf = kzalloc(sizeof(*tmf), GFP_KERNEL); + if (!tmf) + return -ENOMEM; + INIT_LIST_HEAD(&tmf->queue_entry); + vhost_work_init(&tmf->vwork, vhost_scsi_tmf_resp_work); mutex_lock(&vhost_scsi_mutex); mutex_lock(&tpg->tv_tpg_mutex); tpg->tv_tpg_port_count++; + list_add_tail(&tmf->queue_entry, &tpg->tmf_queue); mutex_unlock(&tpg->tv_tpg_mutex); vhost_scsi_hotplug(tpg, lun); @@ -1830,11 +2047,16 @@ static void vhost_scsi_port_unlink(struct se_portal_group *se_tpg, { struct vhost_scsi_tpg *tpg = container_of(se_tpg, struct vhost_scsi_tpg, se_tpg); + struct vhost_scsi_tmf *tmf; mutex_lock(&vhost_scsi_mutex); mutex_lock(&tpg->tv_tpg_mutex); tpg->tv_tpg_port_count--; + tmf = list_first_entry(&tpg->tmf_queue, struct vhost_scsi_tmf, + queue_entry); + list_del(&tmf->queue_entry); + kfree(tmf); mutex_unlock(&tpg->tv_tpg_mutex); vhost_scsi_hotunplug(tpg, lun); @@ -1842,23 +2064,6 @@ static void vhost_scsi_port_unlink(struct se_portal_group *se_tpg, mutex_unlock(&vhost_scsi_mutex); } -static void vhost_scsi_free_cmd_map_res(struct se_session *se_sess) -{ - struct vhost_scsi_cmd *tv_cmd; - unsigned int i; - - if (!se_sess->sess_cmd_map) - return; - - for (i = 0; i < VHOST_SCSI_DEFAULT_TAGS; i++) { - tv_cmd = &((struct vhost_scsi_cmd *)se_sess->sess_cmd_map)[i]; - - kfree(tv_cmd->tvc_sgl); - kfree(tv_cmd->tvc_prot_sgl); - kfree(tv_cmd->tvc_upages); - } -} - static ssize_t vhost_scsi_tpg_attrib_fabric_prot_type_store( struct config_item *item, const char *page, size_t count) { @@ -1898,45 +2103,6 @@ static struct configfs_attribute *vhost_scsi_tpg_attrib_attrs[] = { NULL, }; -static int vhost_scsi_nexus_cb(struct se_portal_group *se_tpg, - struct se_session *se_sess, void *p) -{ - struct vhost_scsi_cmd *tv_cmd; - unsigned int i; - - for (i = 0; i < VHOST_SCSI_DEFAULT_TAGS; i++) { - tv_cmd = &((struct vhost_scsi_cmd *)se_sess->sess_cmd_map)[i]; - - tv_cmd->tvc_sgl = kcalloc(VHOST_SCSI_PREALLOC_SGLS, - sizeof(struct scatterlist), - GFP_KERNEL); - if (!tv_cmd->tvc_sgl) { - pr_err("Unable to allocate tv_cmd->tvc_sgl\n"); - goto out; - } - - tv_cmd->tvc_upages = kcalloc(VHOST_SCSI_PREALLOC_UPAGES, - sizeof(struct page *), - GFP_KERNEL); - if (!tv_cmd->tvc_upages) { - pr_err("Unable to allocate tv_cmd->tvc_upages\n"); - goto out; - } - - tv_cmd->tvc_prot_sgl = kcalloc(VHOST_SCSI_PREALLOC_PROT_SGLS, - sizeof(struct scatterlist), - GFP_KERNEL); - if (!tv_cmd->tvc_prot_sgl) { - pr_err("Unable to allocate tv_cmd->tvc_prot_sgl\n"); - goto out; - } - } - return 0; -out: - vhost_scsi_free_cmd_map_res(se_sess); - return -ENOMEM; -} - static int vhost_scsi_make_nexus(struct vhost_scsi_tpg *tpg, const char *name) { @@ -1960,12 +2126,9 @@ static int vhost_scsi_make_nexus(struct vhost_scsi_tpg *tpg, * struct se_node_acl for the vhost_scsi struct se_portal_group with * the SCSI Initiator port name of the passed configfs group 'name'. */ - tv_nexus->tvn_se_sess = target_setup_session(&tpg->se_tpg, - VHOST_SCSI_DEFAULT_TAGS, - sizeof(struct vhost_scsi_cmd), + tv_nexus->tvn_se_sess = target_setup_session(&tpg->se_tpg, 0, 0, TARGET_PROT_DIN_PASS | TARGET_PROT_DOUT_PASS, - (unsigned char *)name, tv_nexus, - vhost_scsi_nexus_cb); + (unsigned char *)name, tv_nexus, NULL); if (IS_ERR(tv_nexus->tvn_se_sess)) { mutex_unlock(&tpg->tv_tpg_mutex); kfree(tv_nexus); @@ -2015,7 +2178,6 @@ static int vhost_scsi_drop_nexus(struct vhost_scsi_tpg *tpg) " %s Initiator Port: %s\n", vhost_scsi_dump_proto_id(tpg->tport), tv_nexus->tvn_se_sess->se_node_acl->initiatorname); - vhost_scsi_free_cmd_map_res(se_sess); /* * Release the SCSI I_T Nexus to the emulated vhost Target Port */ @@ -2155,6 +2317,7 @@ vhost_scsi_make_tpg(struct se_wwn *wwn, const char *name) } mutex_init(&tpg->tv_tpg_mutex); INIT_LIST_HEAD(&tpg->tv_tpg_list); + INIT_LIST_HEAD(&tpg->tmf_queue); tpg->tport = tport; tpg->tport_tpgt = tpgt; diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 5c835a292783..a262e12c6dc2 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -304,6 +304,12 @@ static void vhost_vring_call_reset(struct vhost_vring_call *call_ctx) memset(&call_ctx->producer, 0x0, sizeof(struct irq_bypass_producer)); } +bool vhost_vq_is_setup(struct vhost_virtqueue *vq) +{ + return vq->avail && vq->desc && vq->used && vhost_vq_access_ok(vq); +} +EXPORT_SYMBOL_GPL(vhost_vq_is_setup); + static void vhost_vq_reset(struct vhost_dev *dev, struct vhost_virtqueue *vq) { diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index e016cd3fa02f..b063324c7669 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -190,6 +190,7 @@ int vhost_get_vq_desc(struct vhost_virtqueue *, struct vhost_log *log, unsigned int *log_num); void vhost_discard_vq_desc(struct vhost_virtqueue *, int n); +bool vhost_vq_is_setup(struct vhost_virtqueue *vq); int vhost_vq_init_access(struct vhost_virtqueue *); int vhost_add_used(struct vhost_virtqueue *, unsigned int head, int len); int vhost_add_used_n(struct vhost_virtqueue *, struct vring_used_elem *heads, diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c index e36fb1a0ecdb..5bc86f481a78 100644 --- a/drivers/video/fbdev/hyperv_fb.c +++ b/drivers/video/fbdev/hyperv_fb.c @@ -47,6 +47,7 @@ #include <linux/module.h> #include <linux/kernel.h> +#include <linux/vmalloc.h> #include <linux/init.h> #include <linux/completion.h> #include <linux/fb.h> diff --git a/drivers/virt/nitro_enclaves/ne_misc_dev.c b/drivers/virt/nitro_enclaves/ne_misc_dev.c index f06622b48d69..f1964ea4b826 100644 --- a/drivers/virt/nitro_enclaves/ne_misc_dev.c +++ b/drivers/virt/nitro_enclaves/ne_misc_dev.c @@ -1505,10 +1505,8 @@ static __poll_t ne_enclave_poll(struct file *file, poll_table *wait) poll_wait(file, &ne_enclave->eventq, wait); - if (!ne_enclave->has_event) - return mask; - - mask = POLLHUP; + if (ne_enclave->has_event) + mask |= EPOLLHUP; return mask; } diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 71ce1b7a23d1..2b385c1b4a99 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -395,8 +395,7 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page, */ trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force); - map = swiotlb_tbl_map_single(dev, virt_to_phys(xen_io_tlb_start), - phys, size, size, dir, attrs); + map = swiotlb_tbl_map_single(dev, phys, size, size, dir, attrs); if (map == (phys_addr_t)DMA_MAPPING_ERROR) return DMA_MAPPING_ERROR; diff --git a/fs/afs/write.c b/fs/afs/write.c index 50371207f327..c9195fc67fd8 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -169,11 +169,14 @@ int afs_write_end(struct file *file, struct address_space *mapping, unsigned int f, from = pos & (PAGE_SIZE - 1); unsigned int t, to = from + copied; loff_t i_size, maybe_i_size; - int ret; + int ret = 0; _enter("{%llx:%llu},{%lx}", vnode->fid.vid, vnode->fid.vnode, page->index); + if (copied == 0) + goto out; + maybe_i_size = pos + copied; i_size = i_size_read(&vnode->vfs_inode); @@ -1572,7 +1572,7 @@ static int aio_write(struct kiocb *req, const struct iocb *iocb, * we return to userspace. */ if (S_ISREG(file_inode(file)->i_mode)) { - __sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, true); + sb_start_write(file_inode(file)->i_sb); __sb_writers_release(file_inode(file)->i_sb, SB_FREEZE_WRITE); } req->ki_flags |= IOCB_WRITE; diff --git a/fs/btrfs/block-rsv.c b/fs/btrfs/block-rsv.c index 7e1549a84fcc..bc920afe23bf 100644 --- a/fs/btrfs/block-rsv.c +++ b/fs/btrfs/block-rsv.c @@ -511,7 +511,8 @@ again: /*DEFAULT_RATELIMIT_BURST*/ 1); if (__ratelimit(&_rs)) WARN(1, KERN_DEBUG - "BTRFS: block rsv returned %d\n", ret); + "BTRFS: block rsv %d returned %d\n", + block_rsv->type, ret); } try_reserve: ret = btrfs_reserve_metadata_bytes(root, block_rsv, blocksize, diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 5b9e3f3ace22..10638537b9ef 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -91,6 +91,17 @@ int btrfs_init_dev_replace(struct btrfs_fs_info *fs_info) ret = btrfs_search_slot(NULL, dev_root, &key, path, 0, 0); if (ret) { no_valid_dev_replace_entry_found: + /* + * We don't have a replace item or it's corrupted. If there is + * a replace target, fail the mount. + */ + if (btrfs_find_device(fs_info->fs_devices, + BTRFS_DEV_REPLACE_DEVID, NULL, NULL, false)) { + btrfs_err(fs_info, + "found replace target device without a valid replace item"); + ret = -EUCLEAN; + goto out; + } ret = 0; dev_replace->replace_state = BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED; @@ -143,8 +154,19 @@ no_valid_dev_replace_entry_found: case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED: case BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED: case BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED: - dev_replace->srcdev = NULL; - dev_replace->tgtdev = NULL; + /* + * We don't have an active replace item but if there is a + * replace target, fail the mount. + */ + if (btrfs_find_device(fs_info->fs_devices, + BTRFS_DEV_REPLACE_DEVID, NULL, NULL, false)) { + btrfs_err(fs_info, + "replace devid present without an active replace item"); + ret = -EUCLEAN; + } else { + dev_replace->srcdev = NULL; + dev_replace->tgtdev = NULL; + } break; case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED: case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED: diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index ab408a23ba32..69a384145dc6 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1274,6 +1274,7 @@ static int cluster_pages_for_defrag(struct inode *inode, u64 page_start; u64 page_end; u64 page_cnt; + u64 start = (u64)start_index << PAGE_SHIFT; int ret; int i; int i_done; @@ -1290,8 +1291,7 @@ static int cluster_pages_for_defrag(struct inode *inode, page_cnt = min_t(u64, (u64)num_pages, (u64)file_end - start_index + 1); ret = btrfs_delalloc_reserve_space(BTRFS_I(inode), &data_reserved, - start_index << PAGE_SHIFT, - page_cnt << PAGE_SHIFT); + start, page_cnt << PAGE_SHIFT); if (ret) return ret; i_done = 0; @@ -1380,8 +1380,7 @@ again: btrfs_mod_outstanding_extents(BTRFS_I(inode), 1); spin_unlock(&BTRFS_I(inode)->lock); btrfs_delalloc_release_space(BTRFS_I(inode), data_reserved, - start_index << PAGE_SHIFT, - (page_cnt - i_done) << PAGE_SHIFT, true); + start, (page_cnt - i_done) << PAGE_SHIFT, true); } @@ -1408,8 +1407,7 @@ out: put_page(pages[i]); } btrfs_delalloc_release_space(BTRFS_I(inode), data_reserved, - start_index << PAGE_SHIFT, - page_cnt << PAGE_SHIFT, true); + start, page_cnt << PAGE_SHIFT, true); btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT); extent_changeset_free(data_reserved); return ret; diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index c54ea6586632..77c54749f432 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -3435,24 +3435,20 @@ static int qgroup_unreserve_range(struct btrfs_inode *inode, { struct rb_node *node; struct rb_node *next; - struct ulist_node *entry = NULL; + struct ulist_node *entry; int ret = 0; node = reserved->range_changed.root.rb_node; + if (!node) + return 0; while (node) { entry = rb_entry(node, struct ulist_node, rb_node); if (entry->val < start) node = node->rb_right; - else if (entry) - node = node->rb_left; else - break; + node = node->rb_left; } - /* Empty changeset */ - if (!entry) - return 0; - if (entry->val > start && rb_prev(&entry->rb_node)) entry = rb_entry(rb_prev(&entry->rb_node), struct ulist_node, rb_node); diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c index 7f03dbe5b609..78693d3dd15b 100644 --- a/fs/btrfs/ref-verify.c +++ b/fs/btrfs/ref-verify.c @@ -860,6 +860,7 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info, "dropping a ref for a root that doesn't have a ref on the block"); dump_block_entry(fs_info, be); dump_ref_action(fs_info, ra); + kfree(ref); kfree(ra); goto out_unlock; } diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 3602806d71bd..9ba92d86da0b 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -1648,6 +1648,7 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc, struct btrfs_root_item *root_item; struct btrfs_path *path; struct extent_buffer *leaf; + int reserve_level; int level; int max_level; int replaced = 0; @@ -1696,7 +1697,8 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc, * Thus the needed metadata size is at most root_level * nodesize, * and * 2 since we have two trees to COW. */ - min_reserved = fs_info->nodesize * btrfs_root_level(root_item) * 2; + reserve_level = max_t(int, 1, btrfs_root_level(root_item)); + min_reserved = fs_info->nodesize * reserve_level * 2; memset(&next_key, 0, sizeof(next_key)); while (1) { diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index cf63f1e27a27..e71e7586e9eb 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -3866,8 +3866,9 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, if (!is_dev_replace && !readonly && !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state)) { mutex_unlock(&fs_info->fs_devices->device_list_mutex); - btrfs_err_in_rcu(fs_info, "scrub: device %s is not writable", - rcu_str_deref(dev->name)); + btrfs_err_in_rcu(fs_info, + "scrub on devid %llu: filesystem on %s is not writable", + devid, rcu_str_deref(dev->name)); ret = -EROFS; goto out; } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index b1e48078c318..a6406b3b8c2b 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1056,22 +1056,13 @@ static void __btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices, continue; } - if (device->devid == BTRFS_DEV_REPLACE_DEVID) { - /* - * In the first step, keep the device which has - * the correct fsid and the devid that is used - * for the dev_replace procedure. - * In the second step, the dev_replace state is - * read from the device tree and it is known - * whether the procedure is really active or - * not, which means whether this device is - * used or whether it should be removed. - */ - if (step == 0 || test_bit(BTRFS_DEV_STATE_REPLACE_TGT, - &device->dev_state)) { - continue; - } - } + /* + * We have already validated the presence of BTRFS_DEV_REPLACE_DEVID, + * in btrfs_init_dev_replace() so just continue. + */ + if (device->devid == BTRFS_DEV_REPLACE_DEVID) + continue; + if (device->bdev) { blkdev_put(device->bdev, device->mode); device->bdev = NULL; @@ -1080,9 +1071,6 @@ static void __btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices, if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) { list_del_init(&device->dev_alloc_list); clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state); - if (!test_bit(BTRFS_DEV_STATE_REPLACE_TGT, - &device->dev_state)) - fs_devices->rw_devices--; } list_del_init(&device->dev_list); fs_devices->num_devices--; diff --git a/fs/crypto/inline_crypt.c b/fs/crypto/inline_crypt.c index 89bffa82ed74..c57bebfa48fe 100644 --- a/fs/crypto/inline_crypt.c +++ b/fs/crypto/inline_crypt.c @@ -74,7 +74,7 @@ int fscrypt_select_encryption_impl(struct fscrypt_info *ci) int i; /* The file must need contents encryption, not filenames encryption */ - if (!fscrypt_needs_contents_encryption(inode)) + if (!S_ISREG(inode->i_mode)) return 0; /* The crypto mode must have a blk-crypto counterpart */ diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c index d3c3e5d9b41f..d595abb8ef90 100644 --- a/fs/crypto/keysetup.c +++ b/fs/crypto/keysetup.c @@ -269,9 +269,7 @@ unlock: * New inodes may not have an inode number assigned yet. * Hashing their inode number is delayed until later. */ - if (ci->ci_inode->i_ino == 0) - WARN_ON(!(ci->ci_inode->i_state & I_CREATING)); - else + if (ci->ci_inode->i_ino) fscrypt_hash_inode_number(ci, mk); return 0; } diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c index 139d0bed42f8..3e21c0e8adae 100644 --- a/fs/erofs/inode.c +++ b/fs/erofs/inode.c @@ -107,11 +107,9 @@ static struct page *erofs_read_inode(struct inode *inode, i_gid_write(inode, le32_to_cpu(die->i_gid)); set_nlink(inode, le32_to_cpu(die->i_nlink)); - /* ns timestamp */ - inode->i_mtime.tv_sec = inode->i_ctime.tv_sec = - le64_to_cpu(die->i_ctime); - inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec = - le32_to_cpu(die->i_ctime_nsec); + /* extended inode has its own timestamp */ + inode->i_ctime.tv_sec = le64_to_cpu(die->i_ctime); + inode->i_ctime.tv_nsec = le32_to_cpu(die->i_ctime_nsec); inode->i_size = le64_to_cpu(die->i_size); @@ -149,11 +147,9 @@ static struct page *erofs_read_inode(struct inode *inode, i_gid_write(inode, le16_to_cpu(dic->i_gid)); set_nlink(inode, le16_to_cpu(dic->i_nlink)); - /* use build time to derive all file time */ - inode->i_mtime.tv_sec = inode->i_ctime.tv_sec = - sbi->build_time; - inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec = - sbi->build_time_nsec; + /* use build time for compact inodes */ + inode->i_ctime.tv_sec = sbi->build_time; + inode->i_ctime.tv_nsec = sbi->build_time_nsec; inode->i_size = le32_to_cpu(dic->i_size); if (erofs_inode_is_data_compressed(vi->datalayout)) @@ -167,6 +163,11 @@ static struct page *erofs_read_inode(struct inode *inode, goto err_out; } + inode->i_mtime.tv_sec = inode->i_ctime.tv_sec; + inode->i_atime.tv_sec = inode->i_ctime.tv_sec; + inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec; + inode->i_atime.tv_nsec = inode->i_ctime.tv_nsec; + if (!nblks) /* measure inode.i_blocks as generic filesystems */ inode->i_blocks = roundup(inode->i_size, EROFS_BLKSIZ) >> 9; diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 50912a5420b4..86fd3bf62af6 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -1078,8 +1078,11 @@ out_allocpage: cond_resched(); goto repeat; } - set_page_private(page, (unsigned long)pcl); - SetPagePrivate(page); + + if (tocache) { + set_page_private(page, (unsigned long)pcl); + SetPagePrivate(page); + } out: /* the only exit (for tracing and debugging) */ return page; } diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 45fcdbf538d1..bf9429484462 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1028,9 +1028,6 @@ struct ext4_inode_info { * protected by sbi->s_fc_lock. */ - /* Fast commit subtid when this inode was committed */ - unsigned int i_fc_committed_subtid; - /* Start of lblk range that needs to be committed in this fast commit */ ext4_lblk_t i_fc_lblk_start; @@ -1234,13 +1231,13 @@ struct ext4_inode_info { blocks */ #define EXT4_MOUNT2_HURD_COMPAT 0x00000004 /* Support HURD-castrated file systems */ -#define EXT4_MOUNT2_DAX_NEVER 0x00000008 /* Do not allow Direct Access */ -#define EXT4_MOUNT2_DAX_INODE 0x00000010 /* For printing options only */ - #define EXT4_MOUNT2_EXPLICIT_JOURNAL_CHECKSUM 0x00000008 /* User explicitly specified journal checksum */ #define EXT4_MOUNT2_JOURNAL_FAST_COMMIT 0x00000010 /* Journal fast commit */ +#define EXT4_MOUNT2_DAX_NEVER 0x00000020 /* Do not allow Direct Access */ +#define EXT4_MOUNT2_DAX_INODE 0x00000040 /* For printing options only */ + #define clear_opt(sb, opt) EXT4_SB(sb)->s_mount_opt &= \ ~EXT4_MOUNT_##opt @@ -1422,16 +1419,6 @@ struct ext4_super_block { #ifdef __KERNEL__ -/* - * run-time mount flags - */ -#define EXT4_MF_MNTDIR_SAMPLED 0x0001 -#define EXT4_MF_FS_ABORTED 0x0002 /* Fatal error detected */ -#define EXT4_MF_FC_INELIGIBLE 0x0004 /* Fast commit ineligible */ -#define EXT4_MF_FC_COMMITTING 0x0008 /* File system underoing a fast - * commit. - */ - #ifdef CONFIG_FS_ENCRYPTION #define DUMMY_ENCRYPTION_ENABLED(sbi) ((sbi)->s_dummy_enc_policy.policy != NULL) #else @@ -1466,7 +1453,7 @@ struct ext4_sb_info { struct buffer_head * __rcu *s_group_desc; unsigned int s_mount_opt; unsigned int s_mount_opt2; - unsigned int s_mount_flags; + unsigned long s_mount_flags; unsigned int s_def_mount_opt; ext4_fsblk_t s_sb_block; atomic64_t s_resv_clusters; @@ -1695,6 +1682,34 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) }) /* + * run-time mount flags + */ +enum { + EXT4_MF_MNTDIR_SAMPLED, + EXT4_MF_FS_ABORTED, /* Fatal error detected */ + EXT4_MF_FC_INELIGIBLE, /* Fast commit ineligible */ + EXT4_MF_FC_COMMITTING /* File system underoing a fast + * commit. + */ +}; + +static inline void ext4_set_mount_flag(struct super_block *sb, int bit) +{ + set_bit(bit, &EXT4_SB(sb)->s_mount_flags); +} + +static inline void ext4_clear_mount_flag(struct super_block *sb, int bit) +{ + clear_bit(bit, &EXT4_SB(sb)->s_mount_flags); +} + +static inline int ext4_test_mount_flag(struct super_block *sb, int bit) +{ + return test_bit(bit, &EXT4_SB(sb)->s_mount_flags); +} + + +/* * Simulate_fail codes */ #define EXT4_SIM_BBITMAP_EIO 1 @@ -1863,6 +1878,13 @@ static inline bool ext4_verity_in_progress(struct inode *inode) #define EXT4_FEATURE_COMPAT_RESIZE_INODE 0x0010 #define EXT4_FEATURE_COMPAT_DIR_INDEX 0x0020 #define EXT4_FEATURE_COMPAT_SPARSE_SUPER2 0x0200 +/* + * The reason why "FAST_COMMIT" is a compat feature is that, FS becomes + * incompatible only if fast commit blocks are present in the FS. Since we + * clear the journal (and thus the fast commit blocks), we don't mark FS as + * incompatible. We also have a JBD2 incompat feature, which gets set when + * there are fast commit blocks present in the journal. + */ #define EXT4_FEATURE_COMPAT_FAST_COMMIT 0x0400 #define EXT4_FEATURE_COMPAT_STABLE_INODES 0x0800 @@ -2731,12 +2753,16 @@ extern void ext4_end_bitmap_read(struct buffer_head *bh, int uptodate); int ext4_fc_info_show(struct seq_file *seq, void *v); void ext4_fc_init(struct super_block *sb, journal_t *journal); void ext4_fc_init_inode(struct inode *inode); -void ext4_fc_track_range(struct inode *inode, ext4_lblk_t start, +void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t start, ext4_lblk_t end); -void ext4_fc_track_unlink(struct inode *inode, struct dentry *dentry); -void ext4_fc_track_link(struct inode *inode, struct dentry *dentry); -void ext4_fc_track_create(struct inode *inode, struct dentry *dentry); -void ext4_fc_track_inode(struct inode *inode); +void __ext4_fc_track_unlink(handle_t *handle, struct inode *inode, + struct dentry *dentry); +void __ext4_fc_track_link(handle_t *handle, struct inode *inode, + struct dentry *dentry); +void ext4_fc_track_unlink(handle_t *handle, struct dentry *dentry); +void ext4_fc_track_link(handle_t *handle, struct dentry *dentry); +void ext4_fc_track_create(handle_t *handle, struct dentry *dentry); +void ext4_fc_track_inode(handle_t *handle, struct inode *inode); void ext4_fc_mark_ineligible(struct super_block *sb, int reason); void ext4_fc_start_ineligible(struct super_block *sb, int reason); void ext4_fc_stop_ineligible(struct super_block *sb); @@ -3452,7 +3478,7 @@ extern int ext4_handle_dirty_dirblock(handle_t *handle, struct inode *inode, extern int ext4_ci_compare(const struct inode *parent, const struct qstr *fname, const struct qstr *entry, bool quick); -extern int __ext4_unlink(struct inode *dir, const struct qstr *d_name, +extern int __ext4_unlink(handle_t *handle, struct inode *dir, const struct qstr *d_name, struct inode *inode); extern int __ext4_link(struct inode *dir, struct inode *inode, struct dentry *dentry); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 57cfa28919a9..17d7096b3212 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3724,7 +3724,6 @@ static int ext4_convert_unwritten_extents_endio(handle_t *handle, err = ext4_ext_dirty(handle, inode, path + path->p_depth); out: ext4_ext_show_leaf(inode, path); - ext4_fc_track_range(inode, ee_block, ee_block + ee_len - 1); return err; } @@ -3796,7 +3795,6 @@ convert_initialized_extent(handle_t *handle, struct inode *inode, if (*allocated > map->m_len) *allocated = map->m_len; map->m_len = *allocated; - ext4_fc_track_range(inode, ee_block, ee_block + ee_len - 1); return 0; } @@ -4329,7 +4327,6 @@ got_allocated_blocks: map->m_len = ar.len; allocated = map->m_len; ext4_ext_show_leaf(inode, path); - ext4_fc_track_range(inode, map->m_lblk, map->m_lblk + map->m_len - 1); out: ext4_ext_drop_refs(path); kfree(path); @@ -4602,7 +4599,7 @@ static long ext4_zero_range(struct file *file, loff_t offset, ret = ext4_mark_inode_dirty(handle, inode); if (unlikely(ret)) goto out_handle; - ext4_fc_track_range(inode, offset >> inode->i_sb->s_blocksize_bits, + ext4_fc_track_range(handle, inode, offset >> inode->i_sb->s_blocksize_bits, (offset + len - 1) >> inode->i_sb->s_blocksize_bits); /* Zero out partial block at the edges of the range */ ret = ext4_zero_partial_blocks(handle, inode, offset, len); @@ -4651,8 +4648,6 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE | FALLOC_FL_INSERT_RANGE)) return -EOPNOTSUPP; - ext4_fc_track_range(inode, offset >> blkbits, - (offset + len - 1) >> blkbits); ext4_fc_start_update(inode); diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index 8d43058386c3..f2033e13a273 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -83,7 +83,7 @@ * * Atomicity of commits * -------------------- - * In order to gaurantee atomicity during the commit operation, fast commit + * In order to guarantee atomicity during the commit operation, fast commit * uses "EXT4_FC_TAG_TAIL" tag that marks a fast commit as complete. Tail * tag contains CRC of the contents and TID of the transaction after which * this fast commit should be applied. Recovery code replays fast commit @@ -152,7 +152,31 @@ void ext4_fc_init_inode(struct inode *inode) INIT_LIST_HEAD(&ei->i_fc_list); init_waitqueue_head(&ei->i_fc_wait); atomic_set(&ei->i_fc_updates, 0); - ei->i_fc_committed_subtid = 0; +} + +/* This function must be called with sbi->s_fc_lock held. */ +static void ext4_fc_wait_committing_inode(struct inode *inode) +__releases(&EXT4_SB(inode->i_sb)->s_fc_lock) +{ + wait_queue_head_t *wq; + struct ext4_inode_info *ei = EXT4_I(inode); + +#if (BITS_PER_LONG < 64) + DEFINE_WAIT_BIT(wait, &ei->i_state_flags, + EXT4_STATE_FC_COMMITTING); + wq = bit_waitqueue(&ei->i_state_flags, + EXT4_STATE_FC_COMMITTING); +#else + DEFINE_WAIT_BIT(wait, &ei->i_flags, + EXT4_STATE_FC_COMMITTING); + wq = bit_waitqueue(&ei->i_flags, + EXT4_STATE_FC_COMMITTING); +#endif + lockdep_assert_held(&EXT4_SB(inode->i_sb)->s_fc_lock); + prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); + spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock); + schedule(); + finish_wait(wq, &wait.wq_entry); } /* @@ -176,22 +200,7 @@ restart: goto out; if (ext4_test_inode_state(inode, EXT4_STATE_FC_COMMITTING)) { - wait_queue_head_t *wq; -#if (BITS_PER_LONG < 64) - DEFINE_WAIT_BIT(wait, &ei->i_state_flags, - EXT4_STATE_FC_COMMITTING); - wq = bit_waitqueue(&ei->i_state_flags, - EXT4_STATE_FC_COMMITTING); -#else - DEFINE_WAIT_BIT(wait, &ei->i_flags, - EXT4_STATE_FC_COMMITTING); - wq = bit_waitqueue(&ei->i_flags, - EXT4_STATE_FC_COMMITTING); -#endif - prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); - spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock); - schedule(); - finish_wait(wq, &wait.wq_entry); + ext4_fc_wait_committing_inode(inode); goto restart; } out: @@ -234,26 +243,10 @@ restart: } if (ext4_test_inode_state(inode, EXT4_STATE_FC_COMMITTING)) { - wait_queue_head_t *wq; -#if (BITS_PER_LONG < 64) - DEFINE_WAIT_BIT(wait, &ei->i_state_flags, - EXT4_STATE_FC_COMMITTING); - wq = bit_waitqueue(&ei->i_state_flags, - EXT4_STATE_FC_COMMITTING); -#else - DEFINE_WAIT_BIT(wait, &ei->i_flags, - EXT4_STATE_FC_COMMITTING); - wq = bit_waitqueue(&ei->i_flags, - EXT4_STATE_FC_COMMITTING); -#endif - prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); - spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock); - schedule(); - finish_wait(wq, &wait.wq_entry); + ext4_fc_wait_committing_inode(inode); goto restart; } - if (!list_empty(&ei->i_fc_list)) - list_del_init(&ei->i_fc_list); + list_del_init(&ei->i_fc_list); spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock); } @@ -269,7 +262,7 @@ void ext4_fc_mark_ineligible(struct super_block *sb, int reason) (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY)) return; - sbi->s_mount_flags |= EXT4_MF_FC_INELIGIBLE; + ext4_set_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); WARN_ON(reason >= EXT4_FC_REASON_MAX); sbi->s_fc_stats.fc_ineligible_reason_count[reason]++; } @@ -302,14 +295,14 @@ void ext4_fc_stop_ineligible(struct super_block *sb) (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY)) return; - EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FC_INELIGIBLE; + ext4_set_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); atomic_dec(&EXT4_SB(sb)->s_fc_ineligible_updates); } static inline int ext4_fc_is_ineligible(struct super_block *sb) { - return (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FC_INELIGIBLE) || - atomic_read(&EXT4_SB(sb)->s_fc_ineligible_updates); + return (ext4_test_mount_flag(sb, EXT4_MF_FC_INELIGIBLE) || + atomic_read(&EXT4_SB(sb)->s_fc_ineligible_updates)); } /* @@ -323,13 +316,14 @@ static inline int ext4_fc_is_ineligible(struct super_block *sb) * If enqueue is set, this function enqueues the inode in fast commit list. */ static int ext4_fc_track_template( - struct inode *inode, int (*__fc_track_fn)(struct inode *, void *, bool), + handle_t *handle, struct inode *inode, + int (*__fc_track_fn)(struct inode *, void *, bool), void *args, int enqueue) { - tid_t running_txn_tid; bool update = false; struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + tid_t tid = 0; int ret; if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) || @@ -339,15 +333,13 @@ static int ext4_fc_track_template( if (ext4_fc_is_ineligible(inode->i_sb)) return -EINVAL; - running_txn_tid = sbi->s_journal ? - sbi->s_journal->j_commit_sequence + 1 : 0; - + tid = handle->h_transaction->t_tid; mutex_lock(&ei->i_fc_lock); - if (running_txn_tid == ei->i_sync_tid) { + if (tid == ei->i_sync_tid) { update = true; } else { ext4_fc_reset_inode(inode); - ei->i_sync_tid = running_txn_tid; + ei->i_sync_tid = tid; } ret = __fc_track_fn(inode, args, update); mutex_unlock(&ei->i_fc_lock); @@ -358,7 +350,7 @@ static int ext4_fc_track_template( spin_lock(&sbi->s_fc_lock); if (list_empty(&EXT4_I(inode)->i_fc_list)) list_add_tail(&EXT4_I(inode)->i_fc_list, - (sbi->s_mount_flags & EXT4_MF_FC_COMMITTING) ? + (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_COMMITTING)) ? &sbi->s_fc_q[FC_Q_STAGING] : &sbi->s_fc_q[FC_Q_MAIN]); spin_unlock(&sbi->s_fc_lock); @@ -384,7 +376,7 @@ static int __track_dentry_update(struct inode *inode, void *arg, bool update) mutex_unlock(&ei->i_fc_lock); node = kmem_cache_alloc(ext4_fc_dentry_cachep, GFP_NOFS); if (!node) { - ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_MEM); + ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM); mutex_lock(&ei->i_fc_lock); return -ENOMEM; } @@ -397,7 +389,7 @@ static int __track_dentry_update(struct inode *inode, void *arg, bool update) if (!node->fcd_name.name) { kmem_cache_free(ext4_fc_dentry_cachep, node); ext4_fc_mark_ineligible(inode->i_sb, - EXT4_FC_REASON_MEM); + EXT4_FC_REASON_NOMEM); mutex_lock(&ei->i_fc_lock); return -ENOMEM; } @@ -411,7 +403,7 @@ static int __track_dentry_update(struct inode *inode, void *arg, bool update) node->fcd_name.len = dentry->d_name.len; spin_lock(&sbi->s_fc_lock); - if (sbi->s_mount_flags & EXT4_MF_FC_COMMITTING) + if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_COMMITTING)) list_add_tail(&node->fcd_list, &sbi->s_fc_dentry_q[FC_Q_STAGING]); else @@ -422,7 +414,8 @@ static int __track_dentry_update(struct inode *inode, void *arg, bool update) return 0; } -void ext4_fc_track_unlink(struct inode *inode, struct dentry *dentry) +void __ext4_fc_track_unlink(handle_t *handle, + struct inode *inode, struct dentry *dentry) { struct __track_dentry_update_args args; int ret; @@ -430,12 +423,18 @@ void ext4_fc_track_unlink(struct inode *inode, struct dentry *dentry) args.dentry = dentry; args.op = EXT4_FC_TAG_UNLINK; - ret = ext4_fc_track_template(inode, __track_dentry_update, + ret = ext4_fc_track_template(handle, inode, __track_dentry_update, (void *)&args, 0); trace_ext4_fc_track_unlink(inode, dentry, ret); } -void ext4_fc_track_link(struct inode *inode, struct dentry *dentry) +void ext4_fc_track_unlink(handle_t *handle, struct dentry *dentry) +{ + __ext4_fc_track_unlink(handle, d_inode(dentry), dentry); +} + +void __ext4_fc_track_link(handle_t *handle, + struct inode *inode, struct dentry *dentry) { struct __track_dentry_update_args args; int ret; @@ -443,20 +442,26 @@ void ext4_fc_track_link(struct inode *inode, struct dentry *dentry) args.dentry = dentry; args.op = EXT4_FC_TAG_LINK; - ret = ext4_fc_track_template(inode, __track_dentry_update, + ret = ext4_fc_track_template(handle, inode, __track_dentry_update, (void *)&args, 0); trace_ext4_fc_track_link(inode, dentry, ret); } -void ext4_fc_track_create(struct inode *inode, struct dentry *dentry) +void ext4_fc_track_link(handle_t *handle, struct dentry *dentry) +{ + __ext4_fc_track_link(handle, d_inode(dentry), dentry); +} + +void ext4_fc_track_create(handle_t *handle, struct dentry *dentry) { struct __track_dentry_update_args args; + struct inode *inode = d_inode(dentry); int ret; args.dentry = dentry; args.op = EXT4_FC_TAG_CREAT; - ret = ext4_fc_track_template(inode, __track_dentry_update, + ret = ext4_fc_track_template(handle, inode, __track_dentry_update, (void *)&args, 0); trace_ext4_fc_track_create(inode, dentry, ret); } @@ -472,14 +477,20 @@ static int __track_inode(struct inode *inode, void *arg, bool update) return 0; } -void ext4_fc_track_inode(struct inode *inode) +void ext4_fc_track_inode(handle_t *handle, struct inode *inode) { int ret; if (S_ISDIR(inode->i_mode)) return; - ret = ext4_fc_track_template(inode, __track_inode, NULL, 1); + if (ext4_should_journal_data(inode)) { + ext4_fc_mark_ineligible(inode->i_sb, + EXT4_FC_REASON_INODE_JOURNAL_DATA); + return; + } + + ret = ext4_fc_track_template(handle, inode, __track_inode, NULL, 1); trace_ext4_fc_track_inode(inode, ret); } @@ -515,7 +526,7 @@ static int __track_range(struct inode *inode, void *arg, bool update) return 0; } -void ext4_fc_track_range(struct inode *inode, ext4_lblk_t start, +void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t start, ext4_lblk_t end) { struct __track_range_args args; @@ -527,7 +538,7 @@ void ext4_fc_track_range(struct inode *inode, ext4_lblk_t start, args.start = start; args.end = end; - ret = ext4_fc_track_template(inode, __track_range, &args, 1); + ret = ext4_fc_track_template(handle, inode, __track_range, &args, 1); trace_ext4_fc_track_range(inode, start, end, ret); } @@ -537,10 +548,11 @@ static void ext4_fc_submit_bh(struct super_block *sb) int write_flags = REQ_SYNC; struct buffer_head *bh = EXT4_SB(sb)->s_fc_bh; + /* TODO: REQ_FUA | REQ_PREFLUSH is unnecessarily expensive. */ if (test_opt(sb, BARRIER)) write_flags |= REQ_FUA | REQ_PREFLUSH; lock_buffer(bh); - clear_buffer_dirty(bh); + set_buffer_dirty(bh); set_buffer_uptodate(bh); bh->b_end_io = ext4_end_buffer_io_sync; submit_bh(REQ_OP_WRITE, write_flags, bh); @@ -846,7 +858,7 @@ static int ext4_fc_submit_inode_data_all(journal_t *journal) int ret = 0; spin_lock(&sbi->s_fc_lock); - sbi->s_mount_flags |= EXT4_MF_FC_COMMITTING; + ext4_set_mount_flag(sb, EXT4_MF_FC_COMMITTING); list_for_each(pos, &sbi->s_fc_q[FC_Q_MAIN]) { ei = list_entry(pos, struct ext4_inode_info, i_fc_list); ext4_set_inode_state(&ei->vfs_inode, EXT4_STATE_FC_COMMITTING); @@ -900,6 +912,8 @@ static int ext4_fc_wait_inode_data_all(journal_t *journal) /* Commit all the directory entry updates */ static int ext4_fc_commit_dentry_updates(journal_t *journal, u32 *crc) +__acquires(&sbi->s_fc_lock) +__releases(&sbi->s_fc_lock) { struct super_block *sb = (struct super_block *)(journal->j_private); struct ext4_sb_info *sbi = EXT4_SB(sb); @@ -996,6 +1010,13 @@ static int ext4_fc_perform_commit(journal_t *journal) if (ret) return ret; + /* + * If file system device is different from journal device, issue a cache + * flush before we start writing fast commit blocks. + */ + if (journal->j_fs_dev != journal->j_dev) + blkdev_issue_flush(journal->j_fs_dev, GFP_NOFS); + blk_start_plug(&plug); if (sbi->s_fc_bytes == 0) { /* @@ -1031,8 +1052,6 @@ static int ext4_fc_perform_commit(journal_t *journal) if (ret) goto out; spin_lock(&sbi->s_fc_lock); - EXT4_I(inode)->i_fc_committed_subtid = - atomic_read(&sbi->s_fc_subtid); } spin_unlock(&sbi->s_fc_lock); @@ -1131,7 +1150,7 @@ out: "Fast commit ended with blks = %d, reason = %d, subtid - %d", nblks, reason, subtid); if (reason == EXT4_FC_REASON_FC_FAILED) - return jbd2_fc_end_commit_fallback(journal, commit_tid); + return jbd2_fc_end_commit_fallback(journal); if (reason == EXT4_FC_REASON_FC_START_FAILED || reason == EXT4_FC_REASON_INELIGIBLE) return jbd2_complete_transaction(journal, commit_tid); @@ -1190,8 +1209,8 @@ static void ext4_fc_cleanup(journal_t *journal, int full) list_splice_init(&sbi->s_fc_q[FC_Q_STAGING], &sbi->s_fc_q[FC_Q_STAGING]); - sbi->s_mount_flags &= ~EXT4_MF_FC_COMMITTING; - sbi->s_mount_flags &= ~EXT4_MF_FC_INELIGIBLE; + ext4_clear_mount_flag(sb, EXT4_MF_FC_COMMITTING); + ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); if (full) sbi->s_fc_bytes = 0; @@ -1263,7 +1282,7 @@ static int ext4_fc_replay_unlink(struct super_block *sb, struct ext4_fc_tl *tl) return 0; } - ret = __ext4_unlink(old_parent, &entry, inode); + ret = __ext4_unlink(NULL, old_parent, &entry, inode); /* -ENOENT ok coz it might not exist anymore. */ if (ret == -ENOENT) ret = 0; @@ -2079,8 +2098,6 @@ static int ext4_fc_replay(journal_t *journal, struct buffer_head *bh, void ext4_fc_init(struct super_block *sb, journal_t *journal) { - int num_fc_blocks; - /* * We set replay callback even if fast commit disabled because we may * could still have fast commit blocks that need to be replayed even if @@ -2090,21 +2107,9 @@ void ext4_fc_init(struct super_block *sb, journal_t *journal) if (!test_opt2(sb, JOURNAL_FAST_COMMIT)) return; journal->j_fc_cleanup_callback = ext4_fc_cleanup; - if (!buffer_uptodate(journal->j_sb_buffer) - && ext4_read_bh_lock(journal->j_sb_buffer, REQ_META | REQ_PRIO, - true)) { - ext4_msg(sb, KERN_ERR, "I/O error on journal"); - return; - } - num_fc_blocks = be32_to_cpu(journal->j_superblock->s_num_fc_blks); - if (jbd2_fc_init(journal, num_fc_blocks ? num_fc_blocks : - EXT4_NUM_FC_BLKS)) { - pr_warn("Error while enabling fast commits, turning off."); - ext4_clear_feature_fast_commit(sb); - } } -const char *fc_ineligible_reasons[] = { +static const char *fc_ineligible_reasons[] = { "Extended attributes changed", "Cross rename", "Journal flag changed", @@ -2113,6 +2118,7 @@ const char *fc_ineligible_reasons[] = { "Resize", "Dir renamed", "Falloc range op", + "Data journalling", "FC Commit Failed" }; diff --git a/fs/ext4/fast_commit.h b/fs/ext4/fast_commit.h index 06907d485989..3a6e5a1fa1b8 100644 --- a/fs/ext4/fast_commit.h +++ b/fs/ext4/fast_commit.h @@ -3,9 +3,6 @@ #ifndef __FAST_COMMIT_H__ #define __FAST_COMMIT_H__ -/* Number of blocks in journal area to allocate for fast commits */ -#define EXT4_NUM_FC_BLKS 256 - /* Fast commit tags */ #define EXT4_FC_TAG_ADD_RANGE 0x0001 #define EXT4_FC_TAG_DEL_RANGE 0x0002 @@ -100,11 +97,12 @@ enum { EXT4_FC_REASON_XATTR = 0, EXT4_FC_REASON_CROSS_RENAME, EXT4_FC_REASON_JOURNAL_FLAG_CHANGE, - EXT4_FC_REASON_MEM, + EXT4_FC_REASON_NOMEM, EXT4_FC_REASON_SWAP_BOOT, EXT4_FC_REASON_RESIZE, EXT4_FC_REASON_RENAME_DIR, EXT4_FC_REASON_FALLOC_RANGE, + EXT4_FC_REASON_INODE_JOURNAL_DATA, EXT4_FC_COMMIT_FAILED, EXT4_FC_REASON_MAX }; diff --git a/fs/ext4/file.c b/fs/ext4/file.c index d85412d12e3a..3ed8c048fb12 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -761,7 +761,6 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma) if (!daxdev_mapping_supported(vma, dax_dev)) return -EOPNOTSUPP; - ext4_fc_start_update(inode); file_accessed(file); if (IS_DAX(file_inode(file))) { vma->vm_ops = &ext4_dax_vm_ops; @@ -769,7 +768,6 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma) } else { vma->vm_ops = &ext4_file_vm_ops; } - ext4_fc_stop_update(inode); return 0; } @@ -782,13 +780,13 @@ static int ext4_sample_last_mounted(struct super_block *sb, handle_t *handle; int err; - if (likely(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED)) + if (likely(ext4_test_mount_flag(sb, EXT4_MF_MNTDIR_SAMPLED))) return 0; if (sb_rdonly(sb) || !sb_start_intwrite_trylock(sb)) return 0; - sbi->s_mount_flags |= EXT4_MF_MNTDIR_SAMPLED; + ext4_set_mount_flag(sb, EXT4_MF_MNTDIR_SAMPLED); /* * Sample where the filesystem has been mounted and * store it in the superblock for sysadmin convenience diff --git a/fs/ext4/fsmap.c b/fs/ext4/fsmap.c index b232c2767534..4c2a9fe30067 100644 --- a/fs/ext4/fsmap.c +++ b/fs/ext4/fsmap.c @@ -280,7 +280,7 @@ static int ext4_getfsmap_logdev(struct super_block *sb, struct ext4_fsmap *keys, /* Fabricate an rmap entry for the external log device. */ irec.fmr_physical = journal->j_blk_offset; - irec.fmr_length = journal->j_maxlen; + irec.fmr_length = journal->j_total_len; irec.fmr_owner = EXT4_FMR_OWN_LOG; irec.fmr_flags = 0; diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 81a545fd14a3..a42ca95840f2 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -143,7 +143,7 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) if (sb_rdonly(inode->i_sb)) { /* Make sure that we read updated s_mount_flags value */ smp_rmb(); - if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) + if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FS_ABORTED)) ret = -EROFS; goto out; } diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index caa51473207d..b41512d1badc 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -1880,6 +1880,7 @@ int ext4_inline_data_truncate(struct inode *inode, int *has_inline) ext4_write_lock_xattr(inode, &no_expand); if (!ext4_has_inline_data(inode)) { + ext4_write_unlock_xattr(inode, &no_expand); *has_inline = 0; ext4_journal_stop(handle); return 0; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index b96a18679a27..0d8385aea898 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -327,6 +327,8 @@ stop_handle: ext4_xattr_inode_array_free(ea_inode_array); return; no_delete: + if (!list_empty(&EXT4_I(inode)->i_fc_list)) + ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM); ext4_clear_inode(inode); /* We must guarantee clearing of inode... */ } @@ -730,7 +732,7 @@ out_sem: if (ret) return ret; } - ext4_fc_track_range(inode, map->m_lblk, + ext4_fc_track_range(handle, inode, map->m_lblk, map->m_lblk + map->m_len - 1); } @@ -2440,7 +2442,7 @@ static int mpage_map_and_submit_extent(handle_t *handle, struct super_block *sb = inode->i_sb; if (ext4_forced_shutdown(EXT4_SB(sb)) || - EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED) + ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED)) goto invalidate_dirty_pages; /* * Let the uper layers retry transient errors. @@ -2674,7 +2676,7 @@ static int ext4_writepages(struct address_space *mapping, * the stack trace. */ if (unlikely(ext4_forced_shutdown(EXT4_SB(mapping->host->i_sb)) || - sbi->s_mount_flags & EXT4_MF_FS_ABORTED)) { + ext4_test_mount_flag(inode->i_sb, EXT4_MF_FS_ABORTED))) { ret = -EROFS; goto out_writepages; } @@ -3310,8 +3312,7 @@ static bool ext4_inode_datasync_dirty(struct inode *inode) EXT4_I(inode)->i_datasync_tid)) return false; if (test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT)) - return atomic_read(&EXT4_SB(inode->i_sb)->s_fc_subtid) < - EXT4_I(inode)->i_fc_committed_subtid; + return !list_empty(&EXT4_I(inode)->i_fc_list); return true; } @@ -4109,7 +4110,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) up_write(&EXT4_I(inode)->i_data_sem); } - ext4_fc_track_range(inode, first_block, stop_block); + ext4_fc_track_range(handle, inode, first_block, stop_block); if (IS_SYNC(inode)) ext4_handle_sync(handle); @@ -5442,14 +5443,14 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) } if (shrink) - ext4_fc_track_range(inode, + ext4_fc_track_range(handle, inode, (attr->ia_size > 0 ? attr->ia_size - 1 : 0) >> inode->i_sb->s_blocksize_bits, (oldsize > 0 ? oldsize - 1 : 0) >> inode->i_sb->s_blocksize_bits); else ext4_fc_track_range( - inode, + handle, inode, (oldsize > 0 ? oldsize - 1 : oldsize) >> inode->i_sb->s_blocksize_bits, (attr->ia_size > 0 ? attr->ia_size - 1 : 0) >> @@ -5699,7 +5700,7 @@ int ext4_mark_iloc_dirty(handle_t *handle, put_bh(iloc->bh); return -EIO; } - ext4_fc_track_inode(inode); + ext4_fc_track_inode(handle, inode); if (IS_I_VERSION(inode)) inode_inc_iversion(inode); diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 85abbfb98cbe..24af9ed5c3e5 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -4477,7 +4477,7 @@ static inline void ext4_mb_show_pa(struct super_block *sb) { ext4_group_t i, ngroups; - if (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED) + if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED)) return; ngroups = ext4_get_groups_count(sb); @@ -4508,7 +4508,7 @@ static void ext4_mb_show_ac(struct ext4_allocation_context *ac) { struct super_block *sb = ac->ac_sb; - if (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED) + if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED)) return; mb_debug(sb, "Can't allocate:" @@ -5167,7 +5167,7 @@ static ext4_fsblk_t ext4_mb_new_blocks_simple(handle_t *handle, struct super_block *sb = ar->inode->i_sb; ext4_group_t group; ext4_grpblk_t blkoff; - int i; + int i = sb->s_blocksize; ext4_fsblk_t goal, block; struct ext4_super_block *es = EXT4_SB(sb)->s_es; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index f458d1d81d96..33509266f5a0 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2606,7 +2606,7 @@ static int ext4_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { handle_t *handle; - struct inode *inode, *inode_save; + struct inode *inode; int err, credits, retries = 0; err = dquot_initialize(dir); @@ -2624,11 +2624,9 @@ retry: inode->i_op = &ext4_file_inode_operations; inode->i_fop = &ext4_file_operations; ext4_set_aops(inode); - inode_save = inode; - ihold(inode_save); err = ext4_add_nondir(handle, dentry, &inode); - ext4_fc_track_create(inode_save, dentry); - iput(inode_save); + if (!err) + ext4_fc_track_create(handle, dentry); } if (handle) ext4_journal_stop(handle); @@ -2643,7 +2641,7 @@ static int ext4_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) { handle_t *handle; - struct inode *inode, *inode_save; + struct inode *inode; int err, credits, retries = 0; err = dquot_initialize(dir); @@ -2660,12 +2658,9 @@ retry: if (!IS_ERR(inode)) { init_special_inode(inode, inode->i_mode, rdev); inode->i_op = &ext4_special_inode_operations; - inode_save = inode; - ihold(inode_save); err = ext4_add_nondir(handle, dentry, &inode); if (!err) - ext4_fc_track_create(inode_save, dentry); - iput(inode_save); + ext4_fc_track_create(handle, dentry); } if (handle) ext4_journal_stop(handle); @@ -2829,7 +2824,6 @@ out_clear_inode: iput(inode); goto out_retry; } - ext4_fc_track_create(inode, dentry); ext4_inc_count(dir); ext4_update_dx_flag(dir); @@ -2837,6 +2831,7 @@ out_clear_inode: if (err) goto out_clear_inode; d_instantiate_new(dentry, inode); + ext4_fc_track_create(handle, dentry); if (IS_DIRSYNC(dir)) ext4_handle_sync(handle); @@ -3171,7 +3166,7 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry) goto end_rmdir; ext4_dec_count(dir); ext4_update_dx_flag(dir); - ext4_fc_track_unlink(inode, dentry); + ext4_fc_track_unlink(handle, dentry); retval = ext4_mark_inode_dirty(handle, dir); #ifdef CONFIG_UNICODE @@ -3192,13 +3187,12 @@ end_rmdir: return retval; } -int __ext4_unlink(struct inode *dir, const struct qstr *d_name, +int __ext4_unlink(handle_t *handle, struct inode *dir, const struct qstr *d_name, struct inode *inode) { int retval = -ENOENT; struct buffer_head *bh; struct ext4_dir_entry_2 *de; - handle_t *handle = NULL; int skip_remove_dentry = 0; bh = ext4_find_entry(dir, d_name, &de, NULL); @@ -3217,14 +3211,7 @@ int __ext4_unlink(struct inode *dir, const struct qstr *d_name, if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) skip_remove_dentry = 1; else - goto out_bh; - } - - handle = ext4_journal_start(dir, EXT4_HT_DIR, - EXT4_DATA_TRANS_BLOCKS(dir->i_sb)); - if (IS_ERR(handle)) { - retval = PTR_ERR(handle); - goto out_bh; + goto out; } if (IS_DIRSYNC(dir)) @@ -3233,12 +3220,12 @@ int __ext4_unlink(struct inode *dir, const struct qstr *d_name, if (!skip_remove_dentry) { retval = ext4_delete_entry(handle, dir, de, bh); if (retval) - goto out_handle; + goto out; dir->i_ctime = dir->i_mtime = current_time(dir); ext4_update_dx_flag(dir); retval = ext4_mark_inode_dirty(handle, dir); if (retval) - goto out_handle; + goto out; } else { retval = 0; } @@ -3252,15 +3239,14 @@ int __ext4_unlink(struct inode *dir, const struct qstr *d_name, inode->i_ctime = current_time(inode); retval = ext4_mark_inode_dirty(handle, inode); -out_handle: - ext4_journal_stop(handle); -out_bh: +out: brelse(bh); return retval; } static int ext4_unlink(struct inode *dir, struct dentry *dentry) { + handle_t *handle; int retval; if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb)))) @@ -3278,9 +3264,16 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry) if (retval) goto out_trace; - retval = __ext4_unlink(dir, &dentry->d_name, d_inode(dentry)); + handle = ext4_journal_start(dir, EXT4_HT_DIR, + EXT4_DATA_TRANS_BLOCKS(dir->i_sb)); + if (IS_ERR(handle)) { + retval = PTR_ERR(handle); + goto out_trace; + } + + retval = __ext4_unlink(handle, dir, &dentry->d_name, d_inode(dentry)); if (!retval) - ext4_fc_track_unlink(d_inode(dentry), dentry); + ext4_fc_track_unlink(handle, dentry); #ifdef CONFIG_UNICODE /* VFS negative dentries are incompatible with Encoding and * Case-insensitiveness. Eventually we'll want avoid @@ -3291,6 +3284,8 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry) if (IS_CASEFOLDED(dir)) d_invalidate(dentry); #endif + if (handle) + ext4_journal_stop(handle); out_trace: trace_ext4_unlink_exit(dentry, retval); @@ -3447,7 +3442,6 @@ retry: err = ext4_add_entry(handle, dentry, inode); if (!err) { - ext4_fc_track_link(inode, dentry); err = ext4_mark_inode_dirty(handle, inode); /* this can happen only for tmpfile being * linked the first time @@ -3455,6 +3449,7 @@ retry: if (inode->i_nlink == 1) ext4_orphan_del(handle, inode); d_instantiate(dentry, inode); + ext4_fc_track_link(handle, dentry); } else { drop_nlink(inode); iput(inode); @@ -3915,9 +3910,9 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, EXT4_FC_REASON_RENAME_DIR); } else { if (new.inode) - ext4_fc_track_unlink(new.inode, new.dentry); - ext4_fc_track_link(old.inode, new.dentry); - ext4_fc_track_unlink(old.inode, old.dentry); + ext4_fc_track_unlink(handle, new.dentry); + __ext4_fc_track_link(handle, old.inode, new.dentry); + __ext4_fc_track_unlink(handle, old.inode, old.dentry); } if (new.inode) { diff --git a/fs/ext4/super.c b/fs/ext4/super.c index ef4734b40e2a..6633b20224d5 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -289,18 +289,7 @@ void ext4_superblock_csum_set(struct super_block *sb) if (!ext4_has_metadata_csum(sb)) return; - /* - * Locking the superblock prevents the scenario - * where: - * 1) a first thread pauses during checksum calculation. - * 2) a second thread updates the superblock, recalculates - * the checksum, and updates s_checksum - * 3) the first thread resumes and finishes its checksum calculation - * and updates s_checksum with a potentially stale or torn value. - */ - lock_buffer(EXT4_SB(sb)->s_sbh); es->s_checksum = ext4_superblock_csum(sb, es); - unlock_buffer(EXT4_SB(sb)->s_sbh); } ext4_fsblk_t ext4_block_bitmap(struct super_block *sb, @@ -686,7 +675,7 @@ static void ext4_handle_error(struct super_block *sb) if (!test_opt(sb, ERRORS_CONT)) { journal_t *journal = EXT4_SB(sb)->s_journal; - EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED; + ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED); if (journal) jbd2_journal_abort(journal, -EIO); } @@ -904,7 +893,7 @@ void __ext4_abort(struct super_block *sb, const char *function, va_end(args); if (sb_rdonly(sb) == 0) { - EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED; + ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED); if (EXT4_SB(sb)->s_journal) jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO); @@ -1716,11 +1705,10 @@ enum { Opt_dioread_nolock, Opt_dioread_lock, Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable, Opt_max_dir_size_kb, Opt_nojournal_checksum, Opt_nombcache, - Opt_prefetch_block_bitmaps, Opt_no_fc, + Opt_prefetch_block_bitmaps, #ifdef CONFIG_EXT4_DEBUG - Opt_fc_debug_max_replay, + Opt_fc_debug_max_replay, Opt_fc_debug_force #endif - Opt_fc_debug_force }; static const match_table_t tokens = { @@ -1807,9 +1795,8 @@ static const match_table_t tokens = { {Opt_init_itable, "init_itable=%u"}, {Opt_init_itable, "init_itable"}, {Opt_noinit_itable, "noinit_itable"}, - {Opt_no_fc, "no_fc"}, - {Opt_fc_debug_force, "fc_debug_force"}, #ifdef CONFIG_EXT4_DEBUG + {Opt_fc_debug_force, "fc_debug_force"}, {Opt_fc_debug_max_replay, "fc_debug_max_replay=%u"}, #endif {Opt_max_dir_size_kb, "max_dir_size_kb=%u"}, @@ -2027,8 +2014,8 @@ static const struct mount_opts { {Opt_noquota, (EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA | EXT4_MOUNT_GRPQUOTA | EXT4_MOUNT_PRJQUOTA), MOPT_CLEAR | MOPT_Q}, - {Opt_usrjquota, 0, MOPT_Q}, - {Opt_grpjquota, 0, MOPT_Q}, + {Opt_usrjquota, 0, MOPT_Q | MOPT_STRING}, + {Opt_grpjquota, 0, MOPT_Q | MOPT_STRING}, {Opt_offusrjquota, 0, MOPT_Q}, {Opt_offgrpjquota, 0, MOPT_Q}, {Opt_jqfmt_vfsold, QFMT_VFS_OLD, MOPT_QFMT}, @@ -2039,11 +2026,9 @@ static const struct mount_opts { {Opt_nombcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET}, {Opt_prefetch_block_bitmaps, EXT4_MOUNT_PREFETCH_BLOCK_BITMAPS, MOPT_SET}, - {Opt_no_fc, EXT4_MOUNT2_JOURNAL_FAST_COMMIT, - MOPT_CLEAR | MOPT_2 | MOPT_EXT4_ONLY}, +#ifdef CONFIG_EXT4_DEBUG {Opt_fc_debug_force, EXT4_MOUNT2_JOURNAL_FAST_COMMIT, MOPT_SET | MOPT_2 | MOPT_EXT4_ONLY}, -#ifdef CONFIG_EXT4_DEBUG {Opt_fc_debug_max_replay, 0, MOPT_GTE0}, #endif {Opt_err, 0, 0} @@ -2153,7 +2138,7 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, ext4_msg(sb, KERN_WARNING, "Ignoring removed %s option", opt); return 1; case Opt_abort: - sbi->s_mount_flags |= EXT4_MF_FS_ABORTED; + ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED); return 1; case Opt_i_version: sb->s_flags |= SB_I_VERSION; @@ -3976,7 +3961,7 @@ int ext4_calculate_overhead(struct super_block *sb) * loaded or not */ if (sbi->s_journal && !sbi->s_journal_bdev) - overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_maxlen); + overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_total_len); else if (ext4_has_feature_journal(sb) && !sbi->s_journal && j_inum) { /* j_inum for internal journal is non-zero */ j_inode = ext4_get_journal_inode(sb, j_inum); @@ -4340,9 +4325,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) #endif if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) { - printk_once(KERN_WARNING "EXT4-fs: Warning: mounting with data=journal disables delayed allocation, dioread_nolock, and O_DIRECT support!\n"); + printk_once(KERN_WARNING "EXT4-fs: Warning: mounting with data=journal disables delayed allocation, dioread_nolock, O_DIRECT and fast_commit support!\n"); /* can't mount with both data=journal and dioread_nolock. */ clear_opt(sb, DIOREAD_NOLOCK); + clear_opt2(sb, JOURNAL_FAST_COMMIT); if (test_opt2(sb, EXPLICIT_DELALLOC)) { ext4_msg(sb, KERN_ERR, "can't mount with " "both data=journal and delalloc"); @@ -4777,8 +4763,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) INIT_LIST_HEAD(&sbi->s_fc_dentry_q[FC_Q_MAIN]); INIT_LIST_HEAD(&sbi->s_fc_dentry_q[FC_Q_STAGING]); sbi->s_fc_bytes = 0; - sbi->s_mount_flags &= ~EXT4_MF_FC_INELIGIBLE; - sbi->s_mount_flags &= ~EXT4_MF_FC_COMMITTING; + ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); + ext4_clear_mount_flag(sb, EXT4_MF_FC_COMMITTING); spin_lock_init(&sbi->s_fc_lock); memset(&sbi->s_fc_stats, 0, sizeof(sbi->s_fc_stats)); sbi->s_fc_replay_state.fc_regions = NULL; @@ -4857,6 +4843,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount_wq; } + if (test_opt2(sb, JOURNAL_FAST_COMMIT) && + !jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0, + JBD2_FEATURE_INCOMPAT_FAST_COMMIT)) { + ext4_msg(sb, KERN_ERR, + "Failed to set fast commit journal feature"); + goto failed_mount_wq; + } + /* We have now updated the journal if required, so we can * validate the data journaling mode. */ switch (test_opt(sb, DATA_FLAGS)) { @@ -5872,7 +5866,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) goto restore_opts; } - if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) + if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED)) ext4_abort(sb, EXT4_ERR_ESHUTDOWN, "Abort forced by user"); sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | @@ -5886,7 +5880,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) } if ((bool)(*flags & SB_RDONLY) != sb_rdonly(sb)) { - if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) { + if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED)) { err = -EROFS; goto restore_opts; } @@ -6560,10 +6554,6 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type, brelse(bh); out: if (inode->i_size < off + len) { - ext4_fc_track_range(inode, - (inode->i_size > 0 ? inode->i_size - 1 : 0) - >> inode->i_sb->s_blocksize_bits, - (off + len) >> inode->i_sb->s_blocksize_bits); i_size_write(inode, off + len); EXT4_I(inode)->i_disksize = inode->i_size; err2 = ext4_mark_inode_dirty(handle, inode); diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 9cd2ecad07db..cc4f987687f3 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -77,7 +77,7 @@ static int gfs2_get_block_noalloc(struct inode *inode, sector_t lblock, if (error) return error; if (!buffer_mapped(bh_result)) - return -EIO; + return -ENODATA; return 0; } diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 8dff9cbd0a87..62d9081d1e26 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -1301,12 +1301,8 @@ int gfs2_block_map(struct inode *inode, sector_t lblock, trace_gfs2_bmap(ip, bh_map, lblock, create, 1); ret = gfs2_iomap_get(inode, pos, length, flags, &iomap, &mp); - if (!ret && iomap.type == IOMAP_HOLE) { - if (create) - ret = gfs2_iomap_alloc(inode, &iomap, &mp); - else - ret = -ENODATA; - } + if (create && !ret && iomap.type == IOMAP_HOLE) + ret = gfs2_iomap_alloc(inode, &iomap, &mp); release_metapath(&mp); if (ret) goto out; diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 9133b3178677..2e9314091c81 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -132,6 +132,8 @@ __acquires(&sdp->sd_ail_lock) spin_unlock(&sdp->sd_ail_lock); ret = generic_writepages(mapping, wbc); spin_lock(&sdp->sd_ail_lock); + if (ret == -ENODATA) /* if a jdata write into a new hole */ + ret = 0; /* ignore it */ if (ret || wbc->nr_to_write <= 0) break; return -EBUSY; diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 92d799a193b8..f7addc6197ed 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -2529,13 +2529,13 @@ int gfs2_check_blk_type(struct gfs2_sbd *sdp, u64 no_addr, unsigned int type) rbm.rgd = rgd; error = gfs2_rbm_from_block(&rbm, no_addr); - if (WARN_ON_ONCE(error)) - goto fail; - - if (gfs2_testbit(&rbm, false) != type) - error = -ESTALE; + if (!WARN_ON_ONCE(error)) { + if (gfs2_testbit(&rbm, false) != type) + error = -ESTALE; + } gfs2_glock_dq_uninit(&rgd_gh); + fail: return error; } diff --git a/fs/io_uring.c b/fs/io_uring.c index 8018c7076b25..4ead291b2976 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -3547,8 +3547,7 @@ static int io_write(struct io_kiocb *req, bool force_nonblock, * we return to userspace. */ if (req->flags & REQ_F_ISREG) { - __sb_start_write(file_inode(req->file)->i_sb, - SB_FREEZE_WRITE, true); + sb_start_write(file_inode(req->file)->i_sb); __sb_writers_release(file_inode(req->file)->i_sb, SB_FREEZE_WRITE); } @@ -9226,6 +9225,7 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, * to a power-of-two, if it isn't already. We do NOT impose * any cq vs sq ring sizing. */ + p->cq_entries = roundup_pow_of_two(p->cq_entries); if (p->cq_entries < p->sq_entries) return -EINVAL; if (p->cq_entries > IORING_MAX_CQ_ENTRIES) { @@ -9233,7 +9233,6 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, return -EINVAL; p->cq_entries = IORING_MAX_CQ_ENTRIES; } - p->cq_entries = roundup_pow_of_two(p->cq_entries); } else { p->cq_entries = 2 * p->sq_entries; } diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 263f02ad8ebf..472932b9e6bc 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -106,6 +106,8 @@ static int __try_to_free_cp_buf(struct journal_head *jh) * for a checkpoint to free up some space in the log. */ void __jbd2_log_wait_for_space(journal_t *journal) +__acquires(&journal->j_state_lock) +__releases(&journal->j_state_lock) { int nblocks, space_left; /* assert_spin_locked(&journal->j_state_lock); */ diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index fa688e163a80..b121d7d434c6 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -450,6 +450,15 @@ void jbd2_journal_commit_transaction(journal_t *journal) schedule(); write_lock(&journal->j_state_lock); finish_wait(&journal->j_fc_wait, &wait); + /* + * TODO: by blocking fast commits here, we are increasing + * fsync() latency slightly. Strictly speaking, we don't need + * to block fast commits until the transaction enters T_FLUSH + * state. So an optimization is possible where we block new fast + * commits here and wait for existing ones to complete + * just before we enter T_FLUSH. That way, the existing fast + * commits and this full commit can proceed parallely. + */ } write_unlock(&journal->j_state_lock); @@ -801,7 +810,7 @@ start_journal_io: if (first_block < journal->j_tail) freed += journal->j_last - journal->j_first; /* Update tail only if we free significant amount of space */ - if (freed < journal->j_maxlen / 4) + if (freed < jbd2_journal_get_max_txn_bufs(journal)) update_tail = 0; } J_ASSERT(commit_transaction->t_state == T_COMMIT); diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 0c7c42bd530f..0c3d5e3b24b2 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -727,6 +727,8 @@ int jbd2_log_wait_commit(journal_t *journal, tid_t tid) */ int jbd2_fc_begin_commit(journal_t *journal, tid_t tid) { + if (unlikely(is_journal_aborted(journal))) + return -EIO; /* * Fast commits only allowed if at least one full commit has * been processed. @@ -734,10 +736,12 @@ int jbd2_fc_begin_commit(journal_t *journal, tid_t tid) if (!journal->j_stats.ts_tid) return -EINVAL; - if (tid <= journal->j_commit_sequence) + write_lock(&journal->j_state_lock); + if (tid <= journal->j_commit_sequence) { + write_unlock(&journal->j_state_lock); return -EALREADY; + } - write_lock(&journal->j_state_lock); if (journal->j_flags & JBD2_FULL_COMMIT_ONGOING || (journal->j_flags & JBD2_FAST_COMMIT_ONGOING)) { DEFINE_WAIT(wait); @@ -777,13 +781,19 @@ static int __jbd2_fc_end_commit(journal_t *journal, tid_t tid, bool fallback) int jbd2_fc_end_commit(journal_t *journal) { - return __jbd2_fc_end_commit(journal, 0, 0); + return __jbd2_fc_end_commit(journal, 0, false); } EXPORT_SYMBOL(jbd2_fc_end_commit); -int jbd2_fc_end_commit_fallback(journal_t *journal, tid_t tid) +int jbd2_fc_end_commit_fallback(journal_t *journal) { - return __jbd2_fc_end_commit(journal, tid, 1); + tid_t tid; + + read_lock(&journal->j_state_lock); + tid = journal->j_running_transaction ? + journal->j_running_transaction->t_tid : 0; + read_unlock(&journal->j_state_lock); + return __jbd2_fc_end_commit(journal, tid, true); } EXPORT_SYMBOL(jbd2_fc_end_commit_fallback); @@ -865,7 +875,6 @@ int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out) int fc_off; *bh_out = NULL; - write_lock(&journal->j_state_lock); if (journal->j_fc_off + journal->j_fc_first < journal->j_fc_last) { fc_off = journal->j_fc_off; @@ -874,7 +883,6 @@ int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out) } else { ret = -EINVAL; } - write_unlock(&journal->j_state_lock); if (ret) return ret; @@ -887,11 +895,7 @@ int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out) if (!bh) return -ENOMEM; - lock_buffer(bh); - clear_buffer_uptodate(bh); - set_buffer_dirty(bh); - unlock_buffer(bh); journal->j_fc_wbuf[fc_off] = bh; *bh_out = bh; @@ -909,9 +913,7 @@ int jbd2_fc_wait_bufs(journal_t *journal, int num_blks) struct buffer_head *bh; int i, j_fc_off; - read_lock(&journal->j_state_lock); j_fc_off = journal->j_fc_off; - read_unlock(&journal->j_state_lock); /* * Wait in reverse order to minimize chances of us being woken up before @@ -939,9 +941,7 @@ int jbd2_fc_release_bufs(journal_t *journal) struct buffer_head *bh; int i, j_fc_off; - read_lock(&journal->j_state_lock); j_fc_off = journal->j_fc_off; - read_unlock(&journal->j_state_lock); /* * Wait in reverse order to minimize chances of us being woken up before @@ -1348,23 +1348,16 @@ static journal_t *journal_init_common(struct block_device *bdev, journal->j_dev = bdev; journal->j_fs_dev = fs_dev; journal->j_blk_offset = start; - journal->j_maxlen = len; + journal->j_total_len = len; /* We need enough buffers to write out full descriptor block. */ n = journal->j_blocksize / jbd2_min_tag_size(); journal->j_wbufsize = n; + journal->j_fc_wbuf = NULL; journal->j_wbuf = kmalloc_array(n, sizeof(struct buffer_head *), GFP_KERNEL); if (!journal->j_wbuf) goto err_cleanup; - if (journal->j_fc_wbufsize > 0) { - journal->j_fc_wbuf = kmalloc_array(journal->j_fc_wbufsize, - sizeof(struct buffer_head *), - GFP_KERNEL); - if (!journal->j_fc_wbuf) - goto err_cleanup; - } - bh = getblk_unmovable(journal->j_dev, start, journal->j_blocksize); if (!bh) { pr_err("%s: Cannot get buffer for journal superblock\n", @@ -1378,23 +1371,11 @@ static journal_t *journal_init_common(struct block_device *bdev, err_cleanup: kfree(journal->j_wbuf); - kfree(journal->j_fc_wbuf); jbd2_journal_destroy_revoke(journal); kfree(journal); return NULL; } -int jbd2_fc_init(journal_t *journal, int num_fc_blks) -{ - journal->j_fc_wbufsize = num_fc_blks; - journal->j_fc_wbuf = kmalloc_array(journal->j_fc_wbufsize, - sizeof(struct buffer_head *), GFP_KERNEL); - if (!journal->j_fc_wbuf) - return -ENOMEM; - return 0; -} -EXPORT_SYMBOL(jbd2_fc_init); - /* jbd2_journal_init_dev and jbd2_journal_init_inode: * * Create a journal structure assigned some fixed set of disk blocks to @@ -1512,16 +1493,7 @@ static int journal_reset(journal_t *journal) } journal->j_first = first; - - if (jbd2_has_feature_fast_commit(journal) && - journal->j_fc_wbufsize > 0) { - journal->j_fc_last = last; - journal->j_last = last - journal->j_fc_wbufsize; - journal->j_fc_first = journal->j_last + 1; - journal->j_fc_off = 0; - } else { - journal->j_last = last; - } + journal->j_last = last; journal->j_head = journal->j_first; journal->j_tail = journal->j_first; @@ -1531,7 +1503,14 @@ static int journal_reset(journal_t *journal) journal->j_commit_sequence = journal->j_transaction_sequence - 1; journal->j_commit_request = journal->j_commit_sequence; - journal->j_max_transaction_buffers = journal->j_maxlen / 4; + journal->j_max_transaction_buffers = jbd2_journal_get_max_txn_bufs(journal); + + /* + * Now that journal recovery is done, turn fast commits off here. This + * way, if fast commit was enabled before the crash but if now FS has + * disabled it, we don't enable fast commits. + */ + jbd2_clear_feature_fast_commit(journal); /* * As a special case, if the on-disk copy is already marked as needing @@ -1792,15 +1771,15 @@ static int journal_get_superblock(journal_t *journal) goto out; } - if (be32_to_cpu(sb->s_maxlen) < journal->j_maxlen) - journal->j_maxlen = be32_to_cpu(sb->s_maxlen); - else if (be32_to_cpu(sb->s_maxlen) > journal->j_maxlen) { + if (be32_to_cpu(sb->s_maxlen) < journal->j_total_len) + journal->j_total_len = be32_to_cpu(sb->s_maxlen); + else if (be32_to_cpu(sb->s_maxlen) > journal->j_total_len) { printk(KERN_WARNING "JBD2: journal file too short\n"); goto out; } if (be32_to_cpu(sb->s_first) == 0 || - be32_to_cpu(sb->s_first) >= journal->j_maxlen) { + be32_to_cpu(sb->s_first) >= journal->j_total_len) { printk(KERN_WARNING "JBD2: Invalid start block of journal: %u\n", be32_to_cpu(sb->s_first)); @@ -1872,6 +1851,7 @@ static int load_superblock(journal_t *journal) { int err; journal_superblock_t *sb; + int num_fc_blocks; err = journal_get_superblock(journal); if (err) @@ -1883,15 +1863,17 @@ static int load_superblock(journal_t *journal) journal->j_tail = be32_to_cpu(sb->s_start); journal->j_first = be32_to_cpu(sb->s_first); journal->j_errno = be32_to_cpu(sb->s_errno); + journal->j_last = be32_to_cpu(sb->s_maxlen); - if (jbd2_has_feature_fast_commit(journal) && - journal->j_fc_wbufsize > 0) { + if (jbd2_has_feature_fast_commit(journal)) { journal->j_fc_last = be32_to_cpu(sb->s_maxlen); - journal->j_last = journal->j_fc_last - journal->j_fc_wbufsize; + num_fc_blocks = be32_to_cpu(sb->s_num_fc_blks); + if (!num_fc_blocks) + num_fc_blocks = JBD2_MIN_FC_BLOCKS; + if (journal->j_last - num_fc_blocks >= JBD2_MIN_JOURNAL_BLOCKS) + journal->j_last = journal->j_fc_last - num_fc_blocks; journal->j_fc_first = journal->j_last + 1; journal->j_fc_off = 0; - } else { - journal->j_last = be32_to_cpu(sb->s_maxlen); } return 0; @@ -1954,9 +1936,6 @@ int jbd2_journal_load(journal_t *journal) */ journal->j_flags &= ~JBD2_ABORT; - if (journal->j_fc_wbufsize > 0) - jbd2_journal_set_features(journal, 0, 0, - JBD2_FEATURE_INCOMPAT_FAST_COMMIT); /* OK, we've finished with the dynamic journal bits: * reinitialise the dynamic contents of the superblock in memory * and reset them on disk. */ @@ -2040,8 +2019,7 @@ int jbd2_journal_destroy(journal_t *journal) jbd2_journal_destroy_revoke(journal); if (journal->j_chksum_driver) crypto_free_shash(journal->j_chksum_driver); - if (journal->j_fc_wbufsize > 0) - kfree(journal->j_fc_wbuf); + kfree(journal->j_fc_wbuf); kfree(journal->j_wbuf); kfree(journal); @@ -2116,6 +2094,37 @@ int jbd2_journal_check_available_features(journal_t *journal, unsigned long comp return 0; } +static int +jbd2_journal_initialize_fast_commit(journal_t *journal) +{ + journal_superblock_t *sb = journal->j_superblock; + unsigned long long num_fc_blks; + + num_fc_blks = be32_to_cpu(sb->s_num_fc_blks); + if (num_fc_blks == 0) + num_fc_blks = JBD2_MIN_FC_BLOCKS; + if (journal->j_last - num_fc_blks < JBD2_MIN_JOURNAL_BLOCKS) + return -ENOSPC; + + /* Are we called twice? */ + WARN_ON(journal->j_fc_wbuf != NULL); + journal->j_fc_wbuf = kmalloc_array(num_fc_blks, + sizeof(struct buffer_head *), GFP_KERNEL); + if (!journal->j_fc_wbuf) + return -ENOMEM; + + journal->j_fc_wbufsize = num_fc_blks; + journal->j_fc_last = journal->j_last; + journal->j_last = journal->j_fc_last - num_fc_blks; + journal->j_fc_first = journal->j_last + 1; + journal->j_fc_off = 0; + journal->j_free = journal->j_last - journal->j_first; + journal->j_max_transaction_buffers = + jbd2_journal_get_max_txn_bufs(journal); + + return 0; +} + /** * int jbd2_journal_set_features() - Mark a given journal feature in the superblock * @journal: Journal to act on. @@ -2159,6 +2168,13 @@ int jbd2_journal_set_features(journal_t *journal, unsigned long compat, sb = journal->j_superblock; + if (incompat & JBD2_FEATURE_INCOMPAT_FAST_COMMIT) { + if (jbd2_journal_initialize_fast_commit(journal)) { + pr_err("JBD2: Cannot enable fast commits.\n"); + return 0; + } + } + /* Load the checksum driver if necessary */ if ((journal->j_chksum_driver == NULL) && INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V3)) { diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c index eb2606133cd8..dc0694fcfcd1 100644 --- a/fs/jbd2/recovery.c +++ b/fs/jbd2/recovery.c @@ -74,8 +74,8 @@ static int do_readahead(journal_t *journal, unsigned int start) /* Do up to 128K of readahead */ max = start + (128 * 1024 / journal->j_blocksize); - if (max > journal->j_maxlen) - max = journal->j_maxlen; + if (max > journal->j_total_len) + max = journal->j_total_len; /* Do the readahead itself. We'll submit MAXBUF buffer_heads at * a time to the block device IO layer. */ @@ -134,7 +134,7 @@ static int jread(struct buffer_head **bhp, journal_t *journal, *bhp = NULL; - if (offset >= journal->j_maxlen) { + if (offset >= journal->j_total_len) { printk(KERN_ERR "JBD2: corrupted journal superblock\n"); return -EFSCORRUPTED; } diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 43985738aa86..d54f04674e8e 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -195,8 +195,10 @@ static void wait_transaction_switching(journal_t *journal) DEFINE_WAIT(wait); if (WARN_ON(!journal->j_running_transaction || - journal->j_running_transaction->t_state != T_SWITCH)) + journal->j_running_transaction->t_state != T_SWITCH)) { + read_unlock(&journal->j_state_lock); return; + } prepare_to_wait(&journal->j_wait_transaction_locked, &wait, TASK_UNINTERRUPTIBLE); read_unlock(&journal->j_state_lock); diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index cb52db9a0cfb..4e011adaf967 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -955,7 +955,6 @@ out: static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence) { - struct inode *inode = file_inode(filp); struct nfs_open_dir_context *dir_ctx = filp->private_data; dfprintk(FILE, "NFS: llseek dir(%pD2, %lld, %d)\n", @@ -967,15 +966,15 @@ static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence) case SEEK_SET: if (offset < 0) return -EINVAL; - inode_lock(inode); + spin_lock(&filp->f_lock); break; case SEEK_CUR: if (offset == 0) return filp->f_pos; - inode_lock(inode); + spin_lock(&filp->f_lock); offset += filp->f_pos; if (offset < 0) { - inode_unlock(inode); + spin_unlock(&filp->f_lock); return -EINVAL; } } @@ -987,7 +986,7 @@ static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence) dir_ctx->dir_cookie = 0; dir_ctx->duped = 0; } - inode_unlock(inode); + spin_unlock(&filp->f_lock); return offset; } @@ -998,13 +997,9 @@ static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence) static int nfs_fsync_dir(struct file *filp, loff_t start, loff_t end, int datasync) { - struct inode *inode = file_inode(filp); - dfprintk(FILE, "NFS: fsync dir(%pD2) datasync %d\n", filp, datasync); - inode_lock(inode); - nfs_inc_stats(inode, NFSIOS_VFSFSYNC); - inode_unlock(inode); + nfs_inc_stats(file_inode(filp), NFSIOS_VFSFSYNC); return 0; } diff --git a/fs/nfs/nfs42xattr.c b/fs/nfs/nfs42xattr.c index b51424ff8159..6c2ce799150f 100644 --- a/fs/nfs/nfs42xattr.c +++ b/fs/nfs/nfs42xattr.c @@ -1047,8 +1047,10 @@ out4: void nfs4_xattr_cache_exit(void) { + unregister_shrinker(&nfs4_xattr_large_entry_shrinker); unregister_shrinker(&nfs4_xattr_entry_shrinker); unregister_shrinker(&nfs4_xattr_cache_shrinker); + list_lru_destroy(&nfs4_xattr_large_entry_lru); list_lru_destroy(&nfs4_xattr_entry_lru); list_lru_destroy(&nfs4_xattr_cache_lru); kmem_cache_destroy(nfs4_xattr_cache_cachep); diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c index 0dc31ad2362e..6e060a88f98c 100644 --- a/fs/nfs/nfs42xdr.c +++ b/fs/nfs/nfs42xdr.c @@ -196,7 +196,7 @@ 1 + nfs4_xattr_name_maxsz + 1) #define decode_setxattr_maxsz (op_decode_hdr_maxsz + decode_change_info_maxsz) #define encode_listxattrs_maxsz (op_encode_hdr_maxsz + 2 + 1) -#define decode_listxattrs_maxsz (op_decode_hdr_maxsz + 2 + 1 + 1) +#define decode_listxattrs_maxsz (op_decode_hdr_maxsz + 2 + 1 + 1 + 1) #define encode_removexattr_maxsz (op_encode_hdr_maxsz + 1 + \ nfs4_xattr_name_maxsz) #define decode_removexattr_maxsz (op_decode_hdr_maxsz + \ @@ -531,7 +531,7 @@ static void encode_listxattrs(struct xdr_stream *xdr, { __be32 *p; - encode_op_hdr(xdr, OP_LISTXATTRS, decode_listxattrs_maxsz + 1, hdr); + encode_op_hdr(xdr, OP_LISTXATTRS, decode_listxattrs_maxsz, hdr); p = reserve_space(xdr, 12); if (unlikely(!p)) diff --git a/fs/nfs/nfsroot.c b/fs/nfs/nfsroot.c index 8d3278805602..fa148308822c 100644 --- a/fs/nfs/nfsroot.c +++ b/fs/nfs/nfsroot.c @@ -88,7 +88,13 @@ #define NFS_ROOT "/tftpboot/%s" /* Default NFSROOT mount options. */ +#if defined(CONFIG_NFS_V2) #define NFS_DEF_OPTIONS "vers=2,tcp,rsize=4096,wsize=4096" +#elif defined(CONFIG_NFS_V3) +#define NFS_DEF_OPTIONS "vers=3,tcp,rsize=4096,wsize=4096" +#else +#define NFS_DEF_OPTIONS "vers=4,tcp,rsize=4096,wsize=4096" +#endif /* Parameters passed from the kernel command line */ static char nfs_root_parms[NFS_MAXPATHLEN + 1] __initdata = ""; diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index 14468613d150..a633044b0dc1 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -316,10 +316,6 @@ nfsd3_proc_mknod(struct svc_rqst *rqstp) fh_copy(&resp->dirfh, &argp->fh); fh_init(&resp->fh, NFS3_FHSIZE); - if (argp->ftype == 0 || argp->ftype >= NF3BAD) { - resp->status = nfserr_inval; - goto out; - } if (argp->ftype == NF3CHR || argp->ftype == NF3BLK) { rdev = MKDEV(argp->major, argp->minor); if (MAJOR(rdev) != argp->major || @@ -328,7 +324,7 @@ nfsd3_proc_mknod(struct svc_rqst *rqstp) goto out; } } else if (argp->ftype != NF3SOCK && argp->ftype != NF3FIFO) { - resp->status = nfserr_inval; + resp->status = nfserr_badtype; goto out; } diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 9c23b6acf234..2277f83da250 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -1114,6 +1114,7 @@ nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, __be32 *p) { struct nfsd3_pathconfres *resp = rqstp->rq_resp; + *p++ = resp->status; *p++ = xdr_zero; /* no post_op_attr */ if (resp->status == 0) { diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index ad2fa1a8e7ad..e83b21778816 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1299,7 +1299,7 @@ nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct nfsd_file *src, struct nfsd_file *dst) { nfs42_ssc_close(src->nf_file); - nfsd_file_put(src); + /* 'src' is freed by nfsd4_do_async_copy */ nfsd_file_put(dst); mntput(ss_mnt); } @@ -1486,6 +1486,7 @@ do_callback: cb_copy = kzalloc(sizeof(struct nfsd4_copy), GFP_KERNEL); if (!cb_copy) goto out; + refcount_set(&cb_copy->refcount, 1); memcpy(&cb_copy->cp_res, ©->cp_res, sizeof(copy->cp_res)); cb_copy->cp_clp = copy->cp_clp; cb_copy->nfserr = copy->nfserr; diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index b9a9d69dde7e..db52e843002a 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -877,7 +877,7 @@ int ocfs2_journal_init(struct ocfs2_journal *journal, int *dirty) goto done; } - trace_ocfs2_journal_init_maxlen(j_journal->j_maxlen); + trace_ocfs2_journal_init_maxlen(j_journal->j_total_len); *dirty = (le32_to_cpu(di->id1.journal1.ij_flags) & OCFS2_JOURNAL_DIRTY_FL); diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 1d91dd1e8711..2febc76e9de7 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1713,6 +1713,7 @@ static void ocfs2_inode_init_once(void *data) oi->ip_blkno = 0ULL; oi->ip_clusters = 0; + oi->ip_next_orphan = NULL; ocfs2_resv_init_once(&oi->ip_la_data_resv); diff --git a/fs/super.c b/fs/super.c index a51c2083cd6b..98bb0629ee10 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1631,55 +1631,6 @@ int super_setup_bdi(struct super_block *sb) } EXPORT_SYMBOL(super_setup_bdi); -/* - * This is an internal function, please use sb_end_{write,pagefault,intwrite} - * instead. - */ -void __sb_end_write(struct super_block *sb, int level) -{ - percpu_up_read(sb->s_writers.rw_sem + level-1); -} -EXPORT_SYMBOL(__sb_end_write); - -/* - * This is an internal function, please use sb_start_{write,pagefault,intwrite} - * instead. - */ -int __sb_start_write(struct super_block *sb, int level, bool wait) -{ - bool force_trylock = false; - int ret = 1; - -#ifdef CONFIG_LOCKDEP - /* - * We want lockdep to tell us about possible deadlocks with freezing - * but it's it bit tricky to properly instrument it. Getting a freeze - * protection works as getting a read lock but there are subtle - * problems. XFS for example gets freeze protection on internal level - * twice in some cases, which is OK only because we already hold a - * freeze protection also on higher level. Due to these cases we have - * to use wait == F (trylock mode) which must not fail. - */ - if (wait) { - int i; - - for (i = 0; i < level - 1; i++) - if (percpu_rwsem_is_held(sb->s_writers.rw_sem + i)) { - force_trylock = true; - break; - } - } -#endif - if (wait && !force_trylock) - percpu_down_read(sb->s_writers.rw_sem + level-1); - else - ret = percpu_down_read_trylock(sb->s_writers.rw_sem + level-1); - - WARN_ON(force_trylock && !ret); - return ret; -} -EXPORT_SYMBOL(__sb_start_write); - /** * sb_wait_write - wait until all writers to given file system finish * @sb: the super for which we wait diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c index 340c83f76c80..2668ebe02865 100644 --- a/fs/xfs/libxfs/xfs_rmap.c +++ b/fs/xfs/libxfs/xfs_rmap.c @@ -1514,7 +1514,7 @@ xfs_rmap_convert_shared( * record for our insertion point. This will also give us the record for * start block contiguity tests. */ - error = xfs_rmap_lookup_le_range(cur, bno, owner, offset, flags, + error = xfs_rmap_lookup_le_range(cur, bno, owner, offset, oldext, &PREV, &i); if (error) goto done; diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c index beb81c84a937..577a66381327 100644 --- a/fs/xfs/libxfs/xfs_rmap_btree.c +++ b/fs/xfs/libxfs/xfs_rmap_btree.c @@ -243,8 +243,8 @@ xfs_rmapbt_key_diff( else if (y > x) return -1; - x = XFS_RMAP_OFF(be64_to_cpu(kp->rm_offset)); - y = rec->rm_offset; + x = be64_to_cpu(kp->rm_offset); + y = xfs_rmap_irec_offset_pack(rec); if (x > y) return 1; else if (y > x) @@ -275,8 +275,8 @@ xfs_rmapbt_diff_two_keys( else if (y > x) return -1; - x = XFS_RMAP_OFF(be64_to_cpu(kp1->rm_offset)); - y = XFS_RMAP_OFF(be64_to_cpu(kp2->rm_offset)); + x = be64_to_cpu(kp1->rm_offset); + y = be64_to_cpu(kp2->rm_offset); if (x > y) return 1; else if (y > x) @@ -390,8 +390,8 @@ xfs_rmapbt_keys_inorder( return 1; else if (a > b) return 0; - a = XFS_RMAP_OFF(be64_to_cpu(k1->rmap.rm_offset)); - b = XFS_RMAP_OFF(be64_to_cpu(k2->rmap.rm_offset)); + a = be64_to_cpu(k1->rmap.rm_offset); + b = be64_to_cpu(k2->rmap.rm_offset); if (a <= b) return 1; return 0; @@ -420,8 +420,8 @@ xfs_rmapbt_recs_inorder( return 1; else if (a > b) return 0; - a = XFS_RMAP_OFF(be64_to_cpu(r1->rmap.rm_offset)); - b = XFS_RMAP_OFF(be64_to_cpu(r2->rmap.rm_offset)); + a = be64_to_cpu(r1->rmap.rm_offset); + b = be64_to_cpu(r2->rmap.rm_offset); if (a <= b) return 1; return 0; diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c index 955302e7cdde..412e2ec55e38 100644 --- a/fs/xfs/scrub/bmap.c +++ b/fs/xfs/scrub/bmap.c @@ -113,6 +113,8 @@ xchk_bmap_get_rmap( if (info->whichfork == XFS_ATTR_FORK) rflags |= XFS_RMAP_ATTR_FORK; + if (irec->br_state == XFS_EXT_UNWRITTEN) + rflags |= XFS_RMAP_UNWRITTEN; /* * CoW staging extents are owned (on disk) by the refcountbt, so diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c index beaeb6fa3119..dd672e6bbc75 100644 --- a/fs/xfs/scrub/refcount.c +++ b/fs/xfs/scrub/refcount.c @@ -170,7 +170,6 @@ xchk_refcountbt_process_rmap_fragments( */ INIT_LIST_HEAD(&worklist); rbno = NULLAGBLOCK; - nr = 1; /* Make sure the fragments actually /are/ in agbno order. */ bno = 0; @@ -184,15 +183,14 @@ xchk_refcountbt_process_rmap_fragments( * Find all the rmaps that start at or before the refc extent, * and put them on the worklist. */ + nr = 0; list_for_each_entry_safe(frag, n, &refchk->fragments, list) { - if (frag->rm.rm_startblock > refchk->bno) - goto done; + if (frag->rm.rm_startblock > refchk->bno || nr > target_nr) + break; bno = frag->rm.rm_startblock + frag->rm.rm_blockcount; if (bno < rbno) rbno = bno; list_move_tail(&frag->list, &worklist); - if (nr == target_nr) - break; nr++; } diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c index b101feb2aab4..f3082a957d5e 100644 --- a/fs/xfs/xfs_pnfs.c +++ b/fs/xfs/xfs_pnfs.c @@ -134,7 +134,7 @@ xfs_fs_map_blocks( goto out_unlock; error = invalidate_inode_pages2(inode->i_mapping); if (WARN_ON_ONCE(error)) - return error; + goto out_unlock; end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + length); offset_fsb = XFS_B_TO_FSBT(mp, offset); diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h index 798027bb89be..640f09479bdf 100644 --- a/include/asm-generic/barrier.h +++ b/include/asm-generic/barrier.h @@ -13,6 +13,7 @@ #ifndef __ASSEMBLY__ +#include <linux/compiler.h> #include <asm/rwonce.h> #ifndef nop diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h index 35e4a53b83e6..6432a7fade91 100644 --- a/include/asm-generic/percpu.h +++ b/include/asm-generic/percpu.h @@ -114,21 +114,21 @@ do { \ #define __this_cpu_generic_read_nopreempt(pcp) \ ({ \ - typeof(pcp) __ret; \ + typeof(pcp) ___ret; \ preempt_disable_notrace(); \ - __ret = READ_ONCE(*raw_cpu_ptr(&(pcp))); \ + ___ret = READ_ONCE(*raw_cpu_ptr(&(pcp))); \ preempt_enable_notrace(); \ - __ret; \ + ___ret; \ }) #define __this_cpu_generic_read_noirq(pcp) \ ({ \ - typeof(pcp) __ret; \ - unsigned long __flags; \ - raw_local_irq_save(__flags); \ - __ret = raw_cpu_generic_read(pcp); \ - raw_local_irq_restore(__flags); \ - __ret; \ + typeof(pcp) ___ret; \ + unsigned long ___flags; \ + raw_local_irq_save(___flags); \ + ___ret = raw_cpu_generic_read(pcp); \ + raw_local_irq_restore(___flags); \ + ___ret; \ }) #define this_cpu_generic_read(pcp) \ diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index 230604e7f057..dd7233c48bf3 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -60,12 +60,6 @@ #define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 #endif -/* The following are for compatibility with GCC, from compiler-gcc.h, - * and may be redefined here because they should not be shared with other - * compilers, like ICC. - */ -#define barrier() __asm__ __volatile__("" : : : "memory") - #if __has_feature(shadow_call_stack) # define __noscs __attribute__((__no_sanitize__("shadow-call-stack"))) #endif diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index d1e3c6896b71..74c6c0486eed 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -15,25 +15,6 @@ # error Sorry, your version of GCC is too old - please use 4.9 or newer. #endif -/* Optimization barrier */ - -/* The "volatile" is due to gcc bugs */ -#define barrier() __asm__ __volatile__("": : :"memory") -/* - * This version is i.e. to prevent dead stores elimination on @ptr - * where gcc and llvm may behave differently when otherwise using - * normal barrier(): while gcc behavior gets along with a normal - * barrier(), llvm needs an explicit input variable to be assumed - * clobbered. The issue is as follows: while the inline asm might - * access any memory it wants, the compiler could have fit all of - * @ptr into memory registers instead, and since @ptr never escaped - * from that, it proved that the inline asm wasn't touching any of - * it. This version works well with both compilers, i.e. we're telling - * the compiler that the inline asm absolutely may see the contents - * of @ptr. See also: https://llvm.org/bugs/show_bug.cgi?id=15495 - */ -#define barrier_data(ptr) __asm__ __volatile__("": :"r"(ptr) :"memory") - /* * This macro obfuscates arithmetic on a variable address so that gcc * shouldn't recognize the original var, and make assumptions about it. @@ -175,5 +156,3 @@ #else #define __diag_GCC_8(s) #endif - -#define __no_fgcse __attribute__((optimize("-fno-gcse"))) diff --git a/include/linux/compiler.h b/include/linux/compiler.h index e512f5505dad..b8fe0c23cfff 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -80,11 +80,25 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, /* Optimization barrier */ #ifndef barrier -# define barrier() __memory_barrier() +/* The "volatile" is due to gcc bugs */ +# define barrier() __asm__ __volatile__("": : :"memory") #endif #ifndef barrier_data -# define barrier_data(ptr) barrier() +/* + * This version is i.e. to prevent dead stores elimination on @ptr + * where gcc and llvm may behave differently when otherwise using + * normal barrier(): while gcc behavior gets along with a normal + * barrier(), llvm needs an explicit input variable to be assumed + * clobbered. The issue is as follows: while the inline asm might + * access any memory it wants, the compiler could have fit all of + * @ptr into memory registers instead, and since @ptr never escaped + * from that, it proved that the inline asm wasn't touching any of + * it. This version works well with both compilers, i.e. we're telling + * the compiler that the inline asm absolutely may see the contents + * of @ptr. See also: https://llvm.org/bugs/show_bug.cgi?id=15495 + */ +# define barrier_data(ptr) __asm__ __volatile__("": :"r"(ptr) :"memory") #endif /* workaround for GCC PR82365 if needed */ diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 6e390d58a9f8..ac3fa37a84f9 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -247,10 +247,6 @@ struct ftrace_likely_data { #define asm_inline asm #endif -#ifndef __no_fgcse -# define __no_fgcse -#endif - /* Are two types/vars the same type (ignoring qualifiers)? */ #define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b)) diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 1eaa04f1bae6..acbad3b36322 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -110,6 +110,12 @@ struct cpufreq_policy { bool fast_switch_enabled; /* + * Set if the CPUFREQ_GOV_STRICT_TARGET flag is set for the current + * governor. + */ + bool strict_target; + + /* * Preferred average time interval between consecutive invocations of * the driver to set the frequency for this policy. To be set by the * scaling driver (0, which is the default, means no preference). @@ -570,12 +576,20 @@ struct cpufreq_governor { char *buf); int (*store_setspeed) (struct cpufreq_policy *policy, unsigned int freq); - /* For governors which change frequency dynamically by themselves */ - bool dynamic_switching; struct list_head governor_list; struct module *owner; + u8 flags; }; +/* Governor flags */ + +/* For governors which change frequency dynamically by themselves */ +#define CPUFREQ_GOV_DYNAMIC_SWITCHING BIT(0) + +/* For governors wanting the target frequency to be set exactly */ +#define CPUFREQ_GOV_STRICT_TARGET BIT(1) + + /* Pass a target to the cpufreq driver */ unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy, unsigned int target_freq); diff --git a/include/linux/filter.h b/include/linux/filter.h index 72d62cbc1578..1b62397bd124 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -558,21 +558,21 @@ struct sk_filter { DECLARE_STATIC_KEY_FALSE(bpf_stats_enabled_key); #define __BPF_PROG_RUN(prog, ctx, dfunc) ({ \ - u32 ret; \ + u32 __ret; \ cant_migrate(); \ if (static_branch_unlikely(&bpf_stats_enabled_key)) { \ - struct bpf_prog_stats *stats; \ - u64 start = sched_clock(); \ - ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func); \ - stats = this_cpu_ptr(prog->aux->stats); \ - u64_stats_update_begin(&stats->syncp); \ - stats->cnt++; \ - stats->nsecs += sched_clock() - start; \ - u64_stats_update_end(&stats->syncp); \ + struct bpf_prog_stats *__stats; \ + u64 __start = sched_clock(); \ + __ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func); \ + __stats = this_cpu_ptr(prog->aux->stats); \ + u64_stats_update_begin(&__stats->syncp); \ + __stats->cnt++; \ + __stats->nsecs += sched_clock() - __start; \ + u64_stats_update_end(&__stats->syncp); \ } else { \ - ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func); \ + __ret = dfunc(ctx, (prog)->insnsi, (prog)->bpf_func); \ } \ - ret; }) + __ret; }) #define BPF_PROG_RUN(prog, ctx) \ __BPF_PROG_RUN(prog, ctx, bpf_dispatcher_nop_func) diff --git a/include/linux/fs.h b/include/linux/fs.h index 21cc971fd960..8667d0cdc71e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1580,8 +1580,24 @@ extern struct timespec64 current_time(struct inode *inode); * Snapshotting support. */ -void __sb_end_write(struct super_block *sb, int level); -int __sb_start_write(struct super_block *sb, int level, bool wait); +/* + * These are internal functions, please use sb_start_{write,pagefault,intwrite} + * instead. + */ +static inline void __sb_end_write(struct super_block *sb, int level) +{ + percpu_up_read(sb->s_writers.rw_sem + level-1); +} + +static inline void __sb_start_write(struct super_block *sb, int level) +{ + percpu_down_read(sb->s_writers.rw_sem + level - 1); +} + +static inline bool __sb_start_write_trylock(struct super_block *sb, int level) +{ + return percpu_down_read_trylock(sb->s_writers.rw_sem + level - 1); +} #define __sb_writers_acquired(sb, lev) \ percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_) @@ -1645,12 +1661,12 @@ static inline void sb_end_intwrite(struct super_block *sb) */ static inline void sb_start_write(struct super_block *sb) { - __sb_start_write(sb, SB_FREEZE_WRITE, true); + __sb_start_write(sb, SB_FREEZE_WRITE); } -static inline int sb_start_write_trylock(struct super_block *sb) +static inline bool sb_start_write_trylock(struct super_block *sb) { - return __sb_start_write(sb, SB_FREEZE_WRITE, false); + return __sb_start_write_trylock(sb, SB_FREEZE_WRITE); } /** @@ -1674,7 +1690,7 @@ static inline int sb_start_write_trylock(struct super_block *sb) */ static inline void sb_start_pagefault(struct super_block *sb) { - __sb_start_write(sb, SB_FREEZE_PAGEFAULT, true); + __sb_start_write(sb, SB_FREEZE_PAGEFAULT); } /* @@ -1692,12 +1708,12 @@ static inline void sb_start_pagefault(struct super_block *sb) */ static inline void sb_start_intwrite(struct super_block *sb) { - __sb_start_write(sb, SB_FREEZE_FS, true); + __sb_start_write(sb, SB_FREEZE_FS); } -static inline int sb_start_intwrite_trylock(struct super_block *sb) +static inline bool sb_start_intwrite_trylock(struct super_block *sb) { - return __sb_start_write(sb, SB_FREEZE_FS, false); + return __sb_start_write_trylock(sb, SB_FREEZE_FS); } @@ -2756,14 +2772,14 @@ static inline void file_start_write(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return; - __sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, true); + sb_start_write(file_inode(file)->i_sb); } static inline bool file_start_write_trylock(struct file *file) { if (!S_ISREG(file_inode(file)->i_mode)) return true; - return __sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, false); + return sb_start_write_trylock(file_inode(file)->i_sb); } static inline void file_end_write(struct file *file) diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 38f23d757013..03da3f603d30 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -315,7 +315,7 @@ static inline int get_disk_ro(struct gendisk *disk) extern void disk_block_events(struct gendisk *disk); extern void disk_unblock_events(struct gendisk *disk); extern void disk_flush_events(struct gendisk *disk, unsigned int mask); -void set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size, +bool set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size, bool update_bdev); /* drivers/char/random.c */ diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 1d5566af48ac..1c49fd62ff2e 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -68,6 +68,7 @@ extern void *jbd2_alloc(size_t size, gfp_t flags); extern void jbd2_free(void *ptr, size_t size); #define JBD2_MIN_JOURNAL_BLOCKS 1024 +#define JBD2_MIN_FC_BLOCKS 256 #ifdef __KERNEL__ @@ -944,8 +945,9 @@ struct journal_s /** * @j_fc_off: * - * Number of fast commit blocks currently allocated. - * [j_state_lock]. + * Number of fast commit blocks currently allocated. Accessed only + * during fast commit. Currently only process can do fast commit, so + * this field is not protected by any lock. */ unsigned long j_fc_off; @@ -988,9 +990,9 @@ struct journal_s struct block_device *j_fs_dev; /** - * @j_maxlen: Total maximum capacity of the journal region on disk. + * @j_total_len: Total maximum capacity of the journal region on disk. */ - unsigned int j_maxlen; + unsigned int j_total_len; /** * @j_reserved_credits: @@ -1108,8 +1110,9 @@ struct journal_s struct buffer_head **j_wbuf; /** - * @j_fc_wbuf: Array of fast commit bhs for - * jbd2_journal_commit_transaction. + * @j_fc_wbuf: Array of fast commit bhs for fast commit. Accessed only + * during a fast commit. Currently only process can do fast commit, so + * this field is not protected by any lock. */ struct buffer_head **j_fc_wbuf; @@ -1614,16 +1617,20 @@ extern void __jbd2_journal_drop_transaction(journal_t *, transaction_t *); extern int jbd2_cleanup_journal_tail(journal_t *); /* Fast commit related APIs */ -int jbd2_fc_init(journal_t *journal, int num_fc_blks); int jbd2_fc_begin_commit(journal_t *journal, tid_t tid); int jbd2_fc_end_commit(journal_t *journal); -int jbd2_fc_end_commit_fallback(journal_t *journal, tid_t tid); +int jbd2_fc_end_commit_fallback(journal_t *journal); int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out); int jbd2_submit_inode_data(struct jbd2_inode *jinode); int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode); int jbd2_fc_wait_bufs(journal_t *journal, int num_blks); int jbd2_fc_release_bufs(journal_t *journal); +static inline int jbd2_journal_get_max_txn_bufs(journal_t *journal) +{ + return (journal->j_total_len - journal->j_fc_wbufsize) / 4; +} + /* * is_journal_abort * diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index e391e3c56de5..a80c59af2c60 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -900,12 +900,19 @@ static inline void count_memcg_event_mm(struct mm_struct *mm, static inline void memcg_memory_event(struct mem_cgroup *memcg, enum memcg_memory_event event) { + bool swap_event = event == MEMCG_SWAP_HIGH || event == MEMCG_SWAP_MAX || + event == MEMCG_SWAP_FAIL; + atomic_long_inc(&memcg->memory_events_local[event]); - cgroup_file_notify(&memcg->events_local_file); + if (!swap_event) + cgroup_file_notify(&memcg->events_local_file); do { atomic_long_inc(&memcg->memory_events[event]); - cgroup_file_notify(&memcg->events_file); + if (swap_event) + cgroup_file_notify(&memcg->swap_events_file); + else + cgroup_file_notify(&memcg->events_file); if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) break; diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 0c19d279b97f..96450f6fb1de 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1022,13 +1022,7 @@ struct perf_sample_data { struct perf_callchain_entry *callchain; u64 aux_size; - /* - * regs_user may point to task_pt_regs or to regs_user_copy, depending - * on arch details. - */ struct perf_regs regs_user; - struct pt_regs regs_user_copy; - struct perf_regs regs_intr; u64 stack_user_size; @@ -1400,11 +1394,14 @@ perf_event_addr_filters(struct perf_event *event) extern void perf_event_addr_filters_sync(struct perf_event *event); extern int perf_output_begin(struct perf_output_handle *handle, + struct perf_sample_data *data, struct perf_event *event, unsigned int size); extern int perf_output_begin_forward(struct perf_output_handle *handle, - struct perf_event *event, - unsigned int size); + struct perf_sample_data *data, + struct perf_event *event, + unsigned int size); extern int perf_output_begin_backward(struct perf_output_handle *handle, + struct perf_sample_data *data, struct perf_event *event, unsigned int size); diff --git a/include/linux/perf_regs.h b/include/linux/perf_regs.h index 2d12e97d5e7b..f632c5725f16 100644 --- a/include/linux/perf_regs.h +++ b/include/linux/perf_regs.h @@ -20,8 +20,7 @@ u64 perf_reg_value(struct pt_regs *regs, int idx); int perf_reg_validate(u64 mask); u64 perf_reg_abi(struct task_struct *task); void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy); + struct pt_regs *regs); #else #define PERF_REG_EXTENDED_MASK 0 @@ -42,8 +41,7 @@ static inline u64 perf_reg_abi(struct task_struct *task) } static inline void perf_get_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { regs_user->regs = task_pt_regs(current); regs_user->abi = perf_reg_abi(current); diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 513913ff7486..fbdc65782195 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -5,6 +5,7 @@ #include <linux/dma-direction.h> #include <linux/init.h> #include <linux/types.h> +#include <linux/limits.h> struct device; struct page; @@ -45,13 +46,9 @@ enum dma_sync_target { SYNC_FOR_DEVICE = 1, }; -extern phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, - dma_addr_t tbl_dma_addr, - phys_addr_t phys, - size_t mapping_size, - size_t alloc_size, - enum dma_data_direction dir, - unsigned long attrs); +phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys, + size_t mapping_size, size_t alloc_size, + enum dma_data_direction dir, unsigned long attrs); extern void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index 0140d086dc84..01755b838c74 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -86,7 +86,7 @@ int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_umem *umem, void xp_destroy(struct xsk_buff_pool *pool); void xp_release(struct xdp_buff_xsk *xskb); void xp_get_pool(struct xsk_buff_pool *pool); -void xp_put_pool(struct xsk_buff_pool *pool); +bool xp_put_pool(struct xsk_buff_pool *pool); void xp_clear_dev(struct xsk_buff_pool *pool); void xp_add_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs); void xp_del_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs); diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index b14314fcf732..70ae5497b73a 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -100,11 +100,12 @@ TRACE_DEFINE_ENUM(ES_REFERENCED_B); { EXT4_FC_REASON_XATTR, "XATTR"}, \ { EXT4_FC_REASON_CROSS_RENAME, "CROSS_RENAME"}, \ { EXT4_FC_REASON_JOURNAL_FLAG_CHANGE, "JOURNAL_FLAG_CHANGE"}, \ - { EXT4_FC_REASON_MEM, "NO_MEM"}, \ + { EXT4_FC_REASON_NOMEM, "NO_MEM"}, \ { EXT4_FC_REASON_SWAP_BOOT, "SWAP_BOOT"}, \ { EXT4_FC_REASON_RESIZE, "RESIZE"}, \ { EXT4_FC_REASON_RENAME_DIR, "RENAME_DIR"}, \ - { EXT4_FC_REASON_FALLOC_RANGE, "FALLOC_RANGE"}) + { EXT4_FC_REASON_FALLOC_RANGE, "FALLOC_RANGE"}, \ + { EXT4_FC_REASON_INODE_JOURNAL_DATA, "INODE_JOURNAL_DATA"}) TRACE_EVENT(ext4_other_inode_update_time, TP_PROTO(struct inode *inode, ino_t orig_ino), @@ -2917,17 +2918,18 @@ TRACE_EVENT(ext4_fc_stats, ), TP_printk("dev %d:%d fc ineligible reasons:\n" - "%s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s,%d; " + "%s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d; " "num_commits:%ld, ineligible: %ld, numblks: %ld", MAJOR(__entry->dev), MINOR(__entry->dev), FC_REASON_NAME_STAT(EXT4_FC_REASON_XATTR), FC_REASON_NAME_STAT(EXT4_FC_REASON_CROSS_RENAME), FC_REASON_NAME_STAT(EXT4_FC_REASON_JOURNAL_FLAG_CHANGE), - FC_REASON_NAME_STAT(EXT4_FC_REASON_MEM), + FC_REASON_NAME_STAT(EXT4_FC_REASON_NOMEM), FC_REASON_NAME_STAT(EXT4_FC_REASON_SWAP_BOOT), FC_REASON_NAME_STAT(EXT4_FC_REASON_RESIZE), FC_REASON_NAME_STAT(EXT4_FC_REASON_RENAME_DIR), FC_REASON_NAME_STAT(EXT4_FC_REASON_FALLOC_RANGE), + FC_REASON_NAME_STAT(EXT4_FC_REASON_INODE_JOURNAL_DATA), __entry->sbi->s_fc_stats.fc_num_commits, __entry->sbi->s_fc_stats.fc_ineligible_commits, __entry->sbi->s_fc_stats.fc_numblks) diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index f45b3c01370c..2477014e3fa6 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -655,10 +655,10 @@ TRACE_EVENT(rpc_xdr_overflow, __field(size_t, tail_len) __field(unsigned int, page_len) __field(unsigned int, len) - __string(progname, - xdr->rqst->rq_task->tk_client->cl_program->name) - __string(procedure, - xdr->rqst->rq_task->tk_msg.rpc_proc->p_name) + __string(progname, xdr->rqst ? + xdr->rqst->rq_task->tk_client->cl_program->name : "unknown") + __string(procedure, xdr->rqst ? + xdr->rqst->rq_task->tk_msg.rpc_proc->p_name : "unknown") ), TP_fast_assign( diff --git a/include/uapi/linux/gpio.h b/include/uapi/linux/gpio.h index 07865c601099..2072c260f5d0 100644 --- a/include/uapi/linux/gpio.h +++ b/include/uapi/linux/gpio.h @@ -26,7 +26,7 @@ * struct gpiochip_info - Information about a certain GPIO chip * @name: the Linux kernel name of this GPIO chip * @label: a functional name for this GPIO chip, such as a product - * number, may be empty + * number, may be empty (i.e. label[0] == '\0') * @lines: number of GPIO lines on this chip */ struct gpiochip_info { @@ -98,7 +98,7 @@ struct gpio_v2_line_values { * identifying which field of the attribute union is in use. * @GPIO_V2_LINE_ATTR_ID_FLAGS: flags field is in use * @GPIO_V2_LINE_ATTR_ID_OUTPUT_VALUES: values field is in use - * @GPIO_V2_LINE_ATTR_ID_DEBOUNCE: debounce_period_us is in use + * @GPIO_V2_LINE_ATTR_ID_DEBOUNCE: debounce_period_us field is in use */ enum gpio_v2_line_attr_id { GPIO_V2_LINE_ATTR_ID_FLAGS = 1, @@ -110,17 +110,17 @@ enum gpio_v2_line_attr_id { * struct gpio_v2_line_attribute - a configurable attribute of a line * @id: attribute identifier with value from &enum gpio_v2_line_attr_id * @padding: reserved for future use and must be zero filled - * @flags: if id is GPIO_V2_LINE_ATTR_ID_FLAGS, the flags for the GPIO - * line, with values from enum gpio_v2_line_flag, such as - * GPIO_V2_LINE_FLAG_ACTIVE_LOW, GPIO_V2_LINE_FLAG_OUTPUT etc, OR:ed + * @flags: if id is %GPIO_V2_LINE_ATTR_ID_FLAGS, the flags for the GPIO + * line, with values from &enum gpio_v2_line_flag, such as + * %GPIO_V2_LINE_FLAG_ACTIVE_LOW, %GPIO_V2_LINE_FLAG_OUTPUT etc, added * together. This overrides the default flags contained in the &struct * gpio_v2_line_config for the associated line. - * @values: if id is GPIO_V2_LINE_ATTR_ID_OUTPUT_VALUES, a bitmap + * @values: if id is %GPIO_V2_LINE_ATTR_ID_OUTPUT_VALUES, a bitmap * containing the values to which the lines will be set, with each bit * number corresponding to the index into &struct * gpio_v2_line_request.offsets. - * @debounce_period_us: if id is GPIO_V2_LINE_ATTR_ID_DEBOUNCE, the desired - * debounce period, in microseconds + * @debounce_period_us: if id is %GPIO_V2_LINE_ATTR_ID_DEBOUNCE, the + * desired debounce period, in microseconds */ struct gpio_v2_line_attribute { __u32 id; @@ -147,12 +147,12 @@ struct gpio_v2_line_config_attribute { /** * struct gpio_v2_line_config - Configuration for GPIO lines - * @flags: flags for the GPIO lines, with values from enum - * gpio_v2_line_flag, such as GPIO_V2_LINE_FLAG_ACTIVE_LOW, - * GPIO_V2_LINE_FLAG_OUTPUT etc, OR:ed together. This is the default for + * @flags: flags for the GPIO lines, with values from &enum + * gpio_v2_line_flag, such as %GPIO_V2_LINE_FLAG_ACTIVE_LOW, + * %GPIO_V2_LINE_FLAG_OUTPUT etc, added together. This is the default for * all requested lines but may be overridden for particular lines using - * attrs. - * @num_attrs: the number of attributes in attrs + * @attrs. + * @num_attrs: the number of attributes in @attrs * @padding: reserved for future use and must be zero filled * @attrs: the configuration attributes associated with the requested * lines. Any attribute should only be associated with a particular line @@ -175,17 +175,17 @@ struct gpio_v2_line_config { * "my-bitbanged-relay" * @config: requested configuration for the lines. * @num_lines: number of lines requested in this request, i.e. the number - * of valid fields in the GPIO_V2_LINES_MAX sized arrays, set to 1 to + * of valid fields in the %GPIO_V2_LINES_MAX sized arrays, set to 1 to * request a single line * @event_buffer_size: a suggested minimum number of line events that the * kernel should buffer. This is only relevant if edge detection is * enabled in the configuration. Note that this is only a suggested value * and the kernel may allocate a larger buffer or cap the size of the * buffer. If this field is zero then the buffer size defaults to a minimum - * of num_lines*16. + * of @num_lines * 16. * @padding: reserved for future use and must be zero filled * @fd: if successful this field will contain a valid anonymous file handle - * after a GPIO_GET_LINE_IOCTL operation, zero or negative value means + * after a %GPIO_GET_LINE_IOCTL operation, zero or negative value means * error */ struct gpio_v2_line_request { @@ -203,15 +203,16 @@ struct gpio_v2_line_request { * struct gpio_v2_line_info - Information about a certain GPIO line * @name: the name of this GPIO line, such as the output pin of the line on * the chip, a rail or a pin header name on a board, as specified by the - * GPIO chip, may be empty + * GPIO chip, may be empty (i.e. name[0] == '\0') * @consumer: a functional name for the consumer of this GPIO line as set * by whatever is using it, will be empty if there is no current user but * may also be empty if the consumer doesn't set this up - * @flags: flags for the GPIO line, such as GPIO_V2_LINE_FLAG_ACTIVE_LOW, - * GPIO_V2_LINE_FLAG_OUTPUT etc, OR:ed together * @offset: the local offset on this GPIO chip, fill this in when * requesting the line information from the kernel - * @num_attrs: the number of attributes in attrs + * @num_attrs: the number of attributes in @attrs + * @flags: flags for the GPIO lines, with values from &enum + * gpio_v2_line_flag, such as %GPIO_V2_LINE_FLAG_ACTIVE_LOW, + * %GPIO_V2_LINE_FLAG_OUTPUT etc, added together. * @attrs: the configuration attributes associated with the line * @padding: reserved for future use */ @@ -244,7 +245,7 @@ enum gpio_v2_line_changed_type { * of a GPIO line * @info: updated line information * @timestamp_ns: estimate of time of status change occurrence, in nanoseconds - * @event_type: the type of change with a value from enum + * @event_type: the type of change with a value from &enum * gpio_v2_line_changed_type * @padding: reserved for future use */ @@ -269,10 +270,10 @@ enum gpio_v2_line_event_id { /** * struct gpio_v2_line_event - The actual event being pushed to userspace * @timestamp_ns: best estimate of time of event occurrence, in nanoseconds. - * The timestamp_ns is read from CLOCK_MONOTONIC and is intended to allow the - * accurate measurement of the time between events. It does not provide + * The @timestamp_ns is read from %CLOCK_MONOTONIC and is intended to allow + * the accurate measurement of the time between events. It does not provide * the wall-clock time. - * @id: event identifier with value from enum gpio_v2_line_event_id + * @id: event identifier with value from &enum gpio_v2_line_event_id * @offset: the offset of the line that triggered the event * @seqno: the sequence number for this event in the sequence of events for * all the lines in this line request @@ -291,7 +292,7 @@ struct gpio_v2_line_event { }; /* - * ABI v1 + * ABI v1 * * This version of the ABI is deprecated. * Use the latest version of the ABI, defined above, instead. @@ -314,13 +315,13 @@ struct gpio_v2_line_event { * @flags: various flags for this line * @name: the name of this GPIO line, such as the output pin of the line on the * chip, a rail or a pin header name on a board, as specified by the gpio - * chip, may be empty + * chip, may be empty (i.e. name[0] == '\0') * @consumer: a functional name for the consumer of this GPIO line as set by * whatever is using it, will be empty if there is no current user but may * also be empty if the consumer doesn't set this up * - * This struct is part of ABI v1 and is deprecated. - * Use struct gpio_v2_line_info instead. + * Note: This struct is part of ABI v1 and is deprecated. + * Use &struct gpio_v2_line_info instead. */ struct gpioline_info { __u32 line_offset; @@ -344,17 +345,18 @@ enum { * of a GPIO line * @info: updated line information * @timestamp: estimate of time of status change occurrence, in nanoseconds - * @event_type: one of GPIOLINE_CHANGED_REQUESTED, GPIOLINE_CHANGED_RELEASED - * and GPIOLINE_CHANGED_CONFIG + * @event_type: one of %GPIOLINE_CHANGED_REQUESTED, + * %GPIOLINE_CHANGED_RELEASED and %GPIOLINE_CHANGED_CONFIG + * @padding: reserved for future use * - * Note: struct gpioline_info embedded here has 32-bit alignment on its own, + * The &struct gpioline_info embedded here has 32-bit alignment on its own, * but it works fine with 64-bit alignment too. With its 72 byte size, we can * guarantee there are no implicit holes between it and subsequent members. * The 20-byte padding at the end makes sure we don't add any implicit padding * at the end of the structure on 64-bit architectures. * - * This struct is part of ABI v1 and is deprecated. - * Use struct gpio_v2_line_info_changed instead. + * Note: This struct is part of ABI v1 and is deprecated. + * Use &struct gpio_v2_line_info_changed instead. */ struct gpioline_info_changed { struct gpioline_info info; @@ -378,13 +380,13 @@ struct gpioline_info_changed { * @lineoffsets: an array of desired lines, specified by offset index for the * associated GPIO device * @flags: desired flags for the desired GPIO lines, such as - * GPIOHANDLE_REQUEST_OUTPUT, GPIOHANDLE_REQUEST_ACTIVE_LOW etc, OR:ed + * %GPIOHANDLE_REQUEST_OUTPUT, %GPIOHANDLE_REQUEST_ACTIVE_LOW etc, added * together. Note that even if multiple lines are requested, the same flags * must be applicable to all of them, if you want lines with individual * flags set, request them one by one. It is possible to select * a batch of input or output lines, but they must all have the same * characteristics, i.e. all inputs or all outputs, all active low etc - * @default_values: if the GPIOHANDLE_REQUEST_OUTPUT is set for a requested + * @default_values: if the %GPIOHANDLE_REQUEST_OUTPUT is set for a requested * line, this specifies the default output value, should be 0 (low) or * 1 (high), anything else than 0 or 1 will be interpreted as 1 (high) * @consumer_label: a desired consumer label for the selected GPIO line(s) @@ -392,11 +394,11 @@ struct gpioline_info_changed { * @lines: number of lines requested in this request, i.e. the number of * valid fields in the above arrays, set to 1 to request a single line * @fd: if successful this field will contain a valid anonymous file handle - * after a GPIO_GET_LINEHANDLE_IOCTL operation, zero or negative value + * after a %GPIO_GET_LINEHANDLE_IOCTL operation, zero or negative value * means error * - * This struct is part of ABI v1 and is deprecated. - * Use struct gpio_v2_line_request instead. + * Note: This struct is part of ABI v1 and is deprecated. + * Use &struct gpio_v2_line_request instead. */ struct gpiohandle_request { __u32 lineoffsets[GPIOHANDLES_MAX]; @@ -410,15 +412,15 @@ struct gpiohandle_request { /** * struct gpiohandle_config - Configuration for a GPIO handle request * @flags: updated flags for the requested GPIO lines, such as - * GPIOHANDLE_REQUEST_OUTPUT, GPIOHANDLE_REQUEST_ACTIVE_LOW etc, OR:ed + * %GPIOHANDLE_REQUEST_OUTPUT, %GPIOHANDLE_REQUEST_ACTIVE_LOW etc, added * together - * @default_values: if the GPIOHANDLE_REQUEST_OUTPUT is set in flags, + * @default_values: if the %GPIOHANDLE_REQUEST_OUTPUT is set in flags, * this specifies the default output value, should be 0 (low) or * 1 (high), anything else than 0 or 1 will be interpreted as 1 (high) * @padding: reserved for future use and should be zero filled * - * This struct is part of ABI v1 and is deprecated. - * Use struct gpio_v2_line_config instead. + * Note: This struct is part of ABI v1 and is deprecated. + * Use &struct gpio_v2_line_config instead. */ struct gpiohandle_config { __u32 flags; @@ -432,8 +434,8 @@ struct gpiohandle_config { * state of a line, when setting the state of lines these should contain * the desired target state * - * This struct is part of ABI v1 and is deprecated. - * Use struct gpio_v2_line_values instead. + * Note: This struct is part of ABI v1 and is deprecated. + * Use &struct gpio_v2_line_values instead. */ struct gpiohandle_data { __u8 values[GPIOHANDLES_MAX]; @@ -449,17 +451,17 @@ struct gpiohandle_data { * @lineoffset: the desired line to subscribe to events from, specified by * offset index for the associated GPIO device * @handleflags: desired handle flags for the desired GPIO line, such as - * GPIOHANDLE_REQUEST_ACTIVE_LOW or GPIOHANDLE_REQUEST_OPEN_DRAIN + * %GPIOHANDLE_REQUEST_ACTIVE_LOW or %GPIOHANDLE_REQUEST_OPEN_DRAIN * @eventflags: desired flags for the desired GPIO event line, such as - * GPIOEVENT_REQUEST_RISING_EDGE or GPIOEVENT_REQUEST_FALLING_EDGE + * %GPIOEVENT_REQUEST_RISING_EDGE or %GPIOEVENT_REQUEST_FALLING_EDGE * @consumer_label: a desired consumer label for the selected GPIO line(s) * such as "my-listener" * @fd: if successful this field will contain a valid anonymous file handle - * after a GPIO_GET_LINEEVENT_IOCTL operation, zero or negative value + * after a %GPIO_GET_LINEEVENT_IOCTL operation, zero or negative value * means error * - * This struct is part of ABI v1 and is deprecated. - * Use struct gpio_v2_line_request instead. + * Note: This struct is part of ABI v1 and is deprecated. + * Use &struct gpio_v2_line_request instead. */ struct gpioevent_request { __u32 lineoffset; @@ -469,7 +471,7 @@ struct gpioevent_request { int fd; }; -/** +/* * GPIO event types */ #define GPIOEVENT_EVENT_RISING_EDGE 0x01 @@ -480,8 +482,8 @@ struct gpioevent_request { * @timestamp: best estimate of time of event occurrence, in nanoseconds * @id: event identifier * - * This struct is part of ABI v1 and is deprecated. - * Use struct gpio_v2_line_event instead. + * Note: This struct is part of ABI v1 and is deprecated. + * Use &struct gpio_v2_line_event instead. */ struct gpioevent_data { __u64 timestamp; diff --git a/init/main.c b/init/main.c index 130376ec10ba..20baced721ad 100644 --- a/init/main.c +++ b/init/main.c @@ -269,14 +269,24 @@ static void * __init get_boot_config_from_initrd(u32 *_size, u32 *_csum) u32 size, csum; char *data; u32 *hdr; + int i; if (!initrd_end) return NULL; data = (char *)initrd_end - BOOTCONFIG_MAGIC_LEN; - if (memcmp(data, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN)) - return NULL; + /* + * Since Grub may align the size of initrd to 4, we must + * check the preceding 3 bytes as well. + */ + for (i = 0; i < 4; i++) { + if (!memcmp(data, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN)) + goto found; + data--; + } + return NULL; +found: hdr = (u32 *)(data - 8); size = hdr[0]; csum = hdr[1]; diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index bdc8cd1b6767..c1b9f71ee6aa 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -1,6 +1,10 @@ # SPDX-License-Identifier: GPL-2.0 obj-y := core.o -CFLAGS_core.o += $(call cc-disable-warning, override-init) +ifneq ($(CONFIG_BPF_JIT_ALWAYS_ON),y) +# ___bpf_prog_run() needs GCSE disabled on x86; see 3193c0836f203 for details +cflags-nogcse-$(CONFIG_X86)$(CONFIG_CC_IS_GCC) := -fno-gcse +endif +CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy) obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o map_iter.o task_iter.o prog_iter.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index 78ea8a7bd27f..56cc5a915f67 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -13,6 +13,7 @@ #include <linux/bpf_verifier.h> #include <net/bpf_sk_storage.h> #include <linux/bpf_local_storage.h> +#include <linux/btf_ids.h> /* For every LSM hook that allows attachment of BPF programs, declare a nop * function where a BPF program can be attached. @@ -26,7 +27,11 @@ noinline RET bpf_lsm_##NAME(__VA_ARGS__) \ #include <linux/lsm_hook_defs.h> #undef LSM_HOOK -#define BPF_LSM_SYM_PREFX "bpf_lsm_" +#define LSM_HOOK(RET, DEFAULT, NAME, ...) BTF_ID(func, bpf_lsm_##NAME) +BTF_SET_START(bpf_lsm_hooks) +#include <linux/lsm_hook_defs.h> +#undef LSM_HOOK +BTF_SET_END(bpf_lsm_hooks) int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog, const struct bpf_prog *prog) @@ -37,8 +42,7 @@ int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog, return -EINVAL; } - if (strncmp(BPF_LSM_SYM_PREFX, prog->aux->attach_func_name, - sizeof(BPF_LSM_SYM_PREFX) - 1)) { + if (!btf_id_set_contains(&bpf_lsm_hooks, prog->aux->attach_btf_id)) { bpf_log(vlog, "attach_btf_id %u points to wrong type name %s\n", prog->aux->attach_btf_id, prog->aux->attach_func_name); return -EINVAL; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 9268d77898b7..55454d2278b1 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1369,7 +1369,7 @@ u64 __weak bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr) * * Decode and execute eBPF instructions. */ -static u64 __no_fgcse ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack) +static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack) { #define BPF_INSN_2_LBL(x, y) [BPF_##x | BPF_##y] = &&x##_##y #define BPF_INSN_3_LBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = &&x##_##y##_##z diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 1815e97d4c9c..1fccba6e88c4 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -821,6 +821,32 @@ static void pcpu_copy_value(struct bpf_htab *htab, void __percpu *pptr, } } +static void pcpu_init_value(struct bpf_htab *htab, void __percpu *pptr, + void *value, bool onallcpus) +{ + /* When using prealloc and not setting the initial value on all cpus, + * zero-fill element values for other cpus (just as what happens when + * not using prealloc). Otherwise, bpf program has no way to ensure + * known initial values for cpus other than current one + * (onallcpus=false always when coming from bpf prog). + */ + if (htab_is_prealloc(htab) && !onallcpus) { + u32 size = round_up(htab->map.value_size, 8); + int current_cpu = raw_smp_processor_id(); + int cpu; + + for_each_possible_cpu(cpu) { + if (cpu == current_cpu) + bpf_long_memcpy(per_cpu_ptr(pptr, cpu), value, + size); + else + memset(per_cpu_ptr(pptr, cpu), 0, size); + } + } else { + pcpu_copy_value(htab, pptr, value, onallcpus); + } +} + static bool fd_htab_map_needs_adjust(const struct bpf_htab *htab) { return htab->map.map_type == BPF_MAP_TYPE_HASH_OF_MAPS && @@ -891,7 +917,7 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, } } - pcpu_copy_value(htab, pptr, value, onallcpus); + pcpu_init_value(htab, pptr, value, onallcpus); if (!prealloc) htab_elem_set_ptr(l_new, key_size, pptr); @@ -1183,7 +1209,7 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, pcpu_copy_value(htab, htab_elem_get_ptr(l_old, key_size), value, onallcpus); } else { - pcpu_copy_value(htab, htab_elem_get_ptr(l_new, key_size), + pcpu_init_value(htab, htab_elem_get_ptr(l_new, key_size), value, onallcpus); hlist_nulls_add_head_rcu(&l_new->hash_node, head); l_new = NULL; diff --git a/kernel/bpf/preload/Kconfig b/kernel/bpf/preload/Kconfig index ace49111d3a3..26bced262473 100644 --- a/kernel/bpf/preload/Kconfig +++ b/kernel/bpf/preload/Kconfig @@ -6,6 +6,7 @@ config USERMODE_DRIVER menuconfig BPF_PRELOAD bool "Preload BPF file system with kernel specific program and map iterators" depends on BPF + depends on BPF_SYSCALL # The dependency on !COMPILE_TEST prevents it from being enabled # in allmodconfig or allyesconfig configurations depends on !COMPILE_TEST diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index b4eea0abc3f0..781b9dca197c 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -229,6 +229,7 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) io_tlb_orig_addr[i] = INVALID_PHYS_ADDR; } io_tlb_index = 0; + no_iotlb_memory = false; if (verbose) swiotlb_print_info(); @@ -260,9 +261,11 @@ swiotlb_init(int verbose) if (vstart && !swiotlb_init_with_tbl(vstart, io_tlb_nslabs, verbose)) return; - if (io_tlb_start) + if (io_tlb_start) { memblock_free_early(io_tlb_start, PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT)); + io_tlb_start = 0; + } pr_warn("Cannot allocate buffer"); no_iotlb_memory = true; } @@ -360,6 +363,7 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) io_tlb_orig_addr[i] = INVALID_PHYS_ADDR; } io_tlb_index = 0; + no_iotlb_memory = false; swiotlb_print_info(); @@ -441,14 +445,11 @@ static void swiotlb_bounce(phys_addr_t orig_addr, phys_addr_t tlb_addr, } } -phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, - dma_addr_t tbl_dma_addr, - phys_addr_t orig_addr, - size_t mapping_size, - size_t alloc_size, - enum dma_data_direction dir, - unsigned long attrs) +phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t orig_addr, + size_t mapping_size, size_t alloc_size, + enum dma_data_direction dir, unsigned long attrs) { + dma_addr_t tbl_dma_addr = phys_to_dma_unencrypted(hwdev, io_tlb_start); unsigned long flags; phys_addr_t tlb_addr; unsigned int nslots, stride, index, wrap; @@ -667,9 +668,8 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size, trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size, swiotlb_force); - swiotlb_addr = swiotlb_tbl_map_single(dev, - phys_to_dma_unencrypted(dev, io_tlb_start), - paddr, size, size, dir, attrs); + swiotlb_addr = swiotlb_tbl_map_single(dev, paddr, size, size, dir, + attrs); if (swiotlb_addr == (phys_addr_t)DMA_MAPPING_ERROR) return DMA_MAPPING_ERROR; diff --git a/kernel/events/core.c b/kernel/events/core.c index 5a29ab09e72d..dc568ca295bd 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2312,9 +2312,6 @@ group_sched_out(struct perf_event *group_event, event_sched_out(event, cpuctx, ctx); perf_pmu_enable(ctx->pmu); - - if (group_event->attr.exclusive) - cpuctx->exclusive = 0; } #define DETACH_GROUP 0x01UL @@ -2583,11 +2580,8 @@ group_sched_in(struct perf_event *group_event, pmu->start_txn(pmu, PERF_PMU_TXN_ADD); - if (event_sched_in(group_event, cpuctx, ctx)) { - pmu->cancel_txn(pmu); - perf_mux_hrtimer_restart(cpuctx); - return -EAGAIN; - } + if (event_sched_in(group_event, cpuctx, ctx)) + goto error; /* * Schedule in siblings as one group (if any): @@ -2616,10 +2610,8 @@ group_error: } event_sched_out(group_event, cpuctx, ctx); +error: pmu->cancel_txn(pmu); - - perf_mux_hrtimer_restart(cpuctx); - return -EAGAIN; } @@ -2645,7 +2637,7 @@ static int group_can_go_on(struct perf_event *event, * If this group is exclusive and there are already * events on the CPU, it can't go on. */ - if (event->attr.exclusive && cpuctx->active_oncpu) + if (event->attr.exclusive && !list_empty(get_event_list(event))) return 0; /* * Otherwise, try to add it if all previous groups were able @@ -3679,6 +3671,7 @@ static int merge_sched_in(struct perf_event *event, void *data) *can_add_hw = 0; ctx->rotate_necessary = 1; + perf_mux_hrtimer_restart(cpuctx); } return 0; @@ -6374,14 +6367,13 @@ perf_output_sample_regs(struct perf_output_handle *handle, } static void perf_sample_regs_user(struct perf_regs *regs_user, - struct pt_regs *regs, - struct pt_regs *regs_user_copy) + struct pt_regs *regs) { if (user_mode(regs)) { regs_user->abi = perf_reg_abi(current); regs_user->regs = regs; } else if (!(current->flags & PF_KTHREAD)) { - perf_get_regs_user(regs_user, regs, regs_user_copy); + perf_get_regs_user(regs_user, regs); } else { regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE; regs_user->regs = NULL; @@ -7083,8 +7075,7 @@ void perf_prepare_sample(struct perf_event_header *header, } if (sample_type & (PERF_SAMPLE_REGS_USER | PERF_SAMPLE_STACK_USER)) - perf_sample_regs_user(&data->regs_user, regs, - &data->regs_user_copy); + perf_sample_regs_user(&data->regs_user, regs); if (sample_type & PERF_SAMPLE_REGS_USER) { /* regs dump ABI info */ @@ -7186,6 +7177,7 @@ __perf_event_output(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs, int (*output_begin)(struct perf_output_handle *, + struct perf_sample_data *, struct perf_event *, unsigned int)) { @@ -7198,7 +7190,7 @@ __perf_event_output(struct perf_event *event, perf_prepare_sample(&header, data, event, regs); - err = output_begin(&handle, event, header.size); + err = output_begin(&handle, data, event, header.size); if (err) goto exit; @@ -7264,7 +7256,7 @@ perf_event_read_event(struct perf_event *event, int ret; perf_event_header__init_id(&read_event.header, &sample, event); - ret = perf_output_begin(&handle, event, read_event.header.size); + ret = perf_output_begin(&handle, &sample, event, read_event.header.size); if (ret) return; @@ -7533,7 +7525,7 @@ static void perf_event_task_output(struct perf_event *event, perf_event_header__init_id(&task_event->event_id.header, &sample, event); - ret = perf_output_begin(&handle, event, + ret = perf_output_begin(&handle, &sample, event, task_event->event_id.header.size); if (ret) goto out; @@ -7636,7 +7628,7 @@ static void perf_event_comm_output(struct perf_event *event, return; perf_event_header__init_id(&comm_event->event_id.header, &sample, event); - ret = perf_output_begin(&handle, event, + ret = perf_output_begin(&handle, &sample, event, comm_event->event_id.header.size); if (ret) @@ -7736,7 +7728,7 @@ static void perf_event_namespaces_output(struct perf_event *event, perf_event_header__init_id(&namespaces_event->event_id.header, &sample, event); - ret = perf_output_begin(&handle, event, + ret = perf_output_begin(&handle, &sample, event, namespaces_event->event_id.header.size); if (ret) goto out; @@ -7863,7 +7855,7 @@ static void perf_event_cgroup_output(struct perf_event *event, void *data) perf_event_header__init_id(&cgroup_event->event_id.header, &sample, event); - ret = perf_output_begin(&handle, event, + ret = perf_output_begin(&handle, &sample, event, cgroup_event->event_id.header.size); if (ret) goto out; @@ -7989,7 +7981,7 @@ static void perf_event_mmap_output(struct perf_event *event, } perf_event_header__init_id(&mmap_event->event_id.header, &sample, event); - ret = perf_output_begin(&handle, event, + ret = perf_output_begin(&handle, &sample, event, mmap_event->event_id.header.size); if (ret) goto out; @@ -8299,7 +8291,7 @@ void perf_event_aux_event(struct perf_event *event, unsigned long head, int ret; perf_event_header__init_id(&rec.header, &sample, event); - ret = perf_output_begin(&handle, event, rec.header.size); + ret = perf_output_begin(&handle, &sample, event, rec.header.size); if (ret) return; @@ -8333,7 +8325,7 @@ void perf_log_lost_samples(struct perf_event *event, u64 lost) perf_event_header__init_id(&lost_samples_event.header, &sample, event); - ret = perf_output_begin(&handle, event, + ret = perf_output_begin(&handle, &sample, event, lost_samples_event.header.size); if (ret) return; @@ -8388,7 +8380,7 @@ static void perf_event_switch_output(struct perf_event *event, void *data) perf_event_header__init_id(&se->event_id.header, &sample, event); - ret = perf_output_begin(&handle, event, se->event_id.header.size); + ret = perf_output_begin(&handle, &sample, event, se->event_id.header.size); if (ret) return; @@ -8463,7 +8455,7 @@ static void perf_log_throttle(struct perf_event *event, int enable) perf_event_header__init_id(&throttle_event.header, &sample, event); - ret = perf_output_begin(&handle, event, + ret = perf_output_begin(&handle, &sample, event, throttle_event.header.size); if (ret) return; @@ -8506,7 +8498,7 @@ static void perf_event_ksymbol_output(struct perf_event *event, void *data) perf_event_header__init_id(&ksymbol_event->event_id.header, &sample, event); - ret = perf_output_begin(&handle, event, + ret = perf_output_begin(&handle, &sample, event, ksymbol_event->event_id.header.size); if (ret) return; @@ -8596,7 +8588,7 @@ static void perf_event_bpf_output(struct perf_event *event, void *data) perf_event_header__init_id(&bpf_event->event_id.header, &sample, event); - ret = perf_output_begin(&handle, event, + ret = perf_output_begin(&handle, data, event, bpf_event->event_id.header.size); if (ret) return; @@ -8705,7 +8697,8 @@ static void perf_event_text_poke_output(struct perf_event *event, void *data) perf_event_header__init_id(&text_poke_event->event_id.header, &sample, event); - ret = perf_output_begin(&handle, event, text_poke_event->event_id.header.size); + ret = perf_output_begin(&handle, &sample, event, + text_poke_event->event_id.header.size); if (ret) return; @@ -8786,7 +8779,7 @@ static void perf_log_itrace_start(struct perf_event *event) rec.tid = perf_event_tid(event, current); perf_event_header__init_id(&rec.header, &sample, event); - ret = perf_output_begin(&handle, event, rec.header.size); + ret = perf_output_begin(&handle, &sample, event, rec.header.size); if (ret) return; diff --git a/kernel/events/internal.h b/kernel/events/internal.h index fcbf5616a441..228801e20788 100644 --- a/kernel/events/internal.h +++ b/kernel/events/internal.h @@ -205,16 +205,12 @@ DEFINE_OUTPUT_COPY(__output_copy_user, arch_perf_out_copy_user) static inline int get_recursion_context(int *recursion) { - int rctx; - - if (unlikely(in_nmi())) - rctx = 3; - else if (in_irq()) - rctx = 2; - else if (in_softirq()) - rctx = 1; - else - rctx = 0; + unsigned int pc = preempt_count(); + unsigned char rctx = 0; + + rctx += !!(pc & (NMI_MASK)); + rctx += !!(pc & (NMI_MASK | HARDIRQ_MASK)); + rctx += !!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET)); if (recursion[rctx]) return -1; diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 192b8abc6330..ef91ae75ca56 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -147,6 +147,7 @@ ring_buffer_has_space(unsigned long head, unsigned long tail, static __always_inline int __perf_output_begin(struct perf_output_handle *handle, + struct perf_sample_data *data, struct perf_event *event, unsigned int size, bool backward) { @@ -237,18 +238,16 @@ __perf_output_begin(struct perf_output_handle *handle, handle->size = (1UL << page_shift) - offset; if (unlikely(have_lost)) { - struct perf_sample_data sample_data; - lost_event.header.size = sizeof(lost_event); lost_event.header.type = PERF_RECORD_LOST; lost_event.header.misc = 0; lost_event.id = event->id; lost_event.lost = local_xchg(&rb->lost, 0); - perf_event_header__init_id(&lost_event.header, - &sample_data, event); + /* XXX mostly redundant; @data is already fully initializes */ + perf_event_header__init_id(&lost_event.header, data, event); perf_output_put(handle, lost_event); - perf_event__output_id_sample(event, handle, &sample_data); + perf_event__output_id_sample(event, handle, data); } return 0; @@ -263,22 +262,25 @@ out: } int perf_output_begin_forward(struct perf_output_handle *handle, - struct perf_event *event, unsigned int size) + struct perf_sample_data *data, + struct perf_event *event, unsigned int size) { - return __perf_output_begin(handle, event, size, false); + return __perf_output_begin(handle, data, event, size, false); } int perf_output_begin_backward(struct perf_output_handle *handle, + struct perf_sample_data *data, struct perf_event *event, unsigned int size) { - return __perf_output_begin(handle, event, size, true); + return __perf_output_begin(handle, data, event, size, true); } int perf_output_begin(struct perf_output_handle *handle, + struct perf_sample_data *data, struct perf_event *event, unsigned int size) { - return __perf_output_begin(handle, event, size, + return __perf_output_begin(handle, data, event, size, unlikely(is_write_backward(event))); } diff --git a/kernel/exit.c b/kernel/exit.c index 87a2d515de0d..1f236ed375f8 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -454,7 +454,10 @@ static void exit_mm(void) mmap_read_unlock(mm); self.task = current; - self.next = xchg(&core_state->dumper.next, &self); + if (self.task->flags & PF_SIGNALED) + self.next = xchg(&core_state->dumper.next, &self); + else + self.task = NULL; /* * Implies mb(), the result of xchg() must be visible * to core_state->dumper. diff --git a/kernel/futex.c b/kernel/futex.c index ac328874f6e5..00259c7e288e 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -788,8 +788,9 @@ static void put_pi_state(struct futex_pi_state *pi_state) */ if (pi_state->owner) { struct task_struct *owner; + unsigned long flags; - raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); + raw_spin_lock_irqsave(&pi_state->pi_mutex.wait_lock, flags); owner = pi_state->owner; if (owner) { raw_spin_lock(&owner->pi_lock); @@ -797,7 +798,7 @@ static void put_pi_state(struct futex_pi_state *pi_state) raw_spin_unlock(&owner->pi_lock); } rt_mutex_proxy_unlock(&pi_state->pi_mutex, owner); - raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); + raw_spin_unlock_irqrestore(&pi_state->pi_mutex.wait_lock, flags); } if (current->pi_state_cache) { diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index b71ad8d9f1c9..d9fb9e19d2ed 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -2765,7 +2765,9 @@ print_deadlock_bug(struct task_struct *curr, struct held_lock *prev, * (Note that this has to be done separately, because the graph cannot * detect such classes of deadlocks.) * - * Returns: 0 on deadlock detected, 1 on OK, 2 on recursive read + * Returns: 0 on deadlock detected, 1 on OK, 2 if another lock with the same + * lock class is held but nest_lock is also held, i.e. we rely on the + * nest_lock to avoid the deadlock. */ static int check_deadlock(struct task_struct *curr, struct held_lock *next) @@ -2788,7 +2790,7 @@ check_deadlock(struct task_struct *curr, struct held_lock *next) * lock class (i.e. read_lock(lock)+read_lock(lock)): */ if ((next->read == 2) && prev->read) - return 2; + continue; /* * We're holding the nest_lock, which serializes this lock's @@ -3593,15 +3595,12 @@ static int validate_chain(struct task_struct *curr, if (!ret) return 0; /* - * Mark recursive read, as we jump over it when - * building dependencies (just like we jump over - * trylock entries): - */ - if (ret == 2) - hlock->read = 2; - /* * Add dependency only if this lock is not the head - * of the chain, and if it's not a secondary read-lock: + * of the chain, and if the new lock introduces no more + * lock dependency (because we already hold a lock with the + * same lock class) nor deadlock (because the nest_lock + * serializes nesting locks), see the comments for + * check_deadlock(). */ if (!chain_head && ret != 2) { if (!check_prevs_add(curr, hlock)) diff --git a/kernel/panic.c b/kernel/panic.c index 396142ee43fd..332736a72a58 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -605,7 +605,8 @@ void __warn(const char *file, int line, void *caller, unsigned taint, panic("panic_on_warn set ...\n"); } - dump_stack(); + if (!regs) + dump_stack(); print_irqtrace_events(current); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 2a52f42f64b6..bd04b09b84b3 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -4077,7 +4077,6 @@ void rcu_cpu_starting(unsigned int cpu) smp_mb(); /* Ensure RCU read-side usage follows above initialization. */ } -#ifdef CONFIG_HOTPLUG_CPU /* * The outgoing function has no further need of RCU, so remove it from * the rcu_node tree's ->qsmaskinitnext bit masks. @@ -4117,6 +4116,7 @@ void rcu_report_dead(unsigned int cpu) rdp->cpu_started = false; } +#ifdef CONFIG_HOTPLUG_CPU /* * The outgoing CPU has just passed through the dying-idle state, and we * are being invoked from the CPU that was IPIed to continue the offline diff --git a/kernel/reboot.c b/kernel/reboot.c index e7b78d5ae1ab..af6f23d8bea1 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -551,22 +551,22 @@ static int __init reboot_setup(char *str) break; case 's': - { - int rc; - - if (isdigit(*(str+1))) { - rc = kstrtoint(str+1, 0, &reboot_cpu); - if (rc) - return rc; - } else if (str[1] == 'm' && str[2] == 'p' && - isdigit(*(str+3))) { - rc = kstrtoint(str+3, 0, &reboot_cpu); - if (rc) - return rc; - } else + if (isdigit(*(str+1))) + reboot_cpu = simple_strtoul(str+1, NULL, 0); + else if (str[1] == 'm' && str[2] == 'p' && + isdigit(*(str+3))) + reboot_cpu = simple_strtoul(str+3, NULL, 0); + else *mode = REBOOT_SOFT; + if (reboot_cpu >= num_possible_cpus()) { + pr_err("Ignoring the CPU number in reboot= option. " + "CPU %d exceeds possible cpu number %d\n", + reboot_cpu, num_possible_cpus()); + reboot_cpu = 0; + break; + } break; - } + case 'g': *mode = REBOOT_GPIO; break; diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index d73bccde2720..97d318b0cd0c 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -881,7 +881,7 @@ static void sugov_limits(struct cpufreq_policy *policy) struct cpufreq_governor schedutil_gov = { .name = "schedutil", .owner = THIS_MODULE, - .dynamic_switching = true, + .flags = CPUFREQ_GOV_DYNAMIC_SWITCHING, .init = sugov_init, .exit = sugov_exit, .start = sugov_start, diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 0655524700d2..2357921580f9 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -251,7 +251,7 @@ static int sd_ctl_doflags(struct ctl_table *table, int write, unsigned long flags = *(unsigned long *)table->data; size_t data_size = 0; size_t len = 0; - char *tmp; + char *tmp, *buf; int idx; if (write) @@ -269,17 +269,17 @@ static int sd_ctl_doflags(struct ctl_table *table, int write, return 0; } - tmp = kcalloc(data_size + 1, sizeof(*tmp), GFP_KERNEL); - if (!tmp) + buf = kcalloc(data_size + 1, sizeof(*buf), GFP_KERNEL); + if (!buf) return -ENOMEM; for_each_set_bit(idx, &flags, __SD_FLAG_CNT) { char *name = sd_flag_debug[idx].name; - len += snprintf(tmp + len, strlen(name) + 2, "%s ", name); + len += snprintf(buf + len, strlen(name) + 2, "%s ", name); } - tmp += *ppos; + tmp = buf + *ppos; len -= *ppos; if (len > *lenp) @@ -294,7 +294,7 @@ static int sd_ctl_doflags(struct ctl_table *table, int write, *lenp = len; *ppos += len; - kfree(tmp); + kfree(buf); return 0; } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 290f9e38378c..8917d2d715ef 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6172,21 +6172,21 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t static int select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target) { - unsigned long best_cap = 0; + unsigned long task_util, best_cap = 0; int cpu, best_cpu = -1; struct cpumask *cpus; - sync_entity_load_avg(&p->se); - cpus = this_cpu_cpumask_var_ptr(select_idle_mask); cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr); + task_util = uclamp_task_util(p); + for_each_cpu_wrap(cpu, cpus, target) { unsigned long cpu_cap = capacity_of(cpu); if (!available_idle_cpu(cpu) && !sched_idle_cpu(cpu)) continue; - if (task_fits_capacity(p, cpu_cap)) + if (fits_capacity(task_util, cpu_cap)) return cpu; if (cpu_cap > best_cap) { @@ -6198,44 +6198,42 @@ select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target) return best_cpu; } +static inline bool asym_fits_capacity(int task_util, int cpu) +{ + if (static_branch_unlikely(&sched_asym_cpucapacity)) + return fits_capacity(task_util, capacity_of(cpu)); + + return true; +} + /* * Try and locate an idle core/thread in the LLC cache domain. */ static int select_idle_sibling(struct task_struct *p, int prev, int target) { struct sched_domain *sd; + unsigned long task_util; int i, recent_used_cpu; /* - * For asymmetric CPU capacity systems, our domain of interest is - * sd_asym_cpucapacity rather than sd_llc. + * On asymmetric system, update task utilization because we will check + * that the task fits with cpu's capacity. */ if (static_branch_unlikely(&sched_asym_cpucapacity)) { - sd = rcu_dereference(per_cpu(sd_asym_cpucapacity, target)); - /* - * On an asymmetric CPU capacity system where an exclusive - * cpuset defines a symmetric island (i.e. one unique - * capacity_orig value through the cpuset), the key will be set - * but the CPUs within that cpuset will not have a domain with - * SD_ASYM_CPUCAPACITY. These should follow the usual symmetric - * capacity path. - */ - if (!sd) - goto symmetric; - - i = select_idle_capacity(p, sd, target); - return ((unsigned)i < nr_cpumask_bits) ? i : target; + sync_entity_load_avg(&p->se); + task_util = uclamp_task_util(p); } -symmetric: - if (available_idle_cpu(target) || sched_idle_cpu(target)) + if ((available_idle_cpu(target) || sched_idle_cpu(target)) && + asym_fits_capacity(task_util, target)) return target; /* * If the previous CPU is cache affine and idle, don't be stupid: */ if (prev != target && cpus_share_cache(prev, target) && - (available_idle_cpu(prev) || sched_idle_cpu(prev))) + (available_idle_cpu(prev) || sched_idle_cpu(prev)) && + asym_fits_capacity(task_util, prev)) return prev; /* @@ -6258,7 +6256,8 @@ symmetric: recent_used_cpu != target && cpus_share_cache(recent_used_cpu, target) && (available_idle_cpu(recent_used_cpu) || sched_idle_cpu(recent_used_cpu)) && - cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr)) { + cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr) && + asym_fits_capacity(task_util, recent_used_cpu)) { /* * Replace recent_used_cpu with prev as it is a potential * candidate for the next wake: @@ -6267,6 +6266,26 @@ symmetric: return recent_used_cpu; } + /* + * For asymmetric CPU capacity systems, our domain of interest is + * sd_asym_cpucapacity rather than sd_llc. + */ + if (static_branch_unlikely(&sched_asym_cpucapacity)) { + sd = rcu_dereference(per_cpu(sd_asym_cpucapacity, target)); + /* + * On an asymmetric CPU capacity system where an exclusive + * cpuset defines a symmetric island (i.e. one unique + * capacity_orig value through the cpuset), the key will be set + * but the CPUs within that cpuset will not have a domain with + * SD_ASYM_CPUCAPACITY. These should follow the usual symmetric + * capacity path. + */ + if (sd) { + i = select_idle_capacity(p, sd, target); + return ((unsigned)i < nr_cpumask_bits) ? i : target; + } + } + sd = rcu_dereference(per_cpu(sd_llc, target)); if (!sd) return target; @@ -9031,7 +9050,8 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s * emptying busiest. */ if (local->group_type == group_has_spare) { - if (busiest->group_type > group_fully_busy) { + if ((busiest->group_type > group_fully_busy) && + !(env->sd->flags & SD_SHARE_PKG_RESOURCES)) { /* * If busiest is overloaded, try to fill spare * capacity. This might end up creating spare capacity diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 5abb5b22ad13..71109065bd8e 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -44,8 +44,6 @@ int __read_mostly soft_watchdog_user_enabled = 1; int __read_mostly watchdog_thresh = 10; static int __read_mostly nmi_watchdog_available; -static struct cpumask watchdog_allowed_mask __read_mostly; - struct cpumask watchdog_cpumask __read_mostly; unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask); @@ -162,6 +160,8 @@ static void lockup_detector_update_enable(void) int __read_mostly sysctl_softlockup_all_cpu_backtrace; #endif +static struct cpumask watchdog_allowed_mask __read_mostly; + /* Global variables, exported for sysctl */ unsigned int __read_mostly softlockup_panic = CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE; diff --git a/mm/compaction.c b/mm/compaction.c index 6e0ee5641788..13cb7a961b31 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -817,6 +817,10 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, * delay for some time until fewer pages are isolated */ while (unlikely(too_many_isolated(pgdat))) { + /* stop isolation if there are still pages not migrated */ + if (cc->nr_migratepages) + return 0; + /* async migration should just abort */ if (cc->mode == MIGRATE_ASYNC) return 0; @@ -1012,8 +1016,8 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, isolate_success: list_add(&page->lru, &cc->migratepages); - cc->nr_migratepages++; - nr_isolated++; + cc->nr_migratepages += compound_nr(page); + nr_isolated += compound_nr(page); /* * Avoid isolating too much unless this block is being @@ -1021,7 +1025,7 @@ isolate_success: * or a lock is contended. For contention, isolate quickly to * potentially remove one source of contention. */ - if (cc->nr_migratepages == COMPACT_CLUSTER_MAX && + if (cc->nr_migratepages >= COMPACT_CLUSTER_MAX && !cc->rescan && !cc->contended) { ++low_pfn; break; @@ -1132,7 +1136,7 @@ isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn, if (!pfn) break; - if (cc->nr_migratepages == COMPACT_CLUSTER_MAX) + if (cc->nr_migratepages >= COMPACT_CLUSTER_MAX) break; } @@ -1647,8 +1647,11 @@ check_again: /* * drop the above get_user_pages reference. */ - for (i = 0; i < nr_pages; i++) - put_page(pages[i]); + if (gup_flags & FOLL_PIN) + unpin_user_pages(pages, nr_pages); + else + for (i = 0; i < nr_pages; i++) + put_page(pages[i]); if (migrate_pages(&cma_page_list, alloc_migration_target, NULL, (unsigned long)&mtc, MIGRATE_SYNC, MR_CONTIG_RANGE)) { @@ -1728,8 +1731,11 @@ static long __gup_longterm_locked(struct mm_struct *mm, goto out; if (check_dax_vmas(vmas_tmp, rc)) { - for (i = 0; i < rc; i++) - put_page(pages[i]); + if (gup_flags & FOLL_PIN) + unpin_user_pages(pages, rc); + else + for (i = 0; i < rc; i++) + put_page(pages[i]); rc = -EOPNOTSUPP; goto out; } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 5a620f690911..37f15c3c24dc 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1568,103 +1568,23 @@ int PageHeadHuge(struct page *page_head) } /* - * Find address_space associated with hugetlbfs page. - * Upon entry page is locked and page 'was' mapped although mapped state - * could change. If necessary, use anon_vma to find vma and associated - * address space. The returned mapping may be stale, but it can not be - * invalid as page lock (which is held) is required to destroy mapping. - */ -static struct address_space *_get_hugetlb_page_mapping(struct page *hpage) -{ - struct anon_vma *anon_vma; - pgoff_t pgoff_start, pgoff_end; - struct anon_vma_chain *avc; - struct address_space *mapping = page_mapping(hpage); - - /* Simple file based mapping */ - if (mapping) - return mapping; - - /* - * Even anonymous hugetlbfs mappings are associated with an - * underlying hugetlbfs file (see hugetlb_file_setup in mmap - * code). Find a vma associated with the anonymous vma, and - * use the file pointer to get address_space. - */ - anon_vma = page_lock_anon_vma_read(hpage); - if (!anon_vma) - return mapping; /* NULL */ - - /* Use first found vma */ - pgoff_start = page_to_pgoff(hpage); - pgoff_end = pgoff_start + pages_per_huge_page(page_hstate(hpage)) - 1; - anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, - pgoff_start, pgoff_end) { - struct vm_area_struct *vma = avc->vma; - - mapping = vma->vm_file->f_mapping; - break; - } - - anon_vma_unlock_read(anon_vma); - return mapping; -} - -/* * Find and lock address space (mapping) in write mode. * - * Upon entry, the page is locked which allows us to find the mapping - * even in the case of an anon page. However, locking order dictates - * the i_mmap_rwsem be acquired BEFORE the page lock. This is hugetlbfs - * specific. So, we first try to lock the sema while still holding the - * page lock. If this works, great! If not, then we need to drop the - * page lock and then acquire i_mmap_rwsem and reacquire page lock. Of - * course, need to revalidate state along the way. + * Upon entry, the page is locked which means that page_mapping() is + * stable. Due to locking order, we can only trylock_write. If we can + * not get the lock, simply return NULL to caller. */ struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage) { - struct address_space *mapping, *mapping2; + struct address_space *mapping = page_mapping(hpage); - mapping = _get_hugetlb_page_mapping(hpage); -retry: if (!mapping) return mapping; - /* - * If no contention, take lock and return - */ if (i_mmap_trylock_write(mapping)) return mapping; - /* - * Must drop page lock and wait on mapping sema. - * Note: Once page lock is dropped, mapping could become invalid. - * As a hack, increase map count until we lock page again. - */ - atomic_inc(&hpage->_mapcount); - unlock_page(hpage); - i_mmap_lock_write(mapping); - lock_page(hpage); - atomic_add_negative(-1, &hpage->_mapcount); - - /* verify page is still mapped */ - if (!page_mapped(hpage)) { - i_mmap_unlock_write(mapping); - return NULL; - } - - /* - * Get address space again and verify it is the same one - * we locked. If not, drop lock and retry. - */ - mapping2 = _get_hugetlb_page_mapping(hpage); - if (mapping2 != mapping) { - i_mmap_unlock_write(mapping); - mapping = mapping2; - goto retry; - } - - return mapping; + return NULL; } pgoff_t __basepage_index(struct page *page) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index c0bb186bba62..5d880d4eb9a2 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1057,27 +1057,25 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, if (!PageHuge(hpage)) { unmap_success = try_to_unmap(hpage, ttu); } else { - /* - * For hugetlb pages, try_to_unmap could potentially call - * huge_pmd_unshare. Because of this, take semaphore in - * write mode here and set TTU_RMAP_LOCKED to indicate we - * have taken the lock at this higer level. - * - * Note that the call to hugetlb_page_mapping_lock_write - * is necessary even if mapping is already set. It handles - * ugliness of potentially having to drop page lock to obtain - * i_mmap_rwsem. - */ - mapping = hugetlb_page_mapping_lock_write(hpage); - - if (mapping) { - unmap_success = try_to_unmap(hpage, + if (!PageAnon(hpage)) { + /* + * For hugetlb pages in shared mappings, try_to_unmap + * could potentially call huge_pmd_unshare. Because of + * this, take semaphore in write mode here and set + * TTU_RMAP_LOCKED to indicate we have taken the lock + * at this higer level. + */ + mapping = hugetlb_page_mapping_lock_write(hpage); + if (mapping) { + unmap_success = try_to_unmap(hpage, ttu|TTU_RMAP_LOCKED); - i_mmap_unlock_write(mapping); + i_mmap_unlock_write(mapping); + } else { + pr_info("Memory failure: %#lx: could not lock mapping for mapped huge page\n", pfn); + unmap_success = false; + } } else { - pr_info("Memory failure: %#lx: could not find mapping for mapped huge page\n", - pfn); - unmap_success = false; + unmap_success = try_to_unmap(hpage, ttu); } } if (!unmap_success) diff --git a/mm/migrate.c b/mm/migrate.c index 5ca5842df5db..5795cb82e27c 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1328,34 +1328,38 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, goto put_anon; if (page_mapped(hpage)) { - /* - * try_to_unmap could potentially call huge_pmd_unshare. - * Because of this, take semaphore in write mode here and - * set TTU_RMAP_LOCKED to let lower levels know we have - * taken the lock. - */ - mapping = hugetlb_page_mapping_lock_write(hpage); - if (unlikely(!mapping)) - goto unlock_put_anon; + bool mapping_locked = false; + enum ttu_flags ttu = TTU_MIGRATION|TTU_IGNORE_MLOCK| + TTU_IGNORE_ACCESS; + + if (!PageAnon(hpage)) { + /* + * In shared mappings, try_to_unmap could potentially + * call huge_pmd_unshare. Because of this, take + * semaphore in write mode here and set TTU_RMAP_LOCKED + * to let lower levels know we have taken the lock. + */ + mapping = hugetlb_page_mapping_lock_write(hpage); + if (unlikely(!mapping)) + goto unlock_put_anon; + + mapping_locked = true; + ttu |= TTU_RMAP_LOCKED; + } - try_to_unmap(hpage, - TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS| - TTU_RMAP_LOCKED); + try_to_unmap(hpage, ttu); page_was_mapped = 1; - /* - * Leave mapping locked until after subsequent call to - * remove_migration_ptes() - */ + + if (mapping_locked) + i_mmap_unlock_write(mapping); } if (!page_mapped(hpage)) rc = move_to_new_page(new_hpage, hpage, mode); - if (page_was_mapped) { + if (page_was_mapped) remove_migration_ptes(hpage, - rc == MIGRATEPAGE_SUCCESS ? new_hpage : hpage, true); - i_mmap_unlock_write(mapping); - } + rc == MIGRATEPAGE_SUCCESS ? new_hpage : hpage, false); unlock_put_anon: unlock_page(new_hpage); diff --git a/mm/percpu.c b/mm/percpu.c index 66a93f096394..ad7a37ee74ef 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -1315,8 +1315,8 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr, region_size = ALIGN(start_offset + map_size, lcm_align); /* allocate chunk */ - alloc_size = sizeof(struct pcpu_chunk) + - BITS_TO_LONGS(region_size >> PAGE_SHIFT) * sizeof(unsigned long); + alloc_size = struct_size(chunk, populated, + BITS_TO_LONGS(region_size >> PAGE_SHIFT)); chunk = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!chunk) panic("%s: Failed to allocate %zu bytes\n", __func__, @@ -2521,8 +2521,8 @@ void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, pcpu_unit_pages = ai->unit_size >> PAGE_SHIFT; pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT; pcpu_atom_size = ai->atom_size; - pcpu_chunk_struct_size = sizeof(struct pcpu_chunk) + - BITS_TO_LONGS(pcpu_unit_pages) * sizeof(unsigned long); + pcpu_chunk_struct_size = struct_size(chunk, populated, + BITS_TO_LONGS(pcpu_unit_pages)); pcpu_stats_save_ai(ai); diff --git a/mm/rmap.c b/mm/rmap.c index 1b84945d655c..31b29321adfe 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1413,9 +1413,6 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, /* * If sharing is possible, start and end will be adjusted * accordingly. - * - * If called for a huge page, caller must hold i_mmap_rwsem - * in write mode as it is possible to call huge_pmd_unshare. */ adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); @@ -1462,7 +1459,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte); address = pvmw.address; - if (PageHuge(page)) { + if (PageHuge(page) && !PageAnon(page)) { /* * To call huge_pmd_unshare, i_mmap_rwsem must be * held in write mode. Caller needs to explicitly diff --git a/mm/slub.c b/mm/slub.c index b30be2385d1c..34dcc09e2ec9 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2852,7 +2852,7 @@ redo: object = c->freelist; page = c->page; - if (unlikely(!object || !node_match(page, node))) { + if (unlikely(!object || !page || !node_match(page, node))) { object = __slab_alloc(s, gfpflags, node, addr, c); } else { void *next_object = get_freepointer_safe(s, object); diff --git a/mm/vmscan.c b/mm/vmscan.c index 1b8f0e059767..7b4e31eac2cf 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1516,7 +1516,8 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone, nr_reclaimed = shrink_page_list(&clean_pages, zone->zone_pgdat, &sc, TTU_IGNORE_ACCESS, &stat, true); list_splice(&clean_pages, page_list); - mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -nr_reclaimed); + mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, + -(long)nr_reclaimed); /* * Since lazyfree pages are isolated from file LRU from the beginning, * they will rotate back to anonymous LRU in the end if it failed to @@ -1526,7 +1527,7 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone, mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_ANON, stat.nr_lazyfree_fail); mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, - -stat.nr_lazyfree_fail); + -(long)stat.nr_lazyfree_fail); return nr_reclaimed; } diff --git a/net/core/devlink.c b/net/core/devlink.c index a932d95be798..ab4b1368904f 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -8254,8 +8254,6 @@ static int __devlink_port_attrs_set(struct devlink_port *devlink_port, { struct devlink_port_attrs *attrs = &devlink_port->attrs; - if (WARN_ON(devlink_port->registered)) - return -EEXIST; devlink_port->attrs_set = true; attrs->flavour = flavour; if (attrs->switch_id.id_len) { @@ -8279,6 +8277,8 @@ void devlink_port_attrs_set(struct devlink_port *devlink_port, { int ret; + if (WARN_ON(devlink_port->registered)) + return; devlink_port->attrs = *attrs; ret = __devlink_port_attrs_set(devlink_port, attrs->flavour); if (ret) @@ -8301,6 +8301,8 @@ void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u32 contro struct devlink_port_attrs *attrs = &devlink_port->attrs; int ret; + if (WARN_ON(devlink_port->registered)) + return; ret = __devlink_port_attrs_set(devlink_port, DEVLINK_PORT_FLAVOUR_PCI_PF); if (ret) @@ -8326,6 +8328,8 @@ void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 contro struct devlink_port_attrs *attrs = &devlink_port->attrs; int ret; + if (WARN_ON(devlink_port->registered)) + return; ret = __devlink_port_attrs_set(devlink_port, DEVLINK_PORT_FLAVOUR_PCI_VF); if (ret) diff --git a/net/ethtool/features.c b/net/ethtool/features.c index 8ee4cdbd6b82..1c9f4df273bd 100644 --- a/net/ethtool/features.c +++ b/net/ethtool/features.c @@ -280,7 +280,7 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info) active_diff_mask, compact); } if (mod) - ethtool_notify(dev, ETHTOOL_MSG_FEATURES_NTF, NULL); + netdev_features_change(dev); out_rtnl: rtnl_unlock(); diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 25f1caf5abf9..e25be2d01a7a 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -263,7 +263,7 @@ static int iptunnel_pmtud_check_icmp(struct sk_buff *skb, int mtu) const struct icmphdr *icmph = icmp_hdr(skb); const struct iphdr *iph = ip_hdr(skb); - if (mtu <= 576 || iph->frag_off != htons(IP_DF)) + if (mtu < 576 || iph->frag_off != htons(IP_DF)) return 0; if (ipv4_is_lbcast(iph->daddr) || ipv4_is_multicast(iph->daddr) || @@ -359,7 +359,7 @@ static int iptunnel_pmtud_check_icmpv6(struct sk_buff *skb, int mtu) __be16 frag_off; int offset; - if (mtu <= IPV6_MIN_MTU) + if (mtu < IPV6_MIN_MTU) return 0; if (stype == IPV6_ADDR_ANY || stype == IPV6_ADDR_MULTICAST || diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 6ac473b47f30..00dc3f943c80 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -331,7 +331,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) __u32 cookie = ntohl(th->ack_seq) - 1; struct sock *ret = sk; struct request_sock *req; - int mss; + int full_space, mss; struct rtable *rt; __u8 rcv_wscale; struct flowi4 fl4; @@ -427,8 +427,13 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) /* Try to redo what tcp_v4_send_synack did. */ req->rsk_window_clamp = tp->window_clamp ? :dst_metric(&rt->dst, RTAX_WINDOW); + /* limit the window selection if the user enforce a smaller rx buffer */ + full_space = tcp_full_space(sk); + if (sk->sk_userlocks & SOCK_RCVBUF_LOCK && + (req->rsk_window_clamp > full_space || req->rsk_window_clamp == 0)) + req->rsk_window_clamp = full_space; - tcp_select_initial_window(sk, tcp_full_space(sk), req->mss, + tcp_select_initial_window(sk, full_space, req->mss, &req->rsk_rcv_wnd, &req->rsk_window_clamp, ireq->wscale_ok, &rcv_wscale, dst_metric(&rt->dst, RTAX_INITRWND)); diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index e67a66fbf27b..c62805cd3131 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -366,7 +366,7 @@ out: static struct sk_buff *udp_gro_receive_segment(struct list_head *head, struct sk_buff *skb) { - struct udphdr *uh = udp_hdr(skb); + struct udphdr *uh = udp_gro_udphdr(skb); struct sk_buff *pp = NULL; struct udphdr *uh2; struct sk_buff *p; @@ -500,12 +500,22 @@ out: } EXPORT_SYMBOL(udp_gro_receive); +static struct sock *udp4_gro_lookup_skb(struct sk_buff *skb, __be16 sport, + __be16 dport) +{ + const struct iphdr *iph = skb_gro_network_header(skb); + + return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport, + iph->daddr, dport, inet_iif(skb), + inet_sdif(skb), &udp_table, NULL); +} + INDIRECT_CALLABLE_SCOPE struct sk_buff *udp4_gro_receive(struct list_head *head, struct sk_buff *skb) { struct udphdr *uh = udp_gro_udphdr(skb); + struct sock *sk = NULL; struct sk_buff *pp; - struct sock *sk; if (unlikely(!uh)) goto flush; @@ -523,7 +533,10 @@ struct sk_buff *udp4_gro_receive(struct list_head *head, struct sk_buff *skb) skip: NAPI_GRO_CB(skb)->is_ipv6 = 0; rcu_read_lock(); - sk = static_branch_unlikely(&udp_encap_needed_key) ? udp4_lib_lookup_skb(skb, uh->source, uh->dest) : NULL; + + if (static_branch_unlikely(&udp_encap_needed_key)) + sk = udp4_gro_lookup_skb(skb, uh->source, uh->dest); + pp = udp_gro_receive(head, skb, uh, sk); rcu_read_unlock(); return pp; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 5e2c34c0ac97..5e7983cb6154 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1128,7 +1128,6 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev) if (tdev && !netif_is_l3_master(tdev)) { int t_hlen = tunnel->hlen + sizeof(struct iphdr); - dev->hard_header_len = tdev->hard_header_len + sizeof(struct iphdr); dev->mtu = tdev->mtu - t_hlen; if (dev->mtu < IPV6_MIN_MTU) dev->mtu = IPV6_MIN_MTU; @@ -1426,7 +1425,6 @@ static void ipip6_tunnel_setup(struct net_device *dev) dev->priv_destructor = ipip6_dev_free; dev->type = ARPHRD_SIT; - dev->hard_header_len = LL_MAX_HEADER + t_hlen; dev->mtu = ETH_DATA_LEN - t_hlen; dev->min_mtu = IPV6_MIN_MTU; dev->max_mtu = IP6_MAX_MTU - t_hlen; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index e796a64be308..9b6cae1e49d9 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -136,7 +136,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) __u32 cookie = ntohl(th->ack_seq) - 1; struct sock *ret = sk; struct request_sock *req; - int mss; + int full_space, mss; struct dst_entry *dst; __u8 rcv_wscale; u32 tsoff = 0; @@ -241,7 +241,13 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) } req->rsk_window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW); - tcp_select_initial_window(sk, tcp_full_space(sk), req->mss, + /* limit the window selection if the user enforce a smaller rx buffer */ + full_space = tcp_full_space(sk); + if (sk->sk_userlocks & SOCK_RCVBUF_LOCK && + (req->rsk_window_clamp > full_space || req->rsk_window_clamp == 0)) + req->rsk_window_clamp = full_space; + + tcp_select_initial_window(sk, full_space, req->mss, &req->rsk_rcv_wnd, &req->rsk_window_clamp, ireq->wscale_ok, &rcv_wscale, dst_metric(dst, RTAX_INITRWND)); diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index 584157a07759..f9e888d1b9af 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -111,12 +111,22 @@ out: return segs; } +static struct sock *udp6_gro_lookup_skb(struct sk_buff *skb, __be16 sport, + __be16 dport) +{ + const struct ipv6hdr *iph = skb_gro_network_header(skb); + + return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport, + &iph->daddr, dport, inet6_iif(skb), + inet6_sdif(skb), &udp_table, NULL); +} + INDIRECT_CALLABLE_SCOPE struct sk_buff *udp6_gro_receive(struct list_head *head, struct sk_buff *skb) { struct udphdr *uh = udp_gro_udphdr(skb); + struct sock *sk = NULL; struct sk_buff *pp; - struct sock *sk; if (unlikely(!uh)) goto flush; @@ -135,7 +145,10 @@ struct sk_buff *udp6_gro_receive(struct list_head *head, struct sk_buff *skb) skip: NAPI_GRO_CB(skb)->is_ipv6 = 1; rcu_read_lock(); - sk = static_branch_unlikely(&udpv6_encap_needed_key) ? udp6_lib_lookup_skb(skb, uh->source, uh->dest) : NULL; + + if (static_branch_unlikely(&udpv6_encap_needed_key)) + sk = udp6_gro_lookup_skb(skb, uh->source, uh->dest); + pp = udp_gro_receive(head, skb, uh, sk); rcu_read_unlock(); return pp; diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index d80572074667..047238f01ba6 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -1434,7 +1434,8 @@ static int iucv_sock_shutdown(struct socket *sock, int how) break; } - if (how == SEND_SHUTDOWN || how == SHUTDOWN_MASK) { + if ((how == SEND_SHUTDOWN || how == SHUTDOWN_MASK) && + sk->sk_state == IUCV_CONNECTED) { if (iucv->transport == AF_IUCV_TRANS_IUCV) { txmsg.class = 0; txmsg.tag = 0; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index e7419fd15d84..88f2a7a0ccb8 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2467,6 +2467,7 @@ static struct proto mptcp_prot = { .memory_pressure = &tcp_memory_pressure, .stream_memory_free = mptcp_memory_free, .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_tcp_wmem), + .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_tcp_rmem), .sysctl_mem = sysctl_tcp_mem, .obj_size = sizeof(struct mptcp_sock), .slab_flags = SLAB_TYPESAFE_BY_RCU, diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index 2e8e3f7b2111..fc55c9116da0 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -1166,12 +1166,13 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb, struct netlbl_unlhsh_walk_arg cb_arg; u32 skip_bkt = cb->args[0]; u32 skip_chain = cb->args[1]; - u32 iter_bkt; - u32 iter_chain = 0, iter_addr4 = 0, iter_addr6 = 0; + u32 skip_addr4 = cb->args[2]; + u32 iter_bkt, iter_chain, iter_addr4 = 0, iter_addr6 = 0; struct netlbl_unlhsh_iface *iface; struct list_head *iter_list; struct netlbl_af4list *addr4; #if IS_ENABLED(CONFIG_IPV6) + u32 skip_addr6 = cb->args[3]; struct netlbl_af6list *addr6; #endif @@ -1182,7 +1183,7 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb, rcu_read_lock(); for (iter_bkt = skip_bkt; iter_bkt < rcu_dereference(netlbl_unlhsh)->size; - iter_bkt++, iter_chain = 0, iter_addr4 = 0, iter_addr6 = 0) { + iter_bkt++) { iter_list = &rcu_dereference(netlbl_unlhsh)->tbl[iter_bkt]; list_for_each_entry_rcu(iface, iter_list, list) { if (!iface->valid || @@ -1190,7 +1191,7 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb, continue; netlbl_af4list_foreach_rcu(addr4, &iface->addr4_list) { - if (iter_addr4++ < cb->args[2]) + if (iter_addr4++ < skip_addr4) continue; if (netlbl_unlabel_staticlist_gen( NLBL_UNLABEL_C_STATICLIST, @@ -1203,10 +1204,12 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb, goto unlabel_staticlist_return; } } + iter_addr4 = 0; + skip_addr4 = 0; #if IS_ENABLED(CONFIG_IPV6) netlbl_af6list_foreach_rcu(addr6, &iface->addr6_list) { - if (iter_addr6++ < cb->args[3]) + if (iter_addr6++ < skip_addr6) continue; if (netlbl_unlabel_staticlist_gen( NLBL_UNLABEL_C_STATICLIST, @@ -1219,8 +1222,12 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb, goto unlabel_staticlist_return; } } + iter_addr6 = 0; + skip_addr6 = 0; #endif /* IPv6 */ } + iter_chain = 0; + skip_chain = 0; } unlabel_staticlist_return: diff --git a/net/sunrpc/sysctl.c b/net/sunrpc/sysctl.c index a18b36b5422d..3aad6ef18504 100644 --- a/net/sunrpc/sysctl.c +++ b/net/sunrpc/sysctl.c @@ -63,19 +63,20 @@ static int proc_do_xprt(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { char tmpbuf[256]; - size_t len; + ssize_t len; - if ((*ppos && !write) || !*lenp) { + if (write || *ppos) { *lenp = 0; return 0; } len = svc_print_xprts(tmpbuf, sizeof(tmpbuf)); - *lenp = memory_read_from_buffer(buffer, *lenp, ppos, tmpbuf, len); + len = memory_read_from_buffer(buffer, *lenp, ppos, tmpbuf, len); - if (*lenp < 0) { + if (len < 0) { *lenp = 0; return -EINVAL; } + *lenp = len; return 0; } diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index 5f6f86051c83..13f3143609f9 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -664,12 +664,18 @@ static int tipc_topsrv_start(struct net *net) ret = tipc_topsrv_work_start(srv); if (ret < 0) - return ret; + goto err_start; ret = tipc_topsrv_create_listener(srv); if (ret < 0) - tipc_topsrv_work_stop(srv); + goto err_create; + return 0; + +err_create: + tipc_topsrv_work_stop(srv); +err_start: + kfree(srv); return ret; } diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 0bbb283f23c9..046d3fee66a9 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -825,7 +825,7 @@ static int x25_connect(struct socket *sock, struct sockaddr *uaddr, sock->state = SS_CONNECTED; rc = 0; out_put_neigh: - if (rc) { + if (rc && x25->neighbour) { read_lock_bh(&x25_list_lock); x25_neigh_put(x25->neighbour); x25->neighbour = NULL; diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index b71a32eeae65..cfbec3989a76 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -1146,7 +1146,8 @@ static void xsk_destruct(struct sock *sk) if (!sock_flag(sk, SOCK_DEAD)) return; - xp_put_pool(xs->pool); + if (!xp_put_pool(xs->pool)) + xdp_put_umem(xs->umem); sk_refcnt_debug_dec(sk); } diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index 64c9e55d4d4e..8a3bf4e1318e 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -251,15 +251,18 @@ void xp_get_pool(struct xsk_buff_pool *pool) refcount_inc(&pool->users); } -void xp_put_pool(struct xsk_buff_pool *pool) +bool xp_put_pool(struct xsk_buff_pool *pool) { if (!pool) - return; + return false; if (refcount_dec_and_test(&pool->users)) { INIT_WORK(&pool->work, xp_release_deferred); schedule_work(&pool->work); + return true; } + + return false; } static struct xsk_dma_map *xp_find_dma_map(struct xsk_buff_pool *pool) diff --git a/samples/bpf/task_fd_query_user.c b/samples/bpf/task_fd_query_user.c index 4a74531dc403..b68bd2f8fdc9 100644 --- a/samples/bpf/task_fd_query_user.c +++ b/samples/bpf/task_fd_query_user.c @@ -290,7 +290,7 @@ static int test_debug_fs_uprobe(char *binary_path, long offset, bool is_return) int main(int argc, char **argv) { - struct rlimit r = {1024*1024, RLIM_INFINITY}; + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; extern char __executable_start; char filename[256], buf[256]; __u64 uprobe_file_offset; diff --git a/samples/bpf/tracex2_user.c b/samples/bpf/tracex2_user.c index 3e36b3e4e3ef..3d6eab711d23 100644 --- a/samples/bpf/tracex2_user.c +++ b/samples/bpf/tracex2_user.c @@ -116,7 +116,7 @@ static void int_exit(int sig) int main(int ac, char **argv) { - struct rlimit r = {1024*1024, RLIM_INFINITY}; + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; long key, next_key, value; struct bpf_link *links[2]; struct bpf_program *prog; diff --git a/samples/bpf/tracex3_user.c b/samples/bpf/tracex3_user.c index 70e987775c15..83e0fecbb01a 100644 --- a/samples/bpf/tracex3_user.c +++ b/samples/bpf/tracex3_user.c @@ -107,7 +107,7 @@ static void print_hist(int fd) int main(int ac, char **argv) { - struct rlimit r = {1024*1024, RLIM_INFINITY}; + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_link *links[2]; struct bpf_program *prog; struct bpf_object *obj; diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c index 6fb8dbde62c5..f78cb18319aa 100644 --- a/samples/bpf/xdp_redirect_cpu_user.c +++ b/samples/bpf/xdp_redirect_cpu_user.c @@ -765,7 +765,7 @@ static int load_cpumap_prog(char *file_name, char *prog_name, int main(int argc, char **argv) { - struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY}; + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; char *prog_name = "xdp_cpu_map5_lb_hash_ip_pairs"; char *mprog_filename = "xdp_redirect_kern.o"; char *redir_interface = NULL, *redir_map = NULL; diff --git a/samples/bpf/xdp_rxq_info_user.c b/samples/bpf/xdp_rxq_info_user.c index caa4e7ffcfc7..93fa1bc54f13 100644 --- a/samples/bpf/xdp_rxq_info_user.c +++ b/samples/bpf/xdp_rxq_info_user.c @@ -450,7 +450,7 @@ static void stats_poll(int interval, int action, __u32 cfg_opt) int main(int argc, char **argv) { __u32 cfg_options= NO_TOUCH ; /* Default: Don't touch packet memory */ - struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY}; + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_prog_load_attr prog_load_attr = { .prog_type = BPF_PROG_TYPE_XDP, }; diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py index 6769caae142f..31484377b8b1 100755 --- a/scripts/bpf_helpers_doc.py +++ b/scripts/bpf_helpers_doc.py @@ -408,6 +408,7 @@ class PrinterHelpers(Printer): 'struct bpf_perf_event_data', 'struct bpf_perf_event_value', 'struct bpf_pidns_info', + 'struct bpf_redir_neigh', 'struct bpf_sock', 'struct bpf_sock_addr', 'struct bpf_sock_ops', diff --git a/security/selinux/ibpkey.c b/security/selinux/ibpkey.c index f68a7617cfb9..3a63a989e55e 100644 --- a/security/selinux/ibpkey.c +++ b/security/selinux/ibpkey.c @@ -151,8 +151,10 @@ static int sel_ib_pkey_sid_slow(u64 subnet_prefix, u16 pkey_num, u32 *sid) * is valid, it just won't be added to the cache. */ new = kzalloc(sizeof(*new), GFP_ATOMIC); - if (!new) + if (!new) { + ret = -ENOMEM; goto out; + } new->psec.subnet_prefix = subnet_prefix; new->psec.pkey = pkey_num; diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c index a43a6f10b564..359960a8f1de 100644 --- a/tools/bpf/bpftool/feature.c +++ b/tools/bpf/bpftool/feature.c @@ -843,9 +843,14 @@ static int handle_perms(void) else p_err("missing %s%s%s%s%s%s%s%srequired for full feature probing; run as root or use 'unprivileged'", capability_msg(bpf_caps, 0), +#ifdef CAP_BPF capability_msg(bpf_caps, 1), capability_msg(bpf_caps, 2), - capability_msg(bpf_caps, 3)); + capability_msg(bpf_caps, 3) +#else + "", "", "", "", "", "" +#endif /* CAP_BPF */ + ); goto exit_free; } diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index d942c1e3372c..acdb2c245f0a 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -940,7 +940,7 @@ static int parse_attach_detach_args(int argc, char **argv, int *progfd, } if (*attach_type == BPF_FLOW_DISSECTOR) { - *mapfd = -1; + *mapfd = 0; return 0; } diff --git a/tools/bpf/bpftool/skeleton/profiler.bpf.c b/tools/bpf/bpftool/skeleton/profiler.bpf.c index 4e3512f700c0..ce5b65e07ab1 100644 --- a/tools/bpf/bpftool/skeleton/profiler.bpf.c +++ b/tools/bpf/bpftool/skeleton/profiler.bpf.c @@ -70,7 +70,7 @@ int BPF_PROG(fentry_XXX) static inline void fexit_update_maps(u32 id, struct bpf_perf_event_value *after) { - struct bpf_perf_event_value *before, diff, *accum; + struct bpf_perf_event_value *before, diff; before = bpf_map_lookup_elem(&fentry_readings, &id); /* only account samples with a valid fentry_reading */ @@ -95,7 +95,7 @@ int BPF_PROG(fexit_XXX) { struct bpf_perf_event_value readings[MAX_NUM_MATRICS]; u32 cpu = bpf_get_smp_processor_id(); - u32 i, one = 1, zero = 0; + u32 i, zero = 0; int err; u64 *count; diff --git a/tools/lib/bpf/hashmap.h b/tools/lib/bpf/hashmap.h index d9b385fe808c..10a4c4cd13cf 100644 --- a/tools/lib/bpf/hashmap.h +++ b/tools/lib/bpf/hashmap.h @@ -15,6 +15,9 @@ static inline size_t hash_bits(size_t h, int bits) { /* shuffle bits and return requested number of upper bits */ + if (bits == 0) + return 0; + #if (__SIZEOF_SIZE_T__ == __SIZEOF_LONG_LONG__) /* LP64 case */ return (h * 11400714819323198485llu) >> (__SIZEOF_LONG_LONG__ * 8 - bits); @@ -174,17 +177,17 @@ bool hashmap__find(const struct hashmap *map, const void *key, void **value); * @key: key to iterate entries for */ #define hashmap__for_each_key_entry(map, cur, _key) \ - for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\ - map->cap_bits); \ - map->buckets ? map->buckets[bkt] : NULL; }); \ + for (cur = map->buckets \ + ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \ + : NULL; \ cur; \ cur = cur->next) \ if (map->equal_fn(cur->key, (_key), map->ctx)) #define hashmap__for_each_key_entry_safe(map, cur, tmp, _key) \ - for (cur = ({ size_t bkt = hash_bits(map->hash_fn((_key), map->ctx),\ - map->cap_bits); \ - cur = map->buckets ? map->buckets[bkt] : NULL; }); \ + for (cur = map->buckets \ + ? map->buckets[hash_bits(map->hash_fn((_key), map->ctx), map->cap_bits)] \ + : NULL; \ cur && ({ tmp = cur->next; true; }); \ cur = tmp) \ if (map->equal_fn(cur->key, (_key), map->ctx)) diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index e3c98c007825..9bc537d0b92d 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -891,13 +891,16 @@ int xsk_umem__delete(struct xsk_umem *umem) void xsk_socket__delete(struct xsk_socket *xsk) { size_t desc_sz = sizeof(struct xdp_desc); - struct xsk_ctx *ctx = xsk->ctx; struct xdp_mmap_offsets off; + struct xsk_umem *umem; + struct xsk_ctx *ctx; int err; if (!xsk) return; + ctx = xsk->ctx; + umem = ctx->umem; if (ctx->prog_fd != -1) { xsk_delete_bpf_maps(xsk); close(ctx->prog_fd); @@ -917,11 +920,11 @@ void xsk_socket__delete(struct xsk_socket *xsk) xsk_put_ctx(ctx); - ctx->umem->refcount--; + umem->refcount--; /* Do not close an fd that also has an associated umem connected * to it. */ - if (xsk->fd != ctx->umem->fd) + if (xsk->fd != umem->fd) close(xsk->fd); free(xsk); } diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile index 2b6551269e43..f3e3c94ab9bd 100644 --- a/tools/power/x86/turbostat/Makefile +++ b/tools/power/x86/turbostat/Makefile @@ -12,11 +12,12 @@ turbostat : turbostat.c override CFLAGS += -O2 -Wall -I../../../include override CFLAGS += -DMSRHEADER='"../../../../arch/x86/include/asm/msr-index.h"' override CFLAGS += -DINTEL_FAMILY_HEADER='"../../../../arch/x86/include/asm/intel-family.h"' +override CFLAGS += -D_FILE_OFFSET_BITS=64 override CFLAGS += -D_FORTIFY_SOURCE=2 %: %.c @mkdir -p $(BUILD_OUTPUT) - $(CC) $(CFLAGS) $< -o $(BUILD_OUTPUT)/$@ $(LDFLAGS) -lcap + $(CC) $(CFLAGS) $< -o $(BUILD_OUTPUT)/$@ $(LDFLAGS) -lcap -lrt .PHONY : clean clean : diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8 index a6db83a88e85..f6b7e85b121c 100644 --- a/tools/power/x86/turbostat/turbostat.8 +++ b/tools/power/x86/turbostat/turbostat.8 @@ -335,7 +335,7 @@ that they count at TSC rate, which is true on all processors tested to date. .SH REFERENCES Volume 3B: System Programming Guide" -http://www.intel.com/products/processor/manuals/ +https://www.intel.com/products/processor/manuals/ .SH FILES .ta diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 33b370865d16..f3a1746f7f45 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -79,6 +79,7 @@ unsigned long long gfx_cur_rc6_ms; unsigned long long cpuidle_cur_cpu_lpi_us; unsigned long long cpuidle_cur_sys_lpi_us; unsigned int gfx_cur_mhz; +unsigned int gfx_act_mhz; unsigned int tcc_activation_temp; unsigned int tcc_activation_temp_override; double rapl_power_units, rapl_time_units; @@ -210,13 +211,14 @@ struct pkg_data { unsigned long long pkg_both_core_gfxe_c0; long long gfx_rc6_ms; unsigned int gfx_mhz; + unsigned int gfx_act_mhz; unsigned int package_id; - unsigned int energy_pkg; /* MSR_PKG_ENERGY_STATUS */ - unsigned int energy_dram; /* MSR_DRAM_ENERGY_STATUS */ - unsigned int energy_cores; /* MSR_PP0_ENERGY_STATUS */ - unsigned int energy_gfx; /* MSR_PP1_ENERGY_STATUS */ - unsigned int rapl_pkg_perf_status; /* MSR_PKG_PERF_STATUS */ - unsigned int rapl_dram_perf_status; /* MSR_DRAM_PERF_STATUS */ + unsigned long long energy_pkg; /* MSR_PKG_ENERGY_STATUS */ + unsigned long long energy_dram; /* MSR_DRAM_ENERGY_STATUS */ + unsigned long long energy_cores; /* MSR_PP0_ENERGY_STATUS */ + unsigned long long energy_gfx; /* MSR_PP1_ENERGY_STATUS */ + unsigned long long rapl_pkg_perf_status; /* MSR_PKG_PERF_STATUS */ + unsigned long long rapl_dram_perf_status; /* MSR_DRAM_PERF_STATUS */ unsigned int pkg_temp_c; unsigned long long counter[MAX_ADDED_COUNTERS]; } *package_even, *package_odd; @@ -259,6 +261,113 @@ struct msr_counter { #define SYSFS_PERCPU (1 << 1) }; +/* + * The accumulated sum of MSR is defined as a monotonic + * increasing MSR, it will be accumulated periodically, + * despite its register's bit width. + */ +enum { + IDX_PKG_ENERGY, + IDX_DRAM_ENERGY, + IDX_PP0_ENERGY, + IDX_PP1_ENERGY, + IDX_PKG_PERF, + IDX_DRAM_PERF, + IDX_COUNT, +}; + +int get_msr_sum(int cpu, off_t offset, unsigned long long *msr); + +struct msr_sum_array { + /* get_msr_sum() = sum + (get_msr() - last) */ + struct { + /*The accumulated MSR value is updated by the timer*/ + unsigned long long sum; + /*The MSR footprint recorded in last timer*/ + unsigned long long last; + } entries[IDX_COUNT]; +}; + +/* The percpu MSR sum array.*/ +struct msr_sum_array *per_cpu_msr_sum; + +int idx_to_offset(int idx) +{ + int offset; + + switch (idx) { + case IDX_PKG_ENERGY: + offset = MSR_PKG_ENERGY_STATUS; + break; + case IDX_DRAM_ENERGY: + offset = MSR_DRAM_ENERGY_STATUS; + break; + case IDX_PP0_ENERGY: + offset = MSR_PP0_ENERGY_STATUS; + break; + case IDX_PP1_ENERGY: + offset = MSR_PP1_ENERGY_STATUS; + break; + case IDX_PKG_PERF: + offset = MSR_PKG_PERF_STATUS; + break; + case IDX_DRAM_PERF: + offset = MSR_DRAM_PERF_STATUS; + break; + default: + offset = -1; + } + return offset; +} + +int offset_to_idx(int offset) +{ + int idx; + + switch (offset) { + case MSR_PKG_ENERGY_STATUS: + idx = IDX_PKG_ENERGY; + break; + case MSR_DRAM_ENERGY_STATUS: + idx = IDX_DRAM_ENERGY; + break; + case MSR_PP0_ENERGY_STATUS: + idx = IDX_PP0_ENERGY; + break; + case MSR_PP1_ENERGY_STATUS: + idx = IDX_PP1_ENERGY; + break; + case MSR_PKG_PERF_STATUS: + idx = IDX_PKG_PERF; + break; + case MSR_DRAM_PERF_STATUS: + idx = IDX_DRAM_PERF; + break; + default: + idx = -1; + } + return idx; +} + +int idx_valid(int idx) +{ + switch (idx) { + case IDX_PKG_ENERGY: + return do_rapl & RAPL_PKG; + case IDX_DRAM_ENERGY: + return do_rapl & RAPL_DRAM; + case IDX_PP0_ENERGY: + return do_rapl & RAPL_CORES_ENERGY_STATUS; + case IDX_PP1_ENERGY: + return do_rapl & RAPL_GFX; + case IDX_PKG_PERF: + return do_rapl & RAPL_PKG_PERF_STATUS; + case IDX_DRAM_PERF: + return do_rapl & RAPL_DRAM_PERF_STATUS; + default: + return 0; + } +} struct sys_counters { unsigned int added_thread_counters; unsigned int added_core_counters; @@ -451,6 +560,7 @@ struct msr_counter bic[] = { { 0x0, "APIC" }, { 0x0, "X2APIC" }, { 0x0, "Die" }, + { 0x0, "GFXAMHz" }, }; #define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter)) @@ -505,6 +615,7 @@ struct msr_counter bic[] = { #define BIC_APIC (1ULL << 48) #define BIC_X2APIC (1ULL << 49) #define BIC_Die (1ULL << 50) +#define BIC_GFXACTMHz (1ULL << 51) #define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC) @@ -724,6 +835,9 @@ void print_header(char *delim) if (DO_BIC(BIC_GFXMHz)) outp += sprintf(outp, "%sGFXMHz", (printed++ ? delim : "")); + if (DO_BIC(BIC_GFXACTMHz)) + outp += sprintf(outp, "%sGFXAMHz", (printed++ ? delim : "")); + if (DO_BIC(BIC_Totl_c0)) outp += sprintf(outp, "%sTotl%%C0", (printed++ ? delim : "")); if (DO_BIC(BIC_Any_c0)) @@ -858,13 +972,13 @@ int dump_counters(struct thread_data *t, struct core_data *c, outp += sprintf(outp, "pc10: %016llX\n", p->pc10); outp += sprintf(outp, "cpu_lpi: %016llX\n", p->cpu_lpi); outp += sprintf(outp, "sys_lpi: %016llX\n", p->sys_lpi); - outp += sprintf(outp, "Joules PKG: %0X\n", p->energy_pkg); - outp += sprintf(outp, "Joules COR: %0X\n", p->energy_cores); - outp += sprintf(outp, "Joules GFX: %0X\n", p->energy_gfx); - outp += sprintf(outp, "Joules RAM: %0X\n", p->energy_dram); - outp += sprintf(outp, "Throttle PKG: %0X\n", + outp += sprintf(outp, "Joules PKG: %0llX\n", p->energy_pkg); + outp += sprintf(outp, "Joules COR: %0llX\n", p->energy_cores); + outp += sprintf(outp, "Joules GFX: %0llX\n", p->energy_gfx); + outp += sprintf(outp, "Joules RAM: %0llX\n", p->energy_dram); + outp += sprintf(outp, "Throttle PKG: %0llX\n", p->rapl_pkg_perf_status); - outp += sprintf(outp, "Throttle RAM: %0X\n", + outp += sprintf(outp, "Throttle RAM: %0llX\n", p->rapl_dram_perf_status); outp += sprintf(outp, "PTM: %dC\n", p->pkg_temp_c); @@ -1062,14 +1176,7 @@ int format_counters(struct thread_data *t, struct core_data *c, } } - /* - * If measurement interval exceeds minimum RAPL Joule Counter range, - * indicate that results are suspect by printing "**" in fraction place. - */ - if (interval_float < rapl_joule_counter_range) - fmt8 = "%s%.2f"; - else - fmt8 = "%6.0f**"; + fmt8 = "%s%.2f"; if (DO_BIC(BIC_CorWatt) && (do_rapl & RAPL_PER_CORE_ENERGY)) outp += sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units / interval_float); @@ -1098,6 +1205,10 @@ int format_counters(struct thread_data *t, struct core_data *c, if (DO_BIC(BIC_GFXMHz)) outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->gfx_mhz); + /* GFXACTMHz */ + if (DO_BIC(BIC_GFXACTMHz)) + outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->gfx_act_mhz); + /* Totl%C0, Any%C0 GFX%C0 CPUGFX% */ if (DO_BIC(BIC_Totl_c0)) outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pkg_wtd_core_c0/tsc); @@ -1210,11 +1321,7 @@ void format_all_counters(struct thread_data *t, struct core_data *c, struct pkg_ } #define DELTA_WRAP32(new, old) \ - if (new > old) { \ - old = new - old; \ - } else { \ - old = 0x100000000 + new - old; \ - } + old = ((((unsigned long long)new << 32) - ((unsigned long long)old << 32)) >> 32); int delta_package(struct pkg_data *new, struct pkg_data *old) @@ -1253,13 +1360,14 @@ delta_package(struct pkg_data *new, struct pkg_data *old) old->gfx_rc6_ms = new->gfx_rc6_ms - old->gfx_rc6_ms; old->gfx_mhz = new->gfx_mhz; + old->gfx_act_mhz = new->gfx_act_mhz; - DELTA_WRAP32(new->energy_pkg, old->energy_pkg); - DELTA_WRAP32(new->energy_cores, old->energy_cores); - DELTA_WRAP32(new->energy_gfx, old->energy_gfx); - DELTA_WRAP32(new->energy_dram, old->energy_dram); - DELTA_WRAP32(new->rapl_pkg_perf_status, old->rapl_pkg_perf_status); - DELTA_WRAP32(new->rapl_dram_perf_status, old->rapl_dram_perf_status); + old->energy_pkg = new->energy_pkg - old->energy_pkg; + old->energy_cores = new->energy_cores - old->energy_cores; + old->energy_gfx = new->energy_gfx - old->energy_gfx; + old->energy_dram = new->energy_dram - old->energy_dram; + old->rapl_pkg_perf_status = new->rapl_pkg_perf_status - old->rapl_pkg_perf_status; + old->rapl_dram_perf_status = new->rapl_dram_perf_status - old->rapl_dram_perf_status; for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) { if (mp->format == FORMAT_RAW) @@ -1469,6 +1577,7 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data p->gfx_rc6_ms = 0; p->gfx_mhz = 0; + p->gfx_act_mhz = 0; for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) t->counter[i] = 0; @@ -1564,6 +1673,7 @@ int sum_counters(struct thread_data *t, struct core_data *c, average.packages.gfx_rc6_ms = p->gfx_rc6_ms; average.packages.gfx_mhz = p->gfx_mhz; + average.packages.gfx_act_mhz = p->gfx_act_mhz; average.packages.pkg_temp_c = MAX(average.packages.pkg_temp_c, p->pkg_temp_c); @@ -1784,7 +1894,7 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) int i; if (cpu_migrate(cpu)) { - fprintf(outf, "Could not migrate to CPU %d\n", cpu); + fprintf(outf, "get_counters: Could not migrate to CPU %d\n", cpu); return -1; } @@ -1966,39 +2076,39 @@ retry: p->sys_lpi = cpuidle_cur_sys_lpi_us; if (do_rapl & RAPL_PKG) { - if (get_msr(cpu, MSR_PKG_ENERGY_STATUS, &msr)) + if (get_msr_sum(cpu, MSR_PKG_ENERGY_STATUS, &msr)) return -13; - p->energy_pkg = msr & 0xFFFFFFFF; + p->energy_pkg = msr; } if (do_rapl & RAPL_CORES_ENERGY_STATUS) { - if (get_msr(cpu, MSR_PP0_ENERGY_STATUS, &msr)) + if (get_msr_sum(cpu, MSR_PP0_ENERGY_STATUS, &msr)) return -14; - p->energy_cores = msr & 0xFFFFFFFF; + p->energy_cores = msr; } if (do_rapl & RAPL_DRAM) { - if (get_msr(cpu, MSR_DRAM_ENERGY_STATUS, &msr)) + if (get_msr_sum(cpu, MSR_DRAM_ENERGY_STATUS, &msr)) return -15; - p->energy_dram = msr & 0xFFFFFFFF; + p->energy_dram = msr; } if (do_rapl & RAPL_GFX) { - if (get_msr(cpu, MSR_PP1_ENERGY_STATUS, &msr)) + if (get_msr_sum(cpu, MSR_PP1_ENERGY_STATUS, &msr)) return -16; - p->energy_gfx = msr & 0xFFFFFFFF; + p->energy_gfx = msr; } if (do_rapl & RAPL_PKG_PERF_STATUS) { - if (get_msr(cpu, MSR_PKG_PERF_STATUS, &msr)) + if (get_msr_sum(cpu, MSR_PKG_PERF_STATUS, &msr)) return -16; - p->rapl_pkg_perf_status = msr & 0xFFFFFFFF; + p->rapl_pkg_perf_status = msr; } if (do_rapl & RAPL_DRAM_PERF_STATUS) { - if (get_msr(cpu, MSR_DRAM_PERF_STATUS, &msr)) + if (get_msr_sum(cpu, MSR_DRAM_PERF_STATUS, &msr)) return -16; - p->rapl_dram_perf_status = msr & 0xFFFFFFFF; + p->rapl_dram_perf_status = msr; } if (do_rapl & RAPL_AMD_F17H) { - if (get_msr(cpu, MSR_PKG_ENERGY_STAT, &msr)) + if (get_msr_sum(cpu, MSR_PKG_ENERGY_STAT, &msr)) return -13; - p->energy_pkg = msr & 0xFFFFFFFF; + p->energy_pkg = msr; } if (DO_BIC(BIC_PkgTmp)) { if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_STATUS, &msr)) @@ -2012,6 +2122,9 @@ retry: if (DO_BIC(BIC_GFXMHz)) p->gfx_mhz = gfx_cur_mhz; + if (DO_BIC(BIC_GFXACTMHz)) + p->gfx_act_mhz = gfx_act_mhz; + for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) { if (get_mp(cpu, mp, &p->counter[i])) return -10; @@ -2173,6 +2286,7 @@ int has_turbo_ratio_group_limits(int family, int model) case INTEL_FAM6_ATOM_GOLDMONT: case INTEL_FAM6_SKYLAKE_X: case INTEL_FAM6_ATOM_GOLDMONT_D: + case INTEL_FAM6_ATOM_TREMONT_D: return 1; } return 0; @@ -2650,7 +2764,12 @@ int get_thread_siblings(struct cpu_topology *thiscpu) sprintf(path, "/sys/devices/system/cpu/cpu%d/topology/thread_siblings", cpu); - filep = fopen_or_die(path, "r"); + filep = fopen(path, "r"); + + if (!filep) { + warnx("%s: open failed", path); + return -1; + } do { offset -= BITMASK_SIZE; if (fscanf(filep, "%lx%c", &map, &character) != 2) @@ -2763,18 +2882,25 @@ void re_initialize(void) { free_all_buffers(); setup_all_buffers(); - printf("turbostat: re-initialized with num_cpus %d\n", topo.num_cpus); + fprintf(outf, "turbostat: re-initialized with num_cpus %d\n", topo.num_cpus); } void set_max_cpu_num(void) { FILE *filep; + int base_cpu; unsigned long dummy; + char pathname[64]; + + base_cpu = sched_getcpu(); + if (base_cpu < 0) + err(1, "cannot find calling cpu ID"); + sprintf(pathname, + "/sys/devices/system/cpu/cpu%d/topology/thread_siblings", + base_cpu); + filep = fopen_or_die(pathname, "r"); topo.max_cpu_num = 0; - filep = fopen_or_die( - "/sys/devices/system/cpu/cpu0/topology/thread_siblings", - "r"); while (fscanf(filep, "%lx,", &dummy) == 1) topo.max_cpu_num += BITMASK_SIZE; fclose(filep); @@ -2916,6 +3042,33 @@ int snapshot_gfx_mhz(void) } /* + * snapshot_gfx_cur_mhz() + * + * record snapshot of + * /sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz + * + * return 1 if config change requires a restart, else return 0 + */ +int snapshot_gfx_act_mhz(void) +{ + static FILE *fp; + int retval; + + if (fp == NULL) + fp = fopen_or_die("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", "r"); + else { + rewind(fp); + fflush(fp); + } + + retval = fscanf(fp, "%d", &gfx_act_mhz); + if (retval != 1) + err(1, "GFX ACT MHz"); + + return 0; +} + +/* * snapshot_cpu_lpi() * * record snapshot of @@ -2980,6 +3133,9 @@ int snapshot_proc_sysfs_files(void) if (DO_BIC(BIC_GFXMHz)) snapshot_gfx_mhz(); + if (DO_BIC(BIC_GFXACTMHz)) + snapshot_gfx_act_mhz(); + if (DO_BIC(BIC_CPU_LPI)) snapshot_cpu_lpi_us(); @@ -3057,6 +3213,111 @@ void do_sleep(void) } } +int get_msr_sum(int cpu, off_t offset, unsigned long long *msr) +{ + int ret, idx; + unsigned long long msr_cur, msr_last; + + if (!per_cpu_msr_sum) + return 1; + + idx = offset_to_idx(offset); + if (idx < 0) + return idx; + /* get_msr_sum() = sum + (get_msr() - last) */ + ret = get_msr(cpu, offset, &msr_cur); + if (ret) + return ret; + msr_last = per_cpu_msr_sum[cpu].entries[idx].last; + DELTA_WRAP32(msr_cur, msr_last); + *msr = msr_last + per_cpu_msr_sum[cpu].entries[idx].sum; + + return 0; +} + +timer_t timerid; + +/* Timer callback, update the sum of MSRs periodically. */ +static int update_msr_sum(struct thread_data *t, struct core_data *c, struct pkg_data *p) +{ + int i, ret; + int cpu = t->cpu_id; + + for (i = IDX_PKG_ENERGY; i < IDX_COUNT; i++) { + unsigned long long msr_cur, msr_last; + int offset; + + if (!idx_valid(i)) + continue; + offset = idx_to_offset(i); + if (offset < 0) + continue; + ret = get_msr(cpu, offset, &msr_cur); + if (ret) { + fprintf(outf, "Can not update msr(0x%x)\n", offset); + continue; + } + + msr_last = per_cpu_msr_sum[cpu].entries[i].last; + per_cpu_msr_sum[cpu].entries[i].last = msr_cur & 0xffffffff; + + DELTA_WRAP32(msr_cur, msr_last); + per_cpu_msr_sum[cpu].entries[i].sum += msr_last; + } + return 0; +} + +static void +msr_record_handler(union sigval v) +{ + for_all_cpus(update_msr_sum, EVEN_COUNTERS); +} + +void msr_sum_record(void) +{ + struct itimerspec its; + struct sigevent sev; + + per_cpu_msr_sum = calloc(topo.max_cpu_num + 1, sizeof(struct msr_sum_array)); + if (!per_cpu_msr_sum) { + fprintf(outf, "Can not allocate memory for long time MSR.\n"); + return; + } + /* + * Signal handler might be restricted, so use thread notifier instead. + */ + memset(&sev, 0, sizeof(struct sigevent)); + sev.sigev_notify = SIGEV_THREAD; + sev.sigev_notify_function = msr_record_handler; + + sev.sigev_value.sival_ptr = &timerid; + if (timer_create(CLOCK_REALTIME, &sev, &timerid) == -1) { + fprintf(outf, "Can not create timer.\n"); + goto release_msr; + } + + its.it_value.tv_sec = 0; + its.it_value.tv_nsec = 1; + /* + * A wraparound time has been calculated early. + * Some sources state that the peak power for a + * microprocessor is usually 1.5 times the TDP rating, + * use 2 * TDP for safety. + */ + its.it_interval.tv_sec = rapl_joule_counter_range / 2; + its.it_interval.tv_nsec = 0; + + if (timer_settime(timerid, 0, &its, NULL) == -1) { + fprintf(outf, "Can not set timer.\n"); + goto release_timer; + } + return; + + release_timer: + timer_delete(timerid); + release_msr: + free(per_cpu_msr_sum); +} void turbostat_loop() { @@ -3075,7 +3336,7 @@ restart: if (retval < -1) { exit(retval); } else if (retval == -1) { - if (restarted > 1) { + if (restarted > 10) { exit(retval); } re_initialize(); @@ -3279,6 +3540,7 @@ int probe_nhm_msrs(unsigned int family, unsigned int model) case INTEL_FAM6_ATOM_GOLDMONT_PLUS: case INTEL_FAM6_ATOM_GOLDMONT_D: /* DNV */ case INTEL_FAM6_ATOM_TREMONT: /* EHL */ + case INTEL_FAM6_ATOM_TREMONT_D: /* JVL */ pkg_cstate_limits = glm_pkg_cstate_limits; break; default: @@ -3361,6 +3623,17 @@ int is_ehl(unsigned int family, unsigned int model) } return 0; } +int is_jvl(unsigned int family, unsigned int model) +{ + if (!genuine_intel) + return 0; + + switch (model) { + case INTEL_FAM6_ATOM_TREMONT_D: + return 1; + } + return 0; +} int has_turbo_ratio_limit(unsigned int family, unsigned int model) { @@ -3475,6 +3748,20 @@ int has_config_tdp(unsigned int family, unsigned int model) } static void +remove_underbar(char *s) +{ + char *to = s; + + while (*s) { + if (*s != '_') + *to++ = *s; + s++; + } + + *to = 0; +} + +static void dump_cstate_pstate_config_info(unsigned int family, unsigned int model) { if (!do_nhm_platform_info) @@ -3530,9 +3817,6 @@ dump_sysfs_cstate_config(void) int state; char *sp; - if (!DO_BIC(BIC_sysfs)) - return; - if (access("/sys/devices/system/cpu/cpuidle", R_OK)) { fprintf(outf, "cpuidle not loaded\n"); return; @@ -3559,6 +3843,8 @@ dump_sysfs_cstate_config(void) *sp = '\0'; fclose(input); + remove_underbar(name_buf); + sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/desc", base_cpu, state); input = fopen(path, "r"); @@ -3645,7 +3931,7 @@ int print_epb(struct thread_data *t, struct core_data *c, struct pkg_data *p) return 0; if (cpu_migrate(cpu)) { - fprintf(outf, "Could not migrate to CPU %d\n", cpu); + fprintf(outf, "print_epb: Could not migrate to CPU %d\n", cpu); return -1; } @@ -3689,7 +3975,7 @@ int print_hwp(struct thread_data *t, struct core_data *c, struct pkg_data *p) return 0; if (cpu_migrate(cpu)) { - fprintf(outf, "Could not migrate to CPU %d\n", cpu); + fprintf(outf, "print_hwp: Could not migrate to CPU %d\n", cpu); return -1; } @@ -3777,7 +4063,7 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data return 0; if (cpu_migrate(cpu)) { - fprintf(outf, "Could not migrate to CPU %d\n", cpu); + fprintf(outf, "print_perf_limit: Could not migrate to CPU %d\n", cpu); return -1; } @@ -3881,13 +4167,8 @@ double get_tdp_intel(unsigned int model) double get_tdp_amd(unsigned int family) { - switch (family) { - case 0x17: - case 0x18: - default: - /* This is the max stock TDP of HEDT/Server Fam17h chips */ - return 250.0; - } + /* This is the max stock TDP of HEDT/Server Fam17h+ chips */ + return 280.0; } /* @@ -3959,6 +4240,14 @@ void rapl_probe_intel(unsigned int family, unsigned int model) BIC_PRESENT(BIC_GFXWatt); } break; + case INTEL_FAM6_ATOM_TREMONT_D: /* JVL */ + do_rapl = RAPL_PKG | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO; + BIC_PRESENT(BIC_PKG__); + if (rapl_joules) + BIC_PRESENT(BIC_Pkg_J); + else + BIC_PRESENT(BIC_PkgWatt); + break; case INTEL_FAM6_SKYLAKE_L: /* SKL */ case INTEL_FAM6_CANNONLAKE_L: /* CNL */ do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_GFX | RAPL_PKG_POWER_INFO; @@ -4069,27 +4358,20 @@ void rapl_probe_amd(unsigned int family, unsigned int model) if (max_extended_level >= 0x80000007) { __cpuid(0x80000007, eax, ebx, ecx, edx); - /* RAPL (Fam 17h) */ + /* RAPL (Fam 17h+) */ has_rapl = edx & (1 << 14); } - if (!has_rapl) + if (!has_rapl || family < 0x17) return; - switch (family) { - case 0x17: /* Zen, Zen+ */ - case 0x18: /* Hygon Dhyana */ - do_rapl = RAPL_AMD_F17H | RAPL_PER_CORE_ENERGY; - if (rapl_joules) { - BIC_PRESENT(BIC_Pkg_J); - BIC_PRESENT(BIC_Cor_J); - } else { - BIC_PRESENT(BIC_PkgWatt); - BIC_PRESENT(BIC_CorWatt); - } - break; - default: - return; + do_rapl = RAPL_AMD_F17H | RAPL_PER_CORE_ENERGY; + if (rapl_joules) { + BIC_PRESENT(BIC_Pkg_J); + BIC_PRESENT(BIC_Cor_J); + } else { + BIC_PRESENT(BIC_PkgWatt); + BIC_PRESENT(BIC_CorWatt); } if (get_msr(base_cpu, MSR_RAPL_PWR_UNIT, &msr)) @@ -4162,7 +4444,7 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p return 0; if (cpu_migrate(cpu)) { - fprintf(outf, "Could not migrate to CPU %d\n", cpu); + fprintf(outf, "print_thermal: Could not migrate to CPU %d\n", cpu); return -1; } @@ -4234,7 +4516,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p) cpu = t->cpu_id; if (cpu_migrate(cpu)) { - fprintf(outf, "Could not migrate to CPU %d\n", cpu); + fprintf(outf, "print_rapl: Could not migrate to CPU %d\n", cpu); return -1; } @@ -4361,6 +4643,7 @@ int has_snb_msrs(unsigned int family, unsigned int model) case INTEL_FAM6_ATOM_GOLDMONT_PLUS: case INTEL_FAM6_ATOM_GOLDMONT_D: /* DNV */ case INTEL_FAM6_ATOM_TREMONT: /* EHL */ + case INTEL_FAM6_ATOM_TREMONT_D: /* JVL */ return 1; } return 0; @@ -4507,12 +4790,33 @@ double discover_bclk(unsigned int family, unsigned int model) * below this value, including the Digital Thermal Sensor (DTS), * Package Thermal Management Sensor (PTM), and thermal event thresholds. */ -int set_temperature_target(struct thread_data *t, struct core_data *c, struct pkg_data *p) +int read_tcc_activation_temp() { unsigned long long msr; - unsigned int target_c_local; - int cpu; + unsigned int tcc, target_c, offset_c; + /* Temperature Target MSR is Nehalem and newer only */ + if (!do_nhm_platform_info) + return 0; + + if (get_msr(base_cpu, MSR_IA32_TEMPERATURE_TARGET, &msr)) + return 0; + + target_c = (msr >> 16) & 0xFF; + + offset_c = (msr >> 24) & 0xF; + + tcc = target_c - offset_c; + + if (!quiet) + fprintf(outf, "cpu%d: MSR_IA32_TEMPERATURE_TARGET: 0x%08llx (%d C) (%d default - %d offset)\n", + base_cpu, msr, tcc, target_c, offset_c); + + return tcc; +} + +int set_temperature_target(struct thread_data *t, struct core_data *c, struct pkg_data *p) +{ /* tcc_activation_temp is used only for dts or ptm */ if (!(do_dts || do_ptm)) return 0; @@ -4521,43 +4825,18 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE) || !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE)) return 0; - cpu = t->cpu_id; - if (cpu_migrate(cpu)) { - fprintf(outf, "Could not migrate to CPU %d\n", cpu); - return -1; - } - if (tcc_activation_temp_override != 0) { tcc_activation_temp = tcc_activation_temp_override; - fprintf(outf, "cpu%d: Using cmdline TCC Target (%d C)\n", - cpu, tcc_activation_temp); + fprintf(outf, "Using cmdline TCC Target (%d C)\n", tcc_activation_temp); return 0; } - /* Temperature Target MSR is Nehalem and newer only */ - if (!do_nhm_platform_info) - goto guess; - - if (get_msr(base_cpu, MSR_IA32_TEMPERATURE_TARGET, &msr)) - goto guess; - - target_c_local = (msr >> 16) & 0xFF; - - if (!quiet) - fprintf(outf, "cpu%d: MSR_IA32_TEMPERATURE_TARGET: 0x%08llx (%d C)\n", - cpu, msr, target_c_local); - - if (!target_c_local) - goto guess; - - tcc_activation_temp = target_c_local; - - return 0; + tcc_activation_temp = read_tcc_activation_temp(); + if (tcc_activation_temp) + return 0; -guess: tcc_activation_temp = TJMAX_DEFAULT; - fprintf(outf, "cpu%d: Guessing tjMax %d C, Please use -T to specify\n", - cpu, tcc_activation_temp); + fprintf(outf, "Guessing tjMax %d C, Please use -T to specify\n", tcc_activation_temp); return 0; } @@ -4685,19 +4964,46 @@ unsigned int intel_model_duplicates(unsigned int model) case INTEL_FAM6_ICELAKE_NNPI: case INTEL_FAM6_TIGERLAKE_L: case INTEL_FAM6_TIGERLAKE: + case INTEL_FAM6_ROCKETLAKE: + case INTEL_FAM6_LAKEFIELD: + case INTEL_FAM6_ALDERLAKE: return INTEL_FAM6_CANNONLAKE_L; - case INTEL_FAM6_ATOM_TREMONT_D: - return INTEL_FAM6_ATOM_GOLDMONT_D; - case INTEL_FAM6_ATOM_TREMONT_L: return INTEL_FAM6_ATOM_TREMONT; case INTEL_FAM6_ICELAKE_X: + case INTEL_FAM6_SAPPHIRERAPIDS_X: return INTEL_FAM6_SKYLAKE_X; } return model; } + +void print_dev_latency(void) +{ + char *path = "/dev/cpu_dma_latency"; + int fd; + int value; + int retval; + + fd = open(path, O_RDONLY); + if (fd < 0) { + warn("fopen %s\n", path); + return; + } + + retval = read(fd, (void *)&value, sizeof(int)); + if (retval != sizeof(int)) { + warn("read %s\n", path); + close(fd); + return; + } + fprintf(outf, "/dev/cpu_dma_latency: %d usec (%s)\n", + value, value == 2000000000 ? "default" : "constrained"); + + close(fd); +} + void process_cpuid() { unsigned int eax, ebx, ecx, edx; @@ -4916,6 +5222,14 @@ void process_cpuid() BIC_PRESENT(BIC_Mod_c6); use_c1_residency_msr = 1; } + if (is_jvl(family, model)) { + BIC_NOT_PRESENT(BIC_CPU_c3); + BIC_NOT_PRESENT(BIC_CPU_c7); + BIC_NOT_PRESENT(BIC_Pkgpc2); + BIC_NOT_PRESENT(BIC_Pkgpc3); + BIC_NOT_PRESENT(BIC_Pkgpc6); + BIC_NOT_PRESENT(BIC_Pkgpc7); + } if (is_dnv(family, model)) { BIC_PRESENT(BIC_CPU_c1); BIC_NOT_PRESENT(BIC_CPU_c3); @@ -4935,9 +5249,12 @@ void process_cpuid() BIC_NOT_PRESENT(BIC_Pkgpc7); } if (has_c8910_msrs(family, model)) { - BIC_PRESENT(BIC_Pkgpc8); - BIC_PRESENT(BIC_Pkgpc9); - BIC_PRESENT(BIC_Pkgpc10); + if (pkg_cstate_limit >= PCL__8) + BIC_PRESENT(BIC_Pkgpc8); + if (pkg_cstate_limit >= PCL__9) + BIC_PRESENT(BIC_Pkgpc9); + if (pkg_cstate_limit >= PCL_10) + BIC_PRESENT(BIC_Pkgpc10); } do_irtl_hsw = has_c8910_msrs(family, model); if (has_skl_msrs(family, model)) { @@ -4967,6 +5284,8 @@ void process_cpuid() dump_cstate_pstate_config_info(family, model); if (!quiet) + print_dev_latency(); + if (!quiet) dump_sysfs_cstate_config(); if (!quiet) dump_sysfs_pstate_config(); @@ -4980,6 +5299,9 @@ void process_cpuid() if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK)) BIC_PRESENT(BIC_GFXMHz); + if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", R_OK)) + BIC_PRESENT(BIC_GFXACTMHz); + if (!access("/sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us", R_OK)) BIC_PRESENT(BIC_CPU_LPI); else @@ -5390,7 +5712,7 @@ int get_and_dump_counters(void) } void print_version() { - fprintf(outf, "turbostat version 20.03.20" + fprintf(outf, "turbostat version 20.09.30" " - Len Brown <lenb@kernel.org>\n"); } @@ -5597,6 +5919,8 @@ void probe_sysfs(void) *sp = '%'; *(sp + 1) = '\0'; + remove_underbar(name_buf); + fclose(input); sprintf(path, "cpuidle/state%d/time", state); @@ -5624,6 +5948,8 @@ void probe_sysfs(void) *sp = '\0'; fclose(input); + remove_underbar(name_buf); + sprintf(path, "cpuidle/state%d/usage", state); if (is_deferred_skip(name_buf)) @@ -5868,6 +6194,7 @@ int main(int argc, char **argv) return 0; } + msr_sum_record(); /* * if any params left, it must be a command to fork */ diff --git a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c index 3fe1eed900d4..ff6c6661f075 100644 --- a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c +++ b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c @@ -622,6 +622,57 @@ void cmdline(int argc, char **argv) } } +/* + * Open a file, and exit on failure + */ +FILE *fopen_or_die(const char *path, const char *mode) +{ + FILE *filep = fopen(path, "r"); + + if (!filep) + err(1, "%s: open failed", path); + return filep; +} + +void err_on_hypervisor(void) +{ + FILE *cpuinfo; + char *flags, *hypervisor; + char *buffer; + + /* On VMs /proc/cpuinfo contains a "flags" entry for hypervisor */ + cpuinfo = fopen_or_die("/proc/cpuinfo", "ro"); + + buffer = malloc(4096); + if (!buffer) { + fclose(cpuinfo); + err(-ENOMEM, "buffer malloc fail"); + } + + if (!fread(buffer, 1024, 1, cpuinfo)) { + fclose(cpuinfo); + free(buffer); + err(1, "Reading /proc/cpuinfo failed"); + } + + flags = strstr(buffer, "flags"); + rewind(cpuinfo); + fseek(cpuinfo, flags - buffer, SEEK_SET); + if (!fgets(buffer, 4096, cpuinfo)) { + fclose(cpuinfo); + free(buffer); + err(1, "Reading /proc/cpuinfo failed"); + } + fclose(cpuinfo); + + hypervisor = strstr(buffer, "hypervisor"); + + free(buffer); + + if (hypervisor) + err(-1, + "not supported on this virtual machine"); +} int get_msr(int cpu, int offset, unsigned long long *msr) { @@ -635,8 +686,10 @@ int get_msr(int cpu, int offset, unsigned long long *msr) err(-1, "%s open failed, try chown or chmod +r /dev/cpu/*/msr, or run as root", pathname); retval = pread(fd, msr, sizeof(*msr), offset); - if (retval != sizeof(*msr)) + if (retval != sizeof(*msr)) { + err_on_hypervisor(); err(-1, "%s offset 0x%llx read failed", pathname, (unsigned long long)offset); + } if (debug > 1) fprintf(stderr, "get_msr(cpu%d, 0x%X, 0x%llX)\n", cpu, offset, *msr); @@ -1086,18 +1139,6 @@ int update_cpu_msrs(int cpu) return 0; } -/* - * Open a file, and exit on failure - */ -FILE *fopen_or_die(const char *path, const char *mode) -{ - FILE *filep = fopen(path, "r"); - - if (!filep) - err(1, "%s: open failed", path); - return filep; -} - unsigned int get_pkg_num(int cpu) { FILE *fp; diff --git a/tools/testing/selftests/bpf/prog_tests/map_init.c b/tools/testing/selftests/bpf/prog_tests/map_init.c new file mode 100644 index 000000000000..14a31109dd0e --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/map_init.c @@ -0,0 +1,214 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2020 Tessares SA <http://www.tessares.net> */ + +#include <test_progs.h> +#include "test_map_init.skel.h" + +#define TEST_VALUE 0x1234 +#define FILL_VALUE 0xdeadbeef + +static int nr_cpus; +static int duration; + +typedef unsigned long long map_key_t; +typedef unsigned long long map_value_t; +typedef struct { + map_value_t v; /* padding */ +} __bpf_percpu_val_align pcpu_map_value_t; + + +static int map_populate(int map_fd, int num) +{ + pcpu_map_value_t value[nr_cpus]; + int i, err; + map_key_t key; + + for (i = 0; i < nr_cpus; i++) + bpf_percpu(value, i) = FILL_VALUE; + + for (key = 1; key <= num; key++) { + err = bpf_map_update_elem(map_fd, &key, value, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem")) + return -1; + } + + return 0; +} + +static struct test_map_init *setup(enum bpf_map_type map_type, int map_sz, + int *map_fd, int populate) +{ + struct test_map_init *skel; + int err; + + skel = test_map_init__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + return NULL; + + err = bpf_map__set_type(skel->maps.hashmap1, map_type); + if (!ASSERT_OK(err, "bpf_map__set_type")) + goto error; + + err = bpf_map__set_max_entries(skel->maps.hashmap1, map_sz); + if (!ASSERT_OK(err, "bpf_map__set_max_entries")) + goto error; + + err = test_map_init__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto error; + + *map_fd = bpf_map__fd(skel->maps.hashmap1); + if (CHECK(*map_fd < 0, "bpf_map__fd", "failed\n")) + goto error; + + err = map_populate(*map_fd, populate); + if (!ASSERT_OK(err, "map_populate")) + goto error_map; + + return skel; + +error_map: + close(*map_fd); +error: + test_map_init__destroy(skel); + return NULL; +} + +/* executes bpf program that updates map with key, value */ +static int prog_run_insert_elem(struct test_map_init *skel, map_key_t key, + map_value_t value) +{ + struct test_map_init__bss *bss; + + bss = skel->bss; + + bss->inKey = key; + bss->inValue = value; + bss->inPid = getpid(); + + if (!ASSERT_OK(test_map_init__attach(skel), "skel_attach")) + return -1; + + /* Let tracepoint trigger */ + syscall(__NR_getpgid); + + test_map_init__detach(skel); + + return 0; +} + +static int check_values_one_cpu(pcpu_map_value_t *value, map_value_t expected) +{ + int i, nzCnt = 0; + map_value_t val; + + for (i = 0; i < nr_cpus; i++) { + val = bpf_percpu(value, i); + if (val) { + if (CHECK(val != expected, "map value", + "unexpected for cpu %d: 0x%llx\n", i, val)) + return -1; + nzCnt++; + } + } + + if (CHECK(nzCnt != 1, "map value", "set for %d CPUs instead of 1!\n", + nzCnt)) + return -1; + + return 0; +} + +/* Add key=1 elem with values set for all CPUs + * Delete elem key=1 + * Run bpf prog that inserts new key=1 elem with value=0x1234 + * (bpf prog can only set value for current CPU) + * Lookup Key=1 and check value is as expected for all CPUs: + * value set by bpf prog for one CPU, 0 for all others + */ +static void test_pcpu_map_init(void) +{ + pcpu_map_value_t value[nr_cpus]; + struct test_map_init *skel; + int map_fd, err; + map_key_t key; + + /* max 1 elem in map so insertion is forced to reuse freed entry */ + skel = setup(BPF_MAP_TYPE_PERCPU_HASH, 1, &map_fd, 1); + if (!ASSERT_OK_PTR(skel, "prog_setup")) + return; + + /* delete element so the entry can be re-used*/ + key = 1; + err = bpf_map_delete_elem(map_fd, &key); + if (!ASSERT_OK(err, "bpf_map_delete_elem")) + goto cleanup; + + /* run bpf prog that inserts new elem, re-using the slot just freed */ + err = prog_run_insert_elem(skel, key, TEST_VALUE); + if (!ASSERT_OK(err, "prog_run_insert_elem")) + goto cleanup; + + /* check that key=1 was re-created by bpf prog */ + err = bpf_map_lookup_elem(map_fd, &key, value); + if (!ASSERT_OK(err, "bpf_map_lookup_elem")) + goto cleanup; + + /* and has expected values */ + check_values_one_cpu(value, TEST_VALUE); + +cleanup: + test_map_init__destroy(skel); +} + +/* Add key=1 and key=2 elems with values set for all CPUs + * Run bpf prog that inserts new key=3 elem + * (only for current cpu; other cpus should have initial value = 0) + * Lookup Key=1 and check value is as expected for all CPUs + */ +static void test_pcpu_lru_map_init(void) +{ + pcpu_map_value_t value[nr_cpus]; + struct test_map_init *skel; + int map_fd, err; + map_key_t key; + + /* Set up LRU map with 2 elements, values filled for all CPUs. + * With these 2 elements, the LRU map is full + */ + skel = setup(BPF_MAP_TYPE_LRU_PERCPU_HASH, 2, &map_fd, 2); + if (!ASSERT_OK_PTR(skel, "prog_setup")) + return; + + /* run bpf prog that inserts new key=3 element, re-using LRU slot */ + key = 3; + err = prog_run_insert_elem(skel, key, TEST_VALUE); + if (!ASSERT_OK(err, "prog_run_insert_elem")) + goto cleanup; + + /* check that key=3 replaced one of earlier elements */ + err = bpf_map_lookup_elem(map_fd, &key, value); + if (!ASSERT_OK(err, "bpf_map_lookup_elem")) + goto cleanup; + + /* and has expected values */ + check_values_one_cpu(value, TEST_VALUE); + +cleanup: + test_map_init__destroy(skel); +} + +void test_map_init(void) +{ + nr_cpus = bpf_num_possible_cpus(); + if (nr_cpus <= 1) { + printf("%s:SKIP: >1 cpu needed for this test\n", __func__); + test__skip(); + return; + } + + if (test__start_subtest("pcpu_map_init")) + test_pcpu_map_init(); + if (test__start_subtest("pcpu_lru_map_init")) + test_pcpu_lru_map_init(); +} diff --git a/tools/testing/selftests/bpf/progs/profiler.inc.h b/tools/testing/selftests/bpf/progs/profiler.inc.h index 00578311a423..30982a7e4d0f 100644 --- a/tools/testing/selftests/bpf/progs/profiler.inc.h +++ b/tools/testing/selftests/bpf/progs/profiler.inc.h @@ -243,7 +243,10 @@ static ino_t get_inode_from_kernfs(struct kernfs_node* node) } } -int pids_cgrp_id = 1; +extern bool CONFIG_CGROUP_PIDS __kconfig __weak; +enum cgroup_subsys_id___local { + pids_cgrp_id___local = 123, /* value doesn't matter */ +}; static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data, struct task_struct* task, @@ -253,7 +256,9 @@ static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data, BPF_CORE_READ(task, nsproxy, cgroup_ns, root_cset, dfl_cgrp, kn); struct kernfs_node* proc_kernfs = BPF_CORE_READ(task, cgroups, dfl_cgrp, kn); - if (ENABLE_CGROUP_V1_RESOLVER) { + if (ENABLE_CGROUP_V1_RESOLVER && CONFIG_CGROUP_PIDS) { + int cgrp_id = bpf_core_enum_value(enum cgroup_subsys_id___local, + pids_cgrp_id___local); #ifdef UNROLL #pragma unroll #endif @@ -262,7 +267,7 @@ static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data, BPF_CORE_READ(task, cgroups, subsys[i]); if (subsys != NULL) { int subsys_id = BPF_CORE_READ(subsys, ss, id); - if (subsys_id == pids_cgrp_id) { + if (subsys_id == cgrp_id) { proc_kernfs = BPF_CORE_READ(subsys, cgroup, kn); root_kernfs = BPF_CORE_READ(subsys, ss, root, kf_root, kn); break; diff --git a/tools/testing/selftests/bpf/progs/test_map_init.c b/tools/testing/selftests/bpf/progs/test_map_init.c new file mode 100644 index 000000000000..c89d28ead673 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_map_init.c @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Tessares SA <http://www.tessares.net> */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +__u64 inKey = 0; +__u64 inValue = 0; +__u32 inPid = 0; + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_HASH); + __uint(max_entries, 2); + __type(key, __u64); + __type(value, __u64); +} hashmap1 SEC(".maps"); + + +SEC("tp/syscalls/sys_enter_getpgid") +int sysenter_getpgid(const void *ctx) +{ + /* Just do it for once, when called from our own test prog. This + * ensures the map value is only updated for a single CPU. + */ + int cur_pid = bpf_get_current_pid_tgid() >> 32; + + if (cur_pid == inPid) + bpf_map_update_elem(&hashmap1, &inKey, &inValue, BPF_NOEXIST); + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index d2c2d6205008..7a2c242b7152 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -1,10 +1,13 @@ # SPDX-License-Identifier: GPL-2.0-only +/aarch64/get-reg-list +/aarch64/get-reg-list-sve /s390x/memop /s390x/resets /s390x/sync_regs_test /x86_64/cr4_cpuid_sync_test /x86_64/debug_regs /x86_64/evmcs_test +/x86_64/kvm_pv_test /x86_64/hyperv_cpuid /x86_64/mmio_warning_test /x86_64/platform_info_test @@ -24,6 +27,7 @@ /clear_dirty_log_test /demand_paging_test /dirty_log_test +/dirty_log_perf_test /kvm_create_max_vcpus /set_memory_region_test /steal_time diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 30afbad36cd5..3d14ef77755e 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -34,13 +34,14 @@ ifeq ($(ARCH),s390) endif LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c lib/test_util.c -LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c +LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c lib/x86_64/handlers.S LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c TEST_GEN_PROGS_x86_64 = x86_64/cr4_cpuid_sync_test TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid +TEST_GEN_PROGS_x86_64 += x86_64/kvm_pv_test TEST_GEN_PROGS_x86_64 += x86_64/mmio_warning_test TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test @@ -58,14 +59,15 @@ TEST_GEN_PROGS_x86_64 += x86_64/xss_msr_test TEST_GEN_PROGS_x86_64 += x86_64/debug_regs TEST_GEN_PROGS_x86_64 += x86_64/tsc_msrs_test TEST_GEN_PROGS_x86_64 += x86_64/user_msr_test -TEST_GEN_PROGS_x86_64 += clear_dirty_log_test TEST_GEN_PROGS_x86_64 += demand_paging_test TEST_GEN_PROGS_x86_64 += dirty_log_test +TEST_GEN_PROGS_x86_64 += dirty_log_perf_test TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus TEST_GEN_PROGS_x86_64 += set_memory_region_test TEST_GEN_PROGS_x86_64 += steal_time -TEST_GEN_PROGS_aarch64 += clear_dirty_log_test +TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list +TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list-sve TEST_GEN_PROGS_aarch64 += demand_paging_test TEST_GEN_PROGS_aarch64 += dirty_log_test TEST_GEN_PROGS_aarch64 += kvm_create_max_vcpus @@ -111,14 +113,21 @@ LDFLAGS += -pthread $(no-pie-option) $(pgste-option) include ../lib.mk STATIC_LIBS := $(OUTPUT)/libkvm.a -LIBKVM_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM)) -EXTRA_CLEAN += $(LIBKVM_OBJ) $(STATIC_LIBS) cscope.* +LIBKVM_C := $(filter %.c,$(LIBKVM)) +LIBKVM_S := $(filter %.S,$(LIBKVM)) +LIBKVM_C_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_C)) +LIBKVM_S_OBJ := $(patsubst %.S, $(OUTPUT)/%.o, $(LIBKVM_S)) +EXTRA_CLEAN += $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ) $(STATIC_LIBS) cscope.* + +x := $(shell mkdir -p $(sort $(dir $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ)))) +$(LIBKVM_C_OBJ): $(OUTPUT)/%.o: %.c + $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@ -x := $(shell mkdir -p $(sort $(dir $(LIBKVM_OBJ)))) -$(LIBKVM_OBJ): $(OUTPUT)/%.o: %.c +$(LIBKVM_S_OBJ): $(OUTPUT)/%.o: %.S $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@ -$(OUTPUT)/libkvm.a: $(LIBKVM_OBJ) +LIBKVM_OBJS = $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ) +$(OUTPUT)/libkvm.a: $(LIBKVM_OBJS) $(AR) crs $@ $^ x := $(shell mkdir -p $(sort $(dir $(TEST_GEN_PROGS)))) diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list-sve.c b/tools/testing/selftests/kvm/aarch64/get-reg-list-sve.c new file mode 100644 index 000000000000..efba76682b4b --- /dev/null +++ b/tools/testing/selftests/kvm/aarch64/get-reg-list-sve.c @@ -0,0 +1,3 @@ +// SPDX-License-Identifier: GPL-2.0 +#define REG_LIST_SVE +#include "get-reg-list.c" diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c new file mode 100644 index 000000000000..33218a395d9f --- /dev/null +++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c @@ -0,0 +1,841 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Check for KVM_GET_REG_LIST regressions. + * + * Copyright (C) 2020, Red Hat, Inc. + * + * When attempting to migrate from a host with an older kernel to a host + * with a newer kernel we allow the newer kernel on the destination to + * list new registers with get-reg-list. We assume they'll be unused, at + * least until the guest reboots, and so they're relatively harmless. + * However, if the destination host with the newer kernel is missing + * registers which the source host with the older kernel has, then that's + * a regression in get-reg-list. This test checks for that regression by + * checking the current list against a blessed list. We should never have + * missing registers, but if new ones appear then they can probably be + * added to the blessed list. A completely new blessed list can be created + * by running the test with the --list command line argument. + * + * Note, the blessed list should be created from the oldest possible + * kernel. We can't go older than v4.15, though, because that's the first + * release to expose the ID system registers in KVM_GET_REG_LIST, see + * commit 93390c0a1b20 ("arm64: KVM: Hide unsupported AArch64 CPU features + * from guests"). Also, one must use the --core-reg-fixup command line + * option when running on an older kernel that doesn't include df205b5c6328 + * ("KVM: arm64: Filter out invalid core register IDs in KVM_GET_REG_LIST") + */ +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include "kvm_util.h" +#include "test_util.h" +#include "processor.h" + +#ifdef REG_LIST_SVE +#define reg_list_sve() (true) +#else +#define reg_list_sve() (false) +#endif + +#define REG_MASK (KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_COPROC_MASK) + +#define for_each_reg(i) \ + for ((i) = 0; (i) < reg_list->n; ++(i)) + +#define for_each_missing_reg(i) \ + for ((i) = 0; (i) < blessed_n; ++(i)) \ + if (!find_reg(reg_list->reg, reg_list->n, blessed_reg[i])) + +#define for_each_new_reg(i) \ + for ((i) = 0; (i) < reg_list->n; ++(i)) \ + if (!find_reg(blessed_reg, blessed_n, reg_list->reg[i])) + + +static struct kvm_reg_list *reg_list; + +static __u64 base_regs[], vregs[], sve_regs[], rejects_set[]; +static __u64 base_regs_n, vregs_n, sve_regs_n, rejects_set_n; +static __u64 *blessed_reg, blessed_n; + +static bool find_reg(__u64 regs[], __u64 nr_regs, __u64 reg) +{ + int i; + + for (i = 0; i < nr_regs; ++i) + if (reg == regs[i]) + return true; + return false; +} + +static const char *str_with_index(const char *template, __u64 index) +{ + char *str, *p; + int n; + + str = strdup(template); + p = strstr(str, "##"); + n = sprintf(p, "%lld", index); + strcat(p + n, strstr(template, "##") + 2); + + return (const char *)str; +} + +#define CORE_REGS_XX_NR_WORDS 2 +#define CORE_SPSR_XX_NR_WORDS 2 +#define CORE_FPREGS_XX_NR_WORDS 4 + +static const char *core_id_to_str(__u64 id) +{ + __u64 core_off = id & ~REG_MASK, idx; + + /* + * core_off is the offset into struct kvm_regs + */ + switch (core_off) { + case KVM_REG_ARM_CORE_REG(regs.regs[0]) ... + KVM_REG_ARM_CORE_REG(regs.regs[30]): + idx = (core_off - KVM_REG_ARM_CORE_REG(regs.regs[0])) / CORE_REGS_XX_NR_WORDS; + TEST_ASSERT(idx < 31, "Unexpected regs.regs index: %lld", idx); + return str_with_index("KVM_REG_ARM_CORE_REG(regs.regs[##])", idx); + case KVM_REG_ARM_CORE_REG(regs.sp): + return "KVM_REG_ARM_CORE_REG(regs.sp)"; + case KVM_REG_ARM_CORE_REG(regs.pc): + return "KVM_REG_ARM_CORE_REG(regs.pc)"; + case KVM_REG_ARM_CORE_REG(regs.pstate): + return "KVM_REG_ARM_CORE_REG(regs.pstate)"; + case KVM_REG_ARM_CORE_REG(sp_el1): + return "KVM_REG_ARM_CORE_REG(sp_el1)"; + case KVM_REG_ARM_CORE_REG(elr_el1): + return "KVM_REG_ARM_CORE_REG(elr_el1)"; + case KVM_REG_ARM_CORE_REG(spsr[0]) ... + KVM_REG_ARM_CORE_REG(spsr[KVM_NR_SPSR - 1]): + idx = (core_off - KVM_REG_ARM_CORE_REG(spsr[0])) / CORE_SPSR_XX_NR_WORDS; + TEST_ASSERT(idx < KVM_NR_SPSR, "Unexpected spsr index: %lld", idx); + return str_with_index("KVM_REG_ARM_CORE_REG(spsr[##])", idx); + case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ... + KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]): + idx = (core_off - KVM_REG_ARM_CORE_REG(fp_regs.vregs[0])) / CORE_FPREGS_XX_NR_WORDS; + TEST_ASSERT(idx < 32, "Unexpected fp_regs.vregs index: %lld", idx); + return str_with_index("KVM_REG_ARM_CORE_REG(fp_regs.vregs[##])", idx); + case KVM_REG_ARM_CORE_REG(fp_regs.fpsr): + return "KVM_REG_ARM_CORE_REG(fp_regs.fpsr)"; + case KVM_REG_ARM_CORE_REG(fp_regs.fpcr): + return "KVM_REG_ARM_CORE_REG(fp_regs.fpcr)"; + } + + TEST_FAIL("Unknown core reg id: 0x%llx", id); + return NULL; +} + +static const char *sve_id_to_str(__u64 id) +{ + __u64 sve_off, n, i; + + if (id == KVM_REG_ARM64_SVE_VLS) + return "KVM_REG_ARM64_SVE_VLS"; + + sve_off = id & ~(REG_MASK | ((1ULL << 5) - 1)); + i = id & (KVM_ARM64_SVE_MAX_SLICES - 1); + + TEST_ASSERT(i == 0, "Currently we don't expect slice > 0, reg id 0x%llx", id); + + switch (sve_off) { + case KVM_REG_ARM64_SVE_ZREG_BASE ... + KVM_REG_ARM64_SVE_ZREG_BASE + (1ULL << 5) * KVM_ARM64_SVE_NUM_ZREGS - 1: + n = (id >> 5) & (KVM_ARM64_SVE_NUM_ZREGS - 1); + TEST_ASSERT(id == KVM_REG_ARM64_SVE_ZREG(n, 0), + "Unexpected bits set in SVE ZREG id: 0x%llx", id); + return str_with_index("KVM_REG_ARM64_SVE_ZREG(##, 0)", n); + case KVM_REG_ARM64_SVE_PREG_BASE ... + KVM_REG_ARM64_SVE_PREG_BASE + (1ULL << 5) * KVM_ARM64_SVE_NUM_PREGS - 1: + n = (id >> 5) & (KVM_ARM64_SVE_NUM_PREGS - 1); + TEST_ASSERT(id == KVM_REG_ARM64_SVE_PREG(n, 0), + "Unexpected bits set in SVE PREG id: 0x%llx", id); + return str_with_index("KVM_REG_ARM64_SVE_PREG(##, 0)", n); + case KVM_REG_ARM64_SVE_FFR_BASE: + TEST_ASSERT(id == KVM_REG_ARM64_SVE_FFR(0), + "Unexpected bits set in SVE FFR id: 0x%llx", id); + return "KVM_REG_ARM64_SVE_FFR(0)"; + } + + return NULL; +} + +static void print_reg(__u64 id) +{ + unsigned op0, op1, crn, crm, op2; + const char *reg_size = NULL; + + TEST_ASSERT((id & KVM_REG_ARCH_MASK) == KVM_REG_ARM64, + "KVM_REG_ARM64 missing in reg id: 0x%llx", id); + + switch (id & KVM_REG_SIZE_MASK) { + case KVM_REG_SIZE_U8: + reg_size = "KVM_REG_SIZE_U8"; + break; + case KVM_REG_SIZE_U16: + reg_size = "KVM_REG_SIZE_U16"; + break; + case KVM_REG_SIZE_U32: + reg_size = "KVM_REG_SIZE_U32"; + break; + case KVM_REG_SIZE_U64: + reg_size = "KVM_REG_SIZE_U64"; + break; + case KVM_REG_SIZE_U128: + reg_size = "KVM_REG_SIZE_U128"; + break; + case KVM_REG_SIZE_U256: + reg_size = "KVM_REG_SIZE_U256"; + break; + case KVM_REG_SIZE_U512: + reg_size = "KVM_REG_SIZE_U512"; + break; + case KVM_REG_SIZE_U1024: + reg_size = "KVM_REG_SIZE_U1024"; + break; + case KVM_REG_SIZE_U2048: + reg_size = "KVM_REG_SIZE_U2048"; + break; + default: + TEST_FAIL("Unexpected reg size: 0x%llx in reg id: 0x%llx", + (id & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT, id); + } + + switch (id & KVM_REG_ARM_COPROC_MASK) { + case KVM_REG_ARM_CORE: + printf("\tKVM_REG_ARM64 | %s | KVM_REG_ARM_CORE | %s,\n", reg_size, core_id_to_str(id)); + break; + case KVM_REG_ARM_DEMUX: + TEST_ASSERT(!(id & ~(REG_MASK | KVM_REG_ARM_DEMUX_ID_MASK | KVM_REG_ARM_DEMUX_VAL_MASK)), + "Unexpected bits set in DEMUX reg id: 0x%llx", id); + printf("\tKVM_REG_ARM64 | %s | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | %lld,\n", + reg_size, id & KVM_REG_ARM_DEMUX_VAL_MASK); + break; + case KVM_REG_ARM64_SYSREG: + op0 = (id & KVM_REG_ARM64_SYSREG_OP0_MASK) >> KVM_REG_ARM64_SYSREG_OP0_SHIFT; + op1 = (id & KVM_REG_ARM64_SYSREG_OP1_MASK) >> KVM_REG_ARM64_SYSREG_OP1_SHIFT; + crn = (id & KVM_REG_ARM64_SYSREG_CRN_MASK) >> KVM_REG_ARM64_SYSREG_CRN_SHIFT; + crm = (id & KVM_REG_ARM64_SYSREG_CRM_MASK) >> KVM_REG_ARM64_SYSREG_CRM_SHIFT; + op2 = (id & KVM_REG_ARM64_SYSREG_OP2_MASK) >> KVM_REG_ARM64_SYSREG_OP2_SHIFT; + TEST_ASSERT(id == ARM64_SYS_REG(op0, op1, crn, crm, op2), + "Unexpected bits set in SYSREG reg id: 0x%llx", id); + printf("\tARM64_SYS_REG(%d, %d, %d, %d, %d),\n", op0, op1, crn, crm, op2); + break; + case KVM_REG_ARM_FW: + TEST_ASSERT(id == KVM_REG_ARM_FW_REG(id & 0xffff), + "Unexpected bits set in FW reg id: 0x%llx", id); + printf("\tKVM_REG_ARM_FW_REG(%lld),\n", id & 0xffff); + break; + case KVM_REG_ARM64_SVE: + if (reg_list_sve()) + printf("\t%s,\n", sve_id_to_str(id)); + else + TEST_FAIL("KVM_REG_ARM64_SVE is an unexpected coproc type in reg id: 0x%llx", id); + break; + default: + TEST_FAIL("Unexpected coproc type: 0x%llx in reg id: 0x%llx", + (id & KVM_REG_ARM_COPROC_MASK) >> KVM_REG_ARM_COPROC_SHIFT, id); + } +} + +/* + * Older kernels listed each 32-bit word of CORE registers separately. + * For 64 and 128-bit registers we need to ignore the extra words. We + * also need to fixup the sizes, because the older kernels stated all + * registers were 64-bit, even when they weren't. + */ +static void core_reg_fixup(void) +{ + struct kvm_reg_list *tmp; + __u64 id, core_off; + int i; + + tmp = calloc(1, sizeof(*tmp) + reg_list->n * sizeof(__u64)); + + for (i = 0; i < reg_list->n; ++i) { + id = reg_list->reg[i]; + + if ((id & KVM_REG_ARM_COPROC_MASK) != KVM_REG_ARM_CORE) { + tmp->reg[tmp->n++] = id; + continue; + } + + core_off = id & ~REG_MASK; + + switch (core_off) { + case 0x52: case 0xd2: case 0xd6: + /* + * These offsets are pointing at padding. + * We need to ignore them too. + */ + continue; + case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ... + KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]): + if (core_off & 3) + continue; + id &= ~KVM_REG_SIZE_MASK; + id |= KVM_REG_SIZE_U128; + tmp->reg[tmp->n++] = id; + continue; + case KVM_REG_ARM_CORE_REG(fp_regs.fpsr): + case KVM_REG_ARM_CORE_REG(fp_regs.fpcr): + id &= ~KVM_REG_SIZE_MASK; + id |= KVM_REG_SIZE_U32; + tmp->reg[tmp->n++] = id; + continue; + default: + if (core_off & 1) + continue; + tmp->reg[tmp->n++] = id; + break; + } + } + + free(reg_list); + reg_list = tmp; +} + +static void prepare_vcpu_init(struct kvm_vcpu_init *init) +{ + if (reg_list_sve()) + init->features[0] |= 1 << KVM_ARM_VCPU_SVE; +} + +static void finalize_vcpu(struct kvm_vm *vm, uint32_t vcpuid) +{ + int feature; + + if (reg_list_sve()) { + feature = KVM_ARM_VCPU_SVE; + vcpu_ioctl(vm, vcpuid, KVM_ARM_VCPU_FINALIZE, &feature); + } +} + +static void check_supported(void) +{ + if (reg_list_sve() && !kvm_check_cap(KVM_CAP_ARM_SVE)) { + fprintf(stderr, "SVE not available, skipping tests\n"); + exit(KSFT_SKIP); + } +} + +int main(int ac, char **av) +{ + struct kvm_vcpu_init init = { .target = -1, }; + int new_regs = 0, missing_regs = 0, i; + int failed_get = 0, failed_set = 0, failed_reject = 0; + bool print_list = false, fixup_core_regs = false; + struct kvm_vm *vm; + __u64 *vec_regs; + + check_supported(); + + for (i = 1; i < ac; ++i) { + if (strcmp(av[i], "--core-reg-fixup") == 0) + fixup_core_regs = true; + else if (strcmp(av[i], "--list") == 0) + print_list = true; + else + fprintf(stderr, "Ignoring unknown option: %s\n", av[i]); + } + + vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR); + prepare_vcpu_init(&init); + aarch64_vcpu_add_default(vm, 0, &init, NULL); + finalize_vcpu(vm, 0); + + reg_list = vcpu_get_reg_list(vm, 0); + + if (fixup_core_regs) + core_reg_fixup(); + + if (print_list) { + putchar('\n'); + for_each_reg(i) + print_reg(reg_list->reg[i]); + putchar('\n'); + return 0; + } + + /* + * We only test that we can get the register and then write back the + * same value. Some registers may allow other values to be written + * back, but others only allow some bits to be changed, and at least + * for ID registers set will fail if the value does not exactly match + * what was returned by get. If registers that allow other values to + * be written need to have the other values tested, then we should + * create a new set of tests for those in a new independent test + * executable. + */ + for_each_reg(i) { + uint8_t addr[2048 / 8]; + struct kvm_one_reg reg = { + .id = reg_list->reg[i], + .addr = (__u64)&addr, + }; + int ret; + + ret = _vcpu_ioctl(vm, 0, KVM_GET_ONE_REG, ®); + if (ret) { + puts("Failed to get "); + print_reg(reg.id); + putchar('\n'); + ++failed_get; + } + + /* rejects_set registers are rejected after KVM_ARM_VCPU_FINALIZE */ + if (find_reg(rejects_set, rejects_set_n, reg.id)) { + ret = _vcpu_ioctl(vm, 0, KVM_SET_ONE_REG, ®); + if (ret != -1 || errno != EPERM) { + printf("Failed to reject (ret=%d, errno=%d) ", ret, errno); + print_reg(reg.id); + putchar('\n'); + ++failed_reject; + } + continue; + } + + ret = _vcpu_ioctl(vm, 0, KVM_SET_ONE_REG, ®); + if (ret) { + puts("Failed to set "); + print_reg(reg.id); + putchar('\n'); + ++failed_set; + } + } + + if (reg_list_sve()) { + blessed_n = base_regs_n + sve_regs_n; + vec_regs = sve_regs; + } else { + blessed_n = base_regs_n + vregs_n; + vec_regs = vregs; + } + + blessed_reg = calloc(blessed_n, sizeof(__u64)); + for (i = 0; i < base_regs_n; ++i) + blessed_reg[i] = base_regs[i]; + for (i = 0; i < blessed_n - base_regs_n; ++i) + blessed_reg[base_regs_n + i] = vec_regs[i]; + + for_each_new_reg(i) + ++new_regs; + + for_each_missing_reg(i) + ++missing_regs; + + if (new_regs || missing_regs) { + printf("Number blessed registers: %5lld\n", blessed_n); + printf("Number registers: %5lld\n", reg_list->n); + } + + if (new_regs) { + printf("\nThere are %d new registers.\n" + "Consider adding them to the blessed reg " + "list with the following lines:\n\n", new_regs); + for_each_new_reg(i) + print_reg(reg_list->reg[i]); + putchar('\n'); + } + + if (missing_regs) { + printf("\nThere are %d missing registers.\n" + "The following lines are missing registers:\n\n", missing_regs); + for_each_missing_reg(i) + print_reg(blessed_reg[i]); + putchar('\n'); + } + + TEST_ASSERT(!missing_regs && !failed_get && !failed_set && !failed_reject, + "There are %d missing registers; " + "%d registers failed get; %d registers failed set; %d registers failed reject", + missing_regs, failed_get, failed_set, failed_reject); + + return 0; +} + +/* + * The current blessed list was primed with the output of kernel version + * v4.15 with --core-reg-fixup and then later updated with new registers. + */ +static __u64 base_regs[] = { + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[0]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[1]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[2]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[3]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[4]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[5]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[6]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[7]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[8]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[9]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[10]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[11]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[12]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[13]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[14]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[15]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[16]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[17]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[18]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[19]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[20]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[21]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[22]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[23]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[24]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[25]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[26]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[27]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[28]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[29]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.regs[30]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.sp), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.pc), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(regs.pstate), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(sp_el1), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(elr_el1), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[0]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[1]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[2]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[3]), + KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[4]), + KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.fpsr), + KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.fpcr), + KVM_REG_ARM_FW_REG(0), + KVM_REG_ARM_FW_REG(1), + KVM_REG_ARM_FW_REG(2), + ARM64_SYS_REG(3, 3, 14, 3, 1), /* CNTV_CTL_EL0 */ + ARM64_SYS_REG(3, 3, 14, 3, 2), /* CNTV_CVAL_EL0 */ + ARM64_SYS_REG(3, 3, 14, 0, 2), + ARM64_SYS_REG(3, 0, 0, 0, 0), /* MIDR_EL1 */ + ARM64_SYS_REG(3, 0, 0, 0, 6), /* REVIDR_EL1 */ + ARM64_SYS_REG(3, 1, 0, 0, 1), /* CLIDR_EL1 */ + ARM64_SYS_REG(3, 1, 0, 0, 7), /* AIDR_EL1 */ + ARM64_SYS_REG(3, 3, 0, 0, 1), /* CTR_EL0 */ + ARM64_SYS_REG(2, 0, 0, 0, 4), + ARM64_SYS_REG(2, 0, 0, 0, 5), + ARM64_SYS_REG(2, 0, 0, 0, 6), + ARM64_SYS_REG(2, 0, 0, 0, 7), + ARM64_SYS_REG(2, 0, 0, 1, 4), + ARM64_SYS_REG(2, 0, 0, 1, 5), + ARM64_SYS_REG(2, 0, 0, 1, 6), + ARM64_SYS_REG(2, 0, 0, 1, 7), + ARM64_SYS_REG(2, 0, 0, 2, 0), /* MDCCINT_EL1 */ + ARM64_SYS_REG(2, 0, 0, 2, 2), /* MDSCR_EL1 */ + ARM64_SYS_REG(2, 0, 0, 2, 4), + ARM64_SYS_REG(2, 0, 0, 2, 5), + ARM64_SYS_REG(2, 0, 0, 2, 6), + ARM64_SYS_REG(2, 0, 0, 2, 7), + ARM64_SYS_REG(2, 0, 0, 3, 4), + ARM64_SYS_REG(2, 0, 0, 3, 5), + ARM64_SYS_REG(2, 0, 0, 3, 6), + ARM64_SYS_REG(2, 0, 0, 3, 7), + ARM64_SYS_REG(2, 0, 0, 4, 4), + ARM64_SYS_REG(2, 0, 0, 4, 5), + ARM64_SYS_REG(2, 0, 0, 4, 6), + ARM64_SYS_REG(2, 0, 0, 4, 7), + ARM64_SYS_REG(2, 0, 0, 5, 4), + ARM64_SYS_REG(2, 0, 0, 5, 5), + ARM64_SYS_REG(2, 0, 0, 5, 6), + ARM64_SYS_REG(2, 0, 0, 5, 7), + ARM64_SYS_REG(2, 0, 0, 6, 4), + ARM64_SYS_REG(2, 0, 0, 6, 5), + ARM64_SYS_REG(2, 0, 0, 6, 6), + ARM64_SYS_REG(2, 0, 0, 6, 7), + ARM64_SYS_REG(2, 0, 0, 7, 4), + ARM64_SYS_REG(2, 0, 0, 7, 5), + ARM64_SYS_REG(2, 0, 0, 7, 6), + ARM64_SYS_REG(2, 0, 0, 7, 7), + ARM64_SYS_REG(2, 0, 0, 8, 4), + ARM64_SYS_REG(2, 0, 0, 8, 5), + ARM64_SYS_REG(2, 0, 0, 8, 6), + ARM64_SYS_REG(2, 0, 0, 8, 7), + ARM64_SYS_REG(2, 0, 0, 9, 4), + ARM64_SYS_REG(2, 0, 0, 9, 5), + ARM64_SYS_REG(2, 0, 0, 9, 6), + ARM64_SYS_REG(2, 0, 0, 9, 7), + ARM64_SYS_REG(2, 0, 0, 10, 4), + ARM64_SYS_REG(2, 0, 0, 10, 5), + ARM64_SYS_REG(2, 0, 0, 10, 6), + ARM64_SYS_REG(2, 0, 0, 10, 7), + ARM64_SYS_REG(2, 0, 0, 11, 4), + ARM64_SYS_REG(2, 0, 0, 11, 5), + ARM64_SYS_REG(2, 0, 0, 11, 6), + ARM64_SYS_REG(2, 0, 0, 11, 7), + ARM64_SYS_REG(2, 0, 0, 12, 4), + ARM64_SYS_REG(2, 0, 0, 12, 5), + ARM64_SYS_REG(2, 0, 0, 12, 6), + ARM64_SYS_REG(2, 0, 0, 12, 7), + ARM64_SYS_REG(2, 0, 0, 13, 4), + ARM64_SYS_REG(2, 0, 0, 13, 5), + ARM64_SYS_REG(2, 0, 0, 13, 6), + ARM64_SYS_REG(2, 0, 0, 13, 7), + ARM64_SYS_REG(2, 0, 0, 14, 4), + ARM64_SYS_REG(2, 0, 0, 14, 5), + ARM64_SYS_REG(2, 0, 0, 14, 6), + ARM64_SYS_REG(2, 0, 0, 14, 7), + ARM64_SYS_REG(2, 0, 0, 15, 4), + ARM64_SYS_REG(2, 0, 0, 15, 5), + ARM64_SYS_REG(2, 0, 0, 15, 6), + ARM64_SYS_REG(2, 0, 0, 15, 7), + ARM64_SYS_REG(2, 4, 0, 7, 0), /* DBGVCR32_EL2 */ + ARM64_SYS_REG(3, 0, 0, 0, 5), /* MPIDR_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 0), /* ID_PFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 1), /* ID_PFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 2), /* ID_DFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 3), /* ID_AFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 4), /* ID_MMFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 5), /* ID_MMFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 6), /* ID_MMFR2_EL1 */ + ARM64_SYS_REG(3, 0, 0, 1, 7), /* ID_MMFR3_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 0), /* ID_ISAR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 1), /* ID_ISAR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 2), /* ID_ISAR2_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 3), /* ID_ISAR3_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 4), /* ID_ISAR4_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 5), /* ID_ISAR5_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 6), /* ID_MMFR4_EL1 */ + ARM64_SYS_REG(3, 0, 0, 2, 7), /* ID_ISAR6_EL1 */ + ARM64_SYS_REG(3, 0, 0, 3, 0), /* MVFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 3, 1), /* MVFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 3, 2), /* MVFR2_EL1 */ + ARM64_SYS_REG(3, 0, 0, 3, 3), + ARM64_SYS_REG(3, 0, 0, 3, 4), /* ID_PFR2_EL1 */ + ARM64_SYS_REG(3, 0, 0, 3, 5), /* ID_DFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 3, 6), /* ID_MMFR5_EL1 */ + ARM64_SYS_REG(3, 0, 0, 3, 7), + ARM64_SYS_REG(3, 0, 0, 4, 0), /* ID_AA64PFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 4, 1), /* ID_AA64PFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 4, 2), + ARM64_SYS_REG(3, 0, 0, 4, 3), + ARM64_SYS_REG(3, 0, 0, 4, 4), /* ID_AA64ZFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 4, 5), + ARM64_SYS_REG(3, 0, 0, 4, 6), + ARM64_SYS_REG(3, 0, 0, 4, 7), + ARM64_SYS_REG(3, 0, 0, 5, 0), /* ID_AA64DFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 5, 1), /* ID_AA64DFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 5, 2), + ARM64_SYS_REG(3, 0, 0, 5, 3), + ARM64_SYS_REG(3, 0, 0, 5, 4), /* ID_AA64AFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 5, 5), /* ID_AA64AFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 5, 6), + ARM64_SYS_REG(3, 0, 0, 5, 7), + ARM64_SYS_REG(3, 0, 0, 6, 0), /* ID_AA64ISAR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 6, 1), /* ID_AA64ISAR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 6, 2), + ARM64_SYS_REG(3, 0, 0, 6, 3), + ARM64_SYS_REG(3, 0, 0, 6, 4), + ARM64_SYS_REG(3, 0, 0, 6, 5), + ARM64_SYS_REG(3, 0, 0, 6, 6), + ARM64_SYS_REG(3, 0, 0, 6, 7), + ARM64_SYS_REG(3, 0, 0, 7, 0), /* ID_AA64MMFR0_EL1 */ + ARM64_SYS_REG(3, 0, 0, 7, 1), /* ID_AA64MMFR1_EL1 */ + ARM64_SYS_REG(3, 0, 0, 7, 2), /* ID_AA64MMFR2_EL1 */ + ARM64_SYS_REG(3, 0, 0, 7, 3), + ARM64_SYS_REG(3, 0, 0, 7, 4), + ARM64_SYS_REG(3, 0, 0, 7, 5), + ARM64_SYS_REG(3, 0, 0, 7, 6), + ARM64_SYS_REG(3, 0, 0, 7, 7), + ARM64_SYS_REG(3, 0, 1, 0, 0), /* SCTLR_EL1 */ + ARM64_SYS_REG(3, 0, 1, 0, 1), /* ACTLR_EL1 */ + ARM64_SYS_REG(3, 0, 1, 0, 2), /* CPACR_EL1 */ + ARM64_SYS_REG(3, 0, 2, 0, 0), /* TTBR0_EL1 */ + ARM64_SYS_REG(3, 0, 2, 0, 1), /* TTBR1_EL1 */ + ARM64_SYS_REG(3, 0, 2, 0, 2), /* TCR_EL1 */ + ARM64_SYS_REG(3, 0, 5, 1, 0), /* AFSR0_EL1 */ + ARM64_SYS_REG(3, 0, 5, 1, 1), /* AFSR1_EL1 */ + ARM64_SYS_REG(3, 0, 5, 2, 0), /* ESR_EL1 */ + ARM64_SYS_REG(3, 0, 6, 0, 0), /* FAR_EL1 */ + ARM64_SYS_REG(3, 0, 7, 4, 0), /* PAR_EL1 */ + ARM64_SYS_REG(3, 0, 9, 14, 1), /* PMINTENSET_EL1 */ + ARM64_SYS_REG(3, 0, 9, 14, 2), /* PMINTENCLR_EL1 */ + ARM64_SYS_REG(3, 0, 10, 2, 0), /* MAIR_EL1 */ + ARM64_SYS_REG(3, 0, 10, 3, 0), /* AMAIR_EL1 */ + ARM64_SYS_REG(3, 0, 12, 0, 0), /* VBAR_EL1 */ + ARM64_SYS_REG(3, 0, 12, 1, 1), /* DISR_EL1 */ + ARM64_SYS_REG(3, 0, 13, 0, 1), /* CONTEXTIDR_EL1 */ + ARM64_SYS_REG(3, 0, 13, 0, 4), /* TPIDR_EL1 */ + ARM64_SYS_REG(3, 0, 14, 1, 0), /* CNTKCTL_EL1 */ + ARM64_SYS_REG(3, 2, 0, 0, 0), /* CSSELR_EL1 */ + ARM64_SYS_REG(3, 3, 9, 12, 0), /* PMCR_EL0 */ + ARM64_SYS_REG(3, 3, 9, 12, 1), /* PMCNTENSET_EL0 */ + ARM64_SYS_REG(3, 3, 9, 12, 2), /* PMCNTENCLR_EL0 */ + ARM64_SYS_REG(3, 3, 9, 12, 3), /* PMOVSCLR_EL0 */ + ARM64_SYS_REG(3, 3, 9, 12, 4), /* PMSWINC_EL0 */ + ARM64_SYS_REG(3, 3, 9, 12, 5), /* PMSELR_EL0 */ + ARM64_SYS_REG(3, 3, 9, 13, 0), /* PMCCNTR_EL0 */ + ARM64_SYS_REG(3, 3, 9, 14, 0), /* PMUSERENR_EL0 */ + ARM64_SYS_REG(3, 3, 9, 14, 3), /* PMOVSSET_EL0 */ + ARM64_SYS_REG(3, 3, 13, 0, 2), /* TPIDR_EL0 */ + ARM64_SYS_REG(3, 3, 13, 0, 3), /* TPIDRRO_EL0 */ + ARM64_SYS_REG(3, 3, 14, 8, 0), + ARM64_SYS_REG(3, 3, 14, 8, 1), + ARM64_SYS_REG(3, 3, 14, 8, 2), + ARM64_SYS_REG(3, 3, 14, 8, 3), + ARM64_SYS_REG(3, 3, 14, 8, 4), + ARM64_SYS_REG(3, 3, 14, 8, 5), + ARM64_SYS_REG(3, 3, 14, 8, 6), + ARM64_SYS_REG(3, 3, 14, 8, 7), + ARM64_SYS_REG(3, 3, 14, 9, 0), + ARM64_SYS_REG(3, 3, 14, 9, 1), + ARM64_SYS_REG(3, 3, 14, 9, 2), + ARM64_SYS_REG(3, 3, 14, 9, 3), + ARM64_SYS_REG(3, 3, 14, 9, 4), + ARM64_SYS_REG(3, 3, 14, 9, 5), + ARM64_SYS_REG(3, 3, 14, 9, 6), + ARM64_SYS_REG(3, 3, 14, 9, 7), + ARM64_SYS_REG(3, 3, 14, 10, 0), + ARM64_SYS_REG(3, 3, 14, 10, 1), + ARM64_SYS_REG(3, 3, 14, 10, 2), + ARM64_SYS_REG(3, 3, 14, 10, 3), + ARM64_SYS_REG(3, 3, 14, 10, 4), + ARM64_SYS_REG(3, 3, 14, 10, 5), + ARM64_SYS_REG(3, 3, 14, 10, 6), + ARM64_SYS_REG(3, 3, 14, 10, 7), + ARM64_SYS_REG(3, 3, 14, 11, 0), + ARM64_SYS_REG(3, 3, 14, 11, 1), + ARM64_SYS_REG(3, 3, 14, 11, 2), + ARM64_SYS_REG(3, 3, 14, 11, 3), + ARM64_SYS_REG(3, 3, 14, 11, 4), + ARM64_SYS_REG(3, 3, 14, 11, 5), + ARM64_SYS_REG(3, 3, 14, 11, 6), + ARM64_SYS_REG(3, 3, 14, 12, 0), + ARM64_SYS_REG(3, 3, 14, 12, 1), + ARM64_SYS_REG(3, 3, 14, 12, 2), + ARM64_SYS_REG(3, 3, 14, 12, 3), + ARM64_SYS_REG(3, 3, 14, 12, 4), + ARM64_SYS_REG(3, 3, 14, 12, 5), + ARM64_SYS_REG(3, 3, 14, 12, 6), + ARM64_SYS_REG(3, 3, 14, 12, 7), + ARM64_SYS_REG(3, 3, 14, 13, 0), + ARM64_SYS_REG(3, 3, 14, 13, 1), + ARM64_SYS_REG(3, 3, 14, 13, 2), + ARM64_SYS_REG(3, 3, 14, 13, 3), + ARM64_SYS_REG(3, 3, 14, 13, 4), + ARM64_SYS_REG(3, 3, 14, 13, 5), + ARM64_SYS_REG(3, 3, 14, 13, 6), + ARM64_SYS_REG(3, 3, 14, 13, 7), + ARM64_SYS_REG(3, 3, 14, 14, 0), + ARM64_SYS_REG(3, 3, 14, 14, 1), + ARM64_SYS_REG(3, 3, 14, 14, 2), + ARM64_SYS_REG(3, 3, 14, 14, 3), + ARM64_SYS_REG(3, 3, 14, 14, 4), + ARM64_SYS_REG(3, 3, 14, 14, 5), + ARM64_SYS_REG(3, 3, 14, 14, 6), + ARM64_SYS_REG(3, 3, 14, 14, 7), + ARM64_SYS_REG(3, 3, 14, 15, 0), + ARM64_SYS_REG(3, 3, 14, 15, 1), + ARM64_SYS_REG(3, 3, 14, 15, 2), + ARM64_SYS_REG(3, 3, 14, 15, 3), + ARM64_SYS_REG(3, 3, 14, 15, 4), + ARM64_SYS_REG(3, 3, 14, 15, 5), + ARM64_SYS_REG(3, 3, 14, 15, 6), + ARM64_SYS_REG(3, 3, 14, 15, 7), /* PMCCFILTR_EL0 */ + ARM64_SYS_REG(3, 4, 3, 0, 0), /* DACR32_EL2 */ + ARM64_SYS_REG(3, 4, 5, 0, 1), /* IFSR32_EL2 */ + ARM64_SYS_REG(3, 4, 5, 3, 0), /* FPEXC32_EL2 */ + KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | 0, + KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | 1, + KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_DEMUX | KVM_REG_ARM_DEMUX_ID_CCSIDR | 2, +}; +static __u64 base_regs_n = ARRAY_SIZE(base_regs); + +static __u64 vregs[] = { + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[1]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[2]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[3]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[4]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[5]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[6]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[7]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[8]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[9]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[10]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[11]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[12]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[13]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[14]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[15]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[16]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[17]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[18]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[19]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[20]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[21]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[22]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[23]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[24]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[25]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[26]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[27]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[28]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[29]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[30]), + KVM_REG_ARM64 | KVM_REG_SIZE_U128 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]), +}; +static __u64 vregs_n = ARRAY_SIZE(vregs); + +static __u64 sve_regs[] = { + KVM_REG_ARM64_SVE_VLS, + KVM_REG_ARM64_SVE_ZREG(0, 0), + KVM_REG_ARM64_SVE_ZREG(1, 0), + KVM_REG_ARM64_SVE_ZREG(2, 0), + KVM_REG_ARM64_SVE_ZREG(3, 0), + KVM_REG_ARM64_SVE_ZREG(4, 0), + KVM_REG_ARM64_SVE_ZREG(5, 0), + KVM_REG_ARM64_SVE_ZREG(6, 0), + KVM_REG_ARM64_SVE_ZREG(7, 0), + KVM_REG_ARM64_SVE_ZREG(8, 0), + KVM_REG_ARM64_SVE_ZREG(9, 0), + KVM_REG_ARM64_SVE_ZREG(10, 0), + KVM_REG_ARM64_SVE_ZREG(11, 0), + KVM_REG_ARM64_SVE_ZREG(12, 0), + KVM_REG_ARM64_SVE_ZREG(13, 0), + KVM_REG_ARM64_SVE_ZREG(14, 0), + KVM_REG_ARM64_SVE_ZREG(15, 0), + KVM_REG_ARM64_SVE_ZREG(16, 0), + KVM_REG_ARM64_SVE_ZREG(17, 0), + KVM_REG_ARM64_SVE_ZREG(18, 0), + KVM_REG_ARM64_SVE_ZREG(19, 0), + KVM_REG_ARM64_SVE_ZREG(20, 0), + KVM_REG_ARM64_SVE_ZREG(21, 0), + KVM_REG_ARM64_SVE_ZREG(22, 0), + KVM_REG_ARM64_SVE_ZREG(23, 0), + KVM_REG_ARM64_SVE_ZREG(24, 0), + KVM_REG_ARM64_SVE_ZREG(25, 0), + KVM_REG_ARM64_SVE_ZREG(26, 0), + KVM_REG_ARM64_SVE_ZREG(27, 0), + KVM_REG_ARM64_SVE_ZREG(28, 0), + KVM_REG_ARM64_SVE_ZREG(29, 0), + KVM_REG_ARM64_SVE_ZREG(30, 0), + KVM_REG_ARM64_SVE_ZREG(31, 0), + KVM_REG_ARM64_SVE_PREG(0, 0), + KVM_REG_ARM64_SVE_PREG(1, 0), + KVM_REG_ARM64_SVE_PREG(2, 0), + KVM_REG_ARM64_SVE_PREG(3, 0), + KVM_REG_ARM64_SVE_PREG(4, 0), + KVM_REG_ARM64_SVE_PREG(5, 0), + KVM_REG_ARM64_SVE_PREG(6, 0), + KVM_REG_ARM64_SVE_PREG(7, 0), + KVM_REG_ARM64_SVE_PREG(8, 0), + KVM_REG_ARM64_SVE_PREG(9, 0), + KVM_REG_ARM64_SVE_PREG(10, 0), + KVM_REG_ARM64_SVE_PREG(11, 0), + KVM_REG_ARM64_SVE_PREG(12, 0), + KVM_REG_ARM64_SVE_PREG(13, 0), + KVM_REG_ARM64_SVE_PREG(14, 0), + KVM_REG_ARM64_SVE_PREG(15, 0), + KVM_REG_ARM64_SVE_FFR(0), + ARM64_SYS_REG(3, 0, 1, 2, 0), /* ZCR_EL1 */ +}; +static __u64 sve_regs_n = ARRAY_SIZE(sve_regs); + +static __u64 rejects_set[] = { +#ifdef REG_LIST_SVE + KVM_REG_ARM64_SVE_VLS, +#endif +}; +static __u64 rejects_set_n = ARRAY_SIZE(rejects_set); diff --git a/tools/testing/selftests/kvm/clear_dirty_log_test.c b/tools/testing/selftests/kvm/clear_dirty_log_test.c deleted file mode 100644 index 11672ec6f74e..000000000000 --- a/tools/testing/selftests/kvm/clear_dirty_log_test.c +++ /dev/null @@ -1,6 +0,0 @@ -#define USE_CLEAR_DIRTY_LOG -#define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (1 << 0) -#define KVM_DIRTY_LOG_INITIALLY_SET (1 << 1) -#define KVM_DIRTY_LOG_MANUAL_CAPS (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \ - KVM_DIRTY_LOG_INITIALLY_SET) -#include "dirty_log_test.c" diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c index 360cd3ea4cd6..3d96a7bfaff3 100644 --- a/tools/testing/selftests/kvm/demand_paging_test.c +++ b/tools/testing/selftests/kvm/demand_paging_test.c @@ -21,20 +21,12 @@ #include <linux/bitops.h> #include <linux/userfaultfd.h> -#include "test_util.h" -#include "kvm_util.h" +#include "perf_test_util.h" #include "processor.h" +#include "test_util.h" #ifdef __NR_userfaultfd -/* The memory slot index demand page */ -#define TEST_MEM_SLOT_INDEX 1 - -/* Default guest test virtual memory offset */ -#define DEFAULT_GUEST_TEST_MEM 0xc0000000 - -#define DEFAULT_GUEST_TEST_MEM_SIZE (1 << 30) /* 1G */ - #ifdef PRINT_PER_PAGE_UPDATES #define PER_PAGE_DEBUG(...) printf(__VA_ARGS__) #else @@ -47,77 +39,17 @@ #define PER_VCPU_DEBUG(...) _no_printf(__VA_ARGS__) #endif -#define MAX_VCPUS 512 - -/* - * Guest/Host shared variables. Ensure addr_gva2hva() and/or - * sync_global_to/from_guest() are used when accessing from - * the host. READ/WRITE_ONCE() should also be used with anything - * that may change. - */ -static uint64_t host_page_size; -static uint64_t guest_page_size; - static char *guest_data_prototype; -/* - * Guest physical memory offset of the testing memory slot. - * This will be set to the topmost valid physical address minus - * the test memory size. - */ -static uint64_t guest_test_phys_mem; - -/* - * Guest virtual memory offset of the testing memory slot. - * Must not conflict with identity mapped test code. - */ -static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM; - -struct vcpu_args { - uint64_t gva; - uint64_t pages; - - /* Only used by the host userspace part of the vCPU thread */ - int vcpu_id; - struct kvm_vm *vm; -}; - -static struct vcpu_args vcpu_args[MAX_VCPUS]; - -/* - * Continuously write to the first 8 bytes of each page in the demand paging - * memory region. - */ -static void guest_code(uint32_t vcpu_id) -{ - uint64_t gva; - uint64_t pages; - int i; - - /* Make sure vCPU args data structure is not corrupt. */ - GUEST_ASSERT(vcpu_args[vcpu_id].vcpu_id == vcpu_id); - - gva = vcpu_args[vcpu_id].gva; - pages = vcpu_args[vcpu_id].pages; - - for (i = 0; i < pages; i++) { - uint64_t addr = gva + (i * guest_page_size); - - addr &= ~(host_page_size - 1); - *(uint64_t *)addr = 0x0123456789ABCDEF; - } - - GUEST_SYNC(1); -} - static void *vcpu_worker(void *data) { int ret; - struct vcpu_args *args = (struct vcpu_args *)data; - struct kvm_vm *vm = args->vm; - int vcpu_id = args->vcpu_id; + struct vcpu_args *vcpu_args = (struct vcpu_args *)data; + int vcpu_id = vcpu_args->vcpu_id; + struct kvm_vm *vm = perf_test_args.vm; struct kvm_run *run; - struct timespec start, end, ts_diff; + struct timespec start; + struct timespec ts_diff; vcpu_args_set(vm, vcpu_id, 1, vcpu_id); run = vcpu_state(vm, vcpu_id); @@ -133,52 +65,18 @@ static void *vcpu_worker(void *data) exit_reason_str(run->exit_reason)); } - clock_gettime(CLOCK_MONOTONIC, &end); - ts_diff = timespec_sub(end, start); + ts_diff = timespec_diff_now(start); PER_VCPU_DEBUG("vCPU %d execution time: %ld.%.9lds\n", vcpu_id, ts_diff.tv_sec, ts_diff.tv_nsec); return NULL; } -#define PAGE_SHIFT_4K 12 -#define PTES_PER_4K_PT 512 - -static struct kvm_vm *create_vm(enum vm_guest_mode mode, int vcpus, - uint64_t vcpu_memory_bytes) -{ - struct kvm_vm *vm; - uint64_t pages = DEFAULT_GUEST_PHY_PAGES; - - /* Account for a few pages per-vCPU for stacks */ - pages += DEFAULT_STACK_PGS * vcpus; - - /* - * Reserve twice the ammount of memory needed to map the test region and - * the page table / stacks region, at 4k, for page tables. Do the - * calculation with 4K page size: the smallest of all archs. (e.g., 64K - * page size guest will need even less memory for page tables). - */ - pages += (2 * pages) / PTES_PER_4K_PT; - pages += ((2 * vcpus * vcpu_memory_bytes) >> PAGE_SHIFT_4K) / - PTES_PER_4K_PT; - pages = vm_adjust_num_guest_pages(mode, pages); - - pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode)); - - vm = _vm_create(mode, pages, O_RDWR); - kvm_vm_elf_load(vm, program_invocation_name, 0, 0); -#ifdef __x86_64__ - vm_create_irqchip(vm); -#endif - return vm; -} - static int handle_uffd_page_request(int uffd, uint64_t addr) { pid_t tid; struct timespec start; - struct timespec end; + struct timespec ts_diff; struct uffdio_copy copy; int r; @@ -186,7 +84,7 @@ static int handle_uffd_page_request(int uffd, uint64_t addr) copy.src = (uint64_t)guest_data_prototype; copy.dst = addr; - copy.len = host_page_size; + copy.len = perf_test_args.host_page_size; copy.mode = 0; clock_gettime(CLOCK_MONOTONIC, &start); @@ -198,12 +96,12 @@ static int handle_uffd_page_request(int uffd, uint64_t addr) return r; } - clock_gettime(CLOCK_MONOTONIC, &end); + ts_diff = timespec_diff_now(start); PER_PAGE_DEBUG("UFFDIO_COPY %d \t%ld ns\n", tid, - timespec_to_ns(timespec_sub(end, start))); + timespec_to_ns(ts_diff)); PER_PAGE_DEBUG("Paged in %ld bytes at 0x%lx from thread %d\n", - host_page_size, addr, tid); + perf_test_args.host_page_size, addr, tid); return 0; } @@ -223,7 +121,8 @@ static void *uffd_handler_thread_fn(void *arg) int pipefd = uffd_args->pipefd; useconds_t delay = uffd_args->delay; int64_t pages = 0; - struct timespec start, end, ts_diff; + struct timespec start; + struct timespec ts_diff; clock_gettime(CLOCK_MONOTONIC, &start); while (!quit_uffd_thread) { @@ -292,8 +191,7 @@ static void *uffd_handler_thread_fn(void *arg) pages++; } - clock_gettime(CLOCK_MONOTONIC, &end); - ts_diff = timespec_sub(end, start); + ts_diff = timespec_diff_now(start); PER_VCPU_DEBUG("userfaulted %ld pages over %ld.%.9lds. (%f/sec)\n", pages, ts_diff.tv_sec, ts_diff.tv_nsec, pages / ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0)); @@ -351,99 +249,54 @@ static int setup_demand_paging(struct kvm_vm *vm, } static void run_test(enum vm_guest_mode mode, bool use_uffd, - useconds_t uffd_delay, int vcpus, - uint64_t vcpu_memory_bytes) + useconds_t uffd_delay) { pthread_t *vcpu_threads; pthread_t *uffd_handler_threads = NULL; struct uffd_handler_args *uffd_args = NULL; - struct timespec start, end, ts_diff; + struct timespec start; + struct timespec ts_diff; int *pipefds = NULL; struct kvm_vm *vm; - uint64_t guest_num_pages; int vcpu_id; int r; - vm = create_vm(mode, vcpus, vcpu_memory_bytes); - - guest_page_size = vm_get_page_size(vm); - - TEST_ASSERT(vcpu_memory_bytes % guest_page_size == 0, - "Guest memory size is not guest page size aligned."); - - guest_num_pages = (vcpus * vcpu_memory_bytes) / guest_page_size; - guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages); - - /* - * If there should be more memory in the guest test region than there - * can be pages in the guest, it will definitely cause problems. - */ - TEST_ASSERT(guest_num_pages < vm_get_max_gfn(vm), - "Requested more guest memory than address space allows.\n" - " guest pages: %lx max gfn: %x vcpus: %d wss: %lx]\n", - guest_num_pages, vm_get_max_gfn(vm), vcpus, - vcpu_memory_bytes); - - host_page_size = getpagesize(); - TEST_ASSERT(vcpu_memory_bytes % host_page_size == 0, - "Guest memory size is not host page size aligned."); + vm = create_vm(mode, nr_vcpus, guest_percpu_mem_size); - guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) * - guest_page_size; - guest_test_phys_mem &= ~(host_page_size - 1); + perf_test_args.wr_fract = 1; -#ifdef __s390x__ - /* Align to 1M (segment size) */ - guest_test_phys_mem &= ~((1 << 20) - 1); -#endif - - pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem); - - /* Add an extra memory slot for testing demand paging */ - vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, - guest_test_phys_mem, - TEST_MEM_SLOT_INDEX, - guest_num_pages, 0); - - /* Do mapping for the demand paging memory slot */ - virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages, 0); - - ucall_init(vm, NULL); - - guest_data_prototype = malloc(host_page_size); + guest_data_prototype = malloc(perf_test_args.host_page_size); TEST_ASSERT(guest_data_prototype, "Failed to allocate buffer for guest data pattern"); - memset(guest_data_prototype, 0xAB, host_page_size); + memset(guest_data_prototype, 0xAB, perf_test_args.host_page_size); - vcpu_threads = malloc(vcpus * sizeof(*vcpu_threads)); + vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads)); TEST_ASSERT(vcpu_threads, "Memory allocation failed"); + add_vcpus(vm, nr_vcpus, guest_percpu_mem_size); + if (use_uffd) { uffd_handler_threads = - malloc(vcpus * sizeof(*uffd_handler_threads)); + malloc(nr_vcpus * sizeof(*uffd_handler_threads)); TEST_ASSERT(uffd_handler_threads, "Memory allocation failed"); - uffd_args = malloc(vcpus * sizeof(*uffd_args)); + uffd_args = malloc(nr_vcpus * sizeof(*uffd_args)); TEST_ASSERT(uffd_args, "Memory allocation failed"); - pipefds = malloc(sizeof(int) * vcpus * 2); + pipefds = malloc(sizeof(int) * nr_vcpus * 2); TEST_ASSERT(pipefds, "Unable to allocate memory for pipefd"); - } - - for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { - vm_paddr_t vcpu_gpa; - void *vcpu_hva; - vm_vcpu_add_default(vm, vcpu_id, guest_code); + for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { + vm_paddr_t vcpu_gpa; + void *vcpu_hva; - vcpu_gpa = guest_test_phys_mem + (vcpu_id * vcpu_memory_bytes); - PER_VCPU_DEBUG("Added VCPU %d with test mem gpa [%lx, %lx)\n", - vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_memory_bytes); + vcpu_gpa = guest_test_phys_mem + (vcpu_id * guest_percpu_mem_size); + PER_VCPU_DEBUG("Added VCPU %d with test mem gpa [%lx, %lx)\n", + vcpu_id, vcpu_gpa, vcpu_gpa + guest_percpu_mem_size); - /* Cache the HVA pointer of the region */ - vcpu_hva = addr_gpa2hva(vm, vcpu_gpa); + /* Cache the HVA pointer of the region */ + vcpu_hva = addr_gpa2hva(vm, vcpu_gpa); - if (use_uffd) { /* * Set up user fault fd to handle demand paging * requests. @@ -456,53 +309,41 @@ static void run_test(enum vm_guest_mode mode, bool use_uffd, &uffd_handler_threads[vcpu_id], pipefds[vcpu_id * 2], uffd_delay, &uffd_args[vcpu_id], - vcpu_hva, vcpu_memory_bytes); + vcpu_hva, guest_percpu_mem_size); if (r < 0) exit(-r); } - -#ifdef __x86_64__ - vcpu_set_cpuid(vm, vcpu_id, kvm_get_supported_cpuid()); -#endif - - vcpu_args[vcpu_id].vm = vm; - vcpu_args[vcpu_id].vcpu_id = vcpu_id; - vcpu_args[vcpu_id].gva = guest_test_virt_mem + - (vcpu_id * vcpu_memory_bytes); - vcpu_args[vcpu_id].pages = vcpu_memory_bytes / guest_page_size; } /* Export the shared variables to the guest */ - sync_global_to_guest(vm, host_page_size); - sync_global_to_guest(vm, guest_page_size); - sync_global_to_guest(vm, vcpu_args); + sync_global_to_guest(vm, perf_test_args); pr_info("Finished creating vCPUs and starting uffd threads\n"); clock_gettime(CLOCK_MONOTONIC, &start); - for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { + for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker, - &vcpu_args[vcpu_id]); + &perf_test_args.vcpu_args[vcpu_id]); } pr_info("Started all vCPUs\n"); /* Wait for the vcpu threads to quit */ - for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { + for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { pthread_join(vcpu_threads[vcpu_id], NULL); PER_VCPU_DEBUG("Joined thread for vCPU %d\n", vcpu_id); } - pr_info("All vCPU threads joined\n"); + ts_diff = timespec_diff_now(start); - clock_gettime(CLOCK_MONOTONIC, &end); + pr_info("All vCPU threads joined\n"); if (use_uffd) { char c; /* Tell the user fault fd handler threads to quit */ - for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { + for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { r = write(pipefds[vcpu_id * 2 + 1], &c, 1); TEST_ASSERT(r == 1, "Unable to write to pipefd"); @@ -510,11 +351,11 @@ static void run_test(enum vm_guest_mode mode, bool use_uffd, } } - ts_diff = timespec_sub(end, start); pr_info("Total guest execution time: %ld.%.9lds\n", ts_diff.tv_sec, ts_diff.tv_nsec); pr_info("Overall demand paging rate: %f pgs/sec\n", - guest_num_pages / ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0)); + perf_test_args.vcpu_args[0].pages * nr_vcpus / + ((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0)); ucall_uninit(vm); kvm_vm_free(vm); @@ -568,9 +409,8 @@ static void help(char *name) int main(int argc, char *argv[]) { + int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS); bool mode_selected = false; - uint64_t vcpu_memory_bytes = DEFAULT_GUEST_TEST_MEM_SIZE; - int vcpus = 1; unsigned int mode; int opt, i; bool use_uffd = false; @@ -619,15 +459,12 @@ int main(int argc, char *argv[]) "A negative UFFD delay is not supported."); break; case 'b': - vcpu_memory_bytes = parse_size(optarg); + guest_percpu_mem_size = parse_size(optarg); break; case 'v': - vcpus = atoi(optarg); - TEST_ASSERT(vcpus > 0, - "Must have a positive number of vCPUs"); - TEST_ASSERT(vcpus <= MAX_VCPUS, - "This test does not currently support\n" - "more than %d vCPUs.", MAX_VCPUS); + nr_vcpus = atoi(optarg); + TEST_ASSERT(nr_vcpus > 0 && nr_vcpus <= max_vcpus, + "Invalid number of vcpus, must be between 1 and %d", max_vcpus); break; case 'h': default: @@ -642,7 +479,7 @@ int main(int argc, char *argv[]) TEST_ASSERT(guest_modes[i].supported, "Guest mode ID %d (%s) not supported.", i, vm_guest_mode_string(i)); - run_test(i, use_uffd, uffd_delay, vcpus, vcpu_memory_bytes); + run_test(i, use_uffd, uffd_delay); } return 0; diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c new file mode 100644 index 000000000000..85c9b8f73142 --- /dev/null +++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c @@ -0,0 +1,376 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KVM dirty page logging performance test + * + * Based on dirty_log_test.c + * + * Copyright (C) 2018, Red Hat, Inc. + * Copyright (C) 2020, Google, Inc. + */ + +#define _GNU_SOURCE /* for program_invocation_name */ + +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <time.h> +#include <pthread.h> +#include <linux/bitmap.h> +#include <linux/bitops.h> + +#include "kvm_util.h" +#include "perf_test_util.h" +#include "processor.h" +#include "test_util.h" + +/* How many host loops to run by default (one KVM_GET_DIRTY_LOG for each loop)*/ +#define TEST_HOST_LOOP_N 2UL + +/* Host variables */ +static bool host_quit; +static uint64_t iteration; +static uint64_t vcpu_last_completed_iteration[MAX_VCPUS]; + +static void *vcpu_worker(void *data) +{ + int ret; + struct kvm_vm *vm = perf_test_args.vm; + uint64_t pages_count = 0; + struct kvm_run *run; + struct timespec start; + struct timespec ts_diff; + struct timespec total = (struct timespec){0}; + struct timespec avg; + struct vcpu_args *vcpu_args = (struct vcpu_args *)data; + int vcpu_id = vcpu_args->vcpu_id; + + vcpu_args_set(vm, vcpu_id, 1, vcpu_id); + run = vcpu_state(vm, vcpu_id); + + while (!READ_ONCE(host_quit)) { + uint64_t current_iteration = READ_ONCE(iteration); + + clock_gettime(CLOCK_MONOTONIC, &start); + ret = _vcpu_run(vm, vcpu_id); + ts_diff = timespec_diff_now(start); + + TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret); + TEST_ASSERT(get_ucall(vm, vcpu_id, NULL) == UCALL_SYNC, + "Invalid guest sync status: exit_reason=%s\n", + exit_reason_str(run->exit_reason)); + + pr_debug("Got sync event from vCPU %d\n", vcpu_id); + vcpu_last_completed_iteration[vcpu_id] = current_iteration; + pr_debug("vCPU %d updated last completed iteration to %lu\n", + vcpu_id, vcpu_last_completed_iteration[vcpu_id]); + + if (current_iteration) { + pages_count += vcpu_args->pages; + total = timespec_add(total, ts_diff); + pr_debug("vCPU %d iteration %lu dirty memory time: %ld.%.9lds\n", + vcpu_id, current_iteration, ts_diff.tv_sec, + ts_diff.tv_nsec); + } else { + pr_debug("vCPU %d iteration %lu populate memory time: %ld.%.9lds\n", + vcpu_id, current_iteration, ts_diff.tv_sec, + ts_diff.tv_nsec); + } + + while (current_iteration == READ_ONCE(iteration) && + !READ_ONCE(host_quit)) {} + } + + avg = timespec_div(total, vcpu_last_completed_iteration[vcpu_id]); + pr_debug("\nvCPU %d dirtied 0x%lx pages over %lu iterations in %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n", + vcpu_id, pages_count, vcpu_last_completed_iteration[vcpu_id], + total.tv_sec, total.tv_nsec, avg.tv_sec, avg.tv_nsec); + + return NULL; +} + +#ifdef USE_CLEAR_DIRTY_LOG +static u64 dirty_log_manual_caps; +#endif + +static void run_test(enum vm_guest_mode mode, unsigned long iterations, + uint64_t phys_offset, int wr_fract) +{ + pthread_t *vcpu_threads; + struct kvm_vm *vm; + unsigned long *bmap; + uint64_t guest_num_pages; + uint64_t host_num_pages; + int vcpu_id; + struct timespec start; + struct timespec ts_diff; + struct timespec get_dirty_log_total = (struct timespec){0}; + struct timespec vcpu_dirty_total = (struct timespec){0}; + struct timespec avg; +#ifdef USE_CLEAR_DIRTY_LOG + struct kvm_enable_cap cap = {}; + struct timespec clear_dirty_log_total = (struct timespec){0}; +#endif + + vm = create_vm(mode, nr_vcpus, guest_percpu_mem_size); + + perf_test_args.wr_fract = wr_fract; + + guest_num_pages = (nr_vcpus * guest_percpu_mem_size) >> vm_get_page_shift(vm); + guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages); + host_num_pages = vm_num_host_pages(mode, guest_num_pages); + bmap = bitmap_alloc(host_num_pages); + +#ifdef USE_CLEAR_DIRTY_LOG + cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2; + cap.args[0] = dirty_log_manual_caps; + vm_enable_cap(vm, &cap); +#endif + + vcpu_threads = malloc(nr_vcpus * sizeof(*vcpu_threads)); + TEST_ASSERT(vcpu_threads, "Memory allocation failed"); + + add_vcpus(vm, nr_vcpus, guest_percpu_mem_size); + + sync_global_to_guest(vm, perf_test_args); + + /* Start the iterations */ + iteration = 0; + host_quit = false; + + clock_gettime(CLOCK_MONOTONIC, &start); + for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { + pthread_create(&vcpu_threads[vcpu_id], NULL, vcpu_worker, + &perf_test_args.vcpu_args[vcpu_id]); + } + + /* Allow the vCPU to populate memory */ + pr_debug("Starting iteration %lu - Populating\n", iteration); + while (READ_ONCE(vcpu_last_completed_iteration[vcpu_id]) != iteration) + pr_debug("Waiting for vcpu_last_completed_iteration == %lu\n", + iteration); + + ts_diff = timespec_diff_now(start); + pr_info("Populate memory time: %ld.%.9lds\n", + ts_diff.tv_sec, ts_diff.tv_nsec); + + /* Enable dirty logging */ + clock_gettime(CLOCK_MONOTONIC, &start); + vm_mem_region_set_flags(vm, TEST_MEM_SLOT_INDEX, + KVM_MEM_LOG_DIRTY_PAGES); + ts_diff = timespec_diff_now(start); + pr_info("Enabling dirty logging time: %ld.%.9lds\n\n", + ts_diff.tv_sec, ts_diff.tv_nsec); + + while (iteration < iterations) { + /* + * Incrementing the iteration number will start the vCPUs + * dirtying memory again. + */ + clock_gettime(CLOCK_MONOTONIC, &start); + iteration++; + + pr_debug("Starting iteration %lu\n", iteration); + for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) { + while (READ_ONCE(vcpu_last_completed_iteration[vcpu_id]) != iteration) + pr_debug("Waiting for vCPU %d vcpu_last_completed_iteration == %lu\n", + vcpu_id, iteration); + } + + ts_diff = timespec_diff_now(start); + vcpu_dirty_total = timespec_add(vcpu_dirty_total, ts_diff); + pr_info("Iteration %lu dirty memory time: %ld.%.9lds\n", + iteration, ts_diff.tv_sec, ts_diff.tv_nsec); + + clock_gettime(CLOCK_MONOTONIC, &start); + kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap); + + ts_diff = timespec_diff_now(start); + get_dirty_log_total = timespec_add(get_dirty_log_total, + ts_diff); + pr_info("Iteration %lu get dirty log time: %ld.%.9lds\n", + iteration, ts_diff.tv_sec, ts_diff.tv_nsec); + +#ifdef USE_CLEAR_DIRTY_LOG + clock_gettime(CLOCK_MONOTONIC, &start); + kvm_vm_clear_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap, 0, + host_num_pages); + + ts_diff = timespec_diff_now(start); + clear_dirty_log_total = timespec_add(clear_dirty_log_total, + ts_diff); + pr_info("Iteration %lu clear dirty log time: %ld.%.9lds\n", + iteration, ts_diff.tv_sec, ts_diff.tv_nsec); +#endif + } + + /* Tell the vcpu thread to quit */ + host_quit = true; + for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) + pthread_join(vcpu_threads[vcpu_id], NULL); + + /* Disable dirty logging */ + clock_gettime(CLOCK_MONOTONIC, &start); + vm_mem_region_set_flags(vm, TEST_MEM_SLOT_INDEX, 0); + ts_diff = timespec_diff_now(start); + pr_info("Disabling dirty logging time: %ld.%.9lds\n", + ts_diff.tv_sec, ts_diff.tv_nsec); + + avg = timespec_div(get_dirty_log_total, iterations); + pr_info("Get dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n", + iterations, get_dirty_log_total.tv_sec, + get_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec); + +#ifdef USE_CLEAR_DIRTY_LOG + avg = timespec_div(clear_dirty_log_total, iterations); + pr_info("Clear dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n", + iterations, clear_dirty_log_total.tv_sec, + clear_dirty_log_total.tv_nsec, avg.tv_sec, avg.tv_nsec); +#endif + + free(bmap); + free(vcpu_threads); + ucall_uninit(vm); + kvm_vm_free(vm); +} + +struct guest_mode { + bool supported; + bool enabled; +}; +static struct guest_mode guest_modes[NUM_VM_MODES]; + +#define guest_mode_init(mode, supported, enabled) ({ \ + guest_modes[mode] = (struct guest_mode){ supported, enabled }; \ +}) + +static void help(char *name) +{ + int i; + + puts(""); + printf("usage: %s [-h] [-i iterations] [-p offset] " + "[-m mode] [-b vcpu bytes] [-v vcpus]\n", name); + puts(""); + printf(" -i: specify iteration counts (default: %"PRIu64")\n", + TEST_HOST_LOOP_N); + printf(" -p: specify guest physical test memory offset\n" + " Warning: a low offset can conflict with the loaded test code.\n"); + printf(" -m: specify the guest mode ID to test " + "(default: test all supported modes)\n" + " This option may be used multiple times.\n" + " Guest mode IDs:\n"); + for (i = 0; i < NUM_VM_MODES; ++i) { + printf(" %d: %s%s\n", i, vm_guest_mode_string(i), + guest_modes[i].supported ? " (supported)" : ""); + } + printf(" -b: specify the size of the memory region which should be\n" + " dirtied by each vCPU. e.g. 10M or 3G.\n" + " (default: 1G)\n"); + printf(" -f: specify the fraction of pages which should be written to\n" + " as opposed to simply read, in the form\n" + " 1/<fraction of pages to write>.\n" + " (default: 1 i.e. all pages are written to.)\n"); + printf(" -v: specify the number of vCPUs to run.\n"); + puts(""); + exit(0); +} + +int main(int argc, char *argv[]) +{ + unsigned long iterations = TEST_HOST_LOOP_N; + bool mode_selected = false; + uint64_t phys_offset = 0; + unsigned int mode; + int opt, i; + int wr_fract = 1; + +#ifdef USE_CLEAR_DIRTY_LOG + dirty_log_manual_caps = + kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2); + if (!dirty_log_manual_caps) { + print_skip("KVM_CLEAR_DIRTY_LOG not available"); + exit(KSFT_SKIP); + } + dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | + KVM_DIRTY_LOG_INITIALLY_SET); +#endif + +#ifdef __x86_64__ + guest_mode_init(VM_MODE_PXXV48_4K, true, true); +#endif +#ifdef __aarch64__ + guest_mode_init(VM_MODE_P40V48_4K, true, true); + guest_mode_init(VM_MODE_P40V48_64K, true, true); + + { + unsigned int limit = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE); + + if (limit >= 52) + guest_mode_init(VM_MODE_P52V48_64K, true, true); + if (limit >= 48) { + guest_mode_init(VM_MODE_P48V48_4K, true, true); + guest_mode_init(VM_MODE_P48V48_64K, true, true); + } + } +#endif +#ifdef __s390x__ + guest_mode_init(VM_MODE_P40V48_4K, true, true); +#endif + + while ((opt = getopt(argc, argv, "hi:p:m:b:f:v:")) != -1) { + switch (opt) { + case 'i': + iterations = strtol(optarg, NULL, 10); + break; + case 'p': + phys_offset = strtoull(optarg, NULL, 0); + break; + case 'm': + if (!mode_selected) { + for (i = 0; i < NUM_VM_MODES; ++i) + guest_modes[i].enabled = false; + mode_selected = true; + } + mode = strtoul(optarg, NULL, 10); + TEST_ASSERT(mode < NUM_VM_MODES, + "Guest mode ID %d too big", mode); + guest_modes[mode].enabled = true; + break; + case 'b': + guest_percpu_mem_size = parse_size(optarg); + break; + case 'f': + wr_fract = atoi(optarg); + TEST_ASSERT(wr_fract >= 1, + "Write fraction cannot be less than one"); + break; + case 'v': + nr_vcpus = atoi(optarg); + TEST_ASSERT(nr_vcpus > 0, + "Must have a positive number of vCPUs"); + TEST_ASSERT(nr_vcpus <= MAX_VCPUS, + "This test does not currently support\n" + "more than %d vCPUs.", MAX_VCPUS); + break; + case 'h': + default: + help(argv[0]); + break; + } + } + + TEST_ASSERT(iterations >= 2, "The test should have at least two iterations"); + + pr_info("Test iterations: %"PRIu64"\n", iterations); + + for (i = 0; i < NUM_VM_MODES; ++i) { + if (!guest_modes[i].enabled) + continue; + TEST_ASSERT(guest_modes[i].supported, + "Guest mode ID %d (%s) not supported.", + i, vm_guest_mode_string(i)); + run_test(i, iterations, phys_offset, wr_fract); + } + + return 0; +} diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c index 752ec158ac59..54da9cc20db4 100644 --- a/tools/testing/selftests/kvm/dirty_log_test.c +++ b/tools/testing/selftests/kvm/dirty_log_test.c @@ -128,6 +128,78 @@ static uint64_t host_dirty_count; static uint64_t host_clear_count; static uint64_t host_track_next_count; +enum log_mode_t { + /* Only use KVM_GET_DIRTY_LOG for logging */ + LOG_MODE_DIRTY_LOG = 0, + + /* Use both KVM_[GET|CLEAR]_DIRTY_LOG for logging */ + LOG_MODE_CLEAR_LOG = 1, + + LOG_MODE_NUM, + + /* Run all supported modes */ + LOG_MODE_ALL = LOG_MODE_NUM, +}; + +/* Mode of logging to test. Default is to run all supported modes */ +static enum log_mode_t host_log_mode_option = LOG_MODE_ALL; +/* Logging mode for current run */ +static enum log_mode_t host_log_mode; + +static bool clear_log_supported(void) +{ + return kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2); +} + +static void clear_log_create_vm_done(struct kvm_vm *vm) +{ + struct kvm_enable_cap cap = {}; + u64 manual_caps; + + manual_caps = kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2); + TEST_ASSERT(manual_caps, "MANUAL_CAPS is zero!"); + manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | + KVM_DIRTY_LOG_INITIALLY_SET); + cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2; + cap.args[0] = manual_caps; + vm_enable_cap(vm, &cap); +} + +static void dirty_log_collect_dirty_pages(struct kvm_vm *vm, int slot, + void *bitmap, uint32_t num_pages) +{ + kvm_vm_get_dirty_log(vm, slot, bitmap); +} + +static void clear_log_collect_dirty_pages(struct kvm_vm *vm, int slot, + void *bitmap, uint32_t num_pages) +{ + kvm_vm_get_dirty_log(vm, slot, bitmap); + kvm_vm_clear_dirty_log(vm, slot, bitmap, 0, num_pages); +} + +struct log_mode { + const char *name; + /* Return true if this mode is supported, otherwise false */ + bool (*supported)(void); + /* Hook when the vm creation is done (before vcpu creation) */ + void (*create_vm_done)(struct kvm_vm *vm); + /* Hook to collect the dirty pages into the bitmap provided */ + void (*collect_dirty_pages) (struct kvm_vm *vm, int slot, + void *bitmap, uint32_t num_pages); +} log_modes[LOG_MODE_NUM] = { + { + .name = "dirty-log", + .collect_dirty_pages = dirty_log_collect_dirty_pages, + }, + { + .name = "clear-log", + .supported = clear_log_supported, + .create_vm_done = clear_log_create_vm_done, + .collect_dirty_pages = clear_log_collect_dirty_pages, + }, +}; + /* * We use this bitmap to track some pages that should have its dirty * bit set in the _next_ iteration. For example, if we detected the @@ -137,6 +209,44 @@ static uint64_t host_track_next_count; */ static unsigned long *host_bmap_track; +static void log_modes_dump(void) +{ + int i; + + printf("all"); + for (i = 0; i < LOG_MODE_NUM; i++) + printf(", %s", log_modes[i].name); + printf("\n"); +} + +static bool log_mode_supported(void) +{ + struct log_mode *mode = &log_modes[host_log_mode]; + + if (mode->supported) + return mode->supported(); + + return true; +} + +static void log_mode_create_vm_done(struct kvm_vm *vm) +{ + struct log_mode *mode = &log_modes[host_log_mode]; + + if (mode->create_vm_done) + mode->create_vm_done(vm); +} + +static void log_mode_collect_dirty_pages(struct kvm_vm *vm, int slot, + void *bitmap, uint32_t num_pages) +{ + struct log_mode *mode = &log_modes[host_log_mode]; + + TEST_ASSERT(mode->collect_dirty_pages != NULL, + "collect_dirty_pages() is required for any log mode!"); + mode->collect_dirty_pages(vm, slot, bitmap, num_pages); +} + static void generate_random_array(uint64_t *guest_array, uint64_t size) { uint64_t i; @@ -195,7 +305,7 @@ static void vm_dirty_log_verify(enum vm_guest_mode mode, unsigned long *bmap) page); } - if (test_bit_le(page, bmap)) { + if (test_and_clear_bit_le(page, bmap)) { host_dirty_count++; /* * If the bit is set, the value written onto @@ -252,11 +362,12 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid, pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode)); - vm = _vm_create(mode, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR); + vm = vm_create(mode, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR); kvm_vm_elf_load(vm, program_invocation_name, 0, 0); #ifdef __x86_64__ vm_create_irqchip(vm); #endif + log_mode_create_vm_done(vm); vm_vcpu_add_default(vm, vcpuid, guest_code); return vm; } @@ -264,10 +375,6 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid, #define DIRTY_MEM_BITS 30 /* 1G */ #define PAGE_SHIFT_4K 12 -#ifdef USE_CLEAR_DIRTY_LOG -static u64 dirty_log_manual_caps; -#endif - static void run_test(enum vm_guest_mode mode, unsigned long iterations, unsigned long interval, uint64_t phys_offset) { @@ -275,6 +382,12 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, struct kvm_vm *vm; unsigned long *bmap; + if (!log_mode_supported()) { + print_skip("Log mode '%s' not supported", + log_modes[host_log_mode].name); + return; + } + /* * We reserve page table for 2 times of extra dirty mem which * will definitely cover the original (1G+) test range. Here @@ -317,14 +430,6 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, bmap = bitmap_alloc(host_num_pages); host_bmap_track = bitmap_alloc(host_num_pages); -#ifdef USE_CLEAR_DIRTY_LOG - struct kvm_enable_cap cap = {}; - - cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2; - cap.args[0] = dirty_log_manual_caps; - vm_enable_cap(vm, &cap); -#endif - /* Add an extra memory slot for testing dirty logging */ vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, guest_test_phys_mem, @@ -362,11 +467,8 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations, while (iteration < iterations) { /* Give the vcpu thread some time to dirty some pages */ usleep(interval * 1000); - kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap); -#ifdef USE_CLEAR_DIRTY_LOG - kvm_vm_clear_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap, 0, - host_num_pages); -#endif + log_mode_collect_dirty_pages(vm, TEST_MEM_SLOT_INDEX, + bmap, host_num_pages); vm_dirty_log_verify(mode, bmap); iteration++; sync_global_to_guest(vm, iteration); @@ -410,6 +512,9 @@ static void help(char *name) TEST_HOST_LOOP_INTERVAL); printf(" -p: specify guest physical test memory offset\n" " Warning: a low offset can conflict with the loaded test code.\n"); + printf(" -M: specify the host logging mode " + "(default: run all log modes). Supported modes: \n\t"); + log_modes_dump(); printf(" -m: specify the guest mode ID to test " "(default: test all supported modes)\n" " This option may be used multiple times.\n" @@ -429,18 +534,7 @@ int main(int argc, char *argv[]) bool mode_selected = false; uint64_t phys_offset = 0; unsigned int mode; - int opt, i; - -#ifdef USE_CLEAR_DIRTY_LOG - dirty_log_manual_caps = - kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2); - if (!dirty_log_manual_caps) { - print_skip("KVM_CLEAR_DIRTY_LOG not available"); - exit(KSFT_SKIP); - } - dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | - KVM_DIRTY_LOG_INITIALLY_SET); -#endif + int opt, i, j; #ifdef __x86_64__ guest_mode_init(VM_MODE_PXXV48_4K, true, true); @@ -464,7 +558,7 @@ int main(int argc, char *argv[]) guest_mode_init(VM_MODE_P40V48_4K, true, true); #endif - while ((opt = getopt(argc, argv, "hi:I:p:m:")) != -1) { + while ((opt = getopt(argc, argv, "hi:I:p:m:M:")) != -1) { switch (opt) { case 'i': iterations = strtol(optarg, NULL, 10); @@ -486,6 +580,26 @@ int main(int argc, char *argv[]) "Guest mode ID %d too big", mode); guest_modes[mode].enabled = true; break; + case 'M': + if (!strcmp(optarg, "all")) { + host_log_mode_option = LOG_MODE_ALL; + break; + } + for (i = 0; i < LOG_MODE_NUM; i++) { + if (!strcmp(optarg, log_modes[i].name)) { + pr_info("Setting log mode to: '%s'\n", + optarg); + host_log_mode_option = i; + break; + } + } + if (i == LOG_MODE_NUM) { + printf("Log mode '%s' invalid. Please choose " + "from: ", optarg); + log_modes_dump(); + exit(1); + } + break; case 'h': default: help(argv[0]); @@ -507,7 +621,18 @@ int main(int argc, char *argv[]) TEST_ASSERT(guest_modes[i].supported, "Guest mode ID %d (%s) not supported.", i, vm_guest_mode_string(i)); - run_test(i, iterations, interval, phys_offset); + if (host_log_mode_option == LOG_MODE_ALL) { + /* Run each log mode */ + for (j = 0; j < LOG_MODE_NUM; j++) { + pr_info("Testing Log Mode '%s'\n", + log_modes[j].name); + host_log_mode = j; + run_test(i, iterations, interval, phys_offset); + } + } else { + host_log_mode = host_log_mode_option; + run_test(i, iterations, interval, phys_offset); + } } return 0; diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index 919e161dd289..7d29aa786959 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -63,9 +63,11 @@ enum vm_mem_backing_src_type { int kvm_check_cap(long cap); int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap); +int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id, + struct kvm_enable_cap *cap); +void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size); struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm); -struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm); void kvm_vm_free(struct kvm_vm *vmp); void kvm_vm_restart(struct kvm_vm *vmp, int perm); void kvm_vm_release(struct kvm_vm *vmp); @@ -149,6 +151,7 @@ void vcpu_set_guest_debug(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_guest_debug *debug); void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_mp_state *mp_state); +struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vm *vm, uint32_t vcpuid); void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs); void vcpu_regs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs); @@ -294,6 +297,8 @@ int vm_create_device(struct kvm_vm *vm, struct kvm_create_device *cd); memcpy(&(g), _p, sizeof(g)); \ }) +void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid); + /* Common ucalls */ enum { UCALL_NONE, diff --git a/tools/testing/selftests/kvm/include/perf_test_util.h b/tools/testing/selftests/kvm/include/perf_test_util.h new file mode 100644 index 000000000000..2618052057b1 --- /dev/null +++ b/tools/testing/selftests/kvm/include/perf_test_util.h @@ -0,0 +1,198 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * tools/testing/selftests/kvm/include/perf_test_util.h + * + * Copyright (C) 2020, Google LLC. + */ + +#ifndef SELFTEST_KVM_PERF_TEST_UTIL_H +#define SELFTEST_KVM_PERF_TEST_UTIL_H + +#include "kvm_util.h" +#include "processor.h" + +#define MAX_VCPUS 512 + +#define PAGE_SHIFT_4K 12 +#define PTES_PER_4K_PT 512 + +#define TEST_MEM_SLOT_INDEX 1 + +/* Default guest test virtual memory offset */ +#define DEFAULT_GUEST_TEST_MEM 0xc0000000 + +#define DEFAULT_PER_VCPU_MEM_SIZE (1 << 30) /* 1G */ + +/* + * Guest physical memory offset of the testing memory slot. + * This will be set to the topmost valid physical address minus + * the test memory size. + */ +static uint64_t guest_test_phys_mem; + +/* + * Guest virtual memory offset of the testing memory slot. + * Must not conflict with identity mapped test code. + */ +static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM; +static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE; + +/* Number of VCPUs for the test */ +static int nr_vcpus = 1; + +struct vcpu_args { + uint64_t gva; + uint64_t pages; + + /* Only used by the host userspace part of the vCPU thread */ + int vcpu_id; +}; + +struct perf_test_args { + struct kvm_vm *vm; + uint64_t host_page_size; + uint64_t guest_page_size; + int wr_fract; + + struct vcpu_args vcpu_args[MAX_VCPUS]; +}; + +static struct perf_test_args perf_test_args; + +/* + * Continuously write to the first 8 bytes of each page in the + * specified region. + */ +static void guest_code(uint32_t vcpu_id) +{ + struct vcpu_args *vcpu_args = &perf_test_args.vcpu_args[vcpu_id]; + uint64_t gva; + uint64_t pages; + int i; + + /* Make sure vCPU args data structure is not corrupt. */ + GUEST_ASSERT(vcpu_args->vcpu_id == vcpu_id); + + gva = vcpu_args->gva; + pages = vcpu_args->pages; + + while (true) { + for (i = 0; i < pages; i++) { + uint64_t addr = gva + (i * perf_test_args.guest_page_size); + + if (i % perf_test_args.wr_fract == 0) + *(uint64_t *)addr = 0x0123456789ABCDEF; + else + READ_ONCE(*(uint64_t *)addr); + } + + GUEST_SYNC(1); + } +} + +static struct kvm_vm *create_vm(enum vm_guest_mode mode, int vcpus, + uint64_t vcpu_memory_bytes) +{ + struct kvm_vm *vm; + uint64_t pages = DEFAULT_GUEST_PHY_PAGES; + uint64_t guest_num_pages; + + /* Account for a few pages per-vCPU for stacks */ + pages += DEFAULT_STACK_PGS * vcpus; + + /* + * Reserve twice the ammount of memory needed to map the test region and + * the page table / stacks region, at 4k, for page tables. Do the + * calculation with 4K page size: the smallest of all archs. (e.g., 64K + * page size guest will need even less memory for page tables). + */ + pages += (2 * pages) / PTES_PER_4K_PT; + pages += ((2 * vcpus * vcpu_memory_bytes) >> PAGE_SHIFT_4K) / + PTES_PER_4K_PT; + pages = vm_adjust_num_guest_pages(mode, pages); + + pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode)); + + vm = vm_create(mode, pages, O_RDWR); + kvm_vm_elf_load(vm, program_invocation_name, 0, 0); +#ifdef __x86_64__ + vm_create_irqchip(vm); +#endif + + perf_test_args.vm = vm; + perf_test_args.guest_page_size = vm_get_page_size(vm); + perf_test_args.host_page_size = getpagesize(); + + TEST_ASSERT(vcpu_memory_bytes % perf_test_args.guest_page_size == 0, + "Guest memory size is not guest page size aligned."); + + guest_num_pages = (vcpus * vcpu_memory_bytes) / + perf_test_args.guest_page_size; + guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages); + + /* + * If there should be more memory in the guest test region than there + * can be pages in the guest, it will definitely cause problems. + */ + TEST_ASSERT(guest_num_pages < vm_get_max_gfn(vm), + "Requested more guest memory than address space allows.\n" + " guest pages: %lx max gfn: %x vcpus: %d wss: %lx]\n", + guest_num_pages, vm_get_max_gfn(vm), vcpus, + vcpu_memory_bytes); + + TEST_ASSERT(vcpu_memory_bytes % perf_test_args.host_page_size == 0, + "Guest memory size is not host page size aligned."); + + guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) * + perf_test_args.guest_page_size; + guest_test_phys_mem &= ~(perf_test_args.host_page_size - 1); + +#ifdef __s390x__ + /* Align to 1M (segment size) */ + guest_test_phys_mem &= ~((1 << 20) - 1); +#endif + + pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem); + + /* Add an extra memory slot for testing */ + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, + guest_test_phys_mem, + TEST_MEM_SLOT_INDEX, + guest_num_pages, 0); + + /* Do mapping for the demand paging memory slot */ + virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages, 0); + + ucall_init(vm, NULL); + + return vm; +} + +static void add_vcpus(struct kvm_vm *vm, int vcpus, uint64_t vcpu_memory_bytes) +{ + vm_paddr_t vcpu_gpa; + struct vcpu_args *vcpu_args; + int vcpu_id; + + for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) { + vcpu_args = &perf_test_args.vcpu_args[vcpu_id]; + + vm_vcpu_add_default(vm, vcpu_id, guest_code); + +#ifdef __x86_64__ + vcpu_set_cpuid(vm, vcpu_id, kvm_get_supported_cpuid()); +#endif + + vcpu_args->vcpu_id = vcpu_id; + vcpu_args->gva = guest_test_virt_mem + + (vcpu_id * vcpu_memory_bytes); + vcpu_args->pages = vcpu_memory_bytes / + perf_test_args.guest_page_size; + + vcpu_gpa = guest_test_phys_mem + (vcpu_id * vcpu_memory_bytes); + pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n", + vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_memory_bytes); + } +} + +#endif /* SELFTEST_KVM_PERF_TEST_UTIL_H */ diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index 5eb01bf51b86..ffffa560436b 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -64,5 +64,7 @@ int64_t timespec_to_ns(struct timespec ts); struct timespec timespec_add_ns(struct timespec ts, int64_t ns); struct timespec timespec_add(struct timespec ts1, struct timespec ts2); struct timespec timespec_sub(struct timespec ts1, struct timespec ts2); +struct timespec timespec_diff_now(struct timespec start); +struct timespec timespec_div(struct timespec ts, int divisor); #endif /* SELFTEST_KVM_TEST_UTIL_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 82b7fe16a824..8e61340b3911 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -36,6 +36,8 @@ #define X86_CR4_SMAP (1ul << 21) #define X86_CR4_PKE (1ul << 22) +#define UNEXPECTED_VECTOR_PORT 0xfff0u + /* General Registers in 64-Bit Mode */ struct gpr64_regs { u64 rax; @@ -59,7 +61,7 @@ struct gpr64_regs { struct desc64 { uint16_t limit0; uint16_t base0; - unsigned base1:8, s:1, type:4, dpl:2, p:1; + unsigned base1:8, type:4, s:1, dpl:2, p:1; unsigned limit1:4, avl:1, l:1, db:1, g:1, base2:8; uint32_t base3; uint32_t zero1; @@ -239,6 +241,11 @@ static inline struct desc_ptr get_idt(void) return idt; } +static inline void outl(uint16_t port, uint32_t value) +{ + __asm__ __volatile__("outl %%eax, %%dx" : : "d"(port), "a"(value)); +} + #define SET_XMM(__var, __xmm) \ asm volatile("movq %0, %%"#__xmm : : "r"(__var) : #__xmm) @@ -338,6 +345,35 @@ uint32_t kvm_get_cpuid_max_basic(void); uint32_t kvm_get_cpuid_max_extended(void); void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits); +struct ex_regs { + uint64_t rax, rcx, rdx, rbx; + uint64_t rbp, rsi, rdi; + uint64_t r8, r9, r10, r11; + uint64_t r12, r13, r14, r15; + uint64_t vector; + uint64_t error_code; + uint64_t rip; + uint64_t cs; + uint64_t rflags; +}; + +void vm_init_descriptor_tables(struct kvm_vm *vm); +void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid); +void vm_handle_exception(struct kvm_vm *vm, int vector, + void (*handler)(struct ex_regs *)); + +/* + * set_cpuid() - overwrites a matching cpuid entry with the provided value. + * matches based on ent->function && ent->index. returns true + * if a match was found and successfully overwritten. + * @cpuid: the kvm cpuid list to modify. + * @ent: cpuid entry to insert + */ +bool set_cpuid(struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 *ent); + +uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2, + uint64_t a3); + /* * Basic CPU control in CR0 */ diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c index 2afa6618b396..d6c32c328e9a 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/processor.c +++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c @@ -350,3 +350,7 @@ void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...) va_end(ap); } + +void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid) +{ +} diff --git a/tools/testing/selftests/kvm/lib/aarch64/ucall.c b/tools/testing/selftests/kvm/lib/aarch64/ucall.c index c8e0ec20d3bf..2f37b90ee1a9 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/ucall.c +++ b/tools/testing/selftests/kvm/lib/aarch64/ucall.c @@ -94,6 +94,9 @@ uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc) struct kvm_run *run = vcpu_state(vm, vcpu_id); struct ucall ucall = {}; + if (uc) + memset(uc, 0, sizeof(*uc)); + if (run->exit_reason == KVM_EXIT_MMIO && run->mmio.phys_addr == (uint64_t)ucall_exit_mmio_addr) { vm_vaddr_t gva; diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 3327cebc1095..126c6727a6b0 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -86,6 +86,34 @@ int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap) return ret; } +/* VCPU Enable Capability + * + * Input Args: + * vm - Virtual Machine + * vcpu_id - VCPU + * cap - Capability + * + * Output Args: None + * + * Return: On success, 0. On failure a TEST_ASSERT failure is produced. + * + * Enables a capability (KVM_CAP_*) on the VCPU. + */ +int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id, + struct kvm_enable_cap *cap) +{ + struct vcpu *vcpu = vcpu_find(vm, vcpu_id); + int r; + + TEST_ASSERT(vcpu, "cannot find vcpu %d", vcpu_id); + + r = ioctl(vcpu->fd, KVM_ENABLE_CAP, cap); + TEST_ASSERT(!r, "KVM_ENABLE_CAP vCPU ioctl failed,\n" + " rc: %i, errno: %i", r, errno); + + return r; +} + static void vm_open(struct kvm_vm *vm, int perm) { vm->kvm_fd = open(KVM_DEV_PATH, perm); @@ -152,7 +180,7 @@ _Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) * descriptor to control the created VM is created with the permissions * given by perm (e.g. O_RDWR). */ -struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) +struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) { struct kvm_vm *vm; @@ -243,11 +271,6 @@ struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) return vm; } -struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) -{ - return _vm_create(mode, phy_pages, perm); -} - /* * VM Restart * @@ -1204,6 +1227,9 @@ int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid) do { rc = ioctl(vcpu->fd, KVM_RUN, NULL); } while (rc == -1 && errno == EINTR); + + assert_on_unhandled_exception(vm, vcpuid); + return rc; } @@ -1261,6 +1287,35 @@ void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid, } /* + * VM VCPU Get Reg List + * + * Input Args: + * vm - Virtual Machine + * vcpuid - VCPU ID + * + * Output Args: + * None + * + * Return: + * A pointer to an allocated struct kvm_reg_list + * + * Get the list of guest registers which are supported for + * KVM_GET_ONE_REG/KVM_SET_ONE_REG calls + */ +struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vm *vm, uint32_t vcpuid) +{ + struct kvm_reg_list reg_list_n = { .n = 0 }, *reg_list; + int ret; + + ret = _vcpu_ioctl(vm, vcpuid, KVM_GET_REG_LIST, ®_list_n); + TEST_ASSERT(ret == -1 && errno == E2BIG, "KVM_GET_REG_LIST n=0"); + reg_list = calloc(1, sizeof(*reg_list) + reg_list_n.n * sizeof(__u64)); + reg_list->n = reg_list_n.n; + vcpu_ioctl(vm, vcpuid, KVM_GET_REG_LIST, reg_list); + return reg_list; +} + +/* * VM VCPU Regs Get * * Input Args: diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h index 2ef446520748..f07d383d03a1 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util_internal.h +++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h @@ -50,6 +50,8 @@ struct kvm_vm { vm_paddr_t pgd; vm_vaddr_t gdt; vm_vaddr_t tss; + vm_vaddr_t idt; + vm_vaddr_t handlers; }; struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid); diff --git a/tools/testing/selftests/kvm/lib/s390x/processor.c b/tools/testing/selftests/kvm/lib/s390x/processor.c index a88c5d665725..7349bb2e1a24 100644 --- a/tools/testing/selftests/kvm/lib/s390x/processor.c +++ b/tools/testing/selftests/kvm/lib/s390x/processor.c @@ -241,3 +241,7 @@ void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent) fprintf(stream, "%*spstate: psw: 0x%.16llx:0x%.16llx\n", indent, "", vcpu->state->psw_mask, vcpu->state->psw_addr); } + +void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid) +{ +} diff --git a/tools/testing/selftests/kvm/lib/s390x/ucall.c b/tools/testing/selftests/kvm/lib/s390x/ucall.c index fd589dc9bfab..9d3b0f15249a 100644 --- a/tools/testing/selftests/kvm/lib/s390x/ucall.c +++ b/tools/testing/selftests/kvm/lib/s390x/ucall.c @@ -38,6 +38,9 @@ uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc) struct kvm_run *run = vcpu_state(vm, vcpu_id); struct ucall ucall = {}; + if (uc) + memset(uc, 0, sizeof(*uc)); + if (run->exit_reason == KVM_EXIT_S390_SIEIC && run->s390_sieic.icptcode == 4 && (run->s390_sieic.ipa >> 8) == 0x83 && /* 0x83 means DIAGNOSE */ diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c index 689e97c27ee2..8e04c0b1608e 100644 --- a/tools/testing/selftests/kvm/lib/test_util.c +++ b/tools/testing/selftests/kvm/lib/test_util.c @@ -4,10 +4,13 @@ * * Copyright (C) 2020, Google LLC. */ -#include <stdlib.h> + +#include <assert.h> #include <ctype.h> #include <limits.h> -#include <assert.h> +#include <stdlib.h> +#include <time.h> + #include "test_util.h" /* @@ -81,6 +84,21 @@ struct timespec timespec_sub(struct timespec ts1, struct timespec ts2) return timespec_add_ns((struct timespec){0}, ns1 - ns2); } +struct timespec timespec_diff_now(struct timespec start) +{ + struct timespec end; + + clock_gettime(CLOCK_MONOTONIC, &end); + return timespec_sub(end, start); +} + +struct timespec timespec_div(struct timespec ts, int divisor) +{ + int64_t ns = timespec_to_ns(ts) / divisor; + + return timespec_add_ns((struct timespec){0}, ns); +} + void print_skip(const char *fmt, ...) { va_list ap; diff --git a/tools/testing/selftests/kvm/lib/x86_64/handlers.S b/tools/testing/selftests/kvm/lib/x86_64/handlers.S new file mode 100644 index 000000000000..aaf7bc7d2ce1 --- /dev/null +++ b/tools/testing/selftests/kvm/lib/x86_64/handlers.S @@ -0,0 +1,81 @@ +handle_exception: + push %r15 + push %r14 + push %r13 + push %r12 + push %r11 + push %r10 + push %r9 + push %r8 + + push %rdi + push %rsi + push %rbp + push %rbx + push %rdx + push %rcx + push %rax + mov %rsp, %rdi + + call route_exception + + pop %rax + pop %rcx + pop %rdx + pop %rbx + pop %rbp + pop %rsi + pop %rdi + pop %r8 + pop %r9 + pop %r10 + pop %r11 + pop %r12 + pop %r13 + pop %r14 + pop %r15 + + /* Discard vector and error code. */ + add $16, %rsp + iretq + +/* + * Build the handle_exception wrappers which push the vector/error code on the + * stack and an array of pointers to those wrappers. + */ +.pushsection .rodata +.globl idt_handlers +idt_handlers: +.popsection + +.macro HANDLERS has_error from to + vector = \from + .rept \to - \from + 1 + .align 8 + + /* Fetch current address and append it to idt_handlers. */ + current_handler = . +.pushsection .rodata +.quad current_handler +.popsection + + .if ! \has_error + pushq $0 + .endif + pushq $vector + jmp handle_exception + vector = vector + 1 + .endr +.endm + +.global idt_handler_code +idt_handler_code: + HANDLERS has_error=0 from=0 to=7 + HANDLERS has_error=1 from=8 to=8 + HANDLERS has_error=0 from=9 to=9 + HANDLERS has_error=1 from=10 to=14 + HANDLERS has_error=0 from=15 to=16 + HANDLERS has_error=1 from=17 to=17 + HANDLERS has_error=0 from=18 to=255 + +.section .note.GNU-stack, "", %progbits diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index f6eb34eaa0d2..d10c5c05bdf0 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -12,9 +12,18 @@ #include "../kvm_util_internal.h" #include "processor.h" +#ifndef NUM_INTERRUPTS +#define NUM_INTERRUPTS 256 +#endif + +#define DEFAULT_CODE_SELECTOR 0x8 +#define DEFAULT_DATA_SELECTOR 0x10 + /* Minimum physical address used for virtual translation tables. */ #define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000 +vm_vaddr_t exception_handlers; + /* Virtual translation table structure declarations */ struct pageMapL4Entry { uint64_t present:1; @@ -392,11 +401,12 @@ static void kvm_seg_fill_gdt_64bit(struct kvm_vm *vm, struct kvm_segment *segp) desc->limit0 = segp->limit & 0xFFFF; desc->base0 = segp->base & 0xFFFF; desc->base1 = segp->base >> 16; - desc->s = segp->s; desc->type = segp->type; + desc->s = segp->s; desc->dpl = segp->dpl; desc->p = segp->present; desc->limit1 = segp->limit >> 16; + desc->avl = segp->avl; desc->l = segp->l; desc->db = segp->db; desc->g = segp->g; @@ -556,9 +566,9 @@ static void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_m sregs.efer |= (EFER_LME | EFER_LMA | EFER_NX); kvm_seg_set_unusable(&sregs.ldt); - kvm_seg_set_kernel_code_64bit(vm, 0x8, &sregs.cs); - kvm_seg_set_kernel_data_64bit(vm, 0x10, &sregs.ds); - kvm_seg_set_kernel_data_64bit(vm, 0x10, &sregs.es); + kvm_seg_set_kernel_code_64bit(vm, DEFAULT_CODE_SELECTOR, &sregs.cs); + kvm_seg_set_kernel_data_64bit(vm, DEFAULT_DATA_SELECTOR, &sregs.ds); + kvm_seg_set_kernel_data_64bit(vm, DEFAULT_DATA_SELECTOR, &sregs.es); kvm_setup_tss_64bit(vm, &sregs.tr, 0x18, gdt_memslot, pgd_memslot); break; @@ -1118,3 +1128,131 @@ void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits) *va_bits = (entry->eax >> 8) & 0xff; } } + +struct idt_entry { + uint16_t offset0; + uint16_t selector; + uint16_t ist : 3; + uint16_t : 5; + uint16_t type : 4; + uint16_t : 1; + uint16_t dpl : 2; + uint16_t p : 1; + uint16_t offset1; + uint32_t offset2; uint32_t reserved; +}; + +static void set_idt_entry(struct kvm_vm *vm, int vector, unsigned long addr, + int dpl, unsigned short selector) +{ + struct idt_entry *base = + (struct idt_entry *)addr_gva2hva(vm, vm->idt); + struct idt_entry *e = &base[vector]; + + memset(e, 0, sizeof(*e)); + e->offset0 = addr; + e->selector = selector; + e->ist = 0; + e->type = 14; + e->dpl = dpl; + e->p = 1; + e->offset1 = addr >> 16; + e->offset2 = addr >> 32; +} + +void kvm_exit_unexpected_vector(uint32_t value) +{ + outl(UNEXPECTED_VECTOR_PORT, value); +} + +void route_exception(struct ex_regs *regs) +{ + typedef void(*handler)(struct ex_regs *); + handler *handlers = (handler *)exception_handlers; + + if (handlers && handlers[regs->vector]) { + handlers[regs->vector](regs); + return; + } + + kvm_exit_unexpected_vector(regs->vector); +} + +void vm_init_descriptor_tables(struct kvm_vm *vm) +{ + extern void *idt_handlers; + int i; + + vm->idt = vm_vaddr_alloc(vm, getpagesize(), 0x2000, 0, 0); + vm->handlers = vm_vaddr_alloc(vm, 256 * sizeof(void *), 0x2000, 0, 0); + /* Handlers have the same address in both address spaces.*/ + for (i = 0; i < NUM_INTERRUPTS; i++) + set_idt_entry(vm, i, (unsigned long)(&idt_handlers)[i], 0, + DEFAULT_CODE_SELECTOR); +} + +void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid) +{ + struct kvm_sregs sregs; + + vcpu_sregs_get(vm, vcpuid, &sregs); + sregs.idt.base = vm->idt; + sregs.idt.limit = NUM_INTERRUPTS * sizeof(struct idt_entry) - 1; + sregs.gdt.base = vm->gdt; + sregs.gdt.limit = getpagesize() - 1; + kvm_seg_set_kernel_data_64bit(NULL, DEFAULT_DATA_SELECTOR, &sregs.gs); + vcpu_sregs_set(vm, vcpuid, &sregs); + *(vm_vaddr_t *)addr_gva2hva(vm, (vm_vaddr_t)(&exception_handlers)) = vm->handlers; +} + +void vm_handle_exception(struct kvm_vm *vm, int vector, + void (*handler)(struct ex_regs *)) +{ + vm_vaddr_t *handlers = (vm_vaddr_t *)addr_gva2hva(vm, vm->handlers); + + handlers[vector] = (vm_vaddr_t)handler; +} + +void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid) +{ + if (vcpu_state(vm, vcpuid)->exit_reason == KVM_EXIT_IO + && vcpu_state(vm, vcpuid)->io.port == UNEXPECTED_VECTOR_PORT + && vcpu_state(vm, vcpuid)->io.size == 4) { + /* Grab pointer to io data */ + uint32_t *data = (void *)vcpu_state(vm, vcpuid) + + vcpu_state(vm, vcpuid)->io.data_offset; + + TEST_ASSERT(false, + "Unexpected vectored event in guest (vector:0x%x)", + *data); + } +} + +bool set_cpuid(struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 *ent) +{ + int i; + + for (i = 0; i < cpuid->nent; i++) { + struct kvm_cpuid_entry2 *cur = &cpuid->entries[i]; + + if (cur->function != ent->function || cur->index != ent->index) + continue; + + memcpy(cur, ent, sizeof(struct kvm_cpuid_entry2)); + return true; + } + + return false; +} + +uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2, + uint64_t a3) +{ + uint64_t r; + + asm volatile("vmcall" + : "=a"(r) + : "b"(a0), "c"(a1), "d"(a2), "S"(a3)); + return r; +} diff --git a/tools/testing/selftests/kvm/lib/x86_64/ucall.c b/tools/testing/selftests/kvm/lib/x86_64/ucall.c index da4d89ad5419..a3489973e290 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/ucall.c +++ b/tools/testing/selftests/kvm/lib/x86_64/ucall.c @@ -40,6 +40,9 @@ uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc) struct kvm_run *run = vcpu_state(vm, vcpu_id); struct ucall ucall = {}; + if (uc) + memset(uc, 0, sizeof(*uc)); + if (run->exit_reason == KVM_EXIT_IO && run->io.port == UCALL_PIO_PORT) { struct kvm_regs regs; diff --git a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c new file mode 100644 index 000000000000..b10a27485bad --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c @@ -0,0 +1,234 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020, Google LLC. + * + * Tests for KVM paravirtual feature disablement + */ +#include <asm/kvm_para.h> +#include <linux/kvm_para.h> +#include <stdint.h> + +#include "test_util.h" +#include "kvm_util.h" +#include "processor.h" + +extern unsigned char rdmsr_start; +extern unsigned char rdmsr_end; + +static u64 do_rdmsr(u32 idx) +{ + u32 lo, hi; + + asm volatile("rdmsr_start: rdmsr;" + "rdmsr_end:" + : "=a"(lo), "=c"(hi) + : "c"(idx)); + + return (((u64) hi) << 32) | lo; +} + +extern unsigned char wrmsr_start; +extern unsigned char wrmsr_end; + +static void do_wrmsr(u32 idx, u64 val) +{ + u32 lo, hi; + + lo = val; + hi = val >> 32; + + asm volatile("wrmsr_start: wrmsr;" + "wrmsr_end:" + : : "a"(lo), "c"(idx), "d"(hi)); +} + +static int nr_gp; + +static void guest_gp_handler(struct ex_regs *regs) +{ + unsigned char *rip = (unsigned char *)regs->rip; + bool r, w; + + r = rip == &rdmsr_start; + w = rip == &wrmsr_start; + GUEST_ASSERT(r || w); + + nr_gp++; + + if (r) + regs->rip = (uint64_t)&rdmsr_end; + else + regs->rip = (uint64_t)&wrmsr_end; +} + +struct msr_data { + uint32_t idx; + const char *name; +}; + +#define TEST_MSR(msr) { .idx = msr, .name = #msr } +#define UCALL_PR_MSR 0xdeadbeef +#define PR_MSR(msr) ucall(UCALL_PR_MSR, 1, msr) + +/* + * KVM paravirtual msrs to test. Expect a #GP if any of these msrs are read or + * written, as the KVM_CPUID_FEATURES leaf is cleared. + */ +static struct msr_data msrs_to_test[] = { + TEST_MSR(MSR_KVM_SYSTEM_TIME), + TEST_MSR(MSR_KVM_SYSTEM_TIME_NEW), + TEST_MSR(MSR_KVM_WALL_CLOCK), + TEST_MSR(MSR_KVM_WALL_CLOCK_NEW), + TEST_MSR(MSR_KVM_ASYNC_PF_EN), + TEST_MSR(MSR_KVM_STEAL_TIME), + TEST_MSR(MSR_KVM_PV_EOI_EN), + TEST_MSR(MSR_KVM_POLL_CONTROL), + TEST_MSR(MSR_KVM_ASYNC_PF_INT), + TEST_MSR(MSR_KVM_ASYNC_PF_ACK), +}; + +static void test_msr(struct msr_data *msr) +{ + PR_MSR(msr); + do_rdmsr(msr->idx); + GUEST_ASSERT(READ_ONCE(nr_gp) == 1); + + nr_gp = 0; + do_wrmsr(msr->idx, 0); + GUEST_ASSERT(READ_ONCE(nr_gp) == 1); + nr_gp = 0; +} + +struct hcall_data { + uint64_t nr; + const char *name; +}; + +#define TEST_HCALL(hc) { .nr = hc, .name = #hc } +#define UCALL_PR_HCALL 0xdeadc0de +#define PR_HCALL(hc) ucall(UCALL_PR_HCALL, 1, hc) + +/* + * KVM hypercalls to test. Expect -KVM_ENOSYS when called, as the corresponding + * features have been cleared in KVM_CPUID_FEATURES. + */ +static struct hcall_data hcalls_to_test[] = { + TEST_HCALL(KVM_HC_KICK_CPU), + TEST_HCALL(KVM_HC_SEND_IPI), + TEST_HCALL(KVM_HC_SCHED_YIELD), +}; + +static void test_hcall(struct hcall_data *hc) +{ + uint64_t r; + + PR_HCALL(hc); + r = kvm_hypercall(hc->nr, 0, 0, 0, 0); + GUEST_ASSERT(r == -KVM_ENOSYS); +} + +static void guest_main(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(msrs_to_test); i++) { + test_msr(&msrs_to_test[i]); + } + + for (i = 0; i < ARRAY_SIZE(hcalls_to_test); i++) { + test_hcall(&hcalls_to_test[i]); + } + + GUEST_DONE(); +} + +static void clear_kvm_cpuid_features(struct kvm_cpuid2 *cpuid) +{ + struct kvm_cpuid_entry2 ent = {0}; + + ent.function = KVM_CPUID_FEATURES; + TEST_ASSERT(set_cpuid(cpuid, &ent), + "failed to clear KVM_CPUID_FEATURES leaf"); +} + +static void pr_msr(struct ucall *uc) +{ + struct msr_data *msr = (struct msr_data *)uc->args[0]; + + pr_info("testing msr: %s (%#x)\n", msr->name, msr->idx); +} + +static void pr_hcall(struct ucall *uc) +{ + struct hcall_data *hc = (struct hcall_data *)uc->args[0]; + + pr_info("testing hcall: %s (%lu)\n", hc->name, hc->nr); +} + +static void handle_abort(struct ucall *uc) +{ + TEST_FAIL("%s at %s:%ld", (const char *)uc->args[0], + __FILE__, uc->args[1]); +} + +#define VCPU_ID 0 + +static void enter_guest(struct kvm_vm *vm) +{ + struct kvm_run *run; + struct ucall uc; + int r; + + run = vcpu_state(vm, VCPU_ID); + + while (true) { + r = _vcpu_run(vm, VCPU_ID); + TEST_ASSERT(!r, "vcpu_run failed: %d\n", r); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "unexpected exit reason: %u (%s)", + run->exit_reason, exit_reason_str(run->exit_reason)); + + switch (get_ucall(vm, VCPU_ID, &uc)) { + case UCALL_PR_MSR: + pr_msr(&uc); + break; + case UCALL_PR_HCALL: + pr_hcall(&uc); + break; + case UCALL_ABORT: + handle_abort(&uc); + return; + case UCALL_DONE: + return; + } + } +} + +int main(void) +{ + struct kvm_enable_cap cap = {0}; + struct kvm_cpuid2 *best; + struct kvm_vm *vm; + + if (!kvm_check_cap(KVM_CAP_ENFORCE_PV_FEATURE_CPUID)) { + pr_info("will skip kvm paravirt restriction tests.\n"); + return 0; + } + + vm = vm_create_default(VCPU_ID, 0, guest_main); + + cap.cap = KVM_CAP_ENFORCE_PV_FEATURE_CPUID; + cap.args[0] = 1; + vcpu_enable_cap(vm, VCPU_ID, &cap); + + best = kvm_get_supported_cpuid(); + clear_kvm_cpuid_features(best); + vcpu_set_cpuid(vm, VCPU_ID, best); + + vm_init_descriptor_tables(vm); + vcpu_init_descriptor_tables(vm, VCPU_ID); + vm_handle_exception(vm, GP_VECTOR, guest_gp_handler); + + enter_guest(vm); + kvm_vm_free(vm); +} diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json index bb543bf69d69..361235ad574b 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json @@ -100,7 +100,7 @@ ], "cmdUnderTest": "$TC filter add dev $DEV2 protocol ip pref 1 ingress flower dst_mac e4:11:22:11:4a:51 action drop", "expExitCode": "0", - "verifyCmd": "$TC filter show terse dev $DEV2 ingress", + "verifyCmd": "$TC -br filter show dev $DEV2 ingress", "matchPattern": "filter protocol ip pref 1 flower.*handle", "matchCount": "1", "teardown": [ @@ -119,7 +119,7 @@ ], "cmdUnderTest": "$TC filter add dev $DEV2 protocol ip pref 1 ingress flower dst_mac e4:11:22:11:4a:51 action drop", "expExitCode": "0", - "verifyCmd": "$TC filter show terse dev $DEV2 ingress", + "verifyCmd": "$TC -br filter show dev $DEV2 ingress", "matchPattern": " dst_mac e4:11:22:11:4a:51", "matchCount": "0", "teardown": [ |