diff options
637 files changed, 8913 insertions, 4365 deletions
diff --git a/Documentation/CodeOfConflict b/Documentation/CodeOfConflict new file mode 100644 index 000000000000..1684d0b4efa6 --- /dev/null +++ b/Documentation/CodeOfConflict @@ -0,0 +1,27 @@ +Code of Conflict +---------------- + +The Linux kernel development effort is a very personal process compared +to "traditional" ways of developing software. Your code and ideas +behind it will be carefully reviewed, often resulting in critique and +criticism. The review will almost always require improvements to the +code before it can be included in the kernel. Know that this happens +because everyone involved wants to see the best possible solution for +the overall success of Linux. This development process has been proven +to create the most robust operating system kernel ever, and we do not +want to do anything to cause the quality of submission and eventual +result to ever decrease. + +If however, anyone feels personally abused, threatened, or otherwise +uncomfortable due to this process, that is not acceptable. If so, +please contact the Linux Foundation's Technical Advisory Board at +<tab@lists.linux-foundation.org>, or the individual members, and they +will work to resolve the issue to the best of their ability. For more +information on who is on the Technical Advisory Board and what their +role is, please see: + http://www.linuxfoundation.org/programs/advisory-councils/tab + +As a reviewer of code, please strive to keep things civil and focused on +the technical issues involved. We are all humans, and frustrations can +be high on both sides of the process. Try to keep in mind the immortal +words of Bill and Ted, "Be excellent to each other." diff --git a/Documentation/cgroups/unified-hierarchy.txt b/Documentation/cgroups/unified-hierarchy.txt index 71daa35ec2d9..eb102fb72213 100644 --- a/Documentation/cgroups/unified-hierarchy.txt +++ b/Documentation/cgroups/unified-hierarchy.txt @@ -404,8 +404,8 @@ supported and the interface files "release_agent" and be understood as an underflow into the highest possible value, -2 or -10M etc. do not work, so it's not consistent. - memory.low, memory.high, and memory.max will use the string - "infinity" to indicate and set the highest possible value. + memory.low, memory.high, and memory.max will use the string "max" to + indicate and set the highest possible value. 5. Planned Changes diff --git a/Documentation/devicetree/bindings/i2c/i2c-imx.txt b/Documentation/devicetree/bindings/i2c/i2c-imx.txt index 52d37fd8d3e5..ce4311d726ae 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-imx.txt +++ b/Documentation/devicetree/bindings/i2c/i2c-imx.txt @@ -7,6 +7,7 @@ Required properties: - "fsl,vf610-i2c" for I2C compatible with the one integrated on Vybrid vf610 SoC - reg : Should contain I2C/HS-I2C registers location and length - interrupts : Should contain I2C/HS-I2C interrupt +- clocks : Should contain the I2C/HS-I2C clock specifier Optional properties: - clock-frequency : Constains desired I2C/HS-I2C bus clock frequency in Hz. diff --git a/Documentation/devicetree/bindings/net/amd-xgbe-phy.txt b/Documentation/devicetree/bindings/net/amd-xgbe-phy.txt index 33df3932168e..8db32384a486 100644 --- a/Documentation/devicetree/bindings/net/amd-xgbe-phy.txt +++ b/Documentation/devicetree/bindings/net/amd-xgbe-phy.txt @@ -27,6 +27,8 @@ property is used. - amd,serdes-cdr-rate: CDR rate speed selection - amd,serdes-pq-skew: PQ (data sampling) skew - amd,serdes-tx-amp: TX amplitude boost +- amd,serdes-dfe-tap-config: DFE taps available to run +- amd,serdes-dfe-tap-enable: DFE taps to enable Example: xgbe_phy@e1240800 { @@ -41,4 +43,6 @@ Example: amd,serdes-cdr-rate = <2>, <2>, <7>; amd,serdes-pq-skew = <10>, <10>, <30>; amd,serdes-tx-amp = <15>, <15>, <10>; + amd,serdes-dfe-tap-config = <3>, <3>, <1>; + amd,serdes-dfe-tap-enable = <0>, <0>, <127>; }; diff --git a/Documentation/devicetree/bindings/net/apm-xgene-enet.txt b/Documentation/devicetree/bindings/net/apm-xgene-enet.txt index cfcc52705ed8..6151999c5dca 100644 --- a/Documentation/devicetree/bindings/net/apm-xgene-enet.txt +++ b/Documentation/devicetree/bindings/net/apm-xgene-enet.txt @@ -4,7 +4,10 @@ Ethernet nodes are defined to describe on-chip ethernet interfaces in APM X-Gene SoC. Required properties for all the ethernet interfaces: -- compatible: Should be "apm,xgene-enet" +- compatible: Should state binding information from the following list, + - "apm,xgene-enet": RGMII based 1G interface + - "apm,xgene1-sgenet": SGMII based 1G interface + - "apm,xgene1-xgenet": XFI based 10G interface - reg: Address and length of the register set for the device. It contains the information of registers in the same order as described by reg-names - reg-names: Should contain the register set names diff --git a/Documentation/devicetree/bindings/serial/snps-dw-apb-uart.txt b/Documentation/devicetree/bindings/serial/snps-dw-apb-uart.txt index 7f76214f728a..289c40ed7470 100644 --- a/Documentation/devicetree/bindings/serial/snps-dw-apb-uart.txt +++ b/Documentation/devicetree/bindings/serial/snps-dw-apb-uart.txt @@ -21,6 +21,18 @@ Optional properties: - reg-io-width : the size (in bytes) of the IO accesses that should be performed on the device. If this property is not present then single byte accesses are used. +- dcd-override : Override the DCD modem status signal. This signal will always + be reported as active instead of being obtained from the modem status + register. Define this if your serial port does not use this pin. +- dsr-override : Override the DTS modem status signal. This signal will always + be reported as active instead of being obtained from the modem status + register. Define this if your serial port does not use this pin. +- cts-override : Override the CTS modem status signal. This signal will always + be reported as active instead of being obtained from the modem status + register. Define this if your serial port does not use this pin. +- ri-override : Override the RI modem status signal. This signal will always be + reported as inactive instead of being obtained from the modem status register. + Define this if your serial port does not use this pin. Example: @@ -31,6 +43,10 @@ Example: interrupts = <10>; reg-shift = <2>; reg-io-width = <4>; + dcd-override; + dsr-override; + cts-override; + ri-override; }; Example with one clock: diff --git a/Documentation/filesystems/dlmfs.txt b/Documentation/filesystems/dlmfs.txt index 1b528b2ad809..fcf4d509d118 100644 --- a/Documentation/filesystems/dlmfs.txt +++ b/Documentation/filesystems/dlmfs.txt @@ -5,8 +5,8 @@ system. dlmfs is built with OCFS2 as it requires most of its infrastructure. -Project web page: http://oss.oracle.com/projects/ocfs2 -Tools web page: http://oss.oracle.com/projects/ocfs2-tools +Project web page: http://ocfs2.wiki.kernel.org +Tools web page: https://github.com/markfasheh/ocfs2-tools OCFS2 mailing lists: http://oss.oracle.com/projects/ocfs2/mailman/ All code copyright 2005 Oracle except when otherwise noted. diff --git a/Documentation/filesystems/ocfs2.txt b/Documentation/filesystems/ocfs2.txt index 28f8c08201e2..4c49e5410595 100644 --- a/Documentation/filesystems/ocfs2.txt +++ b/Documentation/filesystems/ocfs2.txt @@ -8,8 +8,8 @@ also make it attractive for non-clustered use. You'll want to install the ocfs2-tools package in order to at least get "mount.ocfs2" and "ocfs2_hb_ctl". -Project web page: http://oss.oracle.com/projects/ocfs2 -Tools web page: http://oss.oracle.com/projects/ocfs2-tools +Project web page: http://ocfs2.wiki.kernel.org +Tools git tree: https://github.com/markfasheh/ocfs2-tools OCFS2 mailing lists: http://oss.oracle.com/projects/ocfs2/mailman/ All code copyright 2005 Oracle except when otherwise noted. diff --git a/Documentation/power/suspend-and-interrupts.txt b/Documentation/power/suspend-and-interrupts.txt index 2f9c5a5fcb25..8afb29a8604a 100644 --- a/Documentation/power/suspend-and-interrupts.txt +++ b/Documentation/power/suspend-and-interrupts.txt @@ -40,8 +40,10 @@ but also to IPIs and to some other special-purpose interrupts. The IRQF_NO_SUSPEND flag is used to indicate that to the IRQ subsystem when requesting a special-purpose interrupt. It causes suspend_device_irqs() to -leave the corresponding IRQ enabled so as to allow the interrupt to work all -the time as expected. +leave the corresponding IRQ enabled so as to allow the interrupt to work as +expected during the suspend-resume cycle, but does not guarantee that the +interrupt will wake the system from a suspended state -- for such cases it is +necessary to use enable_irq_wake(). Note that the IRQF_NO_SUSPEND flag affects the entire IRQ and not just one user of it. Thus, if the IRQ is shared, all of the interrupt handlers installed @@ -110,8 +112,9 @@ any special interrupt handling logic for it to work. IRQF_NO_SUSPEND and enable_irq_wake() ------------------------------------- -There are no valid reasons to use both enable_irq_wake() and the IRQF_NO_SUSPEND -flag on the same IRQ. +There are very few valid reasons to use both enable_irq_wake() and the +IRQF_NO_SUSPEND flag on the same IRQ, and it is never valid to use both for the +same device. First of all, if the IRQ is not shared, the rules for handling IRQF_NO_SUSPEND interrupts (interrupt handlers are invoked after suspend_device_irqs()) are @@ -120,4 +123,13 @@ handlers are not invoked after suspend_device_irqs()). Second, both enable_irq_wake() and IRQF_NO_SUSPEND apply to entire IRQs and not to individual interrupt handlers, so sharing an IRQ between a system wakeup -interrupt source and an IRQF_NO_SUSPEND interrupt source does not make sense. +interrupt source and an IRQF_NO_SUSPEND interrupt source does not generally +make sense. + +In rare cases an IRQ can be shared between a wakeup device driver and an +IRQF_NO_SUSPEND user. In order for this to be safe, the wakeup device driver +must be able to discern spurious IRQs from genuine wakeup events (signalling +the latter to the core with pm_system_wakeup()), must use enable_irq_wake() to +ensure that the IRQ will function as a wakeup source, and must request the IRQ +with IRQF_COND_SUSPEND to tell the core that it meets these requirements. If +these requirements are not met, it is not valid to use IRQF_COND_SUSPEND. diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 18fb7630e2ad..bc9f6fe44e27 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -997,7 +997,7 @@ for vm-wide capabilities. 4.38 KVM_GET_MP_STATE Capability: KVM_CAP_MP_STATE -Architectures: x86, s390 +Architectures: x86, s390, arm, arm64 Type: vcpu ioctl Parameters: struct kvm_mp_state (out) Returns: 0 on success; -1 on error @@ -1011,7 +1011,7 @@ uniprocessor guests). Possible values are: - - KVM_MP_STATE_RUNNABLE: the vcpu is currently running [x86] + - KVM_MP_STATE_RUNNABLE: the vcpu is currently running [x86,arm/arm64] - KVM_MP_STATE_UNINITIALIZED: the vcpu is an application processor (AP) which has not yet received an INIT signal [x86] - KVM_MP_STATE_INIT_RECEIVED: the vcpu has received an INIT signal, and is @@ -1020,7 +1020,7 @@ Possible values are: is waiting for an interrupt [x86] - KVM_MP_STATE_SIPI_RECEIVED: the vcpu has just received a SIPI (vector accessible via KVM_GET_VCPU_EVENTS) [x86] - - KVM_MP_STATE_STOPPED: the vcpu is stopped [s390] + - KVM_MP_STATE_STOPPED: the vcpu is stopped [s390,arm/arm64] - KVM_MP_STATE_CHECK_STOP: the vcpu is in a special error state [s390] - KVM_MP_STATE_OPERATING: the vcpu is operating (running or halted) [s390] @@ -1031,11 +1031,15 @@ On x86, this ioctl is only useful after KVM_CREATE_IRQCHIP. Without an in-kernel irqchip, the multiprocessing state must be maintained by userspace on these architectures. +For arm/arm64: + +The only states that are valid are KVM_MP_STATE_STOPPED and +KVM_MP_STATE_RUNNABLE which reflect if the vcpu is paused or not. 4.39 KVM_SET_MP_STATE Capability: KVM_CAP_MP_STATE -Architectures: x86, s390 +Architectures: x86, s390, arm, arm64 Type: vcpu ioctl Parameters: struct kvm_mp_state (in) Returns: 0 on success; -1 on error @@ -1047,6 +1051,10 @@ On x86, this ioctl is only useful after KVM_CREATE_IRQCHIP. Without an in-kernel irqchip, the multiprocessing state must be maintained by userspace on these architectures. +For arm/arm64: + +The only states that are valid are KVM_MP_STATE_STOPPED and +KVM_MP_STATE_RUNNABLE which reflect if the vcpu should be paused or not. 4.40 KVM_SET_IDENTITY_MAP_ADDR @@ -1967,15 +1975,25 @@ registers, find a list below: MIPS | KVM_REG_MIPS_CP0_STATUS | 32 MIPS | KVM_REG_MIPS_CP0_CAUSE | 32 MIPS | KVM_REG_MIPS_CP0_EPC | 64 + MIPS | KVM_REG_MIPS_CP0_PRID | 32 MIPS | KVM_REG_MIPS_CP0_CONFIG | 32 MIPS | KVM_REG_MIPS_CP0_CONFIG1 | 32 MIPS | KVM_REG_MIPS_CP0_CONFIG2 | 32 MIPS | KVM_REG_MIPS_CP0_CONFIG3 | 32 + MIPS | KVM_REG_MIPS_CP0_CONFIG4 | 32 + MIPS | KVM_REG_MIPS_CP0_CONFIG5 | 32 MIPS | KVM_REG_MIPS_CP0_CONFIG7 | 32 MIPS | KVM_REG_MIPS_CP0_ERROREPC | 64 MIPS | KVM_REG_MIPS_COUNT_CTL | 64 MIPS | KVM_REG_MIPS_COUNT_RESUME | 64 MIPS | KVM_REG_MIPS_COUNT_HZ | 64 + MIPS | KVM_REG_MIPS_FPR_32(0..31) | 32 + MIPS | KVM_REG_MIPS_FPR_64(0..31) | 64 + MIPS | KVM_REG_MIPS_VEC_128(0..31) | 128 + MIPS | KVM_REG_MIPS_FCR_IR | 32 + MIPS | KVM_REG_MIPS_FCR_CSR | 32 + MIPS | KVM_REG_MIPS_MSA_IR | 32 + MIPS | KVM_REG_MIPS_MSA_CSR | 32 ARM registers are mapped using the lower 32 bits. The upper 16 of that is the register group type, or coprocessor number: @@ -2029,6 +2047,25 @@ patterns depending on whether they're 32-bit or 64-bit registers: MIPS KVM control registers (see above) have the following id bit patterns: 0x7030 0000 0002 <reg:16> +MIPS FPU registers (see KVM_REG_MIPS_FPR_{32,64}() above) have the following +id bit patterns depending on the size of the register being accessed. They are +always accessed according to the current guest FPU mode (Status.FR and +Config5.FRE), i.e. as the guest would see them, and they become unpredictable +if the guest FPU mode is changed. MIPS SIMD Architecture (MSA) vector +registers (see KVM_REG_MIPS_VEC_128() above) have similar patterns as they +overlap the FPU registers: + 0x7020 0000 0003 00 <0:3> <reg:5> (32-bit FPU registers) + 0x7030 0000 0003 00 <0:3> <reg:5> (64-bit FPU registers) + 0x7040 0000 0003 00 <0:3> <reg:5> (128-bit MSA vector registers) + +MIPS FPU control registers (see KVM_REG_MIPS_FCR_{IR,CSR} above) have the +following id bit patterns: + 0x7020 0000 0003 01 <0:3> <reg:5> + +MIPS MSA control registers (see KVM_REG_MIPS_MSA_{IR,CSR} above) have the +following id bit patterns: + 0x7020 0000 0003 02 <0:3> <reg:5> + 4.69 KVM_GET_ONE_REG @@ -2234,7 +2271,7 @@ into the hash PTE second double word). 4.75 KVM_IRQFD Capability: KVM_CAP_IRQFD -Architectures: x86 s390 +Architectures: x86 s390 arm arm64 Type: vm ioctl Parameters: struct kvm_irqfd (in) Returns: 0 on success, -1 on error @@ -2260,6 +2297,10 @@ Note that closing the resamplefd is not sufficient to disable the irqfd. The KVM_IRQFD_FLAG_RESAMPLE is only necessary on assignment and need not be specified with KVM_IRQFD_FLAG_DEASSIGN. +On ARM/ARM64, the gsi field in the kvm_irqfd struct specifies the Shared +Peripheral Interrupt (SPI) index, such that the GIC interrupt ID is +given by gsi + 32. + 4.76 KVM_PPC_ALLOCATE_HTAB Capability: KVM_CAP_PPC_ALLOC_HTAB @@ -3410,6 +3451,31 @@ Parameters: none This capability enables the in-kernel irqchip for s390. Please refer to "4.24 KVM_CREATE_IRQCHIP" for details. +6.9 KVM_CAP_MIPS_FPU + +Architectures: mips +Target: vcpu +Parameters: args[0] is reserved for future use (should be 0). + +This capability allows the use of the host Floating Point Unit by the guest. It +allows the Config1.FP bit to be set to enable the FPU in the guest. Once this is +done the KVM_REG_MIPS_FPR_* and KVM_REG_MIPS_FCR_* registers can be accessed +(depending on the current guest FPU register mode), and the Status.FR, +Config5.FRE bits are accessible via the KVM API and also from the guest, +depending on them being supported by the FPU. + +6.10 KVM_CAP_MIPS_MSA + +Architectures: mips +Target: vcpu +Parameters: args[0] is reserved for future use (should be 0). + +This capability allows the use of the MIPS SIMD Architecture (MSA) by the guest. +It allows the Config3.MSAP bit to be set to enable the use of MSA by the guest. +Once this is done the KVM_REG_MIPS_VEC_* and KVM_REG_MIPS_MSA_* registers can be +accessed, and the Config5.MSAEn bit is accessible via the KVM API and also from +the guest. + 7. Capabilities that can be enabled on VMs ------------------------------------------ diff --git a/MAINTAINERS b/MAINTAINERS index ddc5a8cf9a8a..15e4015c5a2f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2065,7 +2065,7 @@ F: include/net/bluetooth/ BONDING DRIVER M: Jay Vosburgh <j.vosburgh@gmail.com> M: Veaceslav Falico <vfalico@gmail.com> -M: Andy Gospodarek <andy@greyhouse.net> +M: Andy Gospodarek <gospo@cumulusnetworks.com> L: netdev@vger.kernel.org W: http://sourceforge.net/projects/bonding/ S: Supported @@ -2369,8 +2369,9 @@ F: arch/x86/include/asm/tce.h CAN NETWORK LAYER M: Oliver Hartkopp <socketcan@hartkopp.net> +M: Marc Kleine-Budde <mkl@pengutronix.de> L: linux-can@vger.kernel.org -W: http://gitorious.org/linux-can +W: https://github.com/linux-can T: git git://git.kernel.org/pub/scm/linux/kernel/git/mkl/linux-can.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/mkl/linux-can-next.git S: Maintained @@ -2386,7 +2387,7 @@ CAN NETWORK DRIVERS M: Wolfgang Grandegger <wg@grandegger.com> M: Marc Kleine-Budde <mkl@pengutronix.de> L: linux-can@vger.kernel.org -W: http://gitorious.org/linux-can +W: https://github.com/linux-can T: git git://git.kernel.org/pub/scm/linux/kernel/git/mkl/linux-can.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/mkl/linux-can-next.git S: Maintained @@ -5574,6 +5575,8 @@ S: Supported F: Documentation/*/kvm*.txt F: Documentation/virtual/kvm/ F: arch/*/kvm/ +F: arch/x86/kernel/kvm.c +F: arch/x86/kernel/kvmclock.c F: arch/*/include/asm/kvm* F: include/linux/kvm* F: include/uapi/linux/kvm* @@ -7213,8 +7216,7 @@ ORACLE CLUSTER FILESYSTEM 2 (OCFS2) M: Mark Fasheh <mfasheh@suse.com> M: Joel Becker <jlbec@evilplan.org> L: ocfs2-devel@oss.oracle.com (moderated for non-subscribers) -W: http://oss.oracle.com/projects/ocfs2/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/jlbec/ocfs2.git +W: http://ocfs2.wiki.kernel.org S: Supported F: Documentation/filesystems/ocfs2.txt F: Documentation/filesystems/dlmfs.txt @@ -8481,6 +8483,14 @@ S: Supported L: netdev@vger.kernel.org F: drivers/net/ethernet/samsung/sxgbe/ +SAMSUNG THERMAL DRIVER +M: Lukasz Majewski <l.majewski@samsung.com> +L: linux-pm@vger.kernel.org +L: linux-samsung-soc@vger.kernel.org +S: Supported +T: https://github.com/lmajewski/linux-samsung-thermal.git +F: drivers/thermal/samsung/ + SAMSUNG USB2 PHY DRIVER M: Kamil Debski <k.debski@samsung.com> L: linux-kernel@vger.kernel.org @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 0 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc3 NAME = Hurr durr I'ma sheep # *DOCUMENTATION* diff --git a/arch/arc/include/asm/processor.h b/arch/arc/include/asm/processor.h index 4e547296831d..52312cb5dbe2 100644 --- a/arch/arc/include/asm/processor.h +++ b/arch/arc/include/asm/processor.h @@ -47,9 +47,6 @@ struct thread_struct { /* Forward declaration, a strange C thing */ struct task_struct; -/* Return saved PC of a blocked thread */ -unsigned long thread_saved_pc(struct task_struct *t); - #define task_pt_regs(p) \ ((struct pt_regs *)(THREAD_SIZE + (void *)task_stack_page(p)) - 1) @@ -72,18 +69,21 @@ unsigned long thread_saved_pc(struct task_struct *t); #define release_segments(mm) do { } while (0) #define KSTK_EIP(tsk) (task_pt_regs(tsk)->ret) +#define KSTK_ESP(tsk) (task_pt_regs(tsk)->sp) /* * Where abouts of Task's sp, fp, blink when it was last seen in kernel mode. * Look in process.c for details of kernel stack layout */ -#define KSTK_ESP(tsk) (tsk->thread.ksp) +#define TSK_K_ESP(tsk) (tsk->thread.ksp) -#define KSTK_REG(tsk, off) (*((unsigned int *)(KSTK_ESP(tsk) + \ +#define TSK_K_REG(tsk, off) (*((unsigned int *)(TSK_K_ESP(tsk) + \ sizeof(struct callee_regs) + off))) -#define KSTK_BLINK(tsk) KSTK_REG(tsk, 4) -#define KSTK_FP(tsk) KSTK_REG(tsk, 0) +#define TSK_K_BLINK(tsk) TSK_K_REG(tsk, 4) +#define TSK_K_FP(tsk) TSK_K_REG(tsk, 0) + +#define thread_saved_pc(tsk) TSK_K_BLINK(tsk) extern void start_thread(struct pt_regs * regs, unsigned long pc, unsigned long usp); diff --git a/arch/arc/include/asm/stacktrace.h b/arch/arc/include/asm/stacktrace.h new file mode 100644 index 000000000000..b29b6064ea14 --- /dev/null +++ b/arch/arc/include/asm/stacktrace.h @@ -0,0 +1,37 @@ +/* + * Copyright (C) 2014-15 Synopsys, Inc. (www.synopsys.com) + * Copyright (C) 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __ASM_STACKTRACE_H +#define __ASM_STACKTRACE_H + +#include <linux/sched.h> + +/** + * arc_unwind_core - Unwind the kernel mode stack for an execution context + * @tsk: NULL for current task, specific task otherwise + * @regs: pt_regs used to seed the unwinder {SP, FP, BLINK, PC} + * If NULL, use pt_regs of @tsk (if !NULL) otherwise + * use the current values of {SP, FP, BLINK, PC} + * @consumer_fn: Callback invoked for each frame unwound + * Returns 0 to continue unwinding, -1 to stop + * @arg: Arg to callback + * + * Returns the address of first function in stack + * + * Semantics: + * - synchronous unwinding (e.g. dump_stack): @tsk NULL, @regs NULL + * - Asynchronous unwinding of sleeping task: @tsk !NULL, @regs NULL + * - Asynchronous unwinding of intr/excp etc: @tsk !NULL, @regs !NULL + */ +notrace noinline unsigned int arc_unwind_core( + struct task_struct *tsk, struct pt_regs *regs, + int (*consumer_fn) (unsigned int, void *), + void *arg); + +#endif /* __ASM_STACKTRACE_H */ diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c index fdd89715d2d3..98c00a2d4dd9 100644 --- a/arch/arc/kernel/process.c +++ b/arch/arc/kernel/process.c @@ -192,29 +192,6 @@ int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpu) return 0; } -/* - * API: expected by schedular Code: If thread is sleeping where is that. - * What is this good for? it will be always the scheduler or ret_from_fork. - * So we hard code that anyways. - */ -unsigned long thread_saved_pc(struct task_struct *t) -{ - struct pt_regs *regs = task_pt_regs(t); - unsigned long blink = 0; - - /* - * If the thread being queried for in not itself calling this, then it - * implies it is not executing, which in turn implies it is sleeping, - * which in turn implies it got switched OUT by the schedular. - * In that case, it's kernel mode blink can reliably retrieved as per - * the picture above (right above pt_regs). - */ - if (t != current && t->state != TASK_RUNNING) - blink = *((unsigned int *)regs - 1); - - return blink; -} - int elf_check_arch(const struct elf32_hdr *x) { unsigned int eflags; diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c index 9ce47cfe2303..92320d6f737c 100644 --- a/arch/arc/kernel/stacktrace.c +++ b/arch/arc/kernel/stacktrace.c @@ -43,6 +43,10 @@ static void seed_unwind_frame_info(struct task_struct *tsk, struct pt_regs *regs, struct unwind_frame_info *frame_info) { + /* + * synchronous unwinding (e.g. dump_stack) + * - uses current values of SP and friends + */ if (tsk == NULL && regs == NULL) { unsigned long fp, sp, blink, ret; frame_info->task = current; @@ -61,12 +65,17 @@ static void seed_unwind_frame_info(struct task_struct *tsk, frame_info->regs.r63 = ret; frame_info->call_frame = 0; } else if (regs == NULL) { + /* + * Asynchronous unwinding of sleeping task + * - Gets SP etc from task's pt_regs (saved bottom of kernel + * mode stack of task) + */ frame_info->task = tsk; - frame_info->regs.r27 = KSTK_FP(tsk); - frame_info->regs.r28 = KSTK_ESP(tsk); - frame_info->regs.r31 = KSTK_BLINK(tsk); + frame_info->regs.r27 = TSK_K_FP(tsk); + frame_info->regs.r28 = TSK_K_ESP(tsk); + frame_info->regs.r31 = TSK_K_BLINK(tsk); frame_info->regs.r63 = (unsigned int)__switch_to; /* In the prologue of __switch_to, first FP is saved on stack @@ -83,6 +92,10 @@ static void seed_unwind_frame_info(struct task_struct *tsk, frame_info->call_frame = 0; } else { + /* + * Asynchronous unwinding of intr/exception + * - Just uses the pt_regs passed + */ frame_info->task = tsk; frame_info->regs.r27 = regs->fp; @@ -95,7 +108,7 @@ static void seed_unwind_frame_info(struct task_struct *tsk, #endif -static noinline unsigned int +notrace noinline unsigned int arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs, int (*consumer_fn) (unsigned int, void *), void *arg) { diff --git a/arch/arc/kernel/unaligned.c b/arch/arc/kernel/unaligned.c index 7ff5b5c183bb..74db59b6f392 100644 --- a/arch/arc/kernel/unaligned.c +++ b/arch/arc/kernel/unaligned.c @@ -12,6 +12,7 @@ */ #include <linux/types.h> +#include <linux/perf_event.h> #include <linux/ptrace.h> #include <linux/uaccess.h> #include <asm/disasm.h> @@ -253,6 +254,7 @@ int misaligned_fixup(unsigned long address, struct pt_regs *regs, } } + perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, address); return 0; fault: diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c index 563cb27e37f5..6a2e006cbcce 100644 --- a/arch/arc/mm/fault.c +++ b/arch/arc/mm/fault.c @@ -14,6 +14,7 @@ #include <linux/ptrace.h> #include <linux/uaccess.h> #include <linux/kdebug.h> +#include <linux/perf_event.h> #include <asm/pgalloc.h> #include <asm/mmu.h> @@ -139,13 +140,20 @@ good_area: return; } + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); + if (likely(!(fault & VM_FAULT_ERROR))) { if (flags & FAULT_FLAG_ALLOW_RETRY) { /* To avoid updating stats twice for retry case */ - if (fault & VM_FAULT_MAJOR) + if (fault & VM_FAULT_MAJOR) { tsk->maj_flt++; - else + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, + regs, address); + } else { tsk->min_flt++; + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, + regs, address); + } if (fault & VM_FAULT_RETRY) { flags &= ~FAULT_FLAG_ALLOW_RETRY; diff --git a/arch/arm/boot/dts/am335x-bone-common.dtsi b/arch/arm/boot/dts/am335x-bone-common.dtsi index 6cc25ed912ee..2c6248d9a9ef 100644 --- a/arch/arm/boot/dts/am335x-bone-common.dtsi +++ b/arch/arm/boot/dts/am335x-bone-common.dtsi @@ -195,6 +195,7 @@ &usb0 { status = "okay"; + dr_mode = "peripheral"; }; &usb1 { diff --git a/arch/arm/boot/dts/am437x-idk-evm.dts b/arch/arm/boot/dts/am437x-idk-evm.dts index f9a17e2ca8cb..0198f5a62b96 100644 --- a/arch/arm/boot/dts/am437x-idk-evm.dts +++ b/arch/arm/boot/dts/am437x-idk-evm.dts @@ -133,20 +133,6 @@ >; }; - i2c1_pins_default: i2c1_pins_default { - pinctrl-single,pins = < - 0x15c (PIN_INPUT | SLEWCTRL_FAST | MUX_MODE2) /* spi0_cs0.i2c1_scl */ - 0x158 (PIN_INPUT | SLEWCTRL_FAST | MUX_MODE2) /* spi0_d1.i2c1_sda */ - >; - }; - - i2c1_pins_sleep: i2c1_pins_sleep { - pinctrl-single,pins = < - 0x15c (PIN_INPUT_PULLDOWN | MUX_MODE7) /* spi0_cs0.i2c1_scl */ - 0x158 (PIN_INPUT_PULLDOWN | MUX_MODE7) /* spi0_d1.i2c1_sda */ - >; - }; - mmc1_pins_default: pinmux_mmc1_pins_default { pinctrl-single,pins = < 0x100 (PIN_INPUT | MUX_MODE0) /* mmc0_clk.mmc0_clk */ @@ -254,7 +240,7 @@ status = "okay"; pinctrl-names = "default", "sleep"; pinctrl-0 = <&i2c0_pins_default>; - pinctrl-1 = <&i2c0_pins_default>; + pinctrl-1 = <&i2c0_pins_sleep>; clock-frequency = <400000>; at24@50 { @@ -262,17 +248,10 @@ pagesize = <64>; reg = <0x50>; }; -}; - -&i2c1 { - status = "okay"; - pinctrl-names = "default", "sleep"; - pinctrl-0 = <&i2c1_pins_default>; - pinctrl-1 = <&i2c1_pins_default>; - clock-frequency = <400000>; tps: tps62362@60 { compatible = "ti,tps62362"; + reg = <0x60>; regulator-name = "VDD_MPU"; regulator-min-microvolt = <950000>; regulator-max-microvolt = <1330000>; diff --git a/arch/arm/boot/dts/am57xx-beagle-x15.dts b/arch/arm/boot/dts/am57xx-beagle-x15.dts index 03750af3b49a..6463f9ef2b54 100644 --- a/arch/arm/boot/dts/am57xx-beagle-x15.dts +++ b/arch/arm/boot/dts/am57xx-beagle-x15.dts @@ -549,14 +549,6 @@ pinctrl-0 = <&usb1_pins>; }; -&omap_dwc3_1 { - extcon = <&extcon_usb1>; -}; - -&omap_dwc3_2 { - extcon = <&extcon_usb2>; -}; - &usb2 { dr_mode = "peripheral"; }; diff --git a/arch/arm/boot/dts/dm8168-evm.dts b/arch/arm/boot/dts/dm8168-evm.dts index 857d0289ad4d..d3a29c1b8417 100644 --- a/arch/arm/boot/dts/dm8168-evm.dts +++ b/arch/arm/boot/dts/dm8168-evm.dts @@ -35,6 +35,18 @@ DM816X_IOPAD(0x0aac, PIN_INPUT | MUX_MODE0) /* SPI_D1 */ >; }; + + usb0_pins: pinmux_usb0_pins { + pinctrl-single,pins = < + DM816X_IOPAD(0x0d00, MUX_MODE0) /* USB0_DRVVBUS */ + >; + }; + + usb1_pins: pinmux_usb0_pins { + pinctrl-single,pins = < + DM816X_IOPAD(0x0d04, MUX_MODE0) /* USB1_DRVVBUS */ + >; + }; }; &i2c1 { @@ -127,3 +139,16 @@ &mmc1 { vmmc-supply = <&vmmcsd_fixed>; }; + +/* At least dm8168-evm rev c won't support multipoint, later may */ +&usb0 { + pinctrl-names = "default"; + pinctrl-0 = <&usb0_pins>; + mentor,multipoint = <0>; +}; + +&usb1 { + pinctrl-names = "default"; + pinctrl-0 = <&usb1_pins>; + mentor,multipoint = <0>; +}; diff --git a/arch/arm/boot/dts/dm816x.dtsi b/arch/arm/boot/dts/dm816x.dtsi index d98d0f7de380..3c97b5f2addc 100644 --- a/arch/arm/boot/dts/dm816x.dtsi +++ b/arch/arm/boot/dts/dm816x.dtsi @@ -97,10 +97,31 @@ /* Device Configuration Registers */ scm_conf: syscon@600 { - compatible = "syscon"; + compatible = "syscon", "simple-bus"; reg = <0x600 0x110>; #address-cells = <1>; #size-cells = <1>; + ranges = <0 0x600 0x110>; + + usb_phy0: usb-phy@20 { + compatible = "ti,dm8168-usb-phy"; + reg = <0x20 0x8>; + reg-names = "phy"; + clocks = <&main_fapll 6>; + clock-names = "refclk"; + #phy-cells = <0>; + syscon = <&scm_conf>; + }; + + usb_phy1: usb-phy@28 { + compatible = "ti,dm8168-usb-phy"; + reg = <0x28 0x8>; + reg-names = "phy"; + clocks = <&main_fapll 6>; + clock-names = "refclk"; + #phy-cells = <0>; + syscon = <&scm_conf>; + }; }; scrm_clocks: clocks { @@ -357,7 +378,10 @@ reg-names = "mc", "control"; interrupts = <18>; interrupt-names = "mc"; - dr_mode = "otg"; + dr_mode = "host"; + interface-type = <0>; + phys = <&usb_phy0>; + phy-names = "usb2-phy"; mentor,multipoint = <1>; mentor,num-eps = <16>; mentor,ram-bits = <12>; @@ -366,13 +390,15 @@ usb1: usb@47401800 { compatible = "ti,musb-am33xx"; - status = "disabled"; reg = <0x47401c00 0x400 0x47401800 0x200>; reg-names = "mc", "control"; interrupts = <19>; interrupt-names = "mc"; - dr_mode = "otg"; + dr_mode = "host"; + interface-type = <0>; + phys = <&usb_phy1>; + phy-names = "usb2-phy"; mentor,multipoint = <1>; mentor,num-eps = <16>; mentor,ram-bits = <12>; diff --git a/arch/arm/boot/dts/dra7-evm.dts b/arch/arm/boot/dts/dra7-evm.dts index 746cddb1b8f5..3290a96ba586 100644 --- a/arch/arm/boot/dts/dra7-evm.dts +++ b/arch/arm/boot/dts/dra7-evm.dts @@ -543,14 +543,6 @@ }; }; -&omap_dwc3_1 { - extcon = <&extcon_usb1>; -}; - -&omap_dwc3_2 { - extcon = <&extcon_usb2>; -}; - &usb1 { dr_mode = "peripheral"; pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi index 5827fedafd43..127608d79033 100644 --- a/arch/arm/boot/dts/dra7.dtsi +++ b/arch/arm/boot/dts/dra7.dtsi @@ -249,8 +249,8 @@ <GIC_SPI 9 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>; #dma-cells = <1>; - #dma-channels = <32>; - #dma-requests = <127>; + dma-channels = <32>; + dma-requests = <127>; }; gpio1: gpio@4ae10000 { @@ -1090,8 +1090,8 @@ <0x4A096800 0x40>; /* pll_ctrl */ reg-names = "phy_rx", "phy_tx", "pll_ctrl"; ctrl-module = <&omap_control_sata>; - clocks = <&sys_clkin1>; - clock-names = "sysclk"; + clocks = <&sys_clkin1>, <&sata_ref_clk>; + clock-names = "sysclk", "refclk"; #phy-cells = <0>; }; diff --git a/arch/arm/boot/dts/dra72-evm.dts b/arch/arm/boot/dts/dra72-evm.dts index 4d8711713610..e0264d0bf7b9 100644 --- a/arch/arm/boot/dts/dra72-evm.dts +++ b/arch/arm/boot/dts/dra72-evm.dts @@ -380,14 +380,6 @@ phy-supply = <&ldo4_reg>; }; -&omap_dwc3_1 { - extcon = <&extcon_usb1>; -}; - -&omap_dwc3_2 { - extcon = <&extcon_usb2>; -}; - &usb1 { dr_mode = "peripheral"; pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/omap2.dtsi b/arch/arm/boot/dts/omap2.dtsi index 59d1c297bb30..578fa2a54dce 100644 --- a/arch/arm/boot/dts/omap2.dtsi +++ b/arch/arm/boot/dts/omap2.dtsi @@ -87,8 +87,8 @@ <14>, <15>; #dma-cells = <1>; - #dma-channels = <32>; - #dma-requests = <64>; + dma-channels = <32>; + dma-requests = <64>; }; i2c1: i2c@48070000 { diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts index 60403273f83e..db80f9d376fa 100644 --- a/arch/arm/boot/dts/omap3-n900.dts +++ b/arch/arm/boot/dts/omap3-n900.dts @@ -16,6 +16,13 @@ model = "Nokia N900"; compatible = "nokia,omap3-n900", "ti,omap3430", "ti,omap3"; + aliases { + i2c0; + i2c1 = &i2c1; + i2c2 = &i2c2; + i2c3 = &i2c3; + }; + cpus { cpu@0 { cpu0-supply = <&vcc>; @@ -704,7 +711,7 @@ compatible = "smsc,lan91c94"; interrupt-parent = <&gpio2>; interrupts = <22 IRQ_TYPE_LEVEL_HIGH>; /* gpio54 */ - reg = <1 0x300 0xf>; /* 16 byte IO range at offset 0x300 */ + reg = <1 0 0xf>; /* 16 byte IO range */ bank-width = <2>; pinctrl-names = "default"; pinctrl-0 = <ðernet_pins>; diff --git a/arch/arm/boot/dts/omap3.dtsi b/arch/arm/boot/dts/omap3.dtsi index 01b71111bd55..f4f78c40b564 100644 --- a/arch/arm/boot/dts/omap3.dtsi +++ b/arch/arm/boot/dts/omap3.dtsi @@ -155,8 +155,8 @@ <14>, <15>; #dma-cells = <1>; - #dma-channels = <32>; - #dma-requests = <96>; + dma-channels = <32>; + dma-requests = <96>; }; omap3_pmx_core: pinmux@48002030 { diff --git a/arch/arm/boot/dts/omap4.dtsi b/arch/arm/boot/dts/omap4.dtsi index 074147cebae4..87401d9f4d8b 100644 --- a/arch/arm/boot/dts/omap4.dtsi +++ b/arch/arm/boot/dts/omap4.dtsi @@ -223,8 +223,8 @@ <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 15 IRQ_TYPE_LEVEL_HIGH>; #dma-cells = <1>; - #dma-channels = <32>; - #dma-requests = <127>; + dma-channels = <32>; + dma-requests = <127>; }; gpio1: gpio@4a310000 { diff --git a/arch/arm/boot/dts/omap5.dtsi b/arch/arm/boot/dts/omap5.dtsi index b321fdf42c9f..ddff674bd05e 100644 --- a/arch/arm/boot/dts/omap5.dtsi +++ b/arch/arm/boot/dts/omap5.dtsi @@ -238,8 +238,8 @@ <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 15 IRQ_TYPE_LEVEL_HIGH>; #dma-cells = <1>; - #dma-channels = <32>; - #dma-requests = <127>; + dma-channels = <32>; + dma-requests = <127>; }; gpio1: gpio@4ae10000 { @@ -929,8 +929,8 @@ <0x4A096800 0x40>; /* pll_ctrl */ reg-names = "phy_rx", "phy_tx", "pll_ctrl"; ctrl-module = <&omap_control_sata>; - clocks = <&sys_clkin>; - clock-names = "sysclk"; + clocks = <&sys_clkin>, <&sata_ref_clk>; + clock-names = "sysclk", "refclk"; #phy-cells = <0>; }; }; diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index e8a4c955241b..b7e6b6fba5e0 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -62,6 +62,17 @@ CONFIG_MACH_SPEAR1340=y CONFIG_ARCH_STI=y CONFIG_ARCH_EXYNOS=y CONFIG_EXYNOS5420_MCPM=y +CONFIG_ARCH_SHMOBILE_MULTI=y +CONFIG_ARCH_EMEV2=y +CONFIG_ARCH_R7S72100=y +CONFIG_ARCH_R8A73A4=y +CONFIG_ARCH_R8A7740=y +CONFIG_ARCH_R8A7779=y +CONFIG_ARCH_R8A7790=y +CONFIG_ARCH_R8A7791=y +CONFIG_ARCH_R8A7794=y +CONFIG_ARCH_SH73A0=y +CONFIG_MACH_MARZEN=y CONFIG_ARCH_SUNXI=y CONFIG_ARCH_SIRF=y CONFIG_ARCH_TEGRA=y @@ -84,6 +95,8 @@ CONFIG_PCI_KEYSTONE=y CONFIG_PCI_MSI=y CONFIG_PCI_MVEBU=y CONFIG_PCI_TEGRA=y +CONFIG_PCI_RCAR_GEN2=y +CONFIG_PCI_RCAR_GEN2_PCIE=y CONFIG_PCIEPORTBUS=y CONFIG_SMP=y CONFIG_NR_CPUS=8 @@ -130,6 +143,7 @@ CONFIG_DEVTMPFS_MOUNT=y CONFIG_DMA_CMA=y CONFIG_CMA_SIZE_MBYTES=64 CONFIG_OMAP_OCP2SCP=y +CONFIG_SIMPLE_PM_BUS=y CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y CONFIG_MTD_BLOCK=y @@ -157,6 +171,7 @@ CONFIG_AHCI_SUNXI=y CONFIG_AHCI_TEGRA=y CONFIG_SATA_HIGHBANK=y CONFIG_SATA_MV=y +CONFIG_SATA_RCAR=y CONFIG_NETDEVICES=y CONFIG_HIX5HD2_GMAC=y CONFIG_SUN4I_EMAC=y @@ -167,14 +182,17 @@ CONFIG_MV643XX_ETH=y CONFIG_MVNETA=y CONFIG_KS8851=y CONFIG_R8169=y +CONFIG_SH_ETH=y CONFIG_SMSC911X=y CONFIG_STMMAC_ETH=y CONFIG_TI_CPSW=y CONFIG_XILINX_EMACLITE=y CONFIG_AT803X_PHY=y CONFIG_MARVELL_PHY=y +CONFIG_SMSC_PHY=y CONFIG_BROADCOM_PHY=y CONFIG_ICPLUS_PHY=y +CONFIG_MICREL_PHY=y CONFIG_USB_PEGASUS=y CONFIG_USB_USBNET=y CONFIG_USB_NET_SMSC75XX=y @@ -192,15 +210,18 @@ CONFIG_KEYBOARD_CROS_EC=y CONFIG_MOUSE_PS2_ELANTECH=y CONFIG_INPUT_TOUCHSCREEN=y CONFIG_TOUCHSCREEN_ATMEL_MXT=y +CONFIG_TOUCHSCREEN_ST1232=m CONFIG_TOUCHSCREEN_STMPE=y CONFIG_TOUCHSCREEN_SUN4I=y CONFIG_INPUT_MISC=y CONFIG_INPUT_MPU3050=y CONFIG_INPUT_AXP20X_PEK=y +CONFIG_INPUT_ADXL34X=m CONFIG_SERIO_AMBAKMI=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_DW=y +CONFIG_SERIAL_8250_EM=y CONFIG_SERIAL_8250_MT6577=y CONFIG_SERIAL_AMBA_PL011=y CONFIG_SERIAL_AMBA_PL011_CONSOLE=y @@ -213,6 +234,9 @@ CONFIG_SERIAL_SIRFSOC_CONSOLE=y CONFIG_SERIAL_TEGRA=y CONFIG_SERIAL_IMX=y CONFIG_SERIAL_IMX_CONSOLE=y +CONFIG_SERIAL_SH_SCI=y +CONFIG_SERIAL_SH_SCI_NR_UARTS=20 +CONFIG_SERIAL_SH_SCI_CONSOLE=y CONFIG_SERIAL_MSM=y CONFIG_SERIAL_MSM_CONSOLE=y CONFIG_SERIAL_VT8500=y @@ -233,19 +257,26 @@ CONFIG_I2C_MUX_PCA954x=y CONFIG_I2C_MUX_PINCTRL=y CONFIG_I2C_CADENCE=y CONFIG_I2C_DESIGNWARE_PLATFORM=y +CONFIG_I2C_GPIO=m CONFIG_I2C_EXYNOS5=y CONFIG_I2C_MV64XXX=y +CONFIG_I2C_RIIC=y CONFIG_I2C_S3C2410=y +CONFIG_I2C_SH_MOBILE=y CONFIG_I2C_SIRF=y -CONFIG_I2C_TEGRA=y CONFIG_I2C_ST=y -CONFIG_SPI=y +CONFIG_I2C_TEGRA=y CONFIG_I2C_XILINX=y -CONFIG_SPI_DAVINCI=y +CONFIG_I2C_RCAR=y +CONFIG_SPI=y CONFIG_SPI_CADENCE=y +CONFIG_SPI_DAVINCI=y CONFIG_SPI_OMAP24XX=y CONFIG_SPI_ORION=y CONFIG_SPI_PL022=y +CONFIG_SPI_RSPI=y +CONFIG_SPI_SH_MSIOF=m +CONFIG_SPI_SH_HSPI=y CONFIG_SPI_SIRF=y CONFIG_SPI_SUN4I=y CONFIG_SPI_SUN6I=y @@ -259,12 +290,15 @@ CONFIG_PINCTRL_PALMAS=y CONFIG_PINCTRL_APQ8084=y CONFIG_GPIO_SYSFS=y CONFIG_GPIO_GENERIC_PLATFORM=y -CONFIG_GPIO_DWAPB=y CONFIG_GPIO_DAVINCI=y +CONFIG_GPIO_DWAPB=y +CONFIG_GPIO_EM=y +CONFIG_GPIO_RCAR=y CONFIG_GPIO_XILINX=y CONFIG_GPIO_ZYNQ=y CONFIG_GPIO_PCA953X=y CONFIG_GPIO_PCA953X_IRQ=y +CONFIG_GPIO_PCF857X=y CONFIG_GPIO_TWL4030=y CONFIG_GPIO_PALMAS=y CONFIG_GPIO_SYSCON=y @@ -276,10 +310,12 @@ CONFIG_POWER_RESET_AS3722=y CONFIG_POWER_RESET_GPIO=y CONFIG_POWER_RESET_KEYSTONE=y CONFIG_POWER_RESET_SUN6I=y +CONFIG_POWER_RESET_RMOBILE=y CONFIG_SENSORS_LM90=y CONFIG_SENSORS_LM95245=y CONFIG_THERMAL=y CONFIG_CPU_THERMAL=y +CONFIG_RCAR_THERMAL=y CONFIG_ARMADA_THERMAL=y CONFIG_DAVINCI_WATCHDOG CONFIG_ST_THERMAL_SYSCFG=y @@ -290,6 +326,7 @@ CONFIG_ARM_SP805_WATCHDOG=y CONFIG_ORION_WATCHDOG=y CONFIG_SUNXI_WATCHDOG=y CONFIG_MESON_WATCHDOG=y +CONFIG_MFD_AS3711=y CONFIG_MFD_AS3722=y CONFIG_MFD_BCM590XX=y CONFIG_MFD_AXP20X=y @@ -304,13 +341,16 @@ CONFIG_MFD_TPS65090=y CONFIG_MFD_TPS6586X=y CONFIG_MFD_TPS65910=y CONFIG_REGULATOR_AB8500=y +CONFIG_REGULATOR_AS3711=y CONFIG_REGULATOR_AS3722=y CONFIG_REGULATOR_AXP20X=y CONFIG_REGULATOR_BCM590XX=y +CONFIG_REGULATOR_DA9210=y CONFIG_REGULATOR_GPIO=y CONFIG_MFD_SYSCON=y CONFIG_POWER_RESET_SYSCON=y CONFIG_REGULATOR_MAX8907=y +CONFIG_REGULATOR_MAX8973=y CONFIG_REGULATOR_MAX77686=y CONFIG_REGULATOR_PALMAS=y CONFIG_REGULATOR_S2MPS11=y @@ -324,18 +364,32 @@ CONFIG_REGULATOR_TWL4030=y CONFIG_REGULATOR_VEXPRESS=y CONFIG_MEDIA_SUPPORT=y CONFIG_MEDIA_CAMERA_SUPPORT=y +CONFIG_MEDIA_CONTROLLER=y +CONFIG_VIDEO_V4L2_SUBDEV_API=y CONFIG_MEDIA_USB_SUPPORT=y CONFIG_USB_VIDEO_CLASS=y CONFIG_USB_GSPCA=y +CONFIG_V4L_PLATFORM_DRIVERS=y +CONFIG_SOC_CAMERA=m +CONFIG_SOC_CAMERA_PLATFORM=m +CONFIG_VIDEO_RCAR_VIN=m +CONFIG_V4L_MEM2MEM_DRIVERS=y +CONFIG_VIDEO_RENESAS_VSP1=m +# CONFIG_MEDIA_SUBDRV_AUTOSELECT is not set +CONFIG_VIDEO_ADV7180=m CONFIG_DRM=y +CONFIG_DRM_RCAR_DU=m CONFIG_DRM_TEGRA=y CONFIG_DRM_PANEL_SIMPLE=y CONFIG_FB_ARMCLCD=y CONFIG_FB_WM8505=y +CONFIG_FB_SH_MOBILE_LCDC=y CONFIG_FB_SIMPLE=y +CONFIG_FB_SH_MOBILE_MERAM=y CONFIG_BACKLIGHT_LCD_SUPPORT=y CONFIG_BACKLIGHT_CLASS_DEVICE=y CONFIG_BACKLIGHT_PWM=y +CONFIG_BACKLIGHT_AS3711=y CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_FRAMEBUFFER_CONSOLE_ROTATION=y CONFIG_SOUND=y @@ -343,6 +397,8 @@ CONFIG_SND=y CONFIG_SND_DYNAMIC_MINORS=y CONFIG_SND_USB_AUDIO=y CONFIG_SND_SOC=y +CONFIG_SND_SOC_SH4_FSI=m +CONFIG_SND_SOC_RCAR=m CONFIG_SND_SOC_TEGRA=y CONFIG_SND_SOC_TEGRA_RT5640=y CONFIG_SND_SOC_TEGRA_WM8753=y @@ -350,6 +406,8 @@ CONFIG_SND_SOC_TEGRA_WM8903=y CONFIG_SND_SOC_TEGRA_TRIMSLICE=y CONFIG_SND_SOC_TEGRA_ALC5632=y CONFIG_SND_SOC_TEGRA_MAX98090=y +CONFIG_SND_SOC_AK4642=m +CONFIG_SND_SOC_WM8978=m CONFIG_USB=y CONFIG_USB_XHCI_HCD=y CONFIG_USB_XHCI_MVEBU=y @@ -362,6 +420,8 @@ CONFIG_USB_ISP1760_HCD=y CONFIG_USB_OHCI_HCD=y CONFIG_USB_OHCI_HCD_STI=y CONFIG_USB_OHCI_HCD_PLATFORM=y +CONFIG_USB_R8A66597_HCD=m +CONFIG_USB_RENESAS_USBHS=m CONFIG_USB_STORAGE=y CONFIG_USB_DWC3=y CONFIG_USB_CHIPIDEA=y @@ -374,6 +434,10 @@ CONFIG_SAMSUNG_USB3PHY=y CONFIG_USB_GPIO_VBUS=y CONFIG_USB_ISP1301=y CONFIG_USB_MXS_PHY=y +CONFIG_USB_RCAR_PHY=m +CONFIG_USB_RCAR_GEN2_PHY=m +CONFIG_USB_GADGET=y +CONFIG_USB_RENESAS_USBHS_UDC=m CONFIG_MMC=y CONFIG_MMC_BLOCK_MINORS=16 CONFIG_MMC_ARMMMCI=y @@ -392,12 +456,14 @@ CONFIG_MMC_SDHCI_ST=y CONFIG_MMC_OMAP=y CONFIG_MMC_OMAP_HS=y CONFIG_MMC_MVSDIO=y -CONFIG_MMC_SUNXI=y +CONFIG_MMC_SDHI=y CONFIG_MMC_DW=y CONFIG_MMC_DW_IDMAC=y CONFIG_MMC_DW_PLTFM=y CONFIG_MMC_DW_EXYNOS=y CONFIG_MMC_DW_ROCKCHIP=y +CONFIG_MMC_SH_MMCIF=y +CONFIG_MMC_SUNXI=y CONFIG_NEW_LEDS=y CONFIG_LEDS_CLASS=y CONFIG_LEDS_GPIO=y @@ -421,10 +487,12 @@ CONFIG_RTC_DRV_AS3722=y CONFIG_RTC_DRV_DS1307=y CONFIG_RTC_DRV_MAX8907=y CONFIG_RTC_DRV_MAX77686=y +CONFIG_RTC_DRV_RS5C372=m CONFIG_RTC_DRV_PALMAS=y CONFIG_RTC_DRV_TWL4030=y CONFIG_RTC_DRV_TPS6586X=y CONFIG_RTC_DRV_TPS65910=y +CONFIG_RTC_DRV_S35390A=m CONFIG_RTC_DRV_EM3027=y CONFIG_RTC_DRV_PL031=y CONFIG_RTC_DRV_VT8500=y @@ -436,6 +504,9 @@ CONFIG_DMADEVICES=y CONFIG_DW_DMAC=y CONFIG_MV_XOR=y CONFIG_TEGRA20_APB_DMA=y +CONFIG_SH_DMAE=y +CONFIG_RCAR_AUDMAC_PP=m +CONFIG_RCAR_DMAC=y CONFIG_STE_DMA40=y CONFIG_SIRF_DMA=y CONFIG_TI_EDMA=y @@ -468,6 +539,7 @@ CONFIG_IIO=y CONFIG_XILINX_XADC=y CONFIG_AK8975=y CONFIG_PWM=y +CONFIG_PWM_RENESAS_TPU=y CONFIG_PWM_TEGRA=y CONFIG_PWM_VT8500=y CONFIG_PHY_HIX5HD2_SATA=y diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig index b7386524c356..a097cffa1231 100644 --- a/arch/arm/configs/omap2plus_defconfig +++ b/arch/arm/configs/omap2plus_defconfig @@ -114,6 +114,7 @@ CONFIG_MTD_PHYSMAP_OF=y CONFIG_MTD_NAND=y CONFIG_MTD_NAND_ECC_BCH=y CONFIG_MTD_NAND_OMAP2=y +CONFIG_MTD_NAND_OMAP_BCH=y CONFIG_MTD_ONENAND=y CONFIG_MTD_ONENAND_VERIFY_WRITE=y CONFIG_MTD_ONENAND_OMAP2=y @@ -248,6 +249,7 @@ CONFIG_TWL6040_CORE=y CONFIG_REGULATOR_PALMAS=y CONFIG_REGULATOR_PBIAS=y CONFIG_REGULATOR_TI_ABB=y +CONFIG_REGULATOR_TPS62360=m CONFIG_REGULATOR_TPS65023=y CONFIG_REGULATOR_TPS6507X=y CONFIG_REGULATOR_TPS65217=y @@ -374,7 +376,7 @@ CONFIG_PWM_TIEHRPWM=m CONFIG_PWM_TWL=m CONFIG_PWM_TWL_LED=m CONFIG_OMAP_USB2=m -CONFIG_TI_PIPE3=m +CONFIG_TI_PIPE3=y CONFIG_EXT2_FS=y CONFIG_EXT3_FS=y # CONFIG_EXT3_FS_XATTR is not set diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h index 816db0bf2dd8..d995821f1698 100644 --- a/arch/arm/include/asm/kvm_arm.h +++ b/arch/arm/include/asm/kvm_arm.h @@ -185,6 +185,7 @@ #define HSR_COND (0xfU << HSR_COND_SHIFT) #define FSC_FAULT (0x04) +#define FSC_ACCESS (0x08) #define FSC_PERM (0x0c) /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */ diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index 41008cd7c53f..d71607c16601 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -27,6 +27,8 @@ #include <asm/fpstate.h> #include <kvm/arm_arch_timer.h> +#define __KVM_HAVE_ARCH_INTC_INITIALIZED + #if defined(CONFIG_KVM_ARM_MAX_VCPUS) #define KVM_MAX_VCPUS CONFIG_KVM_ARM_MAX_VCPUS #else @@ -165,19 +167,10 @@ void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu); int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices); +int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); +int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); /* We do not have shadow page tables, hence the empty hooks */ -static inline int kvm_age_hva(struct kvm *kvm, unsigned long start, - unsigned long end) -{ - return 0; -} - -static inline int kvm_test_age_hva(struct kvm *kvm, unsigned long hva) -{ - return 0; -} - static inline void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, unsigned long address) { diff --git a/arch/arm/include/asm/kvm_mmio.h b/arch/arm/include/asm/kvm_mmio.h index 3f83db2f6cf0..d8e90c8cb5fa 100644 --- a/arch/arm/include/asm/kvm_mmio.h +++ b/arch/arm/include/asm/kvm_mmio.h @@ -28,28 +28,6 @@ struct kvm_decode { bool sign_extend; }; -/* - * The in-kernel MMIO emulation code wants to use a copy of run->mmio, - * which is an anonymous type. Use our own type instead. - */ -struct kvm_exit_mmio { - phys_addr_t phys_addr; - u8 data[8]; - u32 len; - bool is_write; - void *private; -}; - -static inline void kvm_prepare_mmio(struct kvm_run *run, - struct kvm_exit_mmio *mmio) -{ - run->mmio.phys_addr = mmio->phys_addr; - run->mmio.len = mmio->len; - run->mmio.is_write = mmio->is_write; - memcpy(run->mmio.data, mmio->data, mmio->len); - run->exit_reason = KVM_EXIT_MMIO; -} - int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run); int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, phys_addr_t fault_ipa); diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h index 37ca2a4c6f09..4cf48c3aca13 100644 --- a/arch/arm/include/asm/kvm_mmu.h +++ b/arch/arm/include/asm/kvm_mmu.h @@ -149,29 +149,28 @@ static inline bool kvm_s2pmd_readonly(pmd_t *pmd) (__boundary - 1 < (end) - 1)? __boundary: (end); \ }) +#define kvm_pgd_index(addr) pgd_index(addr) + static inline bool kvm_page_empty(void *ptr) { struct page *ptr_page = virt_to_page(ptr); return page_count(ptr_page) == 1; } - #define kvm_pte_table_empty(kvm, ptep) kvm_page_empty(ptep) #define kvm_pmd_table_empty(kvm, pmdp) kvm_page_empty(pmdp) #define kvm_pud_table_empty(kvm, pudp) (0) #define KVM_PREALLOC_LEVEL 0 -static inline int kvm_prealloc_hwpgd(struct kvm *kvm, pgd_t *pgd) +static inline void *kvm_get_hwpgd(struct kvm *kvm) { - return 0; + return kvm->arch.pgd; } -static inline void kvm_free_hwpgd(struct kvm *kvm) { } - -static inline void *kvm_get_hwpgd(struct kvm *kvm) +static inline unsigned int kvm_get_hwpgd_size(void) { - return kvm->arch.pgd; + return PTRS_PER_S2_PGD * sizeof(pgd_t); } struct kvm; @@ -207,7 +206,7 @@ static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn, bool need_flush = !vcpu_has_cache_enabled(vcpu) || ipa_uncached; - VM_BUG_ON(size & PAGE_MASK); + VM_BUG_ON(size & ~PAGE_MASK); if (!need_flush && !icache_is_pipt()) goto vipt_cache; diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h index 0db25bc32864..2499867dd0d8 100644 --- a/arch/arm/include/uapi/asm/kvm.h +++ b/arch/arm/include/uapi/asm/kvm.h @@ -198,6 +198,9 @@ struct kvm_arch_memory_slot { /* Highest supported SPI, from VGIC_NR_IRQS */ #define KVM_ARM_IRQ_GIC_MAX 127 +/* One single KVM irqchip, ie. the VGIC */ +#define KVM_NR_IRQCHIPS 1 + /* PSCI interface */ #define KVM_PSCI_FN_BASE 0x95c1ba5e #define KVM_PSCI_FN(n) (KVM_PSCI_FN_BASE + (n)) diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c index 2d2d6087b9b1..488eaac56028 100644 --- a/arch/arm/kernel/asm-offsets.c +++ b/arch/arm/kernel/asm-offsets.c @@ -190,7 +190,6 @@ int main(void) DEFINE(VCPU_HxFAR, offsetof(struct kvm_vcpu, arch.fault.hxfar)); DEFINE(VCPU_HPFAR, offsetof(struct kvm_vcpu, arch.fault.hpfar)); DEFINE(VCPU_HYP_PC, offsetof(struct kvm_vcpu, arch.fault.hyp_pc)); -#ifdef CONFIG_KVM_ARM_VGIC DEFINE(VCPU_VGIC_CPU, offsetof(struct kvm_vcpu, arch.vgic_cpu)); DEFINE(VGIC_V2_CPU_HCR, offsetof(struct vgic_cpu, vgic_v2.vgic_hcr)); DEFINE(VGIC_V2_CPU_VMCR, offsetof(struct vgic_cpu, vgic_v2.vgic_vmcr)); @@ -200,14 +199,11 @@ int main(void) DEFINE(VGIC_V2_CPU_APR, offsetof(struct vgic_cpu, vgic_v2.vgic_apr)); DEFINE(VGIC_V2_CPU_LR, offsetof(struct vgic_cpu, vgic_v2.vgic_lr)); DEFINE(VGIC_CPU_NR_LR, offsetof(struct vgic_cpu, nr_lr)); -#ifdef CONFIG_KVM_ARM_TIMER DEFINE(VCPU_TIMER_CNTV_CTL, offsetof(struct kvm_vcpu, arch.timer_cpu.cntv_ctl)); DEFINE(VCPU_TIMER_CNTV_CVAL, offsetof(struct kvm_vcpu, arch.timer_cpu.cntv_cval)); DEFINE(KVM_TIMER_CNTVOFF, offsetof(struct kvm, arch.timer.cntvoff)); DEFINE(KVM_TIMER_ENABLED, offsetof(struct kvm, arch.timer.enabled)); -#endif DEFINE(KVM_VGIC_VCTRL, offsetof(struct kvm, arch.vgic.vctrl_base)); -#endif DEFINE(KVM_VTTBR, offsetof(struct kvm, arch.vttbr)); #endif return 0; diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig index 338ace78ed18..f1f79d104309 100644 --- a/arch/arm/kvm/Kconfig +++ b/arch/arm/kvm/Kconfig @@ -18,6 +18,7 @@ if VIRTUALIZATION config KVM bool "Kernel-based Virtual Machine (KVM) support" + depends on MMU && OF select PREEMPT_NOTIFIERS select ANON_INODES select HAVE_KVM_CPU_RELAX_INTERCEPT @@ -26,10 +27,12 @@ config KVM select KVM_ARM_HOST select KVM_GENERIC_DIRTYLOG_READ_PROTECT select SRCU - depends on ARM_VIRT_EXT && ARM_LPAE + select MMU_NOTIFIER + select HAVE_KVM_EVENTFD + select HAVE_KVM_IRQFD + depends on ARM_VIRT_EXT && ARM_LPAE && ARM_ARCH_TIMER ---help--- - Support hosting virtualized guest machines. You will also - need to select one or more of the processor modules below. + Support hosting virtualized guest machines. This module provides access to the hardware capabilities through a character device node named /dev/kvm. @@ -37,10 +40,7 @@ config KVM If unsure, say N. config KVM_ARM_HOST - bool "KVM host support for ARM cpus." - depends on KVM - depends on MMU - select MMU_NOTIFIER + bool ---help--- Provides host support for ARM processors. @@ -55,20 +55,4 @@ config KVM_ARM_MAX_VCPUS large, so only choose a reasonable number that you expect to actually use. -config KVM_ARM_VGIC - bool "KVM support for Virtual GIC" - depends on KVM_ARM_HOST && OF - select HAVE_KVM_IRQCHIP - default y - ---help--- - Adds support for a hardware assisted, in-kernel GIC emulation. - -config KVM_ARM_TIMER - bool "KVM support for Architected Timers" - depends on KVM_ARM_VGIC && ARM_ARCH_TIMER - select HAVE_KVM_IRQCHIP - default y - ---help--- - Adds support for the Architected Timers in virtual machines - endif # VIRTUALIZATION diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile index 443b8bea43e9..139e46c08b6e 100644 --- a/arch/arm/kvm/Makefile +++ b/arch/arm/kvm/Makefile @@ -7,7 +7,7 @@ ifeq ($(plus_virt),+virt) plus_virt_def := -DREQUIRES_VIRT=1 endif -ccflags-y += -Ivirt/kvm -Iarch/arm/kvm +ccflags-y += -Iarch/arm/kvm CFLAGS_arm.o := -I. $(plus_virt_def) CFLAGS_mmu.o := -I. @@ -15,12 +15,12 @@ AFLAGS_init.o := -Wa,-march=armv7-a$(plus_virt) AFLAGS_interrupts.o := -Wa,-march=armv7-a$(plus_virt) KVM := ../../../virt/kvm -kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o +kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o obj-y += kvm-arm.o init.o interrupts.o obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o obj-y += coproc.o coproc_a15.o coproc_a7.o mmio.o psci.o perf.o -obj-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic.o -obj-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v2.o -obj-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v2-emul.o -obj-$(CONFIG_KVM_ARM_TIMER) += $(KVM)/arm/arch_timer.o +obj-y += $(KVM)/arm/vgic.o +obj-y += $(KVM)/arm/vgic-v2.o +obj-y += $(KVM)/arm/vgic-v2-emul.o +obj-y += $(KVM)/arm/arch_timer.o diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index 07e7eb1d7ab6..6f536451ab78 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -61,8 +61,6 @@ static atomic64_t kvm_vmid_gen = ATOMIC64_INIT(1); static u8 kvm_next_vmid; static DEFINE_SPINLOCK(kvm_vmid_lock); -static bool vgic_present; - static void kvm_arm_set_running_vcpu(struct kvm_vcpu *vcpu) { BUG_ON(preemptible()); @@ -173,8 +171,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) int r; switch (ext) { case KVM_CAP_IRQCHIP: - r = vgic_present; - break; + case KVM_CAP_IRQFD: + case KVM_CAP_IOEVENTFD: case KVM_CAP_DEVICE_CTRL: case KVM_CAP_USER_MEMORY: case KVM_CAP_SYNC_MMU: @@ -183,6 +181,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_ARM_PSCI: case KVM_CAP_ARM_PSCI_0_2: case KVM_CAP_READONLY_MEM: + case KVM_CAP_MP_STATE: r = 1; break; case KVM_CAP_COALESCED_MMIO: @@ -268,7 +267,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) { - return 0; + return kvm_timer_should_fire(vcpu); } int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) @@ -313,13 +312,29 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { - return -EINVAL; + if (vcpu->arch.pause) + mp_state->mp_state = KVM_MP_STATE_STOPPED; + else + mp_state->mp_state = KVM_MP_STATE_RUNNABLE; + + return 0; } int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { - return -EINVAL; + switch (mp_state->mp_state) { + case KVM_MP_STATE_RUNNABLE: + vcpu->arch.pause = false; + break; + case KVM_MP_STATE_STOPPED: + vcpu->arch.pause = true; + break; + default: + return -EINVAL; + } + + return 0; } /** @@ -452,6 +467,11 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu) return 0; } +bool kvm_arch_intc_initialized(struct kvm *kvm) +{ + return vgic_initialized(kvm); +} + static void vcpu_pause(struct kvm_vcpu *vcpu) { wait_queue_head_t *wq = kvm_arch_vcpu_wq(vcpu); @@ -540,7 +560,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) vcpu->mode = OUTSIDE_GUEST_MODE; kvm_guest_exit(); - trace_kvm_exit(*vcpu_pc(vcpu)); + trace_kvm_exit(kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu)); /* * We may have taken a host interrupt in HYP mode (ie * while executing the guest). This interrupt is still @@ -831,8 +851,6 @@ static int kvm_vm_ioctl_set_device_addr(struct kvm *kvm, switch (dev_id) { case KVM_ARM_DEVICE_VGIC_V2: - if (!vgic_present) - return -ENXIO; return kvm_vgic_addr(kvm, type, &dev_addr->addr, true); default: return -ENODEV; @@ -847,10 +865,7 @@ long kvm_arch_vm_ioctl(struct file *filp, switch (ioctl) { case KVM_CREATE_IRQCHIP: { - if (vgic_present) - return kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); - else - return -ENXIO; + return kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); } case KVM_ARM_SET_DEVICE_ADDR: { struct kvm_arm_device_addr dev_addr; @@ -1035,10 +1050,6 @@ static int init_hyp_mode(void) if (err) goto out_free_context; -#ifdef CONFIG_KVM_ARM_VGIC - vgic_present = true; -#endif - /* * Init HYP architected timer support */ diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c index 384bab67c462..d503fbb787d3 100644 --- a/arch/arm/kvm/guest.c +++ b/arch/arm/kvm/guest.c @@ -109,22 +109,6 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) return -EINVAL; } -#ifndef CONFIG_KVM_ARM_TIMER - -#define NUM_TIMER_REGS 0 - -static int copy_timer_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) -{ - return 0; -} - -static bool is_timer_reg(u64 index) -{ - return false; -} - -#else - #define NUM_TIMER_REGS 3 static bool is_timer_reg(u64 index) @@ -152,8 +136,6 @@ static int copy_timer_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) return 0; } -#endif - static int set_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { void __user *uaddr = (void __user *)(long)reg->addr; diff --git a/arch/arm/kvm/interrupts_head.S b/arch/arm/kvm/interrupts_head.S index 14d488388480..35e4a3a0c476 100644 --- a/arch/arm/kvm/interrupts_head.S +++ b/arch/arm/kvm/interrupts_head.S @@ -402,7 +402,6 @@ vcpu .req r0 @ vcpu pointer always in r0 * Assumes vcpu pointer in vcpu reg */ .macro save_vgic_state -#ifdef CONFIG_KVM_ARM_VGIC /* Get VGIC VCTRL base into r2 */ ldr r2, [vcpu, #VCPU_KVM] ldr r2, [r2, #KVM_VGIC_VCTRL] @@ -460,7 +459,6 @@ ARM_BE8(rev r6, r6 ) subs r4, r4, #1 bne 1b 2: -#endif .endm /* @@ -469,7 +467,6 @@ ARM_BE8(rev r6, r6 ) * Assumes vcpu pointer in vcpu reg */ .macro restore_vgic_state -#ifdef CONFIG_KVM_ARM_VGIC /* Get VGIC VCTRL base into r2 */ ldr r2, [vcpu, #VCPU_KVM] ldr r2, [r2, #KVM_VGIC_VCTRL] @@ -501,7 +498,6 @@ ARM_BE8(rev r6, r6 ) subs r4, r4, #1 bne 1b 2: -#endif .endm #define CNTHCTL_PL1PCTEN (1 << 0) @@ -515,7 +511,6 @@ ARM_BE8(rev r6, r6 ) * Clobbers r2-r5 */ .macro save_timer_state -#ifdef CONFIG_KVM_ARM_TIMER ldr r4, [vcpu, #VCPU_KVM] ldr r2, [r4, #KVM_TIMER_ENABLED] cmp r2, #0 @@ -537,7 +532,6 @@ ARM_BE8(rev r6, r6 ) mcrr p15, 4, r2, r2, c14 @ CNTVOFF 1: -#endif @ Allow physical timer/counter access for the host mrc p15, 4, r2, c14, c1, 0 @ CNTHCTL orr r2, r2, #(CNTHCTL_PL1PCEN | CNTHCTL_PL1PCTEN) @@ -559,7 +553,6 @@ ARM_BE8(rev r6, r6 ) bic r2, r2, #CNTHCTL_PL1PCEN mcr p15, 4, r2, c14, c1, 0 @ CNTHCTL -#ifdef CONFIG_KVM_ARM_TIMER ldr r4, [vcpu, #VCPU_KVM] ldr r2, [r4, #KVM_TIMER_ENABLED] cmp r2, #0 @@ -579,7 +572,6 @@ ARM_BE8(rev r6, r6 ) and r2, r2, #3 mcr p15, 0, r2, c14, c3, 1 @ CNTV_CTL 1: -#endif .endm .equ vmentry, 0 diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c index 5d3bfc0eb3f0..974b1c606d04 100644 --- a/arch/arm/kvm/mmio.c +++ b/arch/arm/kvm/mmio.c @@ -121,12 +121,11 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run) return 0; } -static int decode_hsr(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, - struct kvm_exit_mmio *mmio) +static int decode_hsr(struct kvm_vcpu *vcpu, bool *is_write, int *len) { unsigned long rt; - int len; - bool is_write, sign_extend; + int access_size; + bool sign_extend; if (kvm_vcpu_dabt_isextabt(vcpu)) { /* cache operation on I/O addr, tell guest unsupported */ @@ -140,17 +139,15 @@ static int decode_hsr(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, return 1; } - len = kvm_vcpu_dabt_get_as(vcpu); - if (unlikely(len < 0)) - return len; + access_size = kvm_vcpu_dabt_get_as(vcpu); + if (unlikely(access_size < 0)) + return access_size; - is_write = kvm_vcpu_dabt_iswrite(vcpu); + *is_write = kvm_vcpu_dabt_iswrite(vcpu); sign_extend = kvm_vcpu_dabt_issext(vcpu); rt = kvm_vcpu_dabt_get_rd(vcpu); - mmio->is_write = is_write; - mmio->phys_addr = fault_ipa; - mmio->len = len; + *len = access_size; vcpu->arch.mmio_decode.sign_extend = sign_extend; vcpu->arch.mmio_decode.rt = rt; @@ -165,20 +162,20 @@ static int decode_hsr(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, phys_addr_t fault_ipa) { - struct kvm_exit_mmio mmio; unsigned long data; unsigned long rt; int ret; + bool is_write; + int len; + u8 data_buf[8]; /* - * Prepare MMIO operation. First stash it in a private - * structure that we can use for in-kernel emulation. If the - * kernel can't handle it, copy it into run->mmio and let user - * space do its magic. + * Prepare MMIO operation. First decode the syndrome data we get + * from the CPU. Then try if some in-kernel emulation feels + * responsible, otherwise let user space do its magic. */ - if (kvm_vcpu_dabt_isvalid(vcpu)) { - ret = decode_hsr(vcpu, fault_ipa, &mmio); + ret = decode_hsr(vcpu, &is_write, &len); if (ret) return ret; } else { @@ -188,21 +185,34 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, rt = vcpu->arch.mmio_decode.rt; - if (mmio.is_write) { - data = vcpu_data_guest_to_host(vcpu, *vcpu_reg(vcpu, rt), - mmio.len); + if (is_write) { + data = vcpu_data_guest_to_host(vcpu, *vcpu_reg(vcpu, rt), len); + + trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, len, fault_ipa, data); + mmio_write_buf(data_buf, len, data); - trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, mmio.len, - fault_ipa, data); - mmio_write_buf(mmio.data, mmio.len, data); + ret = kvm_io_bus_write(vcpu, KVM_MMIO_BUS, fault_ipa, len, + data_buf); } else { - trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, mmio.len, + trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, len, fault_ipa, 0); + + ret = kvm_io_bus_read(vcpu, KVM_MMIO_BUS, fault_ipa, len, + data_buf); } - if (vgic_handle_mmio(vcpu, run, &mmio)) + /* Now prepare kvm_run for the potential return to userland. */ + run->mmio.is_write = is_write; + run->mmio.phys_addr = fault_ipa; + run->mmio.len = len; + memcpy(run->mmio.data, data_buf, len); + + if (!ret) { + /* We handled the access successfully in the kernel. */ + kvm_handle_mmio_return(vcpu, run); return 1; + } - kvm_prepare_mmio(run, &mmio); + run->exit_reason = KVM_EXIT_MMIO; return 0; } diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 3e6859bc3e11..15b050d46fc9 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -290,7 +290,7 @@ static void unmap_range(struct kvm *kvm, pgd_t *pgdp, phys_addr_t addr = start, end = start + size; phys_addr_t next; - pgd = pgdp + pgd_index(addr); + pgd = pgdp + kvm_pgd_index(addr); do { next = kvm_pgd_addr_end(addr, end); if (!pgd_none(*pgd)) @@ -355,7 +355,7 @@ static void stage2_flush_memslot(struct kvm *kvm, phys_addr_t next; pgd_t *pgd; - pgd = kvm->arch.pgd + pgd_index(addr); + pgd = kvm->arch.pgd + kvm_pgd_index(addr); do { next = kvm_pgd_addr_end(addr, end); stage2_flush_puds(kvm, pgd, addr, next); @@ -632,6 +632,20 @@ int create_hyp_io_mappings(void *from, void *to, phys_addr_t phys_addr) __phys_to_pfn(phys_addr), PAGE_HYP_DEVICE); } +/* Free the HW pgd, one page at a time */ +static void kvm_free_hwpgd(void *hwpgd) +{ + free_pages_exact(hwpgd, kvm_get_hwpgd_size()); +} + +/* Allocate the HW PGD, making sure that each page gets its own refcount */ +static void *kvm_alloc_hwpgd(void) +{ + unsigned int size = kvm_get_hwpgd_size(); + + return alloc_pages_exact(size, GFP_KERNEL | __GFP_ZERO); +} + /** * kvm_alloc_stage2_pgd - allocate level-1 table for stage-2 translation. * @kvm: The KVM struct pointer for the VM. @@ -645,15 +659,31 @@ int create_hyp_io_mappings(void *from, void *to, phys_addr_t phys_addr) */ int kvm_alloc_stage2_pgd(struct kvm *kvm) { - int ret; pgd_t *pgd; + void *hwpgd; if (kvm->arch.pgd != NULL) { kvm_err("kvm_arch already initialized?\n"); return -EINVAL; } + hwpgd = kvm_alloc_hwpgd(); + if (!hwpgd) + return -ENOMEM; + + /* When the kernel uses more levels of page tables than the + * guest, we allocate a fake PGD and pre-populate it to point + * to the next-level page table, which will be the real + * initial page table pointed to by the VTTBR. + * + * When KVM_PREALLOC_LEVEL==2, we allocate a single page for + * the PMD and the kernel will use folded pud. + * When KVM_PREALLOC_LEVEL==1, we allocate 2 consecutive PUD + * pages. + */ if (KVM_PREALLOC_LEVEL > 0) { + int i; + /* * Allocate fake pgd for the page table manipulation macros to * work. This is not used by the hardware and we have no @@ -661,30 +691,32 @@ int kvm_alloc_stage2_pgd(struct kvm *kvm) */ pgd = (pgd_t *)kmalloc(PTRS_PER_S2_PGD * sizeof(pgd_t), GFP_KERNEL | __GFP_ZERO); + + if (!pgd) { + kvm_free_hwpgd(hwpgd); + return -ENOMEM; + } + + /* Plug the HW PGD into the fake one. */ + for (i = 0; i < PTRS_PER_S2_PGD; i++) { + if (KVM_PREALLOC_LEVEL == 1) + pgd_populate(NULL, pgd + i, + (pud_t *)hwpgd + i * PTRS_PER_PUD); + else if (KVM_PREALLOC_LEVEL == 2) + pud_populate(NULL, pud_offset(pgd, 0) + i, + (pmd_t *)hwpgd + i * PTRS_PER_PMD); + } } else { /* * Allocate actual first-level Stage-2 page table used by the * hardware for Stage-2 page table walks. */ - pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, S2_PGD_ORDER); + pgd = (pgd_t *)hwpgd; } - if (!pgd) - return -ENOMEM; - - ret = kvm_prealloc_hwpgd(kvm, pgd); - if (ret) - goto out_err; - kvm_clean_pgd(pgd); kvm->arch.pgd = pgd; return 0; -out_err: - if (KVM_PREALLOC_LEVEL > 0) - kfree(pgd); - else - free_pages((unsigned long)pgd, S2_PGD_ORDER); - return ret; } /** @@ -785,11 +817,10 @@ void kvm_free_stage2_pgd(struct kvm *kvm) return; unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE); - kvm_free_hwpgd(kvm); + kvm_free_hwpgd(kvm_get_hwpgd(kvm)); if (KVM_PREALLOC_LEVEL > 0) kfree(kvm->arch.pgd); - else - free_pages((unsigned long)kvm->arch.pgd, S2_PGD_ORDER); + kvm->arch.pgd = NULL; } @@ -799,7 +830,7 @@ static pud_t *stage2_get_pud(struct kvm *kvm, struct kvm_mmu_memory_cache *cache pgd_t *pgd; pud_t *pud; - pgd = kvm->arch.pgd + pgd_index(addr); + pgd = kvm->arch.pgd + kvm_pgd_index(addr); if (WARN_ON(pgd_none(*pgd))) { if (!cache) return NULL; @@ -1089,7 +1120,7 @@ static void stage2_wp_range(struct kvm *kvm, phys_addr_t addr, phys_addr_t end) pgd_t *pgd; phys_addr_t next; - pgd = kvm->arch.pgd + pgd_index(addr); + pgd = kvm->arch.pgd + kvm_pgd_index(addr); do { /* * Release kvm_mmu_lock periodically if the memory region is @@ -1299,10 +1330,51 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, out_unlock: spin_unlock(&kvm->mmu_lock); + kvm_set_pfn_accessed(pfn); kvm_release_pfn_clean(pfn); return ret; } +/* + * Resolve the access fault by making the page young again. + * Note that because the faulting entry is guaranteed not to be + * cached in the TLB, we don't need to invalidate anything. + */ +static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa) +{ + pmd_t *pmd; + pte_t *pte; + pfn_t pfn; + bool pfn_valid = false; + + trace_kvm_access_fault(fault_ipa); + + spin_lock(&vcpu->kvm->mmu_lock); + + pmd = stage2_get_pmd(vcpu->kvm, NULL, fault_ipa); + if (!pmd || pmd_none(*pmd)) /* Nothing there */ + goto out; + + if (kvm_pmd_huge(*pmd)) { /* THP, HugeTLB */ + *pmd = pmd_mkyoung(*pmd); + pfn = pmd_pfn(*pmd); + pfn_valid = true; + goto out; + } + + pte = pte_offset_kernel(pmd, fault_ipa); + if (pte_none(*pte)) /* Nothing there either */ + goto out; + + *pte = pte_mkyoung(*pte); /* Just a page... */ + pfn = pte_pfn(*pte); + pfn_valid = true; +out: + spin_unlock(&vcpu->kvm->mmu_lock); + if (pfn_valid) + kvm_set_pfn_accessed(pfn); +} + /** * kvm_handle_guest_abort - handles all 2nd stage aborts * @vcpu: the VCPU pointer @@ -1333,7 +1405,8 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run) /* Check the stage-2 fault is trans. fault or write fault */ fault_status = kvm_vcpu_trap_get_fault_type(vcpu); - if (fault_status != FSC_FAULT && fault_status != FSC_PERM) { + if (fault_status != FSC_FAULT && fault_status != FSC_PERM && + fault_status != FSC_ACCESS) { kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n", kvm_vcpu_trap_get_class(vcpu), (unsigned long)kvm_vcpu_trap_get_fault(vcpu), @@ -1369,6 +1442,12 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run) /* Userspace should not be able to register out-of-bounds IPAs */ VM_BUG_ON(fault_ipa >= KVM_PHYS_SIZE); + if (fault_status == FSC_ACCESS) { + handle_access_fault(vcpu, fault_ipa); + ret = 1; + goto out_unlock; + } + ret = user_mem_abort(vcpu, fault_ipa, memslot, hva, fault_status); if (ret == 0) ret = 1; @@ -1377,15 +1456,16 @@ out_unlock: return ret; } -static void handle_hva_to_gpa(struct kvm *kvm, - unsigned long start, - unsigned long end, - void (*handler)(struct kvm *kvm, - gpa_t gpa, void *data), - void *data) +static int handle_hva_to_gpa(struct kvm *kvm, + unsigned long start, + unsigned long end, + int (*handler)(struct kvm *kvm, + gpa_t gpa, void *data), + void *data) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; + int ret = 0; slots = kvm_memslots(kvm); @@ -1409,14 +1489,17 @@ static void handle_hva_to_gpa(struct kvm *kvm, for (; gfn < gfn_end; ++gfn) { gpa_t gpa = gfn << PAGE_SHIFT; - handler(kvm, gpa, data); + ret |= handler(kvm, gpa, data); } } + + return ret; } -static void kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, void *data) +static int kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, void *data) { unmap_stage2_range(kvm, gpa, PAGE_SIZE); + return 0; } int kvm_unmap_hva(struct kvm *kvm, unsigned long hva) @@ -1442,7 +1525,7 @@ int kvm_unmap_hva_range(struct kvm *kvm, return 0; } -static void kvm_set_spte_handler(struct kvm *kvm, gpa_t gpa, void *data) +static int kvm_set_spte_handler(struct kvm *kvm, gpa_t gpa, void *data) { pte_t *pte = (pte_t *)data; @@ -1454,6 +1537,7 @@ static void kvm_set_spte_handler(struct kvm *kvm, gpa_t gpa, void *data) * through this calling path. */ stage2_set_pte(kvm, NULL, gpa, pte, 0); + return 0; } @@ -1470,6 +1554,67 @@ void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte) handle_hva_to_gpa(kvm, hva, end, &kvm_set_spte_handler, &stage2_pte); } +static int kvm_age_hva_handler(struct kvm *kvm, gpa_t gpa, void *data) +{ + pmd_t *pmd; + pte_t *pte; + + pmd = stage2_get_pmd(kvm, NULL, gpa); + if (!pmd || pmd_none(*pmd)) /* Nothing there */ + return 0; + + if (kvm_pmd_huge(*pmd)) { /* THP, HugeTLB */ + if (pmd_young(*pmd)) { + *pmd = pmd_mkold(*pmd); + return 1; + } + + return 0; + } + + pte = pte_offset_kernel(pmd, gpa); + if (pte_none(*pte)) + return 0; + + if (pte_young(*pte)) { + *pte = pte_mkold(*pte); /* Just a page... */ + return 1; + } + + return 0; +} + +static int kvm_test_age_hva_handler(struct kvm *kvm, gpa_t gpa, void *data) +{ + pmd_t *pmd; + pte_t *pte; + + pmd = stage2_get_pmd(kvm, NULL, gpa); + if (!pmd || pmd_none(*pmd)) /* Nothing there */ + return 0; + + if (kvm_pmd_huge(*pmd)) /* THP, HugeTLB */ + return pmd_young(*pmd); + + pte = pte_offset_kernel(pmd, gpa); + if (!pte_none(*pte)) /* Just a page... */ + return pte_young(*pte); + + return 0; +} + +int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end) +{ + trace_kvm_age_hva(start, end); + return handle_hva_to_gpa(kvm, start, end, kvm_age_hva_handler, NULL); +} + +int kvm_test_age_hva(struct kvm *kvm, unsigned long hva) +{ + trace_kvm_test_age_hva(hva); + return handle_hva_to_gpa(kvm, hva, hva, kvm_test_age_hva_handler, NULL); +} + void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu) { mmu_free_memory_cache(&vcpu->arch.mmu_page_cache); diff --git a/arch/arm/kvm/trace.h b/arch/arm/kvm/trace.h index 881874b1a036..0ec35392d208 100644 --- a/arch/arm/kvm/trace.h +++ b/arch/arm/kvm/trace.h @@ -25,18 +25,22 @@ TRACE_EVENT(kvm_entry, ); TRACE_EVENT(kvm_exit, - TP_PROTO(unsigned long vcpu_pc), - TP_ARGS(vcpu_pc), + TP_PROTO(unsigned int exit_reason, unsigned long vcpu_pc), + TP_ARGS(exit_reason, vcpu_pc), TP_STRUCT__entry( + __field( unsigned int, exit_reason ) __field( unsigned long, vcpu_pc ) ), TP_fast_assign( + __entry->exit_reason = exit_reason; __entry->vcpu_pc = vcpu_pc; ), - TP_printk("PC: 0x%08lx", __entry->vcpu_pc) + TP_printk("HSR_EC: 0x%04x, PC: 0x%08lx", + __entry->exit_reason, + __entry->vcpu_pc) ); TRACE_EVENT(kvm_guest_fault, @@ -64,6 +68,21 @@ TRACE_EVENT(kvm_guest_fault, __entry->hxfar, __entry->vcpu_pc) ); +TRACE_EVENT(kvm_access_fault, + TP_PROTO(unsigned long ipa), + TP_ARGS(ipa), + + TP_STRUCT__entry( + __field( unsigned long, ipa ) + ), + + TP_fast_assign( + __entry->ipa = ipa; + ), + + TP_printk("IPA: %lx", __entry->ipa) +); + TRACE_EVENT(kvm_irq_line, TP_PROTO(unsigned int type, int vcpu_idx, int irq_num, int level), TP_ARGS(type, vcpu_idx, irq_num, level), @@ -206,6 +225,39 @@ TRACE_EVENT(kvm_set_spte_hva, TP_printk("mmu notifier set pte hva: %#08lx", __entry->hva) ); +TRACE_EVENT(kvm_age_hva, + TP_PROTO(unsigned long start, unsigned long end), + TP_ARGS(start, end), + + TP_STRUCT__entry( + __field( unsigned long, start ) + __field( unsigned long, end ) + ), + + TP_fast_assign( + __entry->start = start; + __entry->end = end; + ), + + TP_printk("mmu notifier age hva: %#08lx -- %#08lx", + __entry->start, __entry->end) +); + +TRACE_EVENT(kvm_test_age_hva, + TP_PROTO(unsigned long hva), + TP_ARGS(hva), + + TP_STRUCT__entry( + __field( unsigned long, hva ) + ), + + TP_fast_assign( + __entry->hva = hva; + ), + + TP_printk("mmu notifier test age hva: %#08lx", __entry->hva) +); + TRACE_EVENT(kvm_hvc, TP_PROTO(unsigned long vcpu_pc, unsigned long r0, unsigned long imm), TP_ARGS(vcpu_pc, r0, imm), diff --git a/arch/arm/mach-asm9260/Kconfig b/arch/arm/mach-asm9260/Kconfig index 8423be76080e..52241207a82a 100644 --- a/arch/arm/mach-asm9260/Kconfig +++ b/arch/arm/mach-asm9260/Kconfig @@ -2,5 +2,7 @@ config MACH_ASM9260 bool "Alphascale ASM9260" depends on ARCH_MULTI_V5 select CPU_ARM926T + select ASM9260_TIMER + select GENERIC_CLOCKEVENTS help Support for Alphascale ASM9260 based platform. diff --git a/arch/arm/mach-msm/board-halibut.c b/arch/arm/mach-msm/board-halibut.c index 61bfe584a9d7..fc832040c6e9 100644 --- a/arch/arm/mach-msm/board-halibut.c +++ b/arch/arm/mach-msm/board-halibut.c @@ -20,6 +20,7 @@ #include <linux/input.h> #include <linux/io.h> #include <linux/delay.h> +#include <linux/smc91x.h> #include <mach/hardware.h> #include <asm/mach-types.h> @@ -46,15 +47,20 @@ static struct resource smc91x_resources[] = { [1] = { .start = MSM_GPIO_TO_INT(49), .end = MSM_GPIO_TO_INT(49), - .flags = IORESOURCE_IRQ, + .flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHLEVEL, }, }; +static struct smc91x_platdata smc91x_platdata = { + .flags = SMC91X_USE_16BIT | SMC91X_NOWAIT, +}; + static struct platform_device smc91x_device = { .name = "smc91x", .id = 0, .num_resources = ARRAY_SIZE(smc91x_resources), .resource = smc91x_resources, + .dev.platform_data = &smc91x_platdata, }; static struct platform_device *devices[] __initdata = { diff --git a/arch/arm/mach-msm/board-qsd8x50.c b/arch/arm/mach-msm/board-qsd8x50.c index 4c748616ef47..10016a3bc698 100644 --- a/arch/arm/mach-msm/board-qsd8x50.c +++ b/arch/arm/mach-msm/board-qsd8x50.c @@ -22,6 +22,7 @@ #include <linux/usb/msm_hsusb.h> #include <linux/err.h> #include <linux/clkdev.h> +#include <linux/smc91x.h> #include <asm/mach-types.h> #include <asm/mach/arch.h> @@ -49,15 +50,20 @@ static struct resource smc91x_resources[] = { .flags = IORESOURCE_MEM, }, [1] = { - .flags = IORESOURCE_IRQ, + .flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHLEVEL, }, }; +static struct smc91x_platdata smc91x_platdata = { + .flags = SMC91X_USE_16BIT | SMC91X_NOWAIT, +}; + static struct platform_device smc91x_device = { .name = "smc91x", .id = 0, .num_resources = ARRAY_SIZE(smc91x_resources), .resource = smc91x_resources, + .dev.platform_data = &smc91x_platdata, }; static int __init msm_init_smc91x(void) diff --git a/arch/arm/mach-pxa/idp.c b/arch/arm/mach-pxa/idp.c index 343c4e3a7c5d..f6d02e4cbcda 100644 --- a/arch/arm/mach-pxa/idp.c +++ b/arch/arm/mach-pxa/idp.c @@ -36,6 +36,7 @@ #include <linux/platform_data/video-pxafb.h> #include <mach/bitfield.h> #include <linux/platform_data/mmc-pxamci.h> +#include <linux/smc91x.h> #include "generic.h" #include "devices.h" @@ -81,11 +82,16 @@ static struct resource smc91x_resources[] = { } }; +static struct smc91x_platdata smc91x_platdata = { + .flags = SMC91X_USE_32BIT | SMC91X_USE_DMA | SMC91X_NOWAIT, +}; + static struct platform_device smc91x_device = { .name = "smc91x", .id = 0, .num_resources = ARRAY_SIZE(smc91x_resources), .resource = smc91x_resources, + .dev.platform_data = &smc91x_platdata, }; static void idp_backlight_power(int on) diff --git a/arch/arm/mach-pxa/lpd270.c b/arch/arm/mach-pxa/lpd270.c index ad777b353bd5..eaee2c20b189 100644 --- a/arch/arm/mach-pxa/lpd270.c +++ b/arch/arm/mach-pxa/lpd270.c @@ -24,6 +24,7 @@ #include <linux/mtd/mtd.h> #include <linux/mtd/partitions.h> #include <linux/pwm_backlight.h> +#include <linux/smc91x.h> #include <asm/types.h> #include <asm/setup.h> @@ -189,15 +190,20 @@ static struct resource smc91x_resources[] = { [1] = { .start = LPD270_ETHERNET_IRQ, .end = LPD270_ETHERNET_IRQ, - .flags = IORESOURCE_IRQ, + .flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHEDGE, }, }; +struct smc91x_platdata smc91x_platdata = { + .flags = SMC91X_USE_16BIT | SMC91X_NOWAIT, +}; + static struct platform_device smc91x_device = { .name = "smc91x", .id = 0, .num_resources = ARRAY_SIZE(smc91x_resources), .resource = smc91x_resources, + .dev.platform_data = &smc91x_platdata, }; static struct resource lpd270_flash_resources[] = { diff --git a/arch/arm/mach-realview/core.c b/arch/arm/mach-realview/core.c index 850e506926df..c309593abdb2 100644 --- a/arch/arm/mach-realview/core.c +++ b/arch/arm/mach-realview/core.c @@ -28,6 +28,7 @@ #include <linux/platform_data/video-clcd-versatile.h> #include <linux/io.h> #include <linux/smsc911x.h> +#include <linux/smc91x.h> #include <linux/ata_platform.h> #include <linux/amba/mmci.h> #include <linux/gfp.h> @@ -94,6 +95,10 @@ static struct smsc911x_platform_config smsc911x_config = { .phy_interface = PHY_INTERFACE_MODE_MII, }; +static struct smc91x_platdata smc91x_platdata = { + .flags = SMC91X_USE_32BIT | SMC91X_NOWAIT, +}; + static struct platform_device realview_eth_device = { .name = "smsc911x", .id = 0, @@ -107,6 +112,8 @@ int realview_eth_register(const char *name, struct resource *res) realview_eth_device.resource = res; if (strcmp(realview_eth_device.name, "smsc911x") == 0) realview_eth_device.dev.platform_data = &smsc911x_config; + else + realview_eth_device.dev.platform_data = &smc91x_platdata; return platform_device_register(&realview_eth_device); } diff --git a/arch/arm/mach-realview/realview_eb.c b/arch/arm/mach-realview/realview_eb.c index 64c88d657f9e..b3869cbbcc68 100644 --- a/arch/arm/mach-realview/realview_eb.c +++ b/arch/arm/mach-realview/realview_eb.c @@ -234,7 +234,7 @@ static struct resource realview_eb_eth_resources[] = { [1] = { .start = IRQ_EB_ETH, .end = IRQ_EB_ETH, - .flags = IORESOURCE_IRQ, + .flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHEDGE, }, }; diff --git a/arch/arm/mach-sa1100/neponset.c b/arch/arm/mach-sa1100/neponset.c index 169262e3040d..af868d258e66 100644 --- a/arch/arm/mach-sa1100/neponset.c +++ b/arch/arm/mach-sa1100/neponset.c @@ -12,6 +12,7 @@ #include <linux/pm.h> #include <linux/serial_core.h> #include <linux/slab.h> +#include <linux/smc91x.h> #include <asm/mach-types.h> #include <asm/mach/map.h> @@ -258,12 +259,17 @@ static int neponset_probe(struct platform_device *dev) 0x02000000, "smc91x-attrib"), { .flags = IORESOURCE_IRQ }, }; + struct smc91x_platdata smc91x_platdata = { + .flags = SMC91X_USE_8BIT | SMC91X_IO_SHIFT_2 | SMC91X_NOWAIT, + }; struct platform_device_info smc91x_devinfo = { .parent = &dev->dev, .name = "smc91x", .id = 0, .res = smc91x_resources, .num_res = ARRAY_SIZE(smc91x_resources), + .data = &smc91x_platdata, + .size_data = sizeof(smc91x_platdata), }; int ret, irq; diff --git a/arch/arm/mach-sa1100/pleb.c b/arch/arm/mach-sa1100/pleb.c index 091261878eff..1525d7b5f1b7 100644 --- a/arch/arm/mach-sa1100/pleb.c +++ b/arch/arm/mach-sa1100/pleb.c @@ -11,6 +11,7 @@ #include <linux/irq.h> #include <linux/io.h> #include <linux/mtd/partitions.h> +#include <linux/smc91x.h> #include <mach/hardware.h> #include <asm/setup.h> @@ -43,12 +44,18 @@ static struct resource smc91x_resources[] = { #endif }; +static struct smc91x_platdata smc91x_platdata = { + .flags = SMC91X_USE_16BIT | SMC91X_NOWAIT, +}; static struct platform_device smc91x_device = { .name = "smc91x", .id = 0, .num_resources = ARRAY_SIZE(smc91x_resources), .resource = smc91x_resources, + .dev = { + .platform_data = &smc91x_platdata, + }, }; static struct platform_device *devices[] __initdata = { diff --git a/arch/arm64/boot/dts/apm/apm-storm.dtsi b/arch/arm64/boot/dts/apm/apm-storm.dtsi index f1ad9c2ab2e9..a857794432d6 100644 --- a/arch/arm64/boot/dts/apm/apm-storm.dtsi +++ b/arch/arm64/boot/dts/apm/apm-storm.dtsi @@ -622,7 +622,7 @@ }; sgenet0: ethernet@1f210000 { - compatible = "apm,xgene-enet"; + compatible = "apm,xgene1-sgenet"; status = "disabled"; reg = <0x0 0x1f210000 0x0 0xd100>, <0x0 0x1f200000 0x0 0Xc300>, @@ -636,7 +636,7 @@ }; xgenet: ethernet@1f610000 { - compatible = "apm,xgene-enet"; + compatible = "apm,xgene1-xgenet"; status = "disabled"; reg = <0x0 0x1f610000 0x0 0xd100>, <0x0 0x1f600000 0x0 0Xc300>, diff --git a/arch/arm64/boot/dts/arm/foundation-v8.dts b/arch/arm64/boot/dts/arm/foundation-v8.dts index 27f32962e55c..4eac8dcea423 100644 --- a/arch/arm64/boot/dts/arm/foundation-v8.dts +++ b/arch/arm64/boot/dts/arm/foundation-v8.dts @@ -34,6 +34,7 @@ reg = <0x0 0x0>; enable-method = "spin-table"; cpu-release-addr = <0x0 0x8000fff8>; + next-level-cache = <&L2_0>; }; cpu@1 { device_type = "cpu"; @@ -41,6 +42,7 @@ reg = <0x0 0x1>; enable-method = "spin-table"; cpu-release-addr = <0x0 0x8000fff8>; + next-level-cache = <&L2_0>; }; cpu@2 { device_type = "cpu"; @@ -48,6 +50,7 @@ reg = <0x0 0x2>; enable-method = "spin-table"; cpu-release-addr = <0x0 0x8000fff8>; + next-level-cache = <&L2_0>; }; cpu@3 { device_type = "cpu"; @@ -55,6 +58,11 @@ reg = <0x0 0x3>; enable-method = "spin-table"; cpu-release-addr = <0x0 0x8000fff8>; + next-level-cache = <&L2_0>; + }; + + L2_0: l2-cache0 { + compatible = "cache"; }; }; diff --git a/arch/arm64/boot/dts/arm/juno.dts b/arch/arm64/boot/dts/arm/juno.dts index d429129ecb3d..133ee59de2d7 100644 --- a/arch/arm64/boot/dts/arm/juno.dts +++ b/arch/arm64/boot/dts/arm/juno.dts @@ -39,6 +39,7 @@ reg = <0x0 0x0>; device_type = "cpu"; enable-method = "psci"; + next-level-cache = <&A57_L2>; }; A57_1: cpu@1 { @@ -46,6 +47,7 @@ reg = <0x0 0x1>; device_type = "cpu"; enable-method = "psci"; + next-level-cache = <&A57_L2>; }; A53_0: cpu@100 { @@ -53,6 +55,7 @@ reg = <0x0 0x100>; device_type = "cpu"; enable-method = "psci"; + next-level-cache = <&A53_L2>; }; A53_1: cpu@101 { @@ -60,6 +63,7 @@ reg = <0x0 0x101>; device_type = "cpu"; enable-method = "psci"; + next-level-cache = <&A53_L2>; }; A53_2: cpu@102 { @@ -67,6 +71,7 @@ reg = <0x0 0x102>; device_type = "cpu"; enable-method = "psci"; + next-level-cache = <&A53_L2>; }; A53_3: cpu@103 { @@ -74,6 +79,15 @@ reg = <0x0 0x103>; device_type = "cpu"; enable-method = "psci"; + next-level-cache = <&A53_L2>; + }; + + A57_L2: l2-cache0 { + compatible = "cache"; + }; + + A53_L2: l2-cache1 { + compatible = "cache"; }; }; diff --git a/arch/arm64/boot/dts/arm/rtsm_ve-aemv8a.dts b/arch/arm64/boot/dts/arm/rtsm_ve-aemv8a.dts index efc59b3baf63..20addabbd127 100644 --- a/arch/arm64/boot/dts/arm/rtsm_ve-aemv8a.dts +++ b/arch/arm64/boot/dts/arm/rtsm_ve-aemv8a.dts @@ -37,6 +37,7 @@ reg = <0x0 0x0>; enable-method = "spin-table"; cpu-release-addr = <0x0 0x8000fff8>; + next-level-cache = <&L2_0>; }; cpu@1 { device_type = "cpu"; @@ -44,6 +45,7 @@ reg = <0x0 0x1>; enable-method = "spin-table"; cpu-release-addr = <0x0 0x8000fff8>; + next-level-cache = <&L2_0>; }; cpu@2 { device_type = "cpu"; @@ -51,6 +53,7 @@ reg = <0x0 0x2>; enable-method = "spin-table"; cpu-release-addr = <0x0 0x8000fff8>; + next-level-cache = <&L2_0>; }; cpu@3 { device_type = "cpu"; @@ -58,6 +61,11 @@ reg = <0x0 0x3>; enable-method = "spin-table"; cpu-release-addr = <0x0 0x8000fff8>; + next-level-cache = <&L2_0>; + }; + + L2_0: l2-cache0 { + compatible = "cache"; }; }; diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile index 5720608c50b1..abb79b3cfcfe 100644 --- a/arch/arm64/crypto/Makefile +++ b/arch/arm64/crypto/Makefile @@ -29,7 +29,7 @@ aes-ce-blk-y := aes-glue-ce.o aes-ce.o obj-$(CONFIG_CRYPTO_AES_ARM64_NEON_BLK) += aes-neon-blk.o aes-neon-blk-y := aes-glue-neon.o aes-neon.o -AFLAGS_aes-ce.o := -DINTERLEAVE=2 -DINTERLEAVE_INLINE +AFLAGS_aes-ce.o := -DINTERLEAVE=4 AFLAGS_aes-neon.o := -DINTERLEAVE=4 CFLAGS_aes-glue-ce.o := -DUSE_V8_CRYPTO_EXTENSIONS diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 5901480bfdca..750bac4e637e 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -20,6 +20,9 @@ #error "Only include this from assembly code" #endif +#ifndef __ASM_ASSEMBLER_H +#define __ASM_ASSEMBLER_H + #include <asm/ptrace.h> #include <asm/thread_info.h> @@ -155,3 +158,5 @@ lr .req x30 // link register #endif orr \rd, \lbits, \hbits, lsl #32 .endm + +#endif /* __ASM_ASSEMBLER_H */ diff --git a/arch/arm64/include/asm/cpuidle.h b/arch/arm64/include/asm/cpuidle.h index 0710654631e7..c60643f14cda 100644 --- a/arch/arm64/include/asm/cpuidle.h +++ b/arch/arm64/include/asm/cpuidle.h @@ -1,6 +1,8 @@ #ifndef __ASM_CPUIDLE_H #define __ASM_CPUIDLE_H +#include <asm/proc-fns.h> + #ifdef CONFIG_CPU_IDLE extern int cpu_init_idle(unsigned int cpu); extern int cpu_suspend(unsigned long arg); diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h index 92bbae381598..70522450ca23 100644 --- a/arch/arm64/include/asm/esr.h +++ b/arch/arm64/include/asm/esr.h @@ -90,6 +90,7 @@ #define ESR_ELx_FSC (0x3F) #define ESR_ELx_FSC_TYPE (0x3C) #define ESR_ELx_FSC_EXTABT (0x10) +#define ESR_ELx_FSC_ACCESS (0x08) #define ESR_ELx_FSC_FAULT (0x04) #define ESR_ELx_FSC_PERM (0x0C) #define ESR_ELx_CV (UL(1) << 24) diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index e2ff32a93b5c..d2f49423c5dc 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -264,8 +264,10 @@ __AARCH64_INSN_FUNCS(ands, 0x7F200000, 0x6A000000) __AARCH64_INSN_FUNCS(bics, 0x7F200000, 0x6A200000) __AARCH64_INSN_FUNCS(b, 0xFC000000, 0x14000000) __AARCH64_INSN_FUNCS(bl, 0xFC000000, 0x94000000) -__AARCH64_INSN_FUNCS(cbz, 0xFE000000, 0x34000000) -__AARCH64_INSN_FUNCS(cbnz, 0xFE000000, 0x35000000) +__AARCH64_INSN_FUNCS(cbz, 0x7F000000, 0x34000000) +__AARCH64_INSN_FUNCS(cbnz, 0x7F000000, 0x35000000) +__AARCH64_INSN_FUNCS(tbz, 0x7F000000, 0x36000000) +__AARCH64_INSN_FUNCS(tbnz, 0x7F000000, 0x37000000) __AARCH64_INSN_FUNCS(bcond, 0xFF000010, 0x54000000) __AARCH64_INSN_FUNCS(svc, 0xFFE0001F, 0xD4000001) __AARCH64_INSN_FUNCS(hvc, 0xFFE0001F, 0xD4000002) diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 94674eb7e7bb..ac6fafb95fe7 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -129,6 +129,9 @@ * 40 bits wide (T0SZ = 24). Systems with a PARange smaller than 40 bits are * not known to exist and will break with this configuration. * + * VTCR_EL2.PS is extracted from ID_AA64MMFR0_EL1.PARange at boot time + * (see hyp-init.S). + * * Note that when using 4K pages, we concatenate two first level page tables * together. * @@ -138,7 +141,6 @@ #ifdef CONFIG_ARM64_64K_PAGES /* * Stage2 translation configuration: - * 40bits output (PS = 2) * 40bits input (T0SZ = 24) * 64kB pages (TG0 = 1) * 2 level page tables (SL = 1) @@ -150,7 +152,6 @@ #else /* * Stage2 translation configuration: - * 40bits output (PS = 2) * 40bits input (T0SZ = 24) * 4kB pages (TG0 = 0) * 3 level page tables (SL = 1) @@ -187,6 +188,7 @@ /* For compatibility with fault code shared with 32-bit */ #define FSC_FAULT ESR_ELx_FSC_FAULT +#define FSC_ACCESS ESR_ELx_FSC_ACCESS #define FSC_PERM ESR_ELx_FSC_PERM /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */ diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 8ac3c70fe3c6..f0f58c9beec0 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -28,6 +28,8 @@ #include <asm/kvm_asm.h> #include <asm/kvm_mmio.h> +#define __KVM_HAVE_ARCH_INTC_INITIALIZED + #if defined(CONFIG_KVM_ARM_MAX_VCPUS) #define KVM_MAX_VCPUS CONFIG_KVM_ARM_MAX_VCPUS #else @@ -177,19 +179,10 @@ int kvm_unmap_hva(struct kvm *kvm, unsigned long hva); int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end); void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); +int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); +int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); /* We do not have shadow page tables, hence the empty hooks */ -static inline int kvm_age_hva(struct kvm *kvm, unsigned long start, - unsigned long end) -{ - return 0; -} - -static inline int kvm_test_age_hva(struct kvm *kvm, unsigned long hva) -{ - return 0; -} - static inline void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, unsigned long address) { diff --git a/arch/arm64/include/asm/kvm_mmio.h b/arch/arm64/include/asm/kvm_mmio.h index 9f52beb7cb13..889c908ee631 100644 --- a/arch/arm64/include/asm/kvm_mmio.h +++ b/arch/arm64/include/asm/kvm_mmio.h @@ -31,28 +31,6 @@ struct kvm_decode { bool sign_extend; }; -/* - * The in-kernel MMIO emulation code wants to use a copy of run->mmio, - * which is an anonymous type. Use our own type instead. - */ -struct kvm_exit_mmio { - phys_addr_t phys_addr; - u8 data[8]; - u32 len; - bool is_write; - void *private; -}; - -static inline void kvm_prepare_mmio(struct kvm_run *run, - struct kvm_exit_mmio *mmio) -{ - run->mmio.phys_addr = mmio->phys_addr; - run->mmio.len = mmio->len; - run->mmio.is_write = mmio->is_write; - memcpy(run->mmio.data, mmio->data, mmio->len); - run->exit_reason = KVM_EXIT_MMIO; -} - int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run); int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, phys_addr_t fault_ipa); diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 6458b5373142..bbfb600fa822 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -158,6 +158,8 @@ static inline bool kvm_s2pmd_readonly(pmd_t *pmd) #define PTRS_PER_S2_PGD (1 << PTRS_PER_S2_PGD_SHIFT) #define S2_PGD_ORDER get_order(PTRS_PER_S2_PGD * sizeof(pgd_t)) +#define kvm_pgd_index(addr) (((addr) >> PGDIR_SHIFT) & (PTRS_PER_S2_PGD - 1)) + /* * If we are concatenating first level stage-2 page tables, we would have less * than or equal to 16 pointers in the fake PGD, because that's what the @@ -171,43 +173,6 @@ static inline bool kvm_s2pmd_readonly(pmd_t *pmd) #define KVM_PREALLOC_LEVEL (0) #endif -/** - * kvm_prealloc_hwpgd - allocate inital table for VTTBR - * @kvm: The KVM struct pointer for the VM. - * @pgd: The kernel pseudo pgd - * - * When the kernel uses more levels of page tables than the guest, we allocate - * a fake PGD and pre-populate it to point to the next-level page table, which - * will be the real initial page table pointed to by the VTTBR. - * - * When KVM_PREALLOC_LEVEL==2, we allocate a single page for the PMD and - * the kernel will use folded pud. When KVM_PREALLOC_LEVEL==1, we - * allocate 2 consecutive PUD pages. - */ -static inline int kvm_prealloc_hwpgd(struct kvm *kvm, pgd_t *pgd) -{ - unsigned int i; - unsigned long hwpgd; - - if (KVM_PREALLOC_LEVEL == 0) - return 0; - - hwpgd = __get_free_pages(GFP_KERNEL | __GFP_ZERO, PTRS_PER_S2_PGD_SHIFT); - if (!hwpgd) - return -ENOMEM; - - for (i = 0; i < PTRS_PER_S2_PGD; i++) { - if (KVM_PREALLOC_LEVEL == 1) - pgd_populate(NULL, pgd + i, - (pud_t *)hwpgd + i * PTRS_PER_PUD); - else if (KVM_PREALLOC_LEVEL == 2) - pud_populate(NULL, pud_offset(pgd, 0) + i, - (pmd_t *)hwpgd + i * PTRS_PER_PMD); - } - - return 0; -} - static inline void *kvm_get_hwpgd(struct kvm *kvm) { pgd_t *pgd = kvm->arch.pgd; @@ -224,12 +189,11 @@ static inline void *kvm_get_hwpgd(struct kvm *kvm) return pmd_offset(pud, 0); } -static inline void kvm_free_hwpgd(struct kvm *kvm) +static inline unsigned int kvm_get_hwpgd_size(void) { - if (KVM_PREALLOC_LEVEL > 0) { - unsigned long hwpgd = (unsigned long)kvm_get_hwpgd(kvm); - free_pages(hwpgd, PTRS_PER_S2_PGD_SHIFT); - } + if (KVM_PREALLOC_LEVEL > 0) + return PTRS_PER_S2_PGD * PAGE_SIZE; + return PTRS_PER_S2_PGD * sizeof(pgd_t); } static inline bool kvm_page_empty(void *ptr) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 16449c535e50..800ec0e87ed9 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -460,7 +460,7 @@ static inline pud_t *pud_offset(pgd_t *pgd, unsigned long addr) static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { const pteval_t mask = PTE_USER | PTE_PXN | PTE_UXN | PTE_RDONLY | - PTE_PROT_NONE | PTE_VALID | PTE_WRITE; + PTE_PROT_NONE | PTE_WRITE | PTE_TYPE_MASK; pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask); return pte; } diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index f9be30ea1cbd..20e9591a60cf 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -45,7 +45,8 @@ #define STACK_TOP STACK_TOP_MAX #endif /* CONFIG_COMPAT */ -#define ARCH_LOW_ADDRESS_LIMIT PHYS_MASK +extern phys_addr_t arm64_dma_phys_limit; +#define ARCH_LOW_ADDRESS_LIMIT (arm64_dma_phys_limit - 1) #endif /* __KERNEL__ */ struct debug_info { diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h index 73f0ce570fb3..4abe9b945f77 100644 --- a/arch/arm64/include/asm/tlbflush.h +++ b/arch/arm64/include/asm/tlbflush.h @@ -24,11 +24,6 @@ #include <linux/sched.h> #include <asm/cputype.h> -extern void __cpu_flush_user_tlb_range(unsigned long, unsigned long, struct vm_area_struct *); -extern void __cpu_flush_kern_tlb_range(unsigned long, unsigned long); - -extern struct cpu_tlb_fns cpu_tlb; - /* * TLB Management * ============== diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index 3ef77a466018..c154c0b7eb60 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -191,6 +191,9 @@ struct kvm_arch_memory_slot { /* Highest supported SPI, from VGIC_NR_IRQS */ #define KVM_ARM_IRQ_GIC_MAX 127 +/* One single KVM irqchip, ie. the VGIC */ +#define KVM_NR_IRQCHIPS 1 + /* PSCI interface */ #define KVM_PSCI_FN_BASE 0x95c1ba5e #define KVM_PSCI_FN(n) (KVM_PSCI_FN_BASE + (n)) diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index bef04afd6031..5ee07eee80c2 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -15,8 +15,9 @@ CFLAGS_REMOVE_return_address.o = -pg arm64-obj-y := cputable.o debug-monitors.o entry.o irq.o fpsimd.o \ entry-fpsimd.o process.o ptrace.o setup.o signal.o \ sys.o stacktrace.o time.o traps.o io.o vdso.o \ - hyp-stub.o psci.o cpu_ops.o insn.o return_address.o \ - cpuinfo.o cpu_errata.o alternative.o cacheinfo.o + hyp-stub.o psci.o psci-call.o cpu_ops.o insn.o \ + return_address.o cpuinfo.o cpu_errata.o \ + alternative.o cacheinfo.o arm64-obj-$(CONFIG_COMPAT) += sys32.o kuser32.o signal32.o \ sys_compat.o entry32.o \ diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c index cf8556ae09d0..c851be795080 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -156,7 +156,7 @@ static int ftrace_modify_graph_caller(bool enable) branch = aarch64_insn_gen_branch_imm(pc, (unsigned long)ftrace_graph_caller, - AARCH64_INSN_BRANCH_LINK); + AARCH64_INSN_BRANCH_NOLINK); nop = aarch64_insn_gen_nop(); if (enable) diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c index 27d4864577e5..c8eca88f12e6 100644 --- a/arch/arm64/kernel/insn.c +++ b/arch/arm64/kernel/insn.c @@ -87,8 +87,10 @@ static void __kprobes *patch_map(void *addr, int fixmap) if (module && IS_ENABLED(CONFIG_DEBUG_SET_MODULE_RONX)) page = vmalloc_to_page(addr); - else + else if (!module && IS_ENABLED(CONFIG_DEBUG_RODATA)) page = virt_to_page(addr); + else + return addr; BUG_ON(!page); set_fixmap(fixmap, page_to_phys(page)); diff --git a/arch/arm64/kernel/psci-call.S b/arch/arm64/kernel/psci-call.S new file mode 100644 index 000000000000..cf83e61cd3b5 --- /dev/null +++ b/arch/arm64/kernel/psci-call.S @@ -0,0 +1,28 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Copyright (C) 2015 ARM Limited + * + * Author: Will Deacon <will.deacon@arm.com> + */ + +#include <linux/linkage.h> + +/* int __invoke_psci_fn_hvc(u64 function_id, u64 arg0, u64 arg1, u64 arg2) */ +ENTRY(__invoke_psci_fn_hvc) + hvc #0 + ret +ENDPROC(__invoke_psci_fn_hvc) + +/* int __invoke_psci_fn_smc(u64 function_id, u64 arg0, u64 arg1, u64 arg2) */ +ENTRY(__invoke_psci_fn_smc) + smc #0 + ret +ENDPROC(__invoke_psci_fn_smc) diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c index 3425f311c49e..9b8a70ae64a1 100644 --- a/arch/arm64/kernel/psci.c +++ b/arch/arm64/kernel/psci.c @@ -57,6 +57,9 @@ static struct psci_operations psci_ops; static int (*invoke_psci_fn)(u64, u64, u64, u64); typedef int (*psci_initcall_t)(const struct device_node *); +asmlinkage int __invoke_psci_fn_hvc(u64, u64, u64, u64); +asmlinkage int __invoke_psci_fn_smc(u64, u64, u64, u64); + enum psci_function { PSCI_FN_CPU_SUSPEND, PSCI_FN_CPU_ON, @@ -109,40 +112,6 @@ static void psci_power_state_unpack(u32 power_state, PSCI_0_2_POWER_STATE_AFFL_SHIFT; } -/* - * The following two functions are invoked via the invoke_psci_fn pointer - * and will not be inlined, allowing us to piggyback on the AAPCS. - */ -static noinline int __invoke_psci_fn_hvc(u64 function_id, u64 arg0, u64 arg1, - u64 arg2) -{ - asm volatile( - __asmeq("%0", "x0") - __asmeq("%1", "x1") - __asmeq("%2", "x2") - __asmeq("%3", "x3") - "hvc #0\n" - : "+r" (function_id) - : "r" (arg0), "r" (arg1), "r" (arg2)); - - return function_id; -} - -static noinline int __invoke_psci_fn_smc(u64 function_id, u64 arg0, u64 arg1, - u64 arg2) -{ - asm volatile( - __asmeq("%0", "x0") - __asmeq("%1", "x1") - __asmeq("%2", "x2") - __asmeq("%3", "x3") - "smc #0\n" - : "+r" (function_id) - : "r" (arg0), "r" (arg1), "r" (arg2)); - - return function_id; -} - static int psci_get_version(void) { int err; diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c index c20a300e2213..d26fcd4cd6e6 100644 --- a/arch/arm64/kernel/signal32.c +++ b/arch/arm64/kernel/signal32.c @@ -154,8 +154,7 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from) case __SI_TIMER: err |= __put_user(from->si_tid, &to->si_tid); err |= __put_user(from->si_overrun, &to->si_overrun); - err |= __put_user((compat_uptr_t)(unsigned long)from->si_ptr, - &to->si_ptr); + err |= __put_user(from->si_int, &to->si_int); break; case __SI_POLL: err |= __put_user(from->si_band, &to->si_band); @@ -184,7 +183,7 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from) case __SI_MESGQ: /* But this is */ err |= __put_user(from->si_pid, &to->si_pid); err |= __put_user(from->si_uid, &to->si_uid); - err |= __put_user((compat_uptr_t)(unsigned long)from->si_ptr, &to->si_ptr); + err |= __put_user(from->si_int, &to->si_int); break; case __SI_SYS: err |= __put_user((compat_uptr_t)(unsigned long) diff --git a/arch/arm64/kernel/vdso/gettimeofday.S b/arch/arm64/kernel/vdso/gettimeofday.S index fe652ffd34c2..efa79e8d4196 100644 --- a/arch/arm64/kernel/vdso/gettimeofday.S +++ b/arch/arm64/kernel/vdso/gettimeofday.S @@ -174,8 +174,6 @@ ENDPROC(__kernel_clock_gettime) /* int __kernel_clock_getres(clockid_t clock_id, struct timespec *res); */ ENTRY(__kernel_clock_getres) .cfi_startproc - cbz w1, 3f - cmp w0, #CLOCK_REALTIME ccmp w0, #CLOCK_MONOTONIC, #0x4, ne b.ne 1f @@ -188,6 +186,7 @@ ENTRY(__kernel_clock_getres) b.ne 4f ldr x2, 6f 2: + cbz w1, 3f stp xzr, x2, [x1] 3: /* res == NULL. */ diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index f5590c81d95f..5105e297ed5f 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -18,6 +18,7 @@ if VIRTUALIZATION config KVM bool "Kernel-based Virtual Machine (KVM) support" + depends on OF select MMU_NOTIFIER select PREEMPT_NOTIFIERS select ANON_INODES @@ -25,10 +26,10 @@ config KVM select HAVE_KVM_ARCH_TLB_FLUSH_ALL select KVM_MMIO select KVM_ARM_HOST - select KVM_ARM_VGIC - select KVM_ARM_TIMER select KVM_GENERIC_DIRTYLOG_READ_PROTECT select SRCU + select HAVE_KVM_EVENTFD + select HAVE_KVM_IRQFD ---help--- Support hosting virtualized guest machines. @@ -50,17 +51,4 @@ config KVM_ARM_MAX_VCPUS large, so only choose a reasonable number that you expect to actually use. -config KVM_ARM_VGIC - bool - depends on KVM_ARM_HOST && OF - select HAVE_KVM_IRQCHIP - ---help--- - Adds support for a hardware assisted, in-kernel GIC emulation. - -config KVM_ARM_TIMER - bool - depends on KVM_ARM_VGIC - ---help--- - Adds support for the Architected Timers in virtual machines. - endif # VIRTUALIZATION diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile index 4e6e09ee4033..d5904f876cdb 100644 --- a/arch/arm64/kvm/Makefile +++ b/arch/arm64/kvm/Makefile @@ -2,7 +2,7 @@ # Makefile for Kernel-based Virtual Machine module # -ccflags-y += -Ivirt/kvm -Iarch/arm64/kvm +ccflags-y += -Iarch/arm64/kvm CFLAGS_arm.o := -I. CFLAGS_mmu.o := -I. @@ -11,7 +11,7 @@ ARM=../../../arch/arm/kvm obj-$(CONFIG_KVM_ARM_HOST) += kvm.o -kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o +kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o kvm-$(CONFIG_KVM_ARM_HOST) += $(ARM)/arm.o $(ARM)/mmu.o $(ARM)/mmio.o kvm-$(CONFIG_KVM_ARM_HOST) += $(ARM)/psci.o $(ARM)/perf.o @@ -19,11 +19,11 @@ kvm-$(CONFIG_KVM_ARM_HOST) += emulate.o inject_fault.o regmap.o kvm-$(CONFIG_KVM_ARM_HOST) += hyp.o hyp-init.o handle_exit.o kvm-$(CONFIG_KVM_ARM_HOST) += guest.o reset.o sys_regs.o sys_regs_generic_v8.o -kvm-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic.o -kvm-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v2.o -kvm-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v2-emul.o -kvm-$(CONFIG_KVM_ARM_VGIC) += vgic-v2-switch.o -kvm-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v3.o -kvm-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v3-emul.o -kvm-$(CONFIG_KVM_ARM_VGIC) += vgic-v3-switch.o -kvm-$(CONFIG_KVM_ARM_TIMER) += $(KVM)/arm/arch_timer.o +kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic.o +kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v2.o +kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v2-emul.o +kvm-$(CONFIG_KVM_ARM_HOST) += vgic-v2-switch.o +kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v3.o +kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v3-emul.o +kvm-$(CONFIG_KVM_ARM_HOST) += vgic-v3-switch.o +kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/arch_timer.o diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 0a24b9b8c698..58e0c2bdde04 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -348,8 +348,6 @@ static struct dma_map_ops swiotlb_dma_ops = { .mapping_error = swiotlb_dma_mapping_error, }; -extern int swiotlb_late_init_with_default_size(size_t default_size); - static int __init atomic_pool_init(void) { pgprot_t prot = __pgprot(PROT_NORMAL_NC); @@ -411,21 +409,13 @@ out: return -ENOMEM; } -static int __init swiotlb_late_init(void) +static int __init arm64_dma_init(void) { - size_t swiotlb_size = min(SZ_64M, MAX_ORDER_NR_PAGES << PAGE_SHIFT); + int ret; dma_ops = &swiotlb_dma_ops; - return swiotlb_late_init_with_default_size(swiotlb_size); -} - -static int __init arm64_dma_init(void) -{ - int ret = 0; - - ret |= swiotlb_late_init(); - ret |= atomic_pool_init(); + ret = atomic_pool_init(); return ret; } diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 71145f952070..ae85da6307bb 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -33,6 +33,7 @@ #include <linux/dma-mapping.h> #include <linux/dma-contiguous.h> #include <linux/efi.h> +#include <linux/swiotlb.h> #include <asm/fixmap.h> #include <asm/memory.h> @@ -45,6 +46,7 @@ #include "mm.h" phys_addr_t memstart_addr __read_mostly = 0; +phys_addr_t arm64_dma_phys_limit __read_mostly; #ifdef CONFIG_BLK_DEV_INITRD static int __init early_initrd(char *p) @@ -85,7 +87,7 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) /* 4GB maximum for 32-bit only capable devices */ if (IS_ENABLED(CONFIG_ZONE_DMA)) { - max_dma = PFN_DOWN(max_zone_dma_phys()); + max_dma = PFN_DOWN(arm64_dma_phys_limit); zone_size[ZONE_DMA] = max_dma - min; } zone_size[ZONE_NORMAL] = max - max_dma; @@ -156,8 +158,6 @@ early_param("mem", early_mem); void __init arm64_memblock_init(void) { - phys_addr_t dma_phys_limit = 0; - memblock_enforce_memory_limit(memory_limit); /* @@ -174,8 +174,10 @@ void __init arm64_memblock_init(void) /* 4GB maximum for 32-bit only capable devices */ if (IS_ENABLED(CONFIG_ZONE_DMA)) - dma_phys_limit = max_zone_dma_phys(); - dma_contiguous_reserve(dma_phys_limit); + arm64_dma_phys_limit = max_zone_dma_phys(); + else + arm64_dma_phys_limit = PHYS_MASK + 1; + dma_contiguous_reserve(arm64_dma_phys_limit); memblock_allow_resize(); memblock_dump_all(); @@ -276,6 +278,8 @@ static void __init free_unused_memmap(void) */ void __init mem_init(void) { + swiotlb_init(1); + set_max_mapnr(pfn_to_page(max_pfn) - mem_map); #ifndef CONFIG_SPARSEMEM_VMEMMAP diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index bb0ea94c4ba1..1d3ec3ddd84b 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -51,7 +51,10 @@ static int change_memory_common(unsigned long addr, int numpages, WARN_ON_ONCE(1); } - if (!is_module_address(start) || !is_module_address(end - 1)) + if (start < MODULES_VADDR || start >= MODULES_END) + return -EINVAL; + + if (end < MODULES_VADDR || end >= MODULES_END) return -EINVAL; data.set_mask = set_mask; diff --git a/arch/frv/include/asm/pgtable.h b/arch/frv/include/asm/pgtable.h index 93bcf2abd1a1..07d7a7ef8bd5 100644 --- a/arch/frv/include/asm/pgtable.h +++ b/arch/frv/include/asm/pgtable.h @@ -123,12 +123,14 @@ extern unsigned long empty_zero_page; #define PGDIR_MASK (~(PGDIR_SIZE - 1)) #define PTRS_PER_PGD 64 +#define __PAGETABLE_PUD_FOLDED #define PUD_SHIFT 26 #define PTRS_PER_PUD 1 #define PUD_SIZE (1UL << PUD_SHIFT) #define PUD_MASK (~(PUD_SIZE - 1)) #define PUE_SIZE 256 +#define __PAGETABLE_PMD_FOLDED #define PMD_SHIFT 26 #define PMD_SIZE (1UL << PMD_SHIFT) #define PMD_MASK (~(PMD_SIZE - 1)) diff --git a/arch/m32r/include/asm/pgtable-2level.h b/arch/m32r/include/asm/pgtable-2level.h index 8fd8ee70266a..421e6ba3a173 100644 --- a/arch/m32r/include/asm/pgtable-2level.h +++ b/arch/m32r/include/asm/pgtable-2level.h @@ -13,6 +13,7 @@ * the M32R is two-level, so we don't really have any * PMD directory physically. */ +#define __PAGETABLE_PMD_FOLDED #define PMD_SHIFT 22 #define PTRS_PER_PMD 1 diff --git a/arch/m68k/include/asm/pgtable_mm.h b/arch/m68k/include/asm/pgtable_mm.h index 28a145bfbb71..35ed4a9981ae 100644 --- a/arch/m68k/include/asm/pgtable_mm.h +++ b/arch/m68k/include/asm/pgtable_mm.h @@ -54,10 +54,12 @@ */ #ifdef CONFIG_SUN3 #define PTRS_PER_PTE 16 +#define __PAGETABLE_PMD_FOLDED #define PTRS_PER_PMD 1 #define PTRS_PER_PGD 2048 #elif defined(CONFIG_COLDFIRE) #define PTRS_PER_PTE 512 +#define __PAGETABLE_PMD_FOLDED #define PTRS_PER_PMD 1 #define PTRS_PER_PGD 1024 #else diff --git a/arch/metag/include/asm/processor.h b/arch/metag/include/asm/processor.h index 881071c07942..13272fd5a5ba 100644 --- a/arch/metag/include/asm/processor.h +++ b/arch/metag/include/asm/processor.h @@ -149,8 +149,8 @@ extern void exit_thread(void); unsigned long get_wchan(struct task_struct *p); -#define KSTK_EIP(tsk) ((tsk)->thread.kernel_context->CurrPC) -#define KSTK_ESP(tsk) ((tsk)->thread.kernel_context->AX[0].U0) +#define KSTK_EIP(tsk) (task_pt_regs(tsk)->ctx.CurrPC) +#define KSTK_ESP(tsk) (task_pt_regs(tsk)->ctx.AX[0].U0) #define user_stack_pointer(regs) ((regs)->ctx.AX[0].U0) diff --git a/arch/mips/include/asm/asmmacro-32.h b/arch/mips/include/asm/asmmacro-32.h index cdac7b3eeaf7..80386470d3a4 100644 --- a/arch/mips/include/asm/asmmacro-32.h +++ b/arch/mips/include/asm/asmmacro-32.h @@ -16,38 +16,38 @@ .set push SET_HARDFLOAT cfc1 \tmp, fcr31 - swc1 $f0, THREAD_FPR0_LS64(\thread) - swc1 $f1, THREAD_FPR1_LS64(\thread) - swc1 $f2, THREAD_FPR2_LS64(\thread) - swc1 $f3, THREAD_FPR3_LS64(\thread) - swc1 $f4, THREAD_FPR4_LS64(\thread) - swc1 $f5, THREAD_FPR5_LS64(\thread) - swc1 $f6, THREAD_FPR6_LS64(\thread) - swc1 $f7, THREAD_FPR7_LS64(\thread) - swc1 $f8, THREAD_FPR8_LS64(\thread) - swc1 $f9, THREAD_FPR9_LS64(\thread) - swc1 $f10, THREAD_FPR10_LS64(\thread) - swc1 $f11, THREAD_FPR11_LS64(\thread) - swc1 $f12, THREAD_FPR12_LS64(\thread) - swc1 $f13, THREAD_FPR13_LS64(\thread) - swc1 $f14, THREAD_FPR14_LS64(\thread) - swc1 $f15, THREAD_FPR15_LS64(\thread) - swc1 $f16, THREAD_FPR16_LS64(\thread) - swc1 $f17, THREAD_FPR17_LS64(\thread) - swc1 $f18, THREAD_FPR18_LS64(\thread) - swc1 $f19, THREAD_FPR19_LS64(\thread) - swc1 $f20, THREAD_FPR20_LS64(\thread) - swc1 $f21, THREAD_FPR21_LS64(\thread) - swc1 $f22, THREAD_FPR22_LS64(\thread) - swc1 $f23, THREAD_FPR23_LS64(\thread) - swc1 $f24, THREAD_FPR24_LS64(\thread) - swc1 $f25, THREAD_FPR25_LS64(\thread) - swc1 $f26, THREAD_FPR26_LS64(\thread) - swc1 $f27, THREAD_FPR27_LS64(\thread) - swc1 $f28, THREAD_FPR28_LS64(\thread) - swc1 $f29, THREAD_FPR29_LS64(\thread) - swc1 $f30, THREAD_FPR30_LS64(\thread) - swc1 $f31, THREAD_FPR31_LS64(\thread) + swc1 $f0, THREAD_FPR0(\thread) + swc1 $f1, THREAD_FPR1(\thread) + swc1 $f2, THREAD_FPR2(\thread) + swc1 $f3, THREAD_FPR3(\thread) + swc1 $f4, THREAD_FPR4(\thread) + swc1 $f5, THREAD_FPR5(\thread) + swc1 $f6, THREAD_FPR6(\thread) + swc1 $f7, THREAD_FPR7(\thread) + swc1 $f8, THREAD_FPR8(\thread) + swc1 $f9, THREAD_FPR9(\thread) + swc1 $f10, THREAD_FPR10(\thread) + swc1 $f11, THREAD_FPR11(\thread) + swc1 $f12, THREAD_FPR12(\thread) + swc1 $f13, THREAD_FPR13(\thread) + swc1 $f14, THREAD_FPR14(\thread) + swc1 $f15, THREAD_FPR15(\thread) + swc1 $f16, THREAD_FPR16(\thread) + swc1 $f17, THREAD_FPR17(\thread) + swc1 $f18, THREAD_FPR18(\thread) + swc1 $f19, THREAD_FPR19(\thread) + swc1 $f20, THREAD_FPR20(\thread) + swc1 $f21, THREAD_FPR21(\thread) + swc1 $f22, THREAD_FPR22(\thread) + swc1 $f23, THREAD_FPR23(\thread) + swc1 $f24, THREAD_FPR24(\thread) + swc1 $f25, THREAD_FPR25(\thread) + swc1 $f26, THREAD_FPR26(\thread) + swc1 $f27, THREAD_FPR27(\thread) + swc1 $f28, THREAD_FPR28(\thread) + swc1 $f29, THREAD_FPR29(\thread) + swc1 $f30, THREAD_FPR30(\thread) + swc1 $f31, THREAD_FPR31(\thread) sw \tmp, THREAD_FCR31(\thread) .set pop .endm @@ -56,38 +56,38 @@ .set push SET_HARDFLOAT lw \tmp, THREAD_FCR31(\thread) - lwc1 $f0, THREAD_FPR0_LS64(\thread) - lwc1 $f1, THREAD_FPR1_LS64(\thread) - lwc1 $f2, THREAD_FPR2_LS64(\thread) - lwc1 $f3, THREAD_FPR3_LS64(\thread) - lwc1 $f4, THREAD_FPR4_LS64(\thread) - lwc1 $f5, THREAD_FPR5_LS64(\thread) - lwc1 $f6, THREAD_FPR6_LS64(\thread) - lwc1 $f7, THREAD_FPR7_LS64(\thread) - lwc1 $f8, THREAD_FPR8_LS64(\thread) - lwc1 $f9, THREAD_FPR9_LS64(\thread) - lwc1 $f10, THREAD_FPR10_LS64(\thread) - lwc1 $f11, THREAD_FPR11_LS64(\thread) - lwc1 $f12, THREAD_FPR12_LS64(\thread) - lwc1 $f13, THREAD_FPR13_LS64(\thread) - lwc1 $f14, THREAD_FPR14_LS64(\thread) - lwc1 $f15, THREAD_FPR15_LS64(\thread) - lwc1 $f16, THREAD_FPR16_LS64(\thread) - lwc1 $f17, THREAD_FPR17_LS64(\thread) - lwc1 $f18, THREAD_FPR18_LS64(\thread) - lwc1 $f19, THREAD_FPR19_LS64(\thread) - lwc1 $f20, THREAD_FPR20_LS64(\thread) - lwc1 $f21, THREAD_FPR21_LS64(\thread) - lwc1 $f22, THREAD_FPR22_LS64(\thread) - lwc1 $f23, THREAD_FPR23_LS64(\thread) - lwc1 $f24, THREAD_FPR24_LS64(\thread) - lwc1 $f25, THREAD_FPR25_LS64(\thread) - lwc1 $f26, THREAD_FPR26_LS64(\thread) - lwc1 $f27, THREAD_FPR27_LS64(\thread) - lwc1 $f28, THREAD_FPR28_LS64(\thread) - lwc1 $f29, THREAD_FPR29_LS64(\thread) - lwc1 $f30, THREAD_FPR30_LS64(\thread) - lwc1 $f31, THREAD_FPR31_LS64(\thread) + lwc1 $f0, THREAD_FPR0(\thread) + lwc1 $f1, THREAD_FPR1(\thread) + lwc1 $f2, THREAD_FPR2(\thread) + lwc1 $f3, THREAD_FPR3(\thread) + lwc1 $f4, THREAD_FPR4(\thread) + lwc1 $f5, THREAD_FPR5(\thread) + lwc1 $f6, THREAD_FPR6(\thread) + lwc1 $f7, THREAD_FPR7(\thread) + lwc1 $f8, THREAD_FPR8(\thread) + lwc1 $f9, THREAD_FPR9(\thread) + lwc1 $f10, THREAD_FPR10(\thread) + lwc1 $f11, THREAD_FPR11(\thread) + lwc1 $f12, THREAD_FPR12(\thread) + lwc1 $f13, THREAD_FPR13(\thread) + lwc1 $f14, THREAD_FPR14(\thread) + lwc1 $f15, THREAD_FPR15(\thread) + lwc1 $f16, THREAD_FPR16(\thread) + lwc1 $f17, THREAD_FPR17(\thread) + lwc1 $f18, THREAD_FPR18(\thread) + lwc1 $f19, THREAD_FPR19(\thread) + lwc1 $f20, THREAD_FPR20(\thread) + lwc1 $f21, THREAD_FPR21(\thread) + lwc1 $f22, THREAD_FPR22(\thread) + lwc1 $f23, THREAD_FPR23(\thread) + lwc1 $f24, THREAD_FPR24(\thread) + lwc1 $f25, THREAD_FPR25(\thread) + lwc1 $f26, THREAD_FPR26(\thread) + lwc1 $f27, THREAD_FPR27(\thread) + lwc1 $f28, THREAD_FPR28(\thread) + lwc1 $f29, THREAD_FPR29(\thread) + lwc1 $f30, THREAD_FPR30(\thread) + lwc1 $f31, THREAD_FPR31(\thread) ctc1 \tmp, fcr31 .set pop .endm diff --git a/arch/mips/include/asm/asmmacro.h b/arch/mips/include/asm/asmmacro.h index 0cae4595e985..6156ac8c4cfb 100644 --- a/arch/mips/include/asm/asmmacro.h +++ b/arch/mips/include/asm/asmmacro.h @@ -60,22 +60,22 @@ .set push SET_HARDFLOAT cfc1 \tmp, fcr31 - sdc1 $f0, THREAD_FPR0_LS64(\thread) - sdc1 $f2, THREAD_FPR2_LS64(\thread) - sdc1 $f4, THREAD_FPR4_LS64(\thread) - sdc1 $f6, THREAD_FPR6_LS64(\thread) - sdc1 $f8, THREAD_FPR8_LS64(\thread) - sdc1 $f10, THREAD_FPR10_LS64(\thread) - sdc1 $f12, THREAD_FPR12_LS64(\thread) - sdc1 $f14, THREAD_FPR14_LS64(\thread) - sdc1 $f16, THREAD_FPR16_LS64(\thread) - sdc1 $f18, THREAD_FPR18_LS64(\thread) - sdc1 $f20, THREAD_FPR20_LS64(\thread) - sdc1 $f22, THREAD_FPR22_LS64(\thread) - sdc1 $f24, THREAD_FPR24_LS64(\thread) - sdc1 $f26, THREAD_FPR26_LS64(\thread) - sdc1 $f28, THREAD_FPR28_LS64(\thread) - sdc1 $f30, THREAD_FPR30_LS64(\thread) + sdc1 $f0, THREAD_FPR0(\thread) + sdc1 $f2, THREAD_FPR2(\thread) + sdc1 $f4, THREAD_FPR4(\thread) + sdc1 $f6, THREAD_FPR6(\thread) + sdc1 $f8, THREAD_FPR8(\thread) + sdc1 $f10, THREAD_FPR10(\thread) + sdc1 $f12, THREAD_FPR12(\thread) + sdc1 $f14, THREAD_FPR14(\thread) + sdc1 $f16, THREAD_FPR16(\thread) + sdc1 $f18, THREAD_FPR18(\thread) + sdc1 $f20, THREAD_FPR20(\thread) + sdc1 $f22, THREAD_FPR22(\thread) + sdc1 $f24, THREAD_FPR24(\thread) + sdc1 $f26, THREAD_FPR26(\thread) + sdc1 $f28, THREAD_FPR28(\thread) + sdc1 $f30, THREAD_FPR30(\thread) sw \tmp, THREAD_FCR31(\thread) .set pop .endm @@ -84,22 +84,22 @@ .set push .set mips64r2 SET_HARDFLOAT - sdc1 $f1, THREAD_FPR1_LS64(\thread) - sdc1 $f3, THREAD_FPR3_LS64(\thread) - sdc1 $f5, THREAD_FPR5_LS64(\thread) - sdc1 $f7, THREAD_FPR7_LS64(\thread) - sdc1 $f9, THREAD_FPR9_LS64(\thread) - sdc1 $f11, THREAD_FPR11_LS64(\thread) - sdc1 $f13, THREAD_FPR13_LS64(\thread) - sdc1 $f15, THREAD_FPR15_LS64(\thread) - sdc1 $f17, THREAD_FPR17_LS64(\thread) - sdc1 $f19, THREAD_FPR19_LS64(\thread) - sdc1 $f21, THREAD_FPR21_LS64(\thread) - sdc1 $f23, THREAD_FPR23_LS64(\thread) - sdc1 $f25, THREAD_FPR25_LS64(\thread) - sdc1 $f27, THREAD_FPR27_LS64(\thread) - sdc1 $f29, THREAD_FPR29_LS64(\thread) - sdc1 $f31, THREAD_FPR31_LS64(\thread) + sdc1 $f1, THREAD_FPR1(\thread) + sdc1 $f3, THREAD_FPR3(\thread) + sdc1 $f5, THREAD_FPR5(\thread) + sdc1 $f7, THREAD_FPR7(\thread) + sdc1 $f9, THREAD_FPR9(\thread) + sdc1 $f11, THREAD_FPR11(\thread) + sdc1 $f13, THREAD_FPR13(\thread) + sdc1 $f15, THREAD_FPR15(\thread) + sdc1 $f17, THREAD_FPR17(\thread) + sdc1 $f19, THREAD_FPR19(\thread) + sdc1 $f21, THREAD_FPR21(\thread) + sdc1 $f23, THREAD_FPR23(\thread) + sdc1 $f25, THREAD_FPR25(\thread) + sdc1 $f27, THREAD_FPR27(\thread) + sdc1 $f29, THREAD_FPR29(\thread) + sdc1 $f31, THREAD_FPR31(\thread) .set pop .endm @@ -118,22 +118,22 @@ .set push SET_HARDFLOAT lw \tmp, THREAD_FCR31(\thread) - ldc1 $f0, THREAD_FPR0_LS64(\thread) - ldc1 $f2, THREAD_FPR2_LS64(\thread) - ldc1 $f4, THREAD_FPR4_LS64(\thread) - ldc1 $f6, THREAD_FPR6_LS64(\thread) - ldc1 $f8, THREAD_FPR8_LS64(\thread) - ldc1 $f10, THREAD_FPR10_LS64(\thread) - ldc1 $f12, THREAD_FPR12_LS64(\thread) - ldc1 $f14, THREAD_FPR14_LS64(\thread) - ldc1 $f16, THREAD_FPR16_LS64(\thread) - ldc1 $f18, THREAD_FPR18_LS64(\thread) - ldc1 $f20, THREAD_FPR20_LS64(\thread) - ldc1 $f22, THREAD_FPR22_LS64(\thread) - ldc1 $f24, THREAD_FPR24_LS64(\thread) - ldc1 $f26, THREAD_FPR26_LS64(\thread) - ldc1 $f28, THREAD_FPR28_LS64(\thread) - ldc1 $f30, THREAD_FPR30_LS64(\thread) + ldc1 $f0, THREAD_FPR0(\thread) + ldc1 $f2, THREAD_FPR2(\thread) + ldc1 $f4, THREAD_FPR4(\thread) + ldc1 $f6, THREAD_FPR6(\thread) + ldc1 $f8, THREAD_FPR8(\thread) + ldc1 $f10, THREAD_FPR10(\thread) + ldc1 $f12, THREAD_FPR12(\thread) + ldc1 $f14, THREAD_FPR14(\thread) + ldc1 $f16, THREAD_FPR16(\thread) + ldc1 $f18, THREAD_FPR18(\thread) + ldc1 $f20, THREAD_FPR20(\thread) + ldc1 $f22, THREAD_FPR22(\thread) + ldc1 $f24, THREAD_FPR24(\thread) + ldc1 $f26, THREAD_FPR26(\thread) + ldc1 $f28, THREAD_FPR28(\thread) + ldc1 $f30, THREAD_FPR30(\thread) ctc1 \tmp, fcr31 .endm @@ -141,22 +141,22 @@ .set push .set mips64r2 SET_HARDFLOAT - ldc1 $f1, THREAD_FPR1_LS64(\thread) - ldc1 $f3, THREAD_FPR3_LS64(\thread) - ldc1 $f5, THREAD_FPR5_LS64(\thread) - ldc1 $f7, THREAD_FPR7_LS64(\thread) - ldc1 $f9, THREAD_FPR9_LS64(\thread) - ldc1 $f11, THREAD_FPR11_LS64(\thread) - ldc1 $f13, THREAD_FPR13_LS64(\thread) - ldc1 $f15, THREAD_FPR15_LS64(\thread) - ldc1 $f17, THREAD_FPR17_LS64(\thread) - ldc1 $f19, THREAD_FPR19_LS64(\thread) - ldc1 $f21, THREAD_FPR21_LS64(\thread) - ldc1 $f23, THREAD_FPR23_LS64(\thread) - ldc1 $f25, THREAD_FPR25_LS64(\thread) - ldc1 $f27, THREAD_FPR27_LS64(\thread) - ldc1 $f29, THREAD_FPR29_LS64(\thread) - ldc1 $f31, THREAD_FPR31_LS64(\thread) + ldc1 $f1, THREAD_FPR1(\thread) + ldc1 $f3, THREAD_FPR3(\thread) + ldc1 $f5, THREAD_FPR5(\thread) + ldc1 $f7, THREAD_FPR7(\thread) + ldc1 $f9, THREAD_FPR9(\thread) + ldc1 $f11, THREAD_FPR11(\thread) + ldc1 $f13, THREAD_FPR13(\thread) + ldc1 $f15, THREAD_FPR15(\thread) + ldc1 $f17, THREAD_FPR17(\thread) + ldc1 $f19, THREAD_FPR19(\thread) + ldc1 $f21, THREAD_FPR21(\thread) + ldc1 $f23, THREAD_FPR23(\thread) + ldc1 $f25, THREAD_FPR25(\thread) + ldc1 $f27, THREAD_FPR27(\thread) + ldc1 $f29, THREAD_FPR29(\thread) + ldc1 $f31, THREAD_FPR31(\thread) .set pop .endm @@ -211,6 +211,22 @@ .endm #ifdef TOOLCHAIN_SUPPORTS_MSA + .macro _cfcmsa rd, cs + .set push + .set mips32r2 + .set msa + cfcmsa \rd, $\cs + .set pop + .endm + + .macro _ctcmsa cd, rs + .set push + .set mips32r2 + .set msa + ctcmsa $\cd, \rs + .set pop + .endm + .macro ld_d wd, off, base .set push .set mips32r2 @@ -227,35 +243,35 @@ .set pop .endm - .macro copy_u_w rd, ws, n + .macro copy_u_w ws, n .set push .set mips32r2 .set msa - copy_u.w \rd, $w\ws[\n] + copy_u.w $1, $w\ws[\n] .set pop .endm - .macro copy_u_d rd, ws, n + .macro copy_u_d ws, n .set push .set mips64r2 .set msa - copy_u.d \rd, $w\ws[\n] + copy_u.d $1, $w\ws[\n] .set pop .endm - .macro insert_w wd, n, rs + .macro insert_w wd, n .set push .set mips32r2 .set msa - insert.w $w\wd[\n], \rs + insert.w $w\wd[\n], $1 .set pop .endm - .macro insert_d wd, n, rs + .macro insert_d wd, n .set push .set mips64r2 .set msa - insert.d $w\wd[\n], \rs + insert.d $w\wd[\n], $1 .set pop .endm #else @@ -283,7 +299,7 @@ /* * Temporary until all toolchains in use include MSA support. */ - .macro cfcmsa rd, cs + .macro _cfcmsa rd, cs .set push .set noat SET_HARDFLOAT @@ -293,7 +309,7 @@ .set pop .endm - .macro ctcmsa cd, rs + .macro _ctcmsa cd, rs .set push .set noat SET_HARDFLOAT @@ -320,44 +336,36 @@ .set pop .endm - .macro copy_u_w rd, ws, n + .macro copy_u_w ws, n .set push .set noat SET_HARDFLOAT .insn .word COPY_UW_MSA_INSN | (\n << 16) | (\ws << 11) - /* move triggers an assembler bug... */ - or \rd, $1, zero .set pop .endm - .macro copy_u_d rd, ws, n + .macro copy_u_d ws, n .set push .set noat SET_HARDFLOAT .insn .word COPY_UD_MSA_INSN | (\n << 16) | (\ws << 11) - /* move triggers an assembler bug... */ - or \rd, $1, zero .set pop .endm - .macro insert_w wd, n, rs + .macro insert_w wd, n .set push .set noat SET_HARDFLOAT - /* move triggers an assembler bug... */ - or $1, \rs, zero .word INSERT_W_MSA_INSN | (\n << 16) | (\wd << 6) .set pop .endm - .macro insert_d wd, n, rs + .macro insert_d wd, n .set push .set noat SET_HARDFLOAT - /* move triggers an assembler bug... */ - or $1, \rs, zero .word INSERT_D_MSA_INSN | (\n << 16) | (\wd << 6) .set pop .endm @@ -399,7 +407,7 @@ .set push .set noat SET_HARDFLOAT - cfcmsa $1, MSA_CSR + _cfcmsa $1, MSA_CSR sw $1, THREAD_MSA_CSR(\thread) .set pop .endm @@ -409,7 +417,7 @@ .set noat SET_HARDFLOAT lw $1, THREAD_MSA_CSR(\thread) - ctcmsa MSA_CSR, $1 + _ctcmsa MSA_CSR, $1 .set pop ld_d 0, THREAD_FPR0, \thread ld_d 1, THREAD_FPR1, \thread @@ -452,9 +460,6 @@ insert_w \wd, 2 insert_w \wd, 3 #endif - .if 31-\wd - msa_init_upper (\wd+1) - .endif .endm .macro msa_init_all_upper @@ -463,6 +468,37 @@ SET_HARDFLOAT not $1, zero msa_init_upper 0 + msa_init_upper 1 + msa_init_upper 2 + msa_init_upper 3 + msa_init_upper 4 + msa_init_upper 5 + msa_init_upper 6 + msa_init_upper 7 + msa_init_upper 8 + msa_init_upper 9 + msa_init_upper 10 + msa_init_upper 11 + msa_init_upper 12 + msa_init_upper 13 + msa_init_upper 14 + msa_init_upper 15 + msa_init_upper 16 + msa_init_upper 17 + msa_init_upper 18 + msa_init_upper 19 + msa_init_upper 20 + msa_init_upper 21 + msa_init_upper 22 + msa_init_upper 23 + msa_init_upper 24 + msa_init_upper 25 + msa_init_upper 26 + msa_init_upper 27 + msa_init_upper 28 + msa_init_upper 29 + msa_init_upper 30 + msa_init_upper 31 .set pop .endm diff --git a/arch/mips/include/asm/fpu.h b/arch/mips/include/asm/fpu.h index dd083e999b08..b104ad9d655f 100644 --- a/arch/mips/include/asm/fpu.h +++ b/arch/mips/include/asm/fpu.h @@ -48,6 +48,12 @@ enum fpu_mode { #define FPU_FR_MASK 0x1 }; +#define __disable_fpu() \ +do { \ + clear_c0_status(ST0_CU1); \ + disable_fpu_hazard(); \ +} while (0) + static inline int __enable_fpu(enum fpu_mode mode) { int fr; @@ -86,7 +92,12 @@ fr_common: enable_fpu_hazard(); /* check FR has the desired value */ - return (!!(read_c0_status() & ST0_FR) == !!fr) ? 0 : SIGFPE; + if (!!(read_c0_status() & ST0_FR) == !!fr) + return 0; + + /* unsupported FR value */ + __disable_fpu(); + return SIGFPE; default: BUG(); @@ -95,12 +106,6 @@ fr_common: return SIGFPE; } -#define __disable_fpu() \ -do { \ - clear_c0_status(ST0_CU1); \ - disable_fpu_hazard(); \ -} while (0) - #define clear_fpu_owner() clear_thread_flag(TIF_USEDFPU) static inline int __is_fpu_owner(void) @@ -170,6 +175,7 @@ static inline void lose_fpu(int save) } disable_msa(); clear_thread_flag(TIF_USEDMSA); + __disable_fpu(); } else if (is_fpu_owner()) { if (save) _save_fp(current); diff --git a/arch/mips/include/asm/kdebug.h b/arch/mips/include/asm/kdebug.h index 6a9af5fcb5d7..cba22ab7ad4d 100644 --- a/arch/mips/include/asm/kdebug.h +++ b/arch/mips/include/asm/kdebug.h @@ -10,7 +10,8 @@ enum die_val { DIE_RI, DIE_PAGE_FAULT, DIE_BREAK, - DIE_SSTEPBP + DIE_SSTEPBP, + DIE_MSAFP }; #endif /* _ASM_MIPS_KDEBUG_H */ diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index ac4fc716062b..4c25823563fe 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -21,10 +21,10 @@ /* MIPS KVM register ids */ #define MIPS_CP0_32(_R, _S) \ - (KVM_REG_MIPS | KVM_REG_SIZE_U32 | 0x10000 | (8 * (_R) + (_S))) + (KVM_REG_MIPS_CP0 | KVM_REG_SIZE_U32 | (8 * (_R) + (_S))) #define MIPS_CP0_64(_R, _S) \ - (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 0x10000 | (8 * (_R) + (_S))) + (KVM_REG_MIPS_CP0 | KVM_REG_SIZE_U64 | (8 * (_R) + (_S))) #define KVM_REG_MIPS_CP0_INDEX MIPS_CP0_32(0, 0) #define KVM_REG_MIPS_CP0_ENTRYLO0 MIPS_CP0_64(2, 0) @@ -42,11 +42,14 @@ #define KVM_REG_MIPS_CP0_STATUS MIPS_CP0_32(12, 0) #define KVM_REG_MIPS_CP0_CAUSE MIPS_CP0_32(13, 0) #define KVM_REG_MIPS_CP0_EPC MIPS_CP0_64(14, 0) +#define KVM_REG_MIPS_CP0_PRID MIPS_CP0_32(15, 0) #define KVM_REG_MIPS_CP0_EBASE MIPS_CP0_64(15, 1) #define KVM_REG_MIPS_CP0_CONFIG MIPS_CP0_32(16, 0) #define KVM_REG_MIPS_CP0_CONFIG1 MIPS_CP0_32(16, 1) #define KVM_REG_MIPS_CP0_CONFIG2 MIPS_CP0_32(16, 2) #define KVM_REG_MIPS_CP0_CONFIG3 MIPS_CP0_32(16, 3) +#define KVM_REG_MIPS_CP0_CONFIG4 MIPS_CP0_32(16, 4) +#define KVM_REG_MIPS_CP0_CONFIG5 MIPS_CP0_32(16, 5) #define KVM_REG_MIPS_CP0_CONFIG7 MIPS_CP0_32(16, 7) #define KVM_REG_MIPS_CP0_XCONTEXT MIPS_CP0_64(20, 0) #define KVM_REG_MIPS_CP0_ERROREPC MIPS_CP0_64(30, 0) @@ -119,6 +122,10 @@ struct kvm_vcpu_stat { u32 syscall_exits; u32 resvd_inst_exits; u32 break_inst_exits; + u32 trap_inst_exits; + u32 msa_fpe_exits; + u32 fpe_exits; + u32 msa_disabled_exits; u32 flush_dcache_exits; u32 halt_successful_poll; u32 halt_wakeup; @@ -138,6 +145,10 @@ enum kvm_mips_exit_types { SYSCALL_EXITS, RESVD_INST_EXITS, BREAK_INST_EXITS, + TRAP_INST_EXITS, + MSA_FPE_EXITS, + FPE_EXITS, + MSA_DISABLED_EXITS, FLUSH_DCACHE_EXITS, MAX_KVM_MIPS_EXIT_TYPES }; @@ -206,6 +217,8 @@ struct mips_coproc { #define MIPS_CP0_CONFIG1_SEL 1 #define MIPS_CP0_CONFIG2_SEL 2 #define MIPS_CP0_CONFIG3_SEL 3 +#define MIPS_CP0_CONFIG4_SEL 4 +#define MIPS_CP0_CONFIG5_SEL 5 /* Config0 register bits */ #define CP0C0_M 31 @@ -262,31 +275,6 @@ struct mips_coproc { #define CP0C3_SM 1 #define CP0C3_TL 0 -/* Have config1, Cacheable, noncoherent, write-back, write allocate*/ -#define MIPS_CONFIG0 \ - ((1 << CP0C0_M) | (0x3 << CP0C0_K0)) - -/* Have config2, no coprocessor2 attached, no MDMX support attached, - no performance counters, watch registers present, - no code compression, EJTAG present, no FPU, no watch registers */ -#define MIPS_CONFIG1 \ -((1 << CP0C1_M) | \ - (0 << CP0C1_C2) | (0 << CP0C1_MD) | (0 << CP0C1_PC) | \ - (0 << CP0C1_WR) | (0 << CP0C1_CA) | (1 << CP0C1_EP) | \ - (0 << CP0C1_FP)) - -/* Have config3, no tertiary/secondary caches implemented */ -#define MIPS_CONFIG2 \ -((1 << CP0C2_M)) - -/* No config4, no DSP ASE, no large physaddr (PABITS), - no external interrupt controller, no vectored interrupts, - no 1kb pages, no SmartMIPS ASE, no trace logic */ -#define MIPS_CONFIG3 \ -((0 << CP0C3_M) | (0 << CP0C3_DSPP) | (0 << CP0C3_LPA) | \ - (0 << CP0C3_VEIC) | (0 << CP0C3_VInt) | (0 << CP0C3_SP) | \ - (0 << CP0C3_SM) | (0 << CP0C3_TL)) - /* MMU types, the first four entries have the same layout as the CP0C0_MT field. */ enum mips_mmu_types { @@ -321,7 +309,9 @@ enum mips_mmu_types { */ #define T_TRAP 13 /* Trap instruction */ #define T_VCEI 14 /* Virtual coherency exception */ +#define T_MSAFPE 14 /* MSA floating point exception */ #define T_FPE 15 /* Floating point exception */ +#define T_MSADIS 21 /* MSA disabled exception */ #define T_WATCH 23 /* Watch address reference */ #define T_VCED 31 /* Virtual coherency data */ @@ -374,6 +364,9 @@ struct kvm_mips_tlb { long tlb_lo1; }; +#define KVM_MIPS_FPU_FPU 0x1 +#define KVM_MIPS_FPU_MSA 0x2 + #define KVM_MIPS_GUEST_TLB_SIZE 64 struct kvm_vcpu_arch { void *host_ebase, *guest_ebase; @@ -395,6 +388,8 @@ struct kvm_vcpu_arch { /* FPU State */ struct mips_fpu_struct fpu; + /* Which FPU state is loaded (KVM_MIPS_FPU_*) */ + unsigned int fpu_inuse; /* COP0 State */ struct mips_coproc *cop0; @@ -441,6 +436,9 @@ struct kvm_vcpu_arch { /* WAIT executed */ int wait; + + u8 fpu_enabled; + u8 msa_enabled; }; @@ -482,11 +480,15 @@ struct kvm_vcpu_arch { #define kvm_read_c0_guest_config1(cop0) (cop0->reg[MIPS_CP0_CONFIG][1]) #define kvm_read_c0_guest_config2(cop0) (cop0->reg[MIPS_CP0_CONFIG][2]) #define kvm_read_c0_guest_config3(cop0) (cop0->reg[MIPS_CP0_CONFIG][3]) +#define kvm_read_c0_guest_config4(cop0) (cop0->reg[MIPS_CP0_CONFIG][4]) +#define kvm_read_c0_guest_config5(cop0) (cop0->reg[MIPS_CP0_CONFIG][5]) #define kvm_read_c0_guest_config7(cop0) (cop0->reg[MIPS_CP0_CONFIG][7]) #define kvm_write_c0_guest_config(cop0, val) (cop0->reg[MIPS_CP0_CONFIG][0] = (val)) #define kvm_write_c0_guest_config1(cop0, val) (cop0->reg[MIPS_CP0_CONFIG][1] = (val)) #define kvm_write_c0_guest_config2(cop0, val) (cop0->reg[MIPS_CP0_CONFIG][2] = (val)) #define kvm_write_c0_guest_config3(cop0, val) (cop0->reg[MIPS_CP0_CONFIG][3] = (val)) +#define kvm_write_c0_guest_config4(cop0, val) (cop0->reg[MIPS_CP0_CONFIG][4] = (val)) +#define kvm_write_c0_guest_config5(cop0, val) (cop0->reg[MIPS_CP0_CONFIG][5] = (val)) #define kvm_write_c0_guest_config7(cop0, val) (cop0->reg[MIPS_CP0_CONFIG][7] = (val)) #define kvm_read_c0_guest_errorepc(cop0) (cop0->reg[MIPS_CP0_ERROR_PC][0]) #define kvm_write_c0_guest_errorepc(cop0, val) (cop0->reg[MIPS_CP0_ERROR_PC][0] = (val)) @@ -567,6 +569,31 @@ static inline void _kvm_atomic_change_c0_guest_reg(unsigned long *reg, kvm_set_c0_guest_ebase(cop0, ((val) & (change))); \ } +/* Helpers */ + +static inline bool kvm_mips_guest_can_have_fpu(struct kvm_vcpu_arch *vcpu) +{ + return (!__builtin_constant_p(cpu_has_fpu) || cpu_has_fpu) && + vcpu->fpu_enabled; +} + +static inline bool kvm_mips_guest_has_fpu(struct kvm_vcpu_arch *vcpu) +{ + return kvm_mips_guest_can_have_fpu(vcpu) && + kvm_read_c0_guest_config1(vcpu->cop0) & MIPS_CONF1_FP; +} + +static inline bool kvm_mips_guest_can_have_msa(struct kvm_vcpu_arch *vcpu) +{ + return (!__builtin_constant_p(cpu_has_msa) || cpu_has_msa) && + vcpu->msa_enabled; +} + +static inline bool kvm_mips_guest_has_msa(struct kvm_vcpu_arch *vcpu) +{ + return kvm_mips_guest_can_have_msa(vcpu) && + kvm_read_c0_guest_config3(vcpu->cop0) & MIPS_CONF3_MSA; +} struct kvm_mips_callbacks { int (*handle_cop_unusable)(struct kvm_vcpu *vcpu); @@ -578,6 +605,10 @@ struct kvm_mips_callbacks { int (*handle_syscall)(struct kvm_vcpu *vcpu); int (*handle_res_inst)(struct kvm_vcpu *vcpu); int (*handle_break)(struct kvm_vcpu *vcpu); + int (*handle_trap)(struct kvm_vcpu *vcpu); + int (*handle_msa_fpe)(struct kvm_vcpu *vcpu); + int (*handle_fpe)(struct kvm_vcpu *vcpu); + int (*handle_msa_disabled)(struct kvm_vcpu *vcpu); int (*vm_init)(struct kvm *kvm); int (*vcpu_init)(struct kvm_vcpu *vcpu); int (*vcpu_setup)(struct kvm_vcpu *vcpu); @@ -596,6 +627,8 @@ struct kvm_mips_callbacks { const struct kvm_one_reg *reg, s64 *v); int (*set_one_reg)(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg, s64 v); + int (*vcpu_get_regs)(struct kvm_vcpu *vcpu); + int (*vcpu_set_regs)(struct kvm_vcpu *vcpu); }; extern struct kvm_mips_callbacks *kvm_mips_callbacks; int kvm_mips_emulation_init(struct kvm_mips_callbacks **install_callbacks); @@ -606,6 +639,19 @@ int kvm_arch_vcpu_dump_regs(struct kvm_vcpu *vcpu); /* Trampoline ASM routine to start running in "Guest" context */ extern int __kvm_mips_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu); +/* FPU/MSA context management */ +void __kvm_save_fpu(struct kvm_vcpu_arch *vcpu); +void __kvm_restore_fpu(struct kvm_vcpu_arch *vcpu); +void __kvm_restore_fcsr(struct kvm_vcpu_arch *vcpu); +void __kvm_save_msa(struct kvm_vcpu_arch *vcpu); +void __kvm_restore_msa(struct kvm_vcpu_arch *vcpu); +void __kvm_restore_msa_upper(struct kvm_vcpu_arch *vcpu); +void __kvm_restore_msacsr(struct kvm_vcpu_arch *vcpu); +void kvm_own_fpu(struct kvm_vcpu *vcpu); +void kvm_own_msa(struct kvm_vcpu *vcpu); +void kvm_drop_fpu(struct kvm_vcpu *vcpu); +void kvm_lose_fpu(struct kvm_vcpu *vcpu); + /* TLB handling */ uint32_t kvm_get_kernel_asid(struct kvm_vcpu *vcpu); @@ -711,6 +757,26 @@ extern enum emulation_result kvm_mips_emulate_bp_exc(unsigned long cause, struct kvm_run *run, struct kvm_vcpu *vcpu); +extern enum emulation_result kvm_mips_emulate_trap_exc(unsigned long cause, + uint32_t *opc, + struct kvm_run *run, + struct kvm_vcpu *vcpu); + +extern enum emulation_result kvm_mips_emulate_msafpe_exc(unsigned long cause, + uint32_t *opc, + struct kvm_run *run, + struct kvm_vcpu *vcpu); + +extern enum emulation_result kvm_mips_emulate_fpe_exc(unsigned long cause, + uint32_t *opc, + struct kvm_run *run, + struct kvm_vcpu *vcpu); + +extern enum emulation_result kvm_mips_emulate_msadis_exc(unsigned long cause, + uint32_t *opc, + struct kvm_run *run, + struct kvm_vcpu *vcpu); + extern enum emulation_result kvm_mips_complete_mmio_load(struct kvm_vcpu *vcpu, struct kvm_run *run); @@ -749,6 +815,11 @@ enum emulation_result kvm_mips_emulate_load(uint32_t inst, struct kvm_run *run, struct kvm_vcpu *vcpu); +unsigned int kvm_mips_config1_wrmask(struct kvm_vcpu *vcpu); +unsigned int kvm_mips_config3_wrmask(struct kvm_vcpu *vcpu); +unsigned int kvm_mips_config4_wrmask(struct kvm_vcpu *vcpu); +unsigned int kvm_mips_config5_wrmask(struct kvm_vcpu *vcpu); + /* Dynamic binary translation */ extern int kvm_mips_trans_cache_index(uint32_t inst, uint32_t *opc, struct kvm_vcpu *vcpu); diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h index b5dcbee01fd7..9b3b48e21c22 100644 --- a/arch/mips/include/asm/processor.h +++ b/arch/mips/include/asm/processor.h @@ -105,7 +105,7 @@ union fpureg { #ifdef CONFIG_CPU_LITTLE_ENDIAN # define FPR_IDX(width, idx) (idx) #else -# define FPR_IDX(width, idx) ((FPU_REG_WIDTH / (width)) - 1 - (idx)) +# define FPR_IDX(width, idx) ((idx) ^ ((64 / (width)) - 1)) #endif #define BUILD_FPR_ACCESS(width) \ diff --git a/arch/mips/include/uapi/asm/kvm.h b/arch/mips/include/uapi/asm/kvm.h index 2c04b6d9ff85..6985eb59b085 100644 --- a/arch/mips/include/uapi/asm/kvm.h +++ b/arch/mips/include/uapi/asm/kvm.h @@ -36,77 +36,85 @@ struct kvm_regs { /* * for KVM_GET_FPU and KVM_SET_FPU - * - * If Status[FR] is zero (32-bit FPU), the upper 32-bits of the FPRs - * are zero filled. */ struct kvm_fpu { - __u64 fpr[32]; - __u32 fir; - __u32 fccr; - __u32 fexr; - __u32 fenr; - __u32 fcsr; - __u32 pad; }; /* - * For MIPS, we use KVM_SET_ONE_REG and KVM_GET_ONE_REG to access CP0 + * For MIPS, we use KVM_SET_ONE_REG and KVM_GET_ONE_REG to access various * registers. The id field is broken down as follows: * - * bits[2..0] - Register 'sel' index. - * bits[7..3] - Register 'rd' index. - * bits[15..8] - Must be zero. - * bits[31..16] - 1 -> CP0 registers. - * bits[51..32] - Must be zero. * bits[63..52] - As per linux/kvm.h + * bits[51..32] - Must be zero. + * bits[31..16] - Register set. + * + * Register set = 0: GP registers from kvm_regs (see definitions below). + * + * Register set = 1: CP0 registers. + * bits[15..8] - Must be zero. + * bits[7..3] - Register 'rd' index. + * bits[2..0] - Register 'sel' index. + * + * Register set = 2: KVM specific registers (see definitions below). + * + * Register set = 3: FPU / MSA registers (see definitions below). * * Other sets registers may be added in the future. Each set would * have its own identifier in bits[31..16]. - * - * The registers defined in struct kvm_regs are also accessible, the - * id values for these are below. */ -#define KVM_REG_MIPS_R0 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 0) -#define KVM_REG_MIPS_R1 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 1) -#define KVM_REG_MIPS_R2 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 2) -#define KVM_REG_MIPS_R3 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 3) -#define KVM_REG_MIPS_R4 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 4) -#define KVM_REG_MIPS_R5 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 5) -#define KVM_REG_MIPS_R6 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 6) -#define KVM_REG_MIPS_R7 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 7) -#define KVM_REG_MIPS_R8 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 8) -#define KVM_REG_MIPS_R9 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 9) -#define KVM_REG_MIPS_R10 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 10) -#define KVM_REG_MIPS_R11 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 11) -#define KVM_REG_MIPS_R12 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 12) -#define KVM_REG_MIPS_R13 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 13) -#define KVM_REG_MIPS_R14 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 14) -#define KVM_REG_MIPS_R15 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 15) -#define KVM_REG_MIPS_R16 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 16) -#define KVM_REG_MIPS_R17 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 17) -#define KVM_REG_MIPS_R18 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 18) -#define KVM_REG_MIPS_R19 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 19) -#define KVM_REG_MIPS_R20 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 20) -#define KVM_REG_MIPS_R21 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 21) -#define KVM_REG_MIPS_R22 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 22) -#define KVM_REG_MIPS_R23 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 23) -#define KVM_REG_MIPS_R24 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 24) -#define KVM_REG_MIPS_R25 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 25) -#define KVM_REG_MIPS_R26 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 26) -#define KVM_REG_MIPS_R27 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 27) -#define KVM_REG_MIPS_R28 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 28) -#define KVM_REG_MIPS_R29 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 29) -#define KVM_REG_MIPS_R30 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 30) -#define KVM_REG_MIPS_R31 (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 31) - -#define KVM_REG_MIPS_HI (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 32) -#define KVM_REG_MIPS_LO (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 33) -#define KVM_REG_MIPS_PC (KVM_REG_MIPS | KVM_REG_SIZE_U64 | 34) - -/* KVM specific control registers */ +#define KVM_REG_MIPS_GP (KVM_REG_MIPS | 0x0000000000000000ULL) +#define KVM_REG_MIPS_CP0 (KVM_REG_MIPS | 0x0000000000010000ULL) +#define KVM_REG_MIPS_KVM (KVM_REG_MIPS | 0x0000000000020000ULL) +#define KVM_REG_MIPS_FPU (KVM_REG_MIPS | 0x0000000000030000ULL) + + +/* + * KVM_REG_MIPS_GP - General purpose registers from kvm_regs. + */ + +#define KVM_REG_MIPS_R0 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 0) +#define KVM_REG_MIPS_R1 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 1) +#define KVM_REG_MIPS_R2 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 2) +#define KVM_REG_MIPS_R3 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 3) +#define KVM_REG_MIPS_R4 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 4) +#define KVM_REG_MIPS_R5 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 5) +#define KVM_REG_MIPS_R6 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 6) +#define KVM_REG_MIPS_R7 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 7) +#define KVM_REG_MIPS_R8 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 8) +#define KVM_REG_MIPS_R9 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 9) +#define KVM_REG_MIPS_R10 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 10) +#define KVM_REG_MIPS_R11 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 11) +#define KVM_REG_MIPS_R12 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 12) +#define KVM_REG_MIPS_R13 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 13) +#define KVM_REG_MIPS_R14 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 14) +#define KVM_REG_MIPS_R15 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 15) +#define KVM_REG_MIPS_R16 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 16) +#define KVM_REG_MIPS_R17 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 17) +#define KVM_REG_MIPS_R18 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 18) +#define KVM_REG_MIPS_R19 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 19) +#define KVM_REG_MIPS_R20 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 20) +#define KVM_REG_MIPS_R21 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 21) +#define KVM_REG_MIPS_R22 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 22) +#define KVM_REG_MIPS_R23 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 23) +#define KVM_REG_MIPS_R24 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 24) +#define KVM_REG_MIPS_R25 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 25) +#define KVM_REG_MIPS_R26 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 26) +#define KVM_REG_MIPS_R27 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 27) +#define KVM_REG_MIPS_R28 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 28) +#define KVM_REG_MIPS_R29 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 29) +#define KVM_REG_MIPS_R30 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 30) +#define KVM_REG_MIPS_R31 (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 31) + +#define KVM_REG_MIPS_HI (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 32) +#define KVM_REG_MIPS_LO (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 33) +#define KVM_REG_MIPS_PC (KVM_REG_MIPS_GP | KVM_REG_SIZE_U64 | 34) + + +/* + * KVM_REG_MIPS_KVM - KVM specific control registers. + */ /* * CP0_Count control @@ -118,8 +126,7 @@ struct kvm_fpu { * safely without losing time or guest timer interrupts. * Other: Reserved, do not change. */ -#define KVM_REG_MIPS_COUNT_CTL (KVM_REG_MIPS | KVM_REG_SIZE_U64 | \ - 0x20000 | 0) +#define KVM_REG_MIPS_COUNT_CTL (KVM_REG_MIPS_KVM | KVM_REG_SIZE_U64 | 0) #define KVM_REG_MIPS_COUNT_CTL_DC 0x00000001 /* @@ -131,15 +138,46 @@ struct kvm_fpu { * emulated. * Modifications to times in the future are rejected. */ -#define KVM_REG_MIPS_COUNT_RESUME (KVM_REG_MIPS | KVM_REG_SIZE_U64 | \ - 0x20000 | 1) +#define KVM_REG_MIPS_COUNT_RESUME (KVM_REG_MIPS_KVM | KVM_REG_SIZE_U64 | 1) /* * CP0_Count rate in Hz * Specifies the rate of the CP0_Count timer in Hz. Modifications occur without * discontinuities in CP0_Count. */ -#define KVM_REG_MIPS_COUNT_HZ (KVM_REG_MIPS | KVM_REG_SIZE_U64 | \ - 0x20000 | 2) +#define KVM_REG_MIPS_COUNT_HZ (KVM_REG_MIPS_KVM | KVM_REG_SIZE_U64 | 2) + + +/* + * KVM_REG_MIPS_FPU - Floating Point and MIPS SIMD Architecture (MSA) registers. + * + * bits[15..8] - Register subset (see definitions below). + * bits[7..5] - Must be zero. + * bits[4..0] - Register number within register subset. + */ + +#define KVM_REG_MIPS_FPR (KVM_REG_MIPS_FPU | 0x0000000000000000ULL) +#define KVM_REG_MIPS_FCR (KVM_REG_MIPS_FPU | 0x0000000000000100ULL) +#define KVM_REG_MIPS_MSACR (KVM_REG_MIPS_FPU | 0x0000000000000200ULL) + +/* + * KVM_REG_MIPS_FPR - Floating point / Vector registers. + */ +#define KVM_REG_MIPS_FPR_32(n) (KVM_REG_MIPS_FPR | KVM_REG_SIZE_U32 | (n)) +#define KVM_REG_MIPS_FPR_64(n) (KVM_REG_MIPS_FPR | KVM_REG_SIZE_U64 | (n)) +#define KVM_REG_MIPS_VEC_128(n) (KVM_REG_MIPS_FPR | KVM_REG_SIZE_U128 | (n)) + +/* + * KVM_REG_MIPS_FCR - Floating point control registers. + */ +#define KVM_REG_MIPS_FCR_IR (KVM_REG_MIPS_FCR | KVM_REG_SIZE_U32 | 0) +#define KVM_REG_MIPS_FCR_CSR (KVM_REG_MIPS_FCR | KVM_REG_SIZE_U32 | 31) + +/* + * KVM_REG_MIPS_MSACR - MIPS SIMD Architecture (MSA) control registers. + */ +#define KVM_REG_MIPS_MSA_IR (KVM_REG_MIPS_MSACR | KVM_REG_SIZE_U32 | 0) +#define KVM_REG_MIPS_MSA_CSR (KVM_REG_MIPS_MSACR | KVM_REG_SIZE_U32 | 1) + /* * KVM MIPS specific structures and definitions diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c index 750d67ac41e9..e59fd7cfac9e 100644 --- a/arch/mips/kernel/asm-offsets.c +++ b/arch/mips/kernel/asm-offsets.c @@ -167,72 +167,6 @@ void output_thread_fpu_defines(void) OFFSET(THREAD_FPR30, task_struct, thread.fpu.fpr[30]); OFFSET(THREAD_FPR31, task_struct, thread.fpu.fpr[31]); - /* the least significant 64 bits of each FP register */ - OFFSET(THREAD_FPR0_LS64, task_struct, - thread.fpu.fpr[0].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR1_LS64, task_struct, - thread.fpu.fpr[1].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR2_LS64, task_struct, - thread.fpu.fpr[2].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR3_LS64, task_struct, - thread.fpu.fpr[3].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR4_LS64, task_struct, - thread.fpu.fpr[4].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR5_LS64, task_struct, - thread.fpu.fpr[5].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR6_LS64, task_struct, - thread.fpu.fpr[6].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR7_LS64, task_struct, - thread.fpu.fpr[7].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR8_LS64, task_struct, - thread.fpu.fpr[8].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR9_LS64, task_struct, - thread.fpu.fpr[9].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR10_LS64, task_struct, - thread.fpu.fpr[10].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR11_LS64, task_struct, - thread.fpu.fpr[11].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR12_LS64, task_struct, - thread.fpu.fpr[12].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR13_LS64, task_struct, - thread.fpu.fpr[13].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR14_LS64, task_struct, - thread.fpu.fpr[14].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR15_LS64, task_struct, - thread.fpu.fpr[15].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR16_LS64, task_struct, - thread.fpu.fpr[16].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR17_LS64, task_struct, - thread.fpu.fpr[17].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR18_LS64, task_struct, - thread.fpu.fpr[18].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR19_LS64, task_struct, - thread.fpu.fpr[19].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR20_LS64, task_struct, - thread.fpu.fpr[20].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR21_LS64, task_struct, - thread.fpu.fpr[21].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR22_LS64, task_struct, - thread.fpu.fpr[22].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR23_LS64, task_struct, - thread.fpu.fpr[23].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR24_LS64, task_struct, - thread.fpu.fpr[24].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR25_LS64, task_struct, - thread.fpu.fpr[25].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR26_LS64, task_struct, - thread.fpu.fpr[26].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR27_LS64, task_struct, - thread.fpu.fpr[27].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR28_LS64, task_struct, - thread.fpu.fpr[28].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR29_LS64, task_struct, - thread.fpu.fpr[29].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR30_LS64, task_struct, - thread.fpu.fpr[30].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FPR31_LS64, task_struct, - thread.fpu.fpr[31].val64[FPR_IDX(64, 0)]); - OFFSET(THREAD_FCR31, task_struct, thread.fpu.fcr31); OFFSET(THREAD_MSA_CSR, task_struct, thread.fpu.msacsr); BLANK(); @@ -470,6 +404,45 @@ void output_kvm_defines(void) OFFSET(VCPU_LO, kvm_vcpu_arch, lo); OFFSET(VCPU_HI, kvm_vcpu_arch, hi); OFFSET(VCPU_PC, kvm_vcpu_arch, pc); + BLANK(); + + OFFSET(VCPU_FPR0, kvm_vcpu_arch, fpu.fpr[0]); + OFFSET(VCPU_FPR1, kvm_vcpu_arch, fpu.fpr[1]); + OFFSET(VCPU_FPR2, kvm_vcpu_arch, fpu.fpr[2]); + OFFSET(VCPU_FPR3, kvm_vcpu_arch, fpu.fpr[3]); + OFFSET(VCPU_FPR4, kvm_vcpu_arch, fpu.fpr[4]); + OFFSET(VCPU_FPR5, kvm_vcpu_arch, fpu.fpr[5]); + OFFSET(VCPU_FPR6, kvm_vcpu_arch, fpu.fpr[6]); + OFFSET(VCPU_FPR7, kvm_vcpu_arch, fpu.fpr[7]); + OFFSET(VCPU_FPR8, kvm_vcpu_arch, fpu.fpr[8]); + OFFSET(VCPU_FPR9, kvm_vcpu_arch, fpu.fpr[9]); + OFFSET(VCPU_FPR10, kvm_vcpu_arch, fpu.fpr[10]); + OFFSET(VCPU_FPR11, kvm_vcpu_arch, fpu.fpr[11]); + OFFSET(VCPU_FPR12, kvm_vcpu_arch, fpu.fpr[12]); + OFFSET(VCPU_FPR13, kvm_vcpu_arch, fpu.fpr[13]); + OFFSET(VCPU_FPR14, kvm_vcpu_arch, fpu.fpr[14]); + OFFSET(VCPU_FPR15, kvm_vcpu_arch, fpu.fpr[15]); + OFFSET(VCPU_FPR16, kvm_vcpu_arch, fpu.fpr[16]); + OFFSET(VCPU_FPR17, kvm_vcpu_arch, fpu.fpr[17]); + OFFSET(VCPU_FPR18, kvm_vcpu_arch, fpu.fpr[18]); + OFFSET(VCPU_FPR19, kvm_vcpu_arch, fpu.fpr[19]); + OFFSET(VCPU_FPR20, kvm_vcpu_arch, fpu.fpr[20]); + OFFSET(VCPU_FPR21, kvm_vcpu_arch, fpu.fpr[21]); + OFFSET(VCPU_FPR22, kvm_vcpu_arch, fpu.fpr[22]); + OFFSET(VCPU_FPR23, kvm_vcpu_arch, fpu.fpr[23]); + OFFSET(VCPU_FPR24, kvm_vcpu_arch, fpu.fpr[24]); + OFFSET(VCPU_FPR25, kvm_vcpu_arch, fpu.fpr[25]); + OFFSET(VCPU_FPR26, kvm_vcpu_arch, fpu.fpr[26]); + OFFSET(VCPU_FPR27, kvm_vcpu_arch, fpu.fpr[27]); + OFFSET(VCPU_FPR28, kvm_vcpu_arch, fpu.fpr[28]); + OFFSET(VCPU_FPR29, kvm_vcpu_arch, fpu.fpr[29]); + OFFSET(VCPU_FPR30, kvm_vcpu_arch, fpu.fpr[30]); + OFFSET(VCPU_FPR31, kvm_vcpu_arch, fpu.fpr[31]); + + OFFSET(VCPU_FCR31, kvm_vcpu_arch, fpu.fcr31); + OFFSET(VCPU_MSA_CSR, kvm_vcpu_arch, fpu.msacsr); + BLANK(); + OFFSET(VCPU_COP0, kvm_vcpu_arch, cop0); OFFSET(VCPU_GUEST_KERNEL_ASID, kvm_vcpu_arch, guest_kernel_asid); OFFSET(VCPU_GUEST_USER_ASID, kvm_vcpu_arch, guest_user_asid); diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S index 2ebaabe3af15..af42e7003f12 100644 --- a/arch/mips/kernel/genex.S +++ b/arch/mips/kernel/genex.S @@ -360,12 +360,15 @@ NESTED(nmi_handler, PT_SIZE, sp) .set mips1 SET_HARDFLOAT cfc1 a1, fcr31 - li a2, ~(0x3f << 12) - and a2, a1 - ctc1 a2, fcr31 .set pop - TRACE_IRQS_ON - STI + CLI + TRACE_IRQS_OFF + .endm + + .macro __build_clear_msa_fpe + _cfcmsa a1, MSA_CSR + CLI + TRACE_IRQS_OFF .endm .macro __build_clear_ade @@ -426,7 +429,7 @@ NESTED(nmi_handler, PT_SIZE, sp) BUILD_HANDLER cpu cpu sti silent /* #11 */ BUILD_HANDLER ov ov sti silent /* #12 */ BUILD_HANDLER tr tr sti silent /* #13 */ - BUILD_HANDLER msa_fpe msa_fpe sti silent /* #14 */ + BUILD_HANDLER msa_fpe msa_fpe msa_fpe silent /* #14 */ BUILD_HANDLER fpe fpe fpe silent /* #15 */ BUILD_HANDLER ftlb ftlb none silent /* #16 */ BUILD_HANDLER msa msa sti silent /* #21 */ diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c index 510452812594..7da6e324dd35 100644 --- a/arch/mips/kernel/ptrace.c +++ b/arch/mips/kernel/ptrace.c @@ -46,6 +46,26 @@ #define CREATE_TRACE_POINTS #include <trace/events/syscalls.h> +static void init_fp_ctx(struct task_struct *target) +{ + /* If FP has been used then the target already has context */ + if (tsk_used_math(target)) + return; + + /* Begin with data registers set to all 1s... */ + memset(&target->thread.fpu.fpr, ~0, sizeof(target->thread.fpu.fpr)); + + /* ...and FCSR zeroed */ + target->thread.fpu.fcr31 = 0; + + /* + * Record that the target has "used" math, such that the context + * just initialised, and any modifications made by the caller, + * aren't discarded. + */ + set_stopped_child_used_math(target); +} + /* * Called by kernel/ptrace.c when detaching.. * @@ -142,6 +162,7 @@ int ptrace_setfpregs(struct task_struct *child, __u32 __user *data) if (!access_ok(VERIFY_READ, data, 33 * 8)) return -EIO; + init_fp_ctx(child); fregs = get_fpu_regs(child); for (i = 0; i < 32; i++) { @@ -439,6 +460,8 @@ static int fpr_set(struct task_struct *target, /* XXX fcr31 */ + init_fp_ctx(target); + if (sizeof(target->thread.fpu.fpr[i]) == sizeof(elf_fpreg_t)) return user_regset_copyin(&pos, &count, &kbuf, &ubuf, &target->thread.fpu, @@ -660,12 +683,7 @@ long arch_ptrace(struct task_struct *child, long request, case FPR_BASE ... FPR_BASE + 31: { union fpureg *fregs = get_fpu_regs(child); - if (!tsk_used_math(child)) { - /* FP not yet used */ - memset(&child->thread.fpu, ~0, - sizeof(child->thread.fpu)); - child->thread.fpu.fcr31 = 0; - } + init_fp_ctx(child); #ifdef CONFIG_32BIT if (test_thread_flag(TIF_32BIT_FPREGS)) { /* diff --git a/arch/mips/kernel/r4k_fpu.S b/arch/mips/kernel/r4k_fpu.S index 676c5030a953..1d88af26ba82 100644 --- a/arch/mips/kernel/r4k_fpu.S +++ b/arch/mips/kernel/r4k_fpu.S @@ -34,7 +34,6 @@ .endm .set noreorder - .set MIPS_ISA_ARCH_LEVEL_RAW LEAF(_save_fp_context) .set push @@ -103,6 +102,7 @@ LEAF(_save_fp_context) /* Save 32-bit process floating point context */ LEAF(_save_fp_context32) .set push + .set MIPS_ISA_ARCH_LEVEL_RAW SET_HARDFLOAT cfc1 t1, fcr31 diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 33984c04b60b..5b4d711f878d 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -701,6 +701,13 @@ asmlinkage void do_ov(struct pt_regs *regs) int process_fpemu_return(int sig, void __user *fault_addr) { + /* + * We can't allow the emulated instruction to leave any of the cause + * bits set in FCSR. If they were then the kernel would take an FP + * exception when restoring FP context. + */ + current->thread.fpu.fcr31 &= ~FPU_CSR_ALL_X; + if (sig == SIGSEGV || sig == SIGBUS) { struct siginfo si = {0}; si.si_addr = fault_addr; @@ -781,6 +788,11 @@ asmlinkage void do_fpe(struct pt_regs *regs, unsigned long fcr31) if (notify_die(DIE_FP, "FP exception", regs, 0, regs_to_trapnr(regs), SIGFPE) == NOTIFY_STOP) goto out; + + /* Clear FCSR.Cause before enabling interrupts */ + write_32bit_cp1_register(CP1_STATUS, fcr31 & ~FPU_CSR_ALL_X); + local_irq_enable(); + die_if_kernel("FP exception in kernel code", regs); if (fcr31 & FPU_CSR_UNI_X) { @@ -804,18 +816,12 @@ asmlinkage void do_fpe(struct pt_regs *regs, unsigned long fcr31) sig = fpu_emulator_cop1Handler(regs, ¤t->thread.fpu, 1, &fault_addr); - /* - * We can't allow the emulated instruction to leave any of - * the cause bit set in $fcr31. - */ - current->thread.fpu.fcr31 &= ~FPU_CSR_ALL_X; + /* If something went wrong, signal */ + process_fpemu_return(sig, fault_addr); /* Restore the hardware register state */ own_fpu(1); /* Using the FPU again. */ - /* If something went wrong, signal */ - process_fpemu_return(sig, fault_addr); - goto out; } else if (fcr31 & FPU_CSR_INV_X) info.si_code = FPE_FLTINV; @@ -1392,13 +1398,22 @@ out: exception_exit(prev_state); } -asmlinkage void do_msa_fpe(struct pt_regs *regs) +asmlinkage void do_msa_fpe(struct pt_regs *regs, unsigned int msacsr) { enum ctx_state prev_state; prev_state = exception_enter(); + if (notify_die(DIE_MSAFP, "MSA FP exception", regs, 0, + regs_to_trapnr(regs), SIGFPE) == NOTIFY_STOP) + goto out; + + /* Clear MSACSR.Cause before enabling interrupts */ + write_msa_csr(msacsr & ~MSA_CSR_CAUSEF); + local_irq_enable(); + die_if_kernel("do_msa_fpe invoked from kernel context!", regs); force_sig(SIGFPE, current); +out: exception_exit(prev_state); } diff --git a/arch/mips/kvm/Makefile b/arch/mips/kvm/Makefile index 401fe027c261..637ebbebd549 100644 --- a/arch/mips/kvm/Makefile +++ b/arch/mips/kvm/Makefile @@ -1,13 +1,15 @@ # Makefile for KVM support for MIPS # -common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o coalesced_mmio.o) +common-objs-y = $(addprefix ../../../virt/kvm/, kvm_main.o coalesced_mmio.o) EXTRA_CFLAGS += -Ivirt/kvm -Iarch/mips/kvm -kvm-objs := $(common-objs) mips.o emulate.o locore.o \ +common-objs-$(CONFIG_CPU_HAS_MSA) += msa.o + +kvm-objs := $(common-objs-y) mips.o emulate.o locore.o \ interrupt.o stats.o commpage.o \ - dyntrans.o trap_emul.o + dyntrans.o trap_emul.o fpu.o obj-$(CONFIG_KVM) += kvm.o obj-y += callback.o tlb.o diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c index fb3e8dfd1ff6..6230f376a44e 100644 --- a/arch/mips/kvm/emulate.c +++ b/arch/mips/kvm/emulate.c @@ -884,6 +884,84 @@ enum emulation_result kvm_mips_emul_tlbp(struct kvm_vcpu *vcpu) return EMULATE_DONE; } +/** + * kvm_mips_config1_wrmask() - Find mask of writable bits in guest Config1 + * @vcpu: Virtual CPU. + * + * Finds the mask of bits which are writable in the guest's Config1 CP0 + * register, by userland (currently read-only to the guest). + */ +unsigned int kvm_mips_config1_wrmask(struct kvm_vcpu *vcpu) +{ + unsigned int mask = 0; + + /* Permit FPU to be present if FPU is supported */ + if (kvm_mips_guest_can_have_fpu(&vcpu->arch)) + mask |= MIPS_CONF1_FP; + + return mask; +} + +/** + * kvm_mips_config3_wrmask() - Find mask of writable bits in guest Config3 + * @vcpu: Virtual CPU. + * + * Finds the mask of bits which are writable in the guest's Config3 CP0 + * register, by userland (currently read-only to the guest). + */ +unsigned int kvm_mips_config3_wrmask(struct kvm_vcpu *vcpu) +{ + /* Config4 is optional */ + unsigned int mask = MIPS_CONF_M; + + /* Permit MSA to be present if MSA is supported */ + if (kvm_mips_guest_can_have_msa(&vcpu->arch)) + mask |= MIPS_CONF3_MSA; + + return mask; +} + +/** + * kvm_mips_config4_wrmask() - Find mask of writable bits in guest Config4 + * @vcpu: Virtual CPU. + * + * Finds the mask of bits which are writable in the guest's Config4 CP0 + * register, by userland (currently read-only to the guest). + */ +unsigned int kvm_mips_config4_wrmask(struct kvm_vcpu *vcpu) +{ + /* Config5 is optional */ + return MIPS_CONF_M; +} + +/** + * kvm_mips_config5_wrmask() - Find mask of writable bits in guest Config5 + * @vcpu: Virtual CPU. + * + * Finds the mask of bits which are writable in the guest's Config5 CP0 + * register, by the guest itself. + */ +unsigned int kvm_mips_config5_wrmask(struct kvm_vcpu *vcpu) +{ + unsigned int mask = 0; + + /* Permit MSAEn changes if MSA supported and enabled */ + if (kvm_mips_guest_has_msa(&vcpu->arch)) + mask |= MIPS_CONF5_MSAEN; + + /* + * Permit guest FPU mode changes if FPU is enabled and the relevant + * feature exists according to FIR register. + */ + if (kvm_mips_guest_has_fpu(&vcpu->arch)) { + if (cpu_has_fre) + mask |= MIPS_CONF5_FRE; + /* We don't support UFR or UFE */ + } + + return mask; +} + enum emulation_result kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc, uint32_t cause, struct kvm_run *run, struct kvm_vcpu *vcpu) @@ -1021,18 +1099,114 @@ enum emulation_result kvm_mips_emulate_CP0(uint32_t inst, uint32_t *opc, kvm_mips_write_compare(vcpu, vcpu->arch.gprs[rt]); } else if ((rd == MIPS_CP0_STATUS) && (sel == 0)) { - kvm_write_c0_guest_status(cop0, - vcpu->arch.gprs[rt]); + unsigned int old_val, val, change; + + old_val = kvm_read_c0_guest_status(cop0); + val = vcpu->arch.gprs[rt]; + change = val ^ old_val; + + /* Make sure that the NMI bit is never set */ + val &= ~ST0_NMI; + + /* + * Don't allow CU1 or FR to be set unless FPU + * capability enabled and exists in guest + * configuration. + */ + if (!kvm_mips_guest_has_fpu(&vcpu->arch)) + val &= ~(ST0_CU1 | ST0_FR); + + /* + * Also don't allow FR to be set if host doesn't + * support it. + */ + if (!(current_cpu_data.fpu_id & MIPS_FPIR_F64)) + val &= ~ST0_FR; + + + /* Handle changes in FPU mode */ + preempt_disable(); + + /* + * FPU and Vector register state is made + * UNPREDICTABLE by a change of FR, so don't + * even bother saving it. + */ + if (change & ST0_FR) + kvm_drop_fpu(vcpu); + + /* + * If MSA state is already live, it is undefined + * how it interacts with FR=0 FPU state, and we + * don't want to hit reserved instruction + * exceptions trying to save the MSA state later + * when CU=1 && FR=1, so play it safe and save + * it first. + */ + if (change & ST0_CU1 && !(val & ST0_FR) && + vcpu->arch.fpu_inuse & KVM_MIPS_FPU_MSA) + kvm_lose_fpu(vcpu); + /* - * Make sure that CU1 and NMI bits are - * never set + * Propagate CU1 (FPU enable) changes + * immediately if the FPU context is already + * loaded. When disabling we leave the context + * loaded so it can be quickly enabled again in + * the near future. */ - kvm_clear_c0_guest_status(cop0, - (ST0_CU1 | ST0_NMI)); + if (change & ST0_CU1 && + vcpu->arch.fpu_inuse & KVM_MIPS_FPU_FPU) + change_c0_status(ST0_CU1, val); + + preempt_enable(); + + kvm_write_c0_guest_status(cop0, val); #ifdef CONFIG_KVM_MIPS_DYN_TRANS - kvm_mips_trans_mtc0(inst, opc, vcpu); + /* + * If FPU present, we need CU1/FR bits to take + * effect fairly soon. + */ + if (!kvm_mips_guest_has_fpu(&vcpu->arch)) + kvm_mips_trans_mtc0(inst, opc, vcpu); #endif + } else if ((rd == MIPS_CP0_CONFIG) && (sel == 5)) { + unsigned int old_val, val, change, wrmask; + + old_val = kvm_read_c0_guest_config5(cop0); + val = vcpu->arch.gprs[rt]; + + /* Only a few bits are writable in Config5 */ + wrmask = kvm_mips_config5_wrmask(vcpu); + change = (val ^ old_val) & wrmask; + val = old_val ^ change; + + + /* Handle changes in FPU/MSA modes */ + preempt_disable(); + + /* + * Propagate FRE changes immediately if the FPU + * context is already loaded. + */ + if (change & MIPS_CONF5_FRE && + vcpu->arch.fpu_inuse & KVM_MIPS_FPU_FPU) + change_c0_config5(MIPS_CONF5_FRE, val); + + /* + * Propagate MSAEn changes immediately if the + * MSA context is already loaded. When disabling + * we leave the context loaded so it can be + * quickly enabled again in the near future. + */ + if (change & MIPS_CONF5_MSAEN && + vcpu->arch.fpu_inuse & KVM_MIPS_FPU_MSA) + change_c0_config5(MIPS_CONF5_MSAEN, + val); + + preempt_enable(); + + kvm_write_c0_guest_config5(cop0, val); } else if ((rd == MIPS_CP0_CAUSE) && (sel == 0)) { uint32_t old_cause, new_cause; @@ -1970,6 +2144,146 @@ enum emulation_result kvm_mips_emulate_bp_exc(unsigned long cause, return er; } +enum emulation_result kvm_mips_emulate_trap_exc(unsigned long cause, + uint32_t *opc, + struct kvm_run *run, + struct kvm_vcpu *vcpu) +{ + struct mips_coproc *cop0 = vcpu->arch.cop0; + struct kvm_vcpu_arch *arch = &vcpu->arch; + enum emulation_result er = EMULATE_DONE; + + if ((kvm_read_c0_guest_status(cop0) & ST0_EXL) == 0) { + /* save old pc */ + kvm_write_c0_guest_epc(cop0, arch->pc); + kvm_set_c0_guest_status(cop0, ST0_EXL); + + if (cause & CAUSEF_BD) + kvm_set_c0_guest_cause(cop0, CAUSEF_BD); + else + kvm_clear_c0_guest_cause(cop0, CAUSEF_BD); + + kvm_debug("Delivering TRAP @ pc %#lx\n", arch->pc); + + kvm_change_c0_guest_cause(cop0, (0xff), + (T_TRAP << CAUSEB_EXCCODE)); + + /* Set PC to the exception entry point */ + arch->pc = KVM_GUEST_KSEG0 + 0x180; + + } else { + kvm_err("Trying to deliver TRAP when EXL is already set\n"); + er = EMULATE_FAIL; + } + + return er; +} + +enum emulation_result kvm_mips_emulate_msafpe_exc(unsigned long cause, + uint32_t *opc, + struct kvm_run *run, + struct kvm_vcpu *vcpu) +{ + struct mips_coproc *cop0 = vcpu->arch.cop0; + struct kvm_vcpu_arch *arch = &vcpu->arch; + enum emulation_result er = EMULATE_DONE; + + if ((kvm_read_c0_guest_status(cop0) & ST0_EXL) == 0) { + /* save old pc */ + kvm_write_c0_guest_epc(cop0, arch->pc); + kvm_set_c0_guest_status(cop0, ST0_EXL); + + if (cause & CAUSEF_BD) + kvm_set_c0_guest_cause(cop0, CAUSEF_BD); + else + kvm_clear_c0_guest_cause(cop0, CAUSEF_BD); + + kvm_debug("Delivering MSAFPE @ pc %#lx\n", arch->pc); + + kvm_change_c0_guest_cause(cop0, (0xff), + (T_MSAFPE << CAUSEB_EXCCODE)); + + /* Set PC to the exception entry point */ + arch->pc = KVM_GUEST_KSEG0 + 0x180; + + } else { + kvm_err("Trying to deliver MSAFPE when EXL is already set\n"); + er = EMULATE_FAIL; + } + + return er; +} + +enum emulation_result kvm_mips_emulate_fpe_exc(unsigned long cause, + uint32_t *opc, + struct kvm_run *run, + struct kvm_vcpu *vcpu) +{ + struct mips_coproc *cop0 = vcpu->arch.cop0; + struct kvm_vcpu_arch *arch = &vcpu->arch; + enum emulation_result er = EMULATE_DONE; + + if ((kvm_read_c0_guest_status(cop0) & ST0_EXL) == 0) { + /* save old pc */ + kvm_write_c0_guest_epc(cop0, arch->pc); + kvm_set_c0_guest_status(cop0, ST0_EXL); + + if (cause & CAUSEF_BD) + kvm_set_c0_guest_cause(cop0, CAUSEF_BD); + else + kvm_clear_c0_guest_cause(cop0, CAUSEF_BD); + + kvm_debug("Delivering FPE @ pc %#lx\n", arch->pc); + + kvm_change_c0_guest_cause(cop0, (0xff), + (T_FPE << CAUSEB_EXCCODE)); + + /* Set PC to the exception entry point */ + arch->pc = KVM_GUEST_KSEG0 + 0x180; + + } else { + kvm_err("Trying to deliver FPE when EXL is already set\n"); + er = EMULATE_FAIL; + } + + return er; +} + +enum emulation_result kvm_mips_emulate_msadis_exc(unsigned long cause, + uint32_t *opc, + struct kvm_run *run, + struct kvm_vcpu *vcpu) +{ + struct mips_coproc *cop0 = vcpu->arch.cop0; + struct kvm_vcpu_arch *arch = &vcpu->arch; + enum emulation_result er = EMULATE_DONE; + + if ((kvm_read_c0_guest_status(cop0) & ST0_EXL) == 0) { + /* save old pc */ + kvm_write_c0_guest_epc(cop0, arch->pc); + kvm_set_c0_guest_status(cop0, ST0_EXL); + + if (cause & CAUSEF_BD) + kvm_set_c0_guest_cause(cop0, CAUSEF_BD); + else + kvm_clear_c0_guest_cause(cop0, CAUSEF_BD); + + kvm_debug("Delivering MSADIS @ pc %#lx\n", arch->pc); + + kvm_change_c0_guest_cause(cop0, (0xff), + (T_MSADIS << CAUSEB_EXCCODE)); + + /* Set PC to the exception entry point */ + arch->pc = KVM_GUEST_KSEG0 + 0x180; + + } else { + kvm_err("Trying to deliver MSADIS when EXL is already set\n"); + er = EMULATE_FAIL; + } + + return er; +} + /* ll/sc, rdhwr, sync emulation */ #define OPCODE 0xfc000000 @@ -2176,6 +2490,10 @@ enum emulation_result kvm_mips_check_privilege(unsigned long cause, case T_SYSCALL: case T_BREAK: case T_RES_INST: + case T_TRAP: + case T_MSAFPE: + case T_FPE: + case T_MSADIS: break; case T_COP_UNUSABLE: diff --git a/arch/mips/kvm/fpu.S b/arch/mips/kvm/fpu.S new file mode 100644 index 000000000000..531fbf5131c0 --- /dev/null +++ b/arch/mips/kvm/fpu.S @@ -0,0 +1,122 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * FPU context handling code for KVM. + * + * Copyright (C) 2015 Imagination Technologies Ltd. + */ + +#include <asm/asm.h> +#include <asm/asm-offsets.h> +#include <asm/fpregdef.h> +#include <asm/mipsregs.h> +#include <asm/regdef.h> + + .set noreorder + .set noat + +LEAF(__kvm_save_fpu) + .set push + .set mips64r2 + SET_HARDFLOAT + mfc0 t0, CP0_STATUS + sll t0, t0, 5 # is Status.FR set? + bgez t0, 1f # no: skip odd doubles + nop + sdc1 $f1, VCPU_FPR1(a0) + sdc1 $f3, VCPU_FPR3(a0) + sdc1 $f5, VCPU_FPR5(a0) + sdc1 $f7, VCPU_FPR7(a0) + sdc1 $f9, VCPU_FPR9(a0) + sdc1 $f11, VCPU_FPR11(a0) + sdc1 $f13, VCPU_FPR13(a0) + sdc1 $f15, VCPU_FPR15(a0) + sdc1 $f17, VCPU_FPR17(a0) + sdc1 $f19, VCPU_FPR19(a0) + sdc1 $f21, VCPU_FPR21(a0) + sdc1 $f23, VCPU_FPR23(a0) + sdc1 $f25, VCPU_FPR25(a0) + sdc1 $f27, VCPU_FPR27(a0) + sdc1 $f29, VCPU_FPR29(a0) + sdc1 $f31, VCPU_FPR31(a0) +1: sdc1 $f0, VCPU_FPR0(a0) + sdc1 $f2, VCPU_FPR2(a0) + sdc1 $f4, VCPU_FPR4(a0) + sdc1 $f6, VCPU_FPR6(a0) + sdc1 $f8, VCPU_FPR8(a0) + sdc1 $f10, VCPU_FPR10(a0) + sdc1 $f12, VCPU_FPR12(a0) + sdc1 $f14, VCPU_FPR14(a0) + sdc1 $f16, VCPU_FPR16(a0) + sdc1 $f18, VCPU_FPR18(a0) + sdc1 $f20, VCPU_FPR20(a0) + sdc1 $f22, VCPU_FPR22(a0) + sdc1 $f24, VCPU_FPR24(a0) + sdc1 $f26, VCPU_FPR26(a0) + sdc1 $f28, VCPU_FPR28(a0) + jr ra + sdc1 $f30, VCPU_FPR30(a0) + .set pop + END(__kvm_save_fpu) + +LEAF(__kvm_restore_fpu) + .set push + .set mips64r2 + SET_HARDFLOAT + mfc0 t0, CP0_STATUS + sll t0, t0, 5 # is Status.FR set? + bgez t0, 1f # no: skip odd doubles + nop + ldc1 $f1, VCPU_FPR1(a0) + ldc1 $f3, VCPU_FPR3(a0) + ldc1 $f5, VCPU_FPR5(a0) + ldc1 $f7, VCPU_FPR7(a0) + ldc1 $f9, VCPU_FPR9(a0) + ldc1 $f11, VCPU_FPR11(a0) + ldc1 $f13, VCPU_FPR13(a0) + ldc1 $f15, VCPU_FPR15(a0) + ldc1 $f17, VCPU_FPR17(a0) + ldc1 $f19, VCPU_FPR19(a0) + ldc1 $f21, VCPU_FPR21(a0) + ldc1 $f23, VCPU_FPR23(a0) + ldc1 $f25, VCPU_FPR25(a0) + ldc1 $f27, VCPU_FPR27(a0) + ldc1 $f29, VCPU_FPR29(a0) + ldc1 $f31, VCPU_FPR31(a0) +1: ldc1 $f0, VCPU_FPR0(a0) + ldc1 $f2, VCPU_FPR2(a0) + ldc1 $f4, VCPU_FPR4(a0) + ldc1 $f6, VCPU_FPR6(a0) + ldc1 $f8, VCPU_FPR8(a0) + ldc1 $f10, VCPU_FPR10(a0) + ldc1 $f12, VCPU_FPR12(a0) + ldc1 $f14, VCPU_FPR14(a0) + ldc1 $f16, VCPU_FPR16(a0) + ldc1 $f18, VCPU_FPR18(a0) + ldc1 $f20, VCPU_FPR20(a0) + ldc1 $f22, VCPU_FPR22(a0) + ldc1 $f24, VCPU_FPR24(a0) + ldc1 $f26, VCPU_FPR26(a0) + ldc1 $f28, VCPU_FPR28(a0) + jr ra + ldc1 $f30, VCPU_FPR30(a0) + .set pop + END(__kvm_restore_fpu) + +LEAF(__kvm_restore_fcsr) + .set push + SET_HARDFLOAT + lw t0, VCPU_FCR31(a0) + /* + * The ctc1 must stay at this offset in __kvm_restore_fcsr. + * See kvm_mips_csr_die_notify() which handles t0 containing a value + * which triggers an FP Exception, which must be stepped over and + * ignored since the set cause bits must remain there for the guest. + */ + ctc1 t0, fcr31 + jr ra + nop + .set pop + END(__kvm_restore_fcsr) diff --git a/arch/mips/kvm/locore.S b/arch/mips/kvm/locore.S index 4a68b176d6e4..c567240386a0 100644 --- a/arch/mips/kvm/locore.S +++ b/arch/mips/kvm/locore.S @@ -36,6 +36,8 @@ #define PT_HOST_USERLOCAL PT_EPC #define CP0_DDATA_LO $28,3 +#define CP0_CONFIG3 $16,3 +#define CP0_CONFIG5 $16,5 #define CP0_EBASE $15,1 #define CP0_INTCTL $12,1 @@ -353,6 +355,42 @@ NESTED (MIPSX(GuestException), CALLFRAME_SIZ, ra) LONG_L k0, VCPU_HOST_EBASE(k1) mtc0 k0,CP0_EBASE + /* + * If FPU is enabled, save FCR31 and clear it so that later ctc1's don't + * trigger FPE for pending exceptions. + */ + .set at + and v1, v0, ST0_CU1 + beqz v1, 1f + nop + .set push + SET_HARDFLOAT + cfc1 t0, fcr31 + sw t0, VCPU_FCR31(k1) + ctc1 zero,fcr31 + .set pop + .set noat +1: + +#ifdef CONFIG_CPU_HAS_MSA + /* + * If MSA is enabled, save MSACSR and clear it so that later + * instructions don't trigger MSAFPE for pending exceptions. + */ + mfc0 t0, CP0_CONFIG3 + ext t0, t0, 28, 1 /* MIPS_CONF3_MSAP */ + beqz t0, 1f + nop + mfc0 t0, CP0_CONFIG5 + ext t0, t0, 27, 1 /* MIPS_CONF5_MSAEN */ + beqz t0, 1f + nop + _cfcmsa t0, MSA_CSR + sw t0, VCPU_MSA_CSR(k1) + _ctcmsa MSA_CSR, zero +1: +#endif + /* Now that the new EBASE has been loaded, unset BEV and KSU_USER */ .set at and v0, v0, ~(ST0_EXL | KSU_USER | ST0_IE) diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index c9eccf5df912..bb68e8d520e8 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -11,6 +11,7 @@ #include <linux/errno.h> #include <linux/err.h> +#include <linux/kdebug.h> #include <linux/module.h> #include <linux/vmalloc.h> #include <linux/fs.h> @@ -48,6 +49,10 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "syscall", VCPU_STAT(syscall_exits), KVM_STAT_VCPU }, { "resvd_inst", VCPU_STAT(resvd_inst_exits), KVM_STAT_VCPU }, { "break_inst", VCPU_STAT(break_inst_exits), KVM_STAT_VCPU }, + { "trap_inst", VCPU_STAT(trap_inst_exits), KVM_STAT_VCPU }, + { "msa_fpe", VCPU_STAT(msa_fpe_exits), KVM_STAT_VCPU }, + { "fpe", VCPU_STAT(fpe_exits), KVM_STAT_VCPU }, + { "msa_disabled", VCPU_STAT(msa_disabled_exits), KVM_STAT_VCPU }, { "flush_dcache", VCPU_STAT(flush_dcache_exits), KVM_STAT_VCPU }, { "halt_successful_poll", VCPU_STAT(halt_successful_poll), KVM_STAT_VCPU }, { "halt_wakeup", VCPU_STAT(halt_wakeup), KVM_STAT_VCPU }, @@ -504,10 +509,13 @@ static u64 kvm_mips_get_one_regs[] = { KVM_REG_MIPS_CP0_STATUS, KVM_REG_MIPS_CP0_CAUSE, KVM_REG_MIPS_CP0_EPC, + KVM_REG_MIPS_CP0_PRID, KVM_REG_MIPS_CP0_CONFIG, KVM_REG_MIPS_CP0_CONFIG1, KVM_REG_MIPS_CP0_CONFIG2, KVM_REG_MIPS_CP0_CONFIG3, + KVM_REG_MIPS_CP0_CONFIG4, + KVM_REG_MIPS_CP0_CONFIG5, KVM_REG_MIPS_CP0_CONFIG7, KVM_REG_MIPS_CP0_ERROREPC, @@ -520,10 +528,14 @@ static int kvm_mips_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { struct mips_coproc *cop0 = vcpu->arch.cop0; + struct mips_fpu_struct *fpu = &vcpu->arch.fpu; int ret; s64 v; + s64 vs[2]; + unsigned int idx; switch (reg->id) { + /* General purpose registers */ case KVM_REG_MIPS_R0 ... KVM_REG_MIPS_R31: v = (long)vcpu->arch.gprs[reg->id - KVM_REG_MIPS_R0]; break; @@ -537,6 +549,67 @@ static int kvm_mips_get_reg(struct kvm_vcpu *vcpu, v = (long)vcpu->arch.pc; break; + /* Floating point registers */ + case KVM_REG_MIPS_FPR_32(0) ... KVM_REG_MIPS_FPR_32(31): + if (!kvm_mips_guest_has_fpu(&vcpu->arch)) + return -EINVAL; + idx = reg->id - KVM_REG_MIPS_FPR_32(0); + /* Odd singles in top of even double when FR=0 */ + if (kvm_read_c0_guest_status(cop0) & ST0_FR) + v = get_fpr32(&fpu->fpr[idx], 0); + else + v = get_fpr32(&fpu->fpr[idx & ~1], idx & 1); + break; + case KVM_REG_MIPS_FPR_64(0) ... KVM_REG_MIPS_FPR_64(31): + if (!kvm_mips_guest_has_fpu(&vcpu->arch)) + return -EINVAL; + idx = reg->id - KVM_REG_MIPS_FPR_64(0); + /* Can't access odd doubles in FR=0 mode */ + if (idx & 1 && !(kvm_read_c0_guest_status(cop0) & ST0_FR)) + return -EINVAL; + v = get_fpr64(&fpu->fpr[idx], 0); + break; + case KVM_REG_MIPS_FCR_IR: + if (!kvm_mips_guest_has_fpu(&vcpu->arch)) + return -EINVAL; + v = boot_cpu_data.fpu_id; + break; + case KVM_REG_MIPS_FCR_CSR: + if (!kvm_mips_guest_has_fpu(&vcpu->arch)) + return -EINVAL; + v = fpu->fcr31; + break; + + /* MIPS SIMD Architecture (MSA) registers */ + case KVM_REG_MIPS_VEC_128(0) ... KVM_REG_MIPS_VEC_128(31): + if (!kvm_mips_guest_has_msa(&vcpu->arch)) + return -EINVAL; + /* Can't access MSA registers in FR=0 mode */ + if (!(kvm_read_c0_guest_status(cop0) & ST0_FR)) + return -EINVAL; + idx = reg->id - KVM_REG_MIPS_VEC_128(0); +#ifdef CONFIG_CPU_LITTLE_ENDIAN + /* least significant byte first */ + vs[0] = get_fpr64(&fpu->fpr[idx], 0); + vs[1] = get_fpr64(&fpu->fpr[idx], 1); +#else + /* most significant byte first */ + vs[0] = get_fpr64(&fpu->fpr[idx], 1); + vs[1] = get_fpr64(&fpu->fpr[idx], 0); +#endif + break; + case KVM_REG_MIPS_MSA_IR: + if (!kvm_mips_guest_has_msa(&vcpu->arch)) + return -EINVAL; + v = boot_cpu_data.msa_id; + break; + case KVM_REG_MIPS_MSA_CSR: + if (!kvm_mips_guest_has_msa(&vcpu->arch)) + return -EINVAL; + v = fpu->msacsr; + break; + + /* Co-processor 0 registers */ case KVM_REG_MIPS_CP0_INDEX: v = (long)kvm_read_c0_guest_index(cop0); break; @@ -573,8 +646,8 @@ static int kvm_mips_get_reg(struct kvm_vcpu *vcpu, case KVM_REG_MIPS_CP0_EPC: v = (long)kvm_read_c0_guest_epc(cop0); break; - case KVM_REG_MIPS_CP0_ERROREPC: - v = (long)kvm_read_c0_guest_errorepc(cop0); + case KVM_REG_MIPS_CP0_PRID: + v = (long)kvm_read_c0_guest_prid(cop0); break; case KVM_REG_MIPS_CP0_CONFIG: v = (long)kvm_read_c0_guest_config(cop0); @@ -588,9 +661,18 @@ static int kvm_mips_get_reg(struct kvm_vcpu *vcpu, case KVM_REG_MIPS_CP0_CONFIG3: v = (long)kvm_read_c0_guest_config3(cop0); break; + case KVM_REG_MIPS_CP0_CONFIG4: + v = (long)kvm_read_c0_guest_config4(cop0); + break; + case KVM_REG_MIPS_CP0_CONFIG5: + v = (long)kvm_read_c0_guest_config5(cop0); + break; case KVM_REG_MIPS_CP0_CONFIG7: v = (long)kvm_read_c0_guest_config7(cop0); break; + case KVM_REG_MIPS_CP0_ERROREPC: + v = (long)kvm_read_c0_guest_errorepc(cop0); + break; /* registers to be handled specially */ case KVM_REG_MIPS_CP0_COUNT: case KVM_REG_MIPS_COUNT_CTL: @@ -612,6 +694,10 @@ static int kvm_mips_get_reg(struct kvm_vcpu *vcpu, u32 v32 = (u32)v; return put_user(v32, uaddr32); + } else if ((reg->id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U128) { + void __user *uaddr = (void __user *)(long)reg->addr; + + return copy_to_user(uaddr, vs, 16); } else { return -EINVAL; } @@ -621,7 +707,10 @@ static int kvm_mips_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { struct mips_coproc *cop0 = vcpu->arch.cop0; - u64 v; + struct mips_fpu_struct *fpu = &vcpu->arch.fpu; + s64 v; + s64 vs[2]; + unsigned int idx; if ((reg->id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U64) { u64 __user *uaddr64 = (u64 __user *)(long)reg->addr; @@ -635,11 +724,16 @@ static int kvm_mips_set_reg(struct kvm_vcpu *vcpu, if (get_user(v32, uaddr32) != 0) return -EFAULT; v = (s64)v32; + } else if ((reg->id & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U128) { + void __user *uaddr = (void __user *)(long)reg->addr; + + return copy_from_user(vs, uaddr, 16); } else { return -EINVAL; } switch (reg->id) { + /* General purpose registers */ case KVM_REG_MIPS_R0: /* Silently ignore requests to set $0 */ break; @@ -656,6 +750,64 @@ static int kvm_mips_set_reg(struct kvm_vcpu *vcpu, vcpu->arch.pc = v; break; + /* Floating point registers */ + case KVM_REG_MIPS_FPR_32(0) ... KVM_REG_MIPS_FPR_32(31): + if (!kvm_mips_guest_has_fpu(&vcpu->arch)) + return -EINVAL; + idx = reg->id - KVM_REG_MIPS_FPR_32(0); + /* Odd singles in top of even double when FR=0 */ + if (kvm_read_c0_guest_status(cop0) & ST0_FR) + set_fpr32(&fpu->fpr[idx], 0, v); + else + set_fpr32(&fpu->fpr[idx & ~1], idx & 1, v); + break; + case KVM_REG_MIPS_FPR_64(0) ... KVM_REG_MIPS_FPR_64(31): + if (!kvm_mips_guest_has_fpu(&vcpu->arch)) + return -EINVAL; + idx = reg->id - KVM_REG_MIPS_FPR_64(0); + /* Can't access odd doubles in FR=0 mode */ + if (idx & 1 && !(kvm_read_c0_guest_status(cop0) & ST0_FR)) + return -EINVAL; + set_fpr64(&fpu->fpr[idx], 0, v); + break; + case KVM_REG_MIPS_FCR_IR: + if (!kvm_mips_guest_has_fpu(&vcpu->arch)) + return -EINVAL; + /* Read-only */ + break; + case KVM_REG_MIPS_FCR_CSR: + if (!kvm_mips_guest_has_fpu(&vcpu->arch)) + return -EINVAL; + fpu->fcr31 = v; + break; + + /* MIPS SIMD Architecture (MSA) registers */ + case KVM_REG_MIPS_VEC_128(0) ... KVM_REG_MIPS_VEC_128(31): + if (!kvm_mips_guest_has_msa(&vcpu->arch)) + return -EINVAL; + idx = reg->id - KVM_REG_MIPS_VEC_128(0); +#ifdef CONFIG_CPU_LITTLE_ENDIAN + /* least significant byte first */ + set_fpr64(&fpu->fpr[idx], 0, vs[0]); + set_fpr64(&fpu->fpr[idx], 1, vs[1]); +#else + /* most significant byte first */ + set_fpr64(&fpu->fpr[idx], 1, vs[0]); + set_fpr64(&fpu->fpr[idx], 0, vs[1]); +#endif + break; + case KVM_REG_MIPS_MSA_IR: + if (!kvm_mips_guest_has_msa(&vcpu->arch)) + return -EINVAL; + /* Read-only */ + break; + case KVM_REG_MIPS_MSA_CSR: + if (!kvm_mips_guest_has_msa(&vcpu->arch)) + return -EINVAL; + fpu->msacsr = v; + break; + + /* Co-processor 0 registers */ case KVM_REG_MIPS_CP0_INDEX: kvm_write_c0_guest_index(cop0, v); break; @@ -686,6 +838,9 @@ static int kvm_mips_set_reg(struct kvm_vcpu *vcpu, case KVM_REG_MIPS_CP0_EPC: kvm_write_c0_guest_epc(cop0, v); break; + case KVM_REG_MIPS_CP0_PRID: + kvm_write_c0_guest_prid(cop0, v); + break; case KVM_REG_MIPS_CP0_ERROREPC: kvm_write_c0_guest_errorepc(cop0, v); break; @@ -693,6 +848,12 @@ static int kvm_mips_set_reg(struct kvm_vcpu *vcpu, case KVM_REG_MIPS_CP0_COUNT: case KVM_REG_MIPS_CP0_COMPARE: case KVM_REG_MIPS_CP0_CAUSE: + case KVM_REG_MIPS_CP0_CONFIG: + case KVM_REG_MIPS_CP0_CONFIG1: + case KVM_REG_MIPS_CP0_CONFIG2: + case KVM_REG_MIPS_CP0_CONFIG3: + case KVM_REG_MIPS_CP0_CONFIG4: + case KVM_REG_MIPS_CP0_CONFIG5: case KVM_REG_MIPS_COUNT_CTL: case KVM_REG_MIPS_COUNT_RESUME: case KVM_REG_MIPS_COUNT_HZ: @@ -703,6 +864,33 @@ static int kvm_mips_set_reg(struct kvm_vcpu *vcpu, return 0; } +static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, + struct kvm_enable_cap *cap) +{ + int r = 0; + + if (!kvm_vm_ioctl_check_extension(vcpu->kvm, cap->cap)) + return -EINVAL; + if (cap->flags) + return -EINVAL; + if (cap->args[0]) + return -EINVAL; + + switch (cap->cap) { + case KVM_CAP_MIPS_FPU: + vcpu->arch.fpu_enabled = true; + break; + case KVM_CAP_MIPS_MSA: + vcpu->arch.msa_enabled = true; + break; + default: + r = -EINVAL; + break; + } + + return r; +} + long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -760,6 +948,15 @@ long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, r = kvm_vcpu_ioctl_interrupt(vcpu, &irq); break; } + case KVM_ENABLE_CAP: { + struct kvm_enable_cap cap; + + r = -EFAULT; + if (copy_from_user(&cap, argp, sizeof(cap))) + goto out; + r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap); + break; + } default: r = -ENOIOCTLCMD; } @@ -868,11 +1065,30 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) switch (ext) { case KVM_CAP_ONE_REG: + case KVM_CAP_ENABLE_CAP: r = 1; break; case KVM_CAP_COALESCED_MMIO: r = KVM_COALESCED_MMIO_PAGE_OFFSET; break; + case KVM_CAP_MIPS_FPU: + r = !!cpu_has_fpu; + break; + case KVM_CAP_MIPS_MSA: + /* + * We don't support MSA vector partitioning yet: + * 1) It would require explicit support which can't be tested + * yet due to lack of support in current hardware. + * 2) It extends the state that would need to be saved/restored + * by e.g. QEMU for migration. + * + * When vector partitioning hardware becomes available, support + * could be added by requiring a flag when enabling + * KVM_CAP_MIPS_MSA capability to indicate that userland knows + * to save/restore the appropriate extra state. + */ + r = cpu_has_msa && !(boot_cpu_data.msa_id & MSA_IR_WRPF); + break; default: r = 0; break; @@ -1119,6 +1335,30 @@ int kvm_mips_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu) ret = kvm_mips_callbacks->handle_break(vcpu); break; + case T_TRAP: + ++vcpu->stat.trap_inst_exits; + trace_kvm_exit(vcpu, TRAP_INST_EXITS); + ret = kvm_mips_callbacks->handle_trap(vcpu); + break; + + case T_MSAFPE: + ++vcpu->stat.msa_fpe_exits; + trace_kvm_exit(vcpu, MSA_FPE_EXITS); + ret = kvm_mips_callbacks->handle_msa_fpe(vcpu); + break; + + case T_FPE: + ++vcpu->stat.fpe_exits; + trace_kvm_exit(vcpu, FPE_EXITS); + ret = kvm_mips_callbacks->handle_fpe(vcpu); + break; + + case T_MSADIS: + ++vcpu->stat.msa_disabled_exits; + trace_kvm_exit(vcpu, MSA_DISABLED_EXITS); + ret = kvm_mips_callbacks->handle_msa_disabled(vcpu); + break; + default: kvm_err("Exception Code: %d, not yet handled, @ PC: %p, inst: 0x%08x BadVaddr: %#lx Status: %#lx\n", exccode, opc, kvm_get_inst(opc, vcpu), badvaddr, @@ -1146,12 +1386,233 @@ skip_emul: } } + if (ret == RESUME_GUEST) { + /* + * If FPU / MSA are enabled (i.e. the guest's FPU / MSA context + * is live), restore FCR31 / MSACSR. + * + * This should be before returning to the guest exception + * vector, as it may well cause an [MSA] FP exception if there + * are pending exception bits unmasked. (see + * kvm_mips_csr_die_notifier() for how that is handled). + */ + if (kvm_mips_guest_has_fpu(&vcpu->arch) && + read_c0_status() & ST0_CU1) + __kvm_restore_fcsr(&vcpu->arch); + + if (kvm_mips_guest_has_msa(&vcpu->arch) && + read_c0_config5() & MIPS_CONF5_MSAEN) + __kvm_restore_msacsr(&vcpu->arch); + } + /* Disable HTW before returning to guest or host */ htw_stop(); return ret; } +/* Enable FPU for guest and restore context */ +void kvm_own_fpu(struct kvm_vcpu *vcpu) +{ + struct mips_coproc *cop0 = vcpu->arch.cop0; + unsigned int sr, cfg5; + + preempt_disable(); + + sr = kvm_read_c0_guest_status(cop0); + + /* + * If MSA state is already live, it is undefined how it interacts with + * FR=0 FPU state, and we don't want to hit reserved instruction + * exceptions trying to save the MSA state later when CU=1 && FR=1, so + * play it safe and save it first. + * + * In theory we shouldn't ever hit this case since kvm_lose_fpu() should + * get called when guest CU1 is set, however we can't trust the guest + * not to clobber the status register directly via the commpage. + */ + if (cpu_has_msa && sr & ST0_CU1 && !(sr & ST0_FR) && + vcpu->arch.fpu_inuse & KVM_MIPS_FPU_MSA) + kvm_lose_fpu(vcpu); + + /* + * Enable FPU for guest + * We set FR and FRE according to guest context + */ + change_c0_status(ST0_CU1 | ST0_FR, sr); + if (cpu_has_fre) { + cfg5 = kvm_read_c0_guest_config5(cop0); + change_c0_config5(MIPS_CONF5_FRE, cfg5); + } + enable_fpu_hazard(); + + /* If guest FPU state not active, restore it now */ + if (!(vcpu->arch.fpu_inuse & KVM_MIPS_FPU_FPU)) { + __kvm_restore_fpu(&vcpu->arch); + vcpu->arch.fpu_inuse |= KVM_MIPS_FPU_FPU; + } + + preempt_enable(); +} + +#ifdef CONFIG_CPU_HAS_MSA +/* Enable MSA for guest and restore context */ +void kvm_own_msa(struct kvm_vcpu *vcpu) +{ + struct mips_coproc *cop0 = vcpu->arch.cop0; + unsigned int sr, cfg5; + + preempt_disable(); + + /* + * Enable FPU if enabled in guest, since we're restoring FPU context + * anyway. We set FR and FRE according to guest context. + */ + if (kvm_mips_guest_has_fpu(&vcpu->arch)) { + sr = kvm_read_c0_guest_status(cop0); + + /* + * If FR=0 FPU state is already live, it is undefined how it + * interacts with MSA state, so play it safe and save it first. + */ + if (!(sr & ST0_FR) && + (vcpu->arch.fpu_inuse & (KVM_MIPS_FPU_FPU | + KVM_MIPS_FPU_MSA)) == KVM_MIPS_FPU_FPU) + kvm_lose_fpu(vcpu); + + change_c0_status(ST0_CU1 | ST0_FR, sr); + if (sr & ST0_CU1 && cpu_has_fre) { + cfg5 = kvm_read_c0_guest_config5(cop0); + change_c0_config5(MIPS_CONF5_FRE, cfg5); + } + } + + /* Enable MSA for guest */ + set_c0_config5(MIPS_CONF5_MSAEN); + enable_fpu_hazard(); + + switch (vcpu->arch.fpu_inuse & (KVM_MIPS_FPU_FPU | KVM_MIPS_FPU_MSA)) { + case KVM_MIPS_FPU_FPU: + /* + * Guest FPU state already loaded, only restore upper MSA state + */ + __kvm_restore_msa_upper(&vcpu->arch); + vcpu->arch.fpu_inuse |= KVM_MIPS_FPU_MSA; + break; + case 0: + /* Neither FPU or MSA already active, restore full MSA state */ + __kvm_restore_msa(&vcpu->arch); + vcpu->arch.fpu_inuse |= KVM_MIPS_FPU_MSA; + if (kvm_mips_guest_has_fpu(&vcpu->arch)) + vcpu->arch.fpu_inuse |= KVM_MIPS_FPU_FPU; + break; + default: + break; + } + + preempt_enable(); +} +#endif + +/* Drop FPU & MSA without saving it */ +void kvm_drop_fpu(struct kvm_vcpu *vcpu) +{ + preempt_disable(); + if (cpu_has_msa && vcpu->arch.fpu_inuse & KVM_MIPS_FPU_MSA) { + disable_msa(); + vcpu->arch.fpu_inuse &= ~KVM_MIPS_FPU_MSA; + } + if (vcpu->arch.fpu_inuse & KVM_MIPS_FPU_FPU) { + clear_c0_status(ST0_CU1 | ST0_FR); + vcpu->arch.fpu_inuse &= ~KVM_MIPS_FPU_FPU; + } + preempt_enable(); +} + +/* Save and disable FPU & MSA */ +void kvm_lose_fpu(struct kvm_vcpu *vcpu) +{ + /* + * FPU & MSA get disabled in root context (hardware) when it is disabled + * in guest context (software), but the register state in the hardware + * may still be in use. This is why we explicitly re-enable the hardware + * before saving. + */ + + preempt_disable(); + if (cpu_has_msa && vcpu->arch.fpu_inuse & KVM_MIPS_FPU_MSA) { + set_c0_config5(MIPS_CONF5_MSAEN); + enable_fpu_hazard(); + + __kvm_save_msa(&vcpu->arch); + + /* Disable MSA & FPU */ + disable_msa(); + if (vcpu->arch.fpu_inuse & KVM_MIPS_FPU_FPU) + clear_c0_status(ST0_CU1 | ST0_FR); + vcpu->arch.fpu_inuse &= ~(KVM_MIPS_FPU_FPU | KVM_MIPS_FPU_MSA); + } else if (vcpu->arch.fpu_inuse & KVM_MIPS_FPU_FPU) { + set_c0_status(ST0_CU1); + enable_fpu_hazard(); + + __kvm_save_fpu(&vcpu->arch); + vcpu->arch.fpu_inuse &= ~KVM_MIPS_FPU_FPU; + + /* Disable FPU */ + clear_c0_status(ST0_CU1 | ST0_FR); + } + preempt_enable(); +} + +/* + * Step over a specific ctc1 to FCSR and a specific ctcmsa to MSACSR which are + * used to restore guest FCSR/MSACSR state and may trigger a "harmless" FP/MSAFP + * exception if cause bits are set in the value being written. + */ +static int kvm_mips_csr_die_notify(struct notifier_block *self, + unsigned long cmd, void *ptr) +{ + struct die_args *args = (struct die_args *)ptr; + struct pt_regs *regs = args->regs; + unsigned long pc; + + /* Only interested in FPE and MSAFPE */ + if (cmd != DIE_FP && cmd != DIE_MSAFP) + return NOTIFY_DONE; + + /* Return immediately if guest context isn't active */ + if (!(current->flags & PF_VCPU)) + return NOTIFY_DONE; + + /* Should never get here from user mode */ + BUG_ON(user_mode(regs)); + + pc = instruction_pointer(regs); + switch (cmd) { + case DIE_FP: + /* match 2nd instruction in __kvm_restore_fcsr */ + if (pc != (unsigned long)&__kvm_restore_fcsr + 4) + return NOTIFY_DONE; + break; + case DIE_MSAFP: + /* match 2nd/3rd instruction in __kvm_restore_msacsr */ + if (!cpu_has_msa || + pc < (unsigned long)&__kvm_restore_msacsr + 4 || + pc > (unsigned long)&__kvm_restore_msacsr + 8) + return NOTIFY_DONE; + break; + } + + /* Move PC forward a little and continue executing */ + instruction_pointer(regs) += 4; + + return NOTIFY_STOP; +} + +static struct notifier_block kvm_mips_csr_die_notifier = { + .notifier_call = kvm_mips_csr_die_notify, +}; + int __init kvm_mips_init(void) { int ret; @@ -1161,6 +1622,8 @@ int __init kvm_mips_init(void) if (ret) return ret; + register_die_notifier(&kvm_mips_csr_die_notifier); + /* * On MIPS, kernel modules are executed from "mapped space", which * requires TLBs. The TLB handling code is statically linked with @@ -1173,7 +1636,6 @@ int __init kvm_mips_init(void) kvm_mips_release_pfn_clean = kvm_release_pfn_clean; kvm_mips_is_error_pfn = is_error_pfn; - pr_info("KVM/MIPS Initialized\n"); return 0; } @@ -1185,7 +1647,7 @@ void __exit kvm_mips_exit(void) kvm_mips_release_pfn_clean = NULL; kvm_mips_is_error_pfn = NULL; - pr_info("KVM/MIPS unloaded\n"); + unregister_die_notifier(&kvm_mips_csr_die_notifier); } module_init(kvm_mips_init); diff --git a/arch/mips/kvm/msa.S b/arch/mips/kvm/msa.S new file mode 100644 index 000000000000..d02f0c6cc2cc --- /dev/null +++ b/arch/mips/kvm/msa.S @@ -0,0 +1,161 @@ +/* + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * MIPS SIMD Architecture (MSA) context handling code for KVM. + * + * Copyright (C) 2015 Imagination Technologies Ltd. + */ + +#include <asm/asm.h> +#include <asm/asm-offsets.h> +#include <asm/asmmacro.h> +#include <asm/regdef.h> + + .set noreorder + .set noat + +LEAF(__kvm_save_msa) + st_d 0, VCPU_FPR0, a0 + st_d 1, VCPU_FPR1, a0 + st_d 2, VCPU_FPR2, a0 + st_d 3, VCPU_FPR3, a0 + st_d 4, VCPU_FPR4, a0 + st_d 5, VCPU_FPR5, a0 + st_d 6, VCPU_FPR6, a0 + st_d 7, VCPU_FPR7, a0 + st_d 8, VCPU_FPR8, a0 + st_d 9, VCPU_FPR9, a0 + st_d 10, VCPU_FPR10, a0 + st_d 11, VCPU_FPR11, a0 + st_d 12, VCPU_FPR12, a0 + st_d 13, VCPU_FPR13, a0 + st_d 14, VCPU_FPR14, a0 + st_d 15, VCPU_FPR15, a0 + st_d 16, VCPU_FPR16, a0 + st_d 17, VCPU_FPR17, a0 + st_d 18, VCPU_FPR18, a0 + st_d 19, VCPU_FPR19, a0 + st_d 20, VCPU_FPR20, a0 + st_d 21, VCPU_FPR21, a0 + st_d 22, VCPU_FPR22, a0 + st_d 23, VCPU_FPR23, a0 + st_d 24, VCPU_FPR24, a0 + st_d 25, VCPU_FPR25, a0 + st_d 26, VCPU_FPR26, a0 + st_d 27, VCPU_FPR27, a0 + st_d 28, VCPU_FPR28, a0 + st_d 29, VCPU_FPR29, a0 + st_d 30, VCPU_FPR30, a0 + st_d 31, VCPU_FPR31, a0 + jr ra + nop + END(__kvm_save_msa) + +LEAF(__kvm_restore_msa) + ld_d 0, VCPU_FPR0, a0 + ld_d 1, VCPU_FPR1, a0 + ld_d 2, VCPU_FPR2, a0 + ld_d 3, VCPU_FPR3, a0 + ld_d 4, VCPU_FPR4, a0 + ld_d 5, VCPU_FPR5, a0 + ld_d 6, VCPU_FPR6, a0 + ld_d 7, VCPU_FPR7, a0 + ld_d 8, VCPU_FPR8, a0 + ld_d 9, VCPU_FPR9, a0 + ld_d 10, VCPU_FPR10, a0 + ld_d 11, VCPU_FPR11, a0 + ld_d 12, VCPU_FPR12, a0 + ld_d 13, VCPU_FPR13, a0 + ld_d 14, VCPU_FPR14, a0 + ld_d 15, VCPU_FPR15, a0 + ld_d 16, VCPU_FPR16, a0 + ld_d 17, VCPU_FPR17, a0 + ld_d 18, VCPU_FPR18, a0 + ld_d 19, VCPU_FPR19, a0 + ld_d 20, VCPU_FPR20, a0 + ld_d 21, VCPU_FPR21, a0 + ld_d 22, VCPU_FPR22, a0 + ld_d 23, VCPU_FPR23, a0 + ld_d 24, VCPU_FPR24, a0 + ld_d 25, VCPU_FPR25, a0 + ld_d 26, VCPU_FPR26, a0 + ld_d 27, VCPU_FPR27, a0 + ld_d 28, VCPU_FPR28, a0 + ld_d 29, VCPU_FPR29, a0 + ld_d 30, VCPU_FPR30, a0 + ld_d 31, VCPU_FPR31, a0 + jr ra + nop + END(__kvm_restore_msa) + + .macro kvm_restore_msa_upper wr, off, base + .set push + .set noat +#ifdef CONFIG_64BIT + ld $1, \off(\base) + insert_d \wr, 1 +#elif defined(CONFIG_CPU_LITTLE_ENDIAN) + lw $1, \off(\base) + insert_w \wr, 2 + lw $1, (\off+4)(\base) + insert_w \wr, 3 +#else /* CONFIG_CPU_BIG_ENDIAN */ + lw $1, (\off+4)(\base) + insert_w \wr, 2 + lw $1, \off(\base) + insert_w \wr, 3 +#endif + .set pop + .endm + +LEAF(__kvm_restore_msa_upper) + kvm_restore_msa_upper 0, VCPU_FPR0 +8, a0 + kvm_restore_msa_upper 1, VCPU_FPR1 +8, a0 + kvm_restore_msa_upper 2, VCPU_FPR2 +8, a0 + kvm_restore_msa_upper 3, VCPU_FPR3 +8, a0 + kvm_restore_msa_upper 4, VCPU_FPR4 +8, a0 + kvm_restore_msa_upper 5, VCPU_FPR5 +8, a0 + kvm_restore_msa_upper 6, VCPU_FPR6 +8, a0 + kvm_restore_msa_upper 7, VCPU_FPR7 +8, a0 + kvm_restore_msa_upper 8, VCPU_FPR8 +8, a0 + kvm_restore_msa_upper 9, VCPU_FPR9 +8, a0 + kvm_restore_msa_upper 10, VCPU_FPR10+8, a0 + kvm_restore_msa_upper 11, VCPU_FPR11+8, a0 + kvm_restore_msa_upper 12, VCPU_FPR12+8, a0 + kvm_restore_msa_upper 13, VCPU_FPR13+8, a0 + kvm_restore_msa_upper 14, VCPU_FPR14+8, a0 + kvm_restore_msa_upper 15, VCPU_FPR15+8, a0 + kvm_restore_msa_upper 16, VCPU_FPR16+8, a0 + kvm_restore_msa_upper 17, VCPU_FPR17+8, a0 + kvm_restore_msa_upper 18, VCPU_FPR18+8, a0 + kvm_restore_msa_upper 19, VCPU_FPR19+8, a0 + kvm_restore_msa_upper 20, VCPU_FPR20+8, a0 + kvm_restore_msa_upper 21, VCPU_FPR21+8, a0 + kvm_restore_msa_upper 22, VCPU_FPR22+8, a0 + kvm_restore_msa_upper 23, VCPU_FPR23+8, a0 + kvm_restore_msa_upper 24, VCPU_FPR24+8, a0 + kvm_restore_msa_upper 25, VCPU_FPR25+8, a0 + kvm_restore_msa_upper 26, VCPU_FPR26+8, a0 + kvm_restore_msa_upper 27, VCPU_FPR27+8, a0 + kvm_restore_msa_upper 28, VCPU_FPR28+8, a0 + kvm_restore_msa_upper 29, VCPU_FPR29+8, a0 + kvm_restore_msa_upper 30, VCPU_FPR30+8, a0 + kvm_restore_msa_upper 31, VCPU_FPR31+8, a0 + jr ra + nop + END(__kvm_restore_msa_upper) + +LEAF(__kvm_restore_msacsr) + lw t0, VCPU_MSA_CSR(a0) + /* + * The ctcmsa must stay at this offset in __kvm_restore_msacsr. + * See kvm_mips_csr_die_notify() which handles t0 containing a value + * which triggers an MSA FP Exception, which must be stepped over and + * ignored since the set cause bits must remain there for the guest. + */ + _ctcmsa MSA_CSR, t0 + jr ra + nop + END(__kvm_restore_msacsr) diff --git a/arch/mips/kvm/stats.c b/arch/mips/kvm/stats.c index a74d6024c5ad..888bb67070ac 100644 --- a/arch/mips/kvm/stats.c +++ b/arch/mips/kvm/stats.c @@ -25,6 +25,10 @@ char *kvm_mips_exit_types_str[MAX_KVM_MIPS_EXIT_TYPES] = { "System Call", "Reserved Inst", "Break Inst", + "Trap Inst", + "MSA FPE", + "FPE", + "MSA Disabled", "D-Cache Flushes", }; diff --git a/arch/mips/kvm/tlb.c b/arch/mips/kvm/tlb.c index bbcd82242059..aed0ac2a4972 100644 --- a/arch/mips/kvm/tlb.c +++ b/arch/mips/kvm/tlb.c @@ -216,6 +216,7 @@ int kvm_mips_host_tlb_write(struct kvm_vcpu *vcpu, unsigned long entryhi, if (idx > current_cpu_data.tlbsize) { kvm_err("%s: Invalid Index: %d\n", __func__, idx); kvm_mips_dump_host_tlbs(); + local_irq_restore(flags); return -1; } @@ -732,6 +733,9 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) } } + /* restore guest state to registers */ + kvm_mips_callbacks->vcpu_set_regs(vcpu); + local_irq_restore(flags); } @@ -750,6 +754,9 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) vcpu->arch.preempt_entryhi = read_c0_entryhi(); vcpu->arch.last_sched_cpu = cpu; + /* save guest state in registers */ + kvm_mips_callbacks->vcpu_get_regs(vcpu); + if (((cpu_context(cpu, current->mm) ^ asid_cache(cpu)) & ASID_VERSION_MASK)) { kvm_debug("%s: Dropping MMU Context: %#lx\n", __func__, diff --git a/arch/mips/kvm/trace.h b/arch/mips/kvm/trace.h index c1388d40663b..bd6437f67dc0 100644 --- a/arch/mips/kvm/trace.h +++ b/arch/mips/kvm/trace.h @@ -24,18 +24,18 @@ TRACE_EVENT(kvm_exit, TP_PROTO(struct kvm_vcpu *vcpu, unsigned int reason), TP_ARGS(vcpu, reason), TP_STRUCT__entry( - __field(struct kvm_vcpu *, vcpu) + __field(unsigned long, pc) __field(unsigned int, reason) ), TP_fast_assign( - __entry->vcpu = vcpu; + __entry->pc = vcpu->arch.pc; __entry->reason = reason; ), TP_printk("[%s]PC: 0x%08lx", kvm_mips_exit_types_str[__entry->reason], - __entry->vcpu->arch.pc) + __entry->pc) ); #endif /* _TRACE_KVM_H */ diff --git a/arch/mips/kvm/trap_emul.c b/arch/mips/kvm/trap_emul.c index fd7257b70e65..d836ed5b0bc7 100644 --- a/arch/mips/kvm/trap_emul.c +++ b/arch/mips/kvm/trap_emul.c @@ -39,16 +39,30 @@ static gpa_t kvm_trap_emul_gva_to_gpa_cb(gva_t gva) static int kvm_trap_emul_handle_cop_unusable(struct kvm_vcpu *vcpu) { + struct mips_coproc *cop0 = vcpu->arch.cop0; struct kvm_run *run = vcpu->run; uint32_t __user *opc = (uint32_t __user *) vcpu->arch.pc; unsigned long cause = vcpu->arch.host_cp0_cause; enum emulation_result er = EMULATE_DONE; int ret = RESUME_GUEST; - if (((cause & CAUSEF_CE) >> CAUSEB_CE) == 1) - er = kvm_mips_emulate_fpu_exc(cause, opc, run, vcpu); - else + if (((cause & CAUSEF_CE) >> CAUSEB_CE) == 1) { + /* FPU Unusable */ + if (!kvm_mips_guest_has_fpu(&vcpu->arch) || + (kvm_read_c0_guest_status(cop0) & ST0_CU1) == 0) { + /* + * Unusable/no FPU in guest: + * deliver guest COP1 Unusable Exception + */ + er = kvm_mips_emulate_fpu_exc(cause, opc, run, vcpu); + } else { + /* Restore FPU state */ + kvm_own_fpu(vcpu); + er = EMULATE_DONE; + } + } else { er = kvm_mips_emulate_inst(cause, opc, run, vcpu); + } switch (er) { case EMULATE_DONE: @@ -330,6 +344,107 @@ static int kvm_trap_emul_handle_break(struct kvm_vcpu *vcpu) return ret; } +static int kvm_trap_emul_handle_trap(struct kvm_vcpu *vcpu) +{ + struct kvm_run *run = vcpu->run; + uint32_t __user *opc = (uint32_t __user *)vcpu->arch.pc; + unsigned long cause = vcpu->arch.host_cp0_cause; + enum emulation_result er = EMULATE_DONE; + int ret = RESUME_GUEST; + + er = kvm_mips_emulate_trap_exc(cause, opc, run, vcpu); + if (er == EMULATE_DONE) { + ret = RESUME_GUEST; + } else { + run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + ret = RESUME_HOST; + } + return ret; +} + +static int kvm_trap_emul_handle_msa_fpe(struct kvm_vcpu *vcpu) +{ + struct kvm_run *run = vcpu->run; + uint32_t __user *opc = (uint32_t __user *)vcpu->arch.pc; + unsigned long cause = vcpu->arch.host_cp0_cause; + enum emulation_result er = EMULATE_DONE; + int ret = RESUME_GUEST; + + er = kvm_mips_emulate_msafpe_exc(cause, opc, run, vcpu); + if (er == EMULATE_DONE) { + ret = RESUME_GUEST; + } else { + run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + ret = RESUME_HOST; + } + return ret; +} + +static int kvm_trap_emul_handle_fpe(struct kvm_vcpu *vcpu) +{ + struct kvm_run *run = vcpu->run; + uint32_t __user *opc = (uint32_t __user *)vcpu->arch.pc; + unsigned long cause = vcpu->arch.host_cp0_cause; + enum emulation_result er = EMULATE_DONE; + int ret = RESUME_GUEST; + + er = kvm_mips_emulate_fpe_exc(cause, opc, run, vcpu); + if (er == EMULATE_DONE) { + ret = RESUME_GUEST; + } else { + run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + ret = RESUME_HOST; + } + return ret; +} + +/** + * kvm_trap_emul_handle_msa_disabled() - Guest used MSA while disabled in root. + * @vcpu: Virtual CPU context. + * + * Handle when the guest attempts to use MSA when it is disabled. + */ +static int kvm_trap_emul_handle_msa_disabled(struct kvm_vcpu *vcpu) +{ + struct mips_coproc *cop0 = vcpu->arch.cop0; + struct kvm_run *run = vcpu->run; + uint32_t __user *opc = (uint32_t __user *) vcpu->arch.pc; + unsigned long cause = vcpu->arch.host_cp0_cause; + enum emulation_result er = EMULATE_DONE; + int ret = RESUME_GUEST; + + if (!kvm_mips_guest_has_msa(&vcpu->arch) || + (kvm_read_c0_guest_status(cop0) & (ST0_CU1 | ST0_FR)) == ST0_CU1) { + /* + * No MSA in guest, or FPU enabled and not in FR=1 mode, + * guest reserved instruction exception + */ + er = kvm_mips_emulate_ri_exc(cause, opc, run, vcpu); + } else if (!(kvm_read_c0_guest_config5(cop0) & MIPS_CONF5_MSAEN)) { + /* MSA disabled by guest, guest MSA disabled exception */ + er = kvm_mips_emulate_msadis_exc(cause, opc, run, vcpu); + } else { + /* Restore MSA/FPU state */ + kvm_own_msa(vcpu); + er = EMULATE_DONE; + } + + switch (er) { + case EMULATE_DONE: + ret = RESUME_GUEST; + break; + + case EMULATE_FAIL: + run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + ret = RESUME_HOST; + break; + + default: + BUG(); + } + return ret; +} + static int kvm_trap_emul_vm_init(struct kvm *kvm) { return 0; @@ -351,8 +466,9 @@ static int kvm_trap_emul_vcpu_setup(struct kvm_vcpu *vcpu) * guest will come up as expected, for now we simulate a MIPS 24kc */ kvm_write_c0_guest_prid(cop0, 0x00019300); - kvm_write_c0_guest_config(cop0, - MIPS_CONFIG0 | (0x1 << CP0C0_AR) | + /* Have config1, Cacheable, noncoherent, write-back, write allocate */ + kvm_write_c0_guest_config(cop0, MIPS_CONF_M | (0x3 << CP0C0_K0) | + (0x1 << CP0C0_AR) | (MMU_TYPE_R4000 << CP0C0_MT)); /* Read the cache characteristics from the host Config1 Register */ @@ -368,10 +484,18 @@ static int kvm_trap_emul_vcpu_setup(struct kvm_vcpu *vcpu) (1 << CP0C1_WR) | (1 << CP0C1_CA)); kvm_write_c0_guest_config1(cop0, config1); - kvm_write_c0_guest_config2(cop0, MIPS_CONFIG2); - /* MIPS_CONFIG2 | (read_c0_config2() & 0xfff) */ - kvm_write_c0_guest_config3(cop0, MIPS_CONFIG3 | (0 << CP0C3_VInt) | - (1 << CP0C3_ULRI)); + /* Have config3, no tertiary/secondary caches implemented */ + kvm_write_c0_guest_config2(cop0, MIPS_CONF_M); + /* MIPS_CONF_M | (read_c0_config2() & 0xfff) */ + + /* Have config4, UserLocal */ + kvm_write_c0_guest_config3(cop0, MIPS_CONF_M | MIPS_CONF3_ULRI); + + /* Have config5 */ + kvm_write_c0_guest_config4(cop0, MIPS_CONF_M); + + /* No config6 */ + kvm_write_c0_guest_config5(cop0, 0); /* Set Wait IE/IXMT Ignore in Config7, IAR, AR */ kvm_write_c0_guest_config7(cop0, (MIPS_CONF7_WII) | (1 << 10)); @@ -416,6 +540,7 @@ static int kvm_trap_emul_set_one_reg(struct kvm_vcpu *vcpu, { struct mips_coproc *cop0 = vcpu->arch.cop0; int ret = 0; + unsigned int cur, change; switch (reg->id) { case KVM_REG_MIPS_CP0_COUNT: @@ -444,6 +569,44 @@ static int kvm_trap_emul_set_one_reg(struct kvm_vcpu *vcpu, kvm_write_c0_guest_cause(cop0, v); } break; + case KVM_REG_MIPS_CP0_CONFIG: + /* read-only for now */ + break; + case KVM_REG_MIPS_CP0_CONFIG1: + cur = kvm_read_c0_guest_config1(cop0); + change = (cur ^ v) & kvm_mips_config1_wrmask(vcpu); + if (change) { + v = cur ^ change; + kvm_write_c0_guest_config1(cop0, v); + } + break; + case KVM_REG_MIPS_CP0_CONFIG2: + /* read-only for now */ + break; + case KVM_REG_MIPS_CP0_CONFIG3: + cur = kvm_read_c0_guest_config3(cop0); + change = (cur ^ v) & kvm_mips_config3_wrmask(vcpu); + if (change) { + v = cur ^ change; + kvm_write_c0_guest_config3(cop0, v); + } + break; + case KVM_REG_MIPS_CP0_CONFIG4: + cur = kvm_read_c0_guest_config4(cop0); + change = (cur ^ v) & kvm_mips_config4_wrmask(vcpu); + if (change) { + v = cur ^ change; + kvm_write_c0_guest_config4(cop0, v); + } + break; + case KVM_REG_MIPS_CP0_CONFIG5: + cur = kvm_read_c0_guest_config5(cop0); + change = (cur ^ v) & kvm_mips_config5_wrmask(vcpu); + if (change) { + v = cur ^ change; + kvm_write_c0_guest_config5(cop0, v); + } + break; case KVM_REG_MIPS_COUNT_CTL: ret = kvm_mips_set_count_ctl(vcpu, v); break; @@ -459,6 +622,18 @@ static int kvm_trap_emul_set_one_reg(struct kvm_vcpu *vcpu, return ret; } +static int kvm_trap_emul_vcpu_get_regs(struct kvm_vcpu *vcpu) +{ + kvm_lose_fpu(vcpu); + + return 0; +} + +static int kvm_trap_emul_vcpu_set_regs(struct kvm_vcpu *vcpu) +{ + return 0; +} + static struct kvm_mips_callbacks kvm_trap_emul_callbacks = { /* exit handlers */ .handle_cop_unusable = kvm_trap_emul_handle_cop_unusable, @@ -470,6 +645,10 @@ static struct kvm_mips_callbacks kvm_trap_emul_callbacks = { .handle_syscall = kvm_trap_emul_handle_syscall, .handle_res_inst = kvm_trap_emul_handle_res_inst, .handle_break = kvm_trap_emul_handle_break, + .handle_trap = kvm_trap_emul_handle_trap, + .handle_msa_fpe = kvm_trap_emul_handle_msa_fpe, + .handle_fpe = kvm_trap_emul_handle_fpe, + .handle_msa_disabled = kvm_trap_emul_handle_msa_disabled, .vm_init = kvm_trap_emul_vm_init, .vcpu_init = kvm_trap_emul_vcpu_init, @@ -483,6 +662,8 @@ static struct kvm_mips_callbacks kvm_trap_emul_callbacks = { .irq_clear = kvm_mips_irq_clear_cb, .get_one_reg = kvm_trap_emul_get_one_reg, .set_one_reg = kvm_trap_emul_set_one_reg, + .vcpu_get_regs = kvm_trap_emul_vcpu_get_regs, + .vcpu_set_regs = kvm_trap_emul_vcpu_set_regs, }; int kvm_mips_emulation_init(struct kvm_mips_callbacks **install_callbacks) diff --git a/arch/mn10300/include/asm/pgtable.h b/arch/mn10300/include/asm/pgtable.h index afab728ab65e..96d3f9deb59c 100644 --- a/arch/mn10300/include/asm/pgtable.h +++ b/arch/mn10300/include/asm/pgtable.h @@ -56,7 +56,9 @@ extern void paging_init(void); #define PGDIR_SHIFT 22 #define PTRS_PER_PGD 1024 #define PTRS_PER_PUD 1 /* we don't really have any PUD physically */ +#define __PAGETABLE_PUD_FOLDED #define PTRS_PER_PMD 1 /* we don't really have any PMD physically */ +#define __PAGETABLE_PMD_FOLDED #define PTRS_PER_PTE 1024 #define PGD_SIZE PAGE_SIZE diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index 8c966b2270aa..15207b9362bf 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -96,6 +96,7 @@ extern void purge_tlb_entries(struct mm_struct *, unsigned long); #if PT_NLEVELS == 3 #define BITS_PER_PMD (PAGE_SHIFT + PMD_ORDER - BITS_PER_PMD_ENTRY) #else +#define __PAGETABLE_PMD_FOLDED #define BITS_PER_PMD 0 #endif #define PTRS_PER_PMD (1UL << BITS_PER_PMD) diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index 9cfa3706a1b8..f1ea5972f6ec 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -113,6 +113,7 @@ extern void iommu_register_group(struct iommu_table *tbl, int pci_domain_number, unsigned long pe_num); extern int iommu_add_device(struct device *dev); extern void iommu_del_device(struct device *dev); +extern int __init tce_iommu_bus_notifier_init(void); #else static inline void iommu_register_group(struct iommu_table *tbl, int pci_domain_number, @@ -128,6 +129,11 @@ static inline int iommu_add_device(struct device *dev) static inline void iommu_del_device(struct device *dev) { } + +static inline int __init tce_iommu_bus_notifier_init(void) +{ + return 0; +} #endif /* !CONFIG_IOMMU_API */ static inline void set_iommu_table_base_and_group(struct device *dev, diff --git a/arch/powerpc/include/asm/irq_work.h b/arch/powerpc/include/asm/irq_work.h new file mode 100644 index 000000000000..744fd54de374 --- /dev/null +++ b/arch/powerpc/include/asm/irq_work.h @@ -0,0 +1,9 @@ +#ifndef _ASM_POWERPC_IRQ_WORK_H +#define _ASM_POWERPC_IRQ_WORK_H + +static inline bool arch_irq_work_has_interrupt(void) +{ + return true; +} + +#endif /* _ASM_POWERPC_IRQ_WORK_H */ diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 5d3968c4d799..b054f33ab1fb 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -1175,4 +1175,30 @@ void iommu_del_device(struct device *dev) } EXPORT_SYMBOL_GPL(iommu_del_device); +static int tce_iommu_bus_notifier(struct notifier_block *nb, + unsigned long action, void *data) +{ + struct device *dev = data; + + switch (action) { + case BUS_NOTIFY_ADD_DEVICE: + return iommu_add_device(dev); + case BUS_NOTIFY_DEL_DEVICE: + if (dev->iommu_group) + iommu_del_device(dev); + return 0; + default: + return 0; + } +} + +static struct notifier_block tce_iommu_bus_nb = { + .notifier_call = tce_iommu_bus_notifier, +}; + +int __init tce_iommu_bus_notifier_init(void) +{ + bus_register_notifier(&pci_bus_type, &tce_iommu_bus_nb); + return 0; +} #endif /* CONFIG_IOMMU_API */ diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 6e19afa35a15..ec9ec2058d2d 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -541,8 +541,8 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle) if (smp_ops->give_timebase) smp_ops->give_timebase(); - /* Wait until cpu puts itself in the online map */ - while (!cpu_online(cpu)) + /* Wait until cpu puts itself in the online & active maps */ + while (!cpu_online(cpu) || !cpu_active(cpu)) cpu_relax(); return 0; diff --git a/arch/powerpc/kvm/mpic.c b/arch/powerpc/kvm/mpic.c index 39b3a8f816f2..4703fadd2737 100644 --- a/arch/powerpc/kvm/mpic.c +++ b/arch/powerpc/kvm/mpic.c @@ -34,7 +34,7 @@ #include <asm/kvm_para.h> #include <asm/kvm_host.h> #include <asm/kvm_ppc.h> -#include "iodev.h" +#include <kvm/iodev.h> #define MAX_CPU 32 #define MAX_SRC 256 @@ -1374,8 +1374,9 @@ static int kvm_mpic_write_internal(struct openpic *opp, gpa_t addr, u32 val) return -ENXIO; } -static int kvm_mpic_read(struct kvm_io_device *this, gpa_t addr, - int len, void *ptr) +static int kvm_mpic_read(struct kvm_vcpu *vcpu, + struct kvm_io_device *this, + gpa_t addr, int len, void *ptr) { struct openpic *opp = container_of(this, struct openpic, mmio); int ret; @@ -1415,8 +1416,9 @@ static int kvm_mpic_read(struct kvm_io_device *this, gpa_t addr, return ret; } -static int kvm_mpic_write(struct kvm_io_device *this, gpa_t addr, - int len, const void *ptr) +static int kvm_mpic_write(struct kvm_vcpu *vcpu, + struct kvm_io_device *this, + gpa_t addr, int len, const void *ptr) { struct openpic *opp = container_of(this, struct openpic, mmio); int ret; diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 27c0face86f4..24bfe401373e 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -807,7 +807,7 @@ int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu, idx = srcu_read_lock(&vcpu->kvm->srcu); - ret = kvm_io_bus_read(vcpu->kvm, KVM_MMIO_BUS, run->mmio.phys_addr, + ret = kvm_io_bus_read(vcpu, KVM_MMIO_BUS, run->mmio.phys_addr, bytes, &run->mmio.data); srcu_read_unlock(&vcpu->kvm->srcu, idx); @@ -880,7 +880,7 @@ int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu, idx = srcu_read_lock(&vcpu->kvm->srcu); - ret = kvm_io_bus_write(vcpu->kvm, KVM_MMIO_BUS, run->mmio.phys_addr, + ret = kvm_io_bus_write(vcpu, KVM_MMIO_BUS, run->mmio.phys_addr, bytes, &run->mmio.data); srcu_read_unlock(&vcpu->kvm->srcu, idx); diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index e69142f4af08..54323d6b5166 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -836,30 +836,4 @@ void __init pnv_pci_init(void) #endif } -static int tce_iommu_bus_notifier(struct notifier_block *nb, - unsigned long action, void *data) -{ - struct device *dev = data; - - switch (action) { - case BUS_NOTIFY_ADD_DEVICE: - return iommu_add_device(dev); - case BUS_NOTIFY_DEL_DEVICE: - if (dev->iommu_group) - iommu_del_device(dev); - return 0; - default: - return 0; - } -} - -static struct notifier_block tce_iommu_bus_nb = { - .notifier_call = tce_iommu_bus_notifier, -}; - -static int __init tce_iommu_bus_notifier_init(void) -{ - bus_register_notifier(&pci_bus_type, &tce_iommu_bus_nb); - return 0; -} machine_subsys_initcall_sync(powernv, tce_iommu_bus_notifier_init); diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 1d3d52dc3ff3..7803a19adb31 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -1340,3 +1340,5 @@ static int __init disable_multitce(char *str) } __setup("multitce=", disable_multitce); + +machine_subsys_initcall_sync(pseries, tce_iommu_bus_notifier_init); diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index f49b71954654..8fb3802f8fad 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -62,6 +62,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, { int cpu = smp_processor_id(); + S390_lowcore.user_asce = next->context.asce_bits | __pa(next->pgd); if (prev == next) return; if (MACHINE_HAS_TLB_LC) @@ -73,7 +74,6 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, atomic_dec(&prev->context.attach_count); if (MACHINE_HAS_TLB_LC) cpumask_clear_cpu(cpu, &prev->context.cpu_attach_mask); - S390_lowcore.user_asce = next->context.asce_bits | __pa(next->pgd); } #define finish_arch_post_lock_switch finish_arch_post_lock_switch diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h index 7b2ac6e44166..53eacbd4f09b 100644 --- a/arch/s390/include/asm/page.h +++ b/arch/s390/include/asm/page.h @@ -37,16 +37,7 @@ static inline void storage_key_init_range(unsigned long start, unsigned long end #endif } -static inline void clear_page(void *page) -{ - register unsigned long reg1 asm ("1") = 0; - register void *reg2 asm ("2") = page; - register unsigned long reg3 asm ("3") = 4096; - asm volatile( - " mvcl 2,0" - : "+d" (reg2), "+d" (reg3) : "d" (reg1) - : "memory", "cc"); -} +#define clear_page(page) memset((page), 0, PAGE_SIZE) /* * copy_page uses the mvcl instruction with 0xb0 padding byte in order to diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index fbb5ee3ae57c..e08ec38f8c6e 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -91,7 +91,9 @@ extern unsigned long zero_page_mask; */ #define PTRS_PER_PTE 256 #ifndef CONFIG_64BIT +#define __PAGETABLE_PUD_FOLDED #define PTRS_PER_PMD 1 +#define __PAGETABLE_PMD_FOLDED #define PTRS_PER_PUD 1 #else /* CONFIG_64BIT */ #define PTRS_PER_PMD 2048 diff --git a/arch/s390/kernel/jump_label.c b/arch/s390/kernel/jump_label.c index cb2d51e779df..830066f936c8 100644 --- a/arch/s390/kernel/jump_label.c +++ b/arch/s390/kernel/jump_label.c @@ -36,16 +36,20 @@ static void jump_label_make_branch(struct jump_entry *entry, struct insn *insn) insn->offset = (entry->target - entry->code) >> 1; } -static void jump_label_bug(struct jump_entry *entry, struct insn *insn) +static void jump_label_bug(struct jump_entry *entry, struct insn *expected, + struct insn *new) { unsigned char *ipc = (unsigned char *)entry->code; - unsigned char *ipe = (unsigned char *)insn; + unsigned char *ipe = (unsigned char *)expected; + unsigned char *ipn = (unsigned char *)new; pr_emerg("Jump label code mismatch at %pS [%p]\n", ipc, ipc); pr_emerg("Found: %02x %02x %02x %02x %02x %02x\n", ipc[0], ipc[1], ipc[2], ipc[3], ipc[4], ipc[5]); pr_emerg("Expected: %02x %02x %02x %02x %02x %02x\n", ipe[0], ipe[1], ipe[2], ipe[3], ipe[4], ipe[5]); + pr_emerg("New: %02x %02x %02x %02x %02x %02x\n", + ipn[0], ipn[1], ipn[2], ipn[3], ipn[4], ipn[5]); panic("Corrupted kernel text"); } @@ -69,10 +73,10 @@ static void __jump_label_transform(struct jump_entry *entry, } if (init) { if (memcmp((void *)entry->code, &orignop, sizeof(orignop))) - jump_label_bug(entry, &old); + jump_label_bug(entry, &orignop, &new); } else { if (memcmp((void *)entry->code, &old, sizeof(old))) - jump_label_bug(entry, &old); + jump_label_bug(entry, &old, &new); } probe_kernel_write((void *)entry->code, &new, sizeof(new)); } diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c index 36154a2f1814..2ca95862e336 100644 --- a/arch/s390/kernel/module.c +++ b/arch/s390/kernel/module.c @@ -436,6 +436,7 @@ int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *me) { + jump_label_apply_nops(me); vfree(me->arch.syminfo); me->arch.syminfo = NULL; return 0; diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c index 26108232fcaa..dc488e13b7e3 100644 --- a/arch/s390/kernel/processor.c +++ b/arch/s390/kernel/processor.c @@ -18,7 +18,7 @@ static DEFINE_PER_CPU(struct cpuid, cpu_id); -void cpu_relax(void) +void notrace cpu_relax(void) { if (!smp_cpu_mtid && MACHINE_HAS_DIAG44) asm volatile("diag 0,0,0x44"); diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c index 89140ddb998c..fc7ec95848c3 100644 --- a/arch/s390/kvm/diag.c +++ b/arch/s390/kvm/diag.c @@ -213,7 +213,7 @@ static int __diag_virtio_hypercall(struct kvm_vcpu *vcpu) * - gpr 3 contains the virtqueue index (passed as datamatch) * - gpr 4 contains the index on the bus (optionally) */ - ret = kvm_io_bus_write_cookie(vcpu->kvm, KVM_VIRTIO_CCW_NOTIFY_BUS, + ret = kvm_io_bus_write_cookie(vcpu, KVM_VIRTIO_CCW_NOTIFY_BUS, vcpu->run->s.regs.gprs[2] & 0xffffffff, 8, &vcpu->run->s.regs.gprs[3], vcpu->run->s.regs.gprs[4]); diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 753a56731951..f0b85443e060 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -287,7 +287,7 @@ void __iomem *pci_iomap_range(struct pci_dev *pdev, addr = ZPCI_IOMAP_ADDR_BASE | ((u64) idx << 48); return (void __iomem *) addr + offset; } -EXPORT_SYMBOL_GPL(pci_iomap_range); +EXPORT_SYMBOL(pci_iomap_range); void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen) { @@ -309,7 +309,7 @@ void pci_iounmap(struct pci_dev *pdev, void __iomem *addr) } spin_unlock(&zpci_iomap_lock); } -EXPORT_SYMBOL_GPL(pci_iounmap); +EXPORT_SYMBOL(pci_iounmap); static int pci_read(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 *val) @@ -483,9 +483,8 @@ void arch_teardown_msi_irqs(struct pci_dev *pdev) airq_iv_free_bit(zpci_aisb_iv, zdev->aisb); } -static void zpci_map_resources(struct zpci_dev *zdev) +static void zpci_map_resources(struct pci_dev *pdev) { - struct pci_dev *pdev = zdev->pdev; resource_size_t len; int i; @@ -499,9 +498,8 @@ static void zpci_map_resources(struct zpci_dev *zdev) } } -static void zpci_unmap_resources(struct zpci_dev *zdev) +static void zpci_unmap_resources(struct pci_dev *pdev) { - struct pci_dev *pdev = zdev->pdev; resource_size_t len; int i; @@ -651,7 +649,7 @@ int pcibios_add_device(struct pci_dev *pdev) zdev->pdev = pdev; pdev->dev.groups = zpci_attr_groups; - zpci_map_resources(zdev); + zpci_map_resources(pdev); for (i = 0; i < PCI_BAR_COUNT; i++) { res = &pdev->resource[i]; @@ -663,6 +661,11 @@ int pcibios_add_device(struct pci_dev *pdev) return 0; } +void pcibios_release_device(struct pci_dev *pdev) +{ + zpci_unmap_resources(pdev); +} + int pcibios_enable_device(struct pci_dev *pdev, int mask) { struct zpci_dev *zdev = get_zdev(pdev); @@ -670,7 +673,6 @@ int pcibios_enable_device(struct pci_dev *pdev, int mask) zdev->pdev = pdev; zpci_debug_init_device(zdev); zpci_fmb_enable_device(zdev); - zpci_map_resources(zdev); return pci_enable_resources(pdev, mask); } @@ -679,7 +681,6 @@ void pcibios_disable_device(struct pci_dev *pdev) { struct zpci_dev *zdev = get_zdev(pdev); - zpci_unmap_resources(zdev); zpci_fmb_disable_device(zdev); zpci_debug_exit_device(zdev); zdev->pdev = NULL; @@ -688,7 +689,8 @@ void pcibios_disable_device(struct pci_dev *pdev) #ifdef CONFIG_HIBERNATE_CALLBACKS static int zpci_restore(struct device *dev) { - struct zpci_dev *zdev = get_zdev(to_pci_dev(dev)); + struct pci_dev *pdev = to_pci_dev(dev); + struct zpci_dev *zdev = get_zdev(pdev); int ret = 0; if (zdev->state != ZPCI_FN_STATE_ONLINE) @@ -698,7 +700,7 @@ static int zpci_restore(struct device *dev) if (ret) goto out; - zpci_map_resources(zdev); + zpci_map_resources(pdev); zpci_register_ioat(zdev, 0, zdev->start_dma + PAGE_OFFSET, zdev->start_dma + zdev->iommu_size - 1, (u64) zdev->dma_table); @@ -709,12 +711,14 @@ out: static int zpci_freeze(struct device *dev) { - struct zpci_dev *zdev = get_zdev(to_pci_dev(dev)); + struct pci_dev *pdev = to_pci_dev(dev); + struct zpci_dev *zdev = get_zdev(pdev); if (zdev->state != ZPCI_FN_STATE_ONLINE) return 0; zpci_unregister_ioat(zdev, 0); + zpci_unmap_resources(pdev); return clp_disable_fh(zdev); } diff --git a/arch/s390/pci/pci_mmio.c b/arch/s390/pci/pci_mmio.c index 8aa271b3d1ad..b1bb2b72302c 100644 --- a/arch/s390/pci/pci_mmio.c +++ b/arch/s390/pci/pci_mmio.c @@ -64,8 +64,7 @@ SYSCALL_DEFINE3(s390_pci_mmio_write, unsigned long, mmio_addr, if (copy_from_user(buf, user_buffer, length)) goto out; - memcpy_toio(io_addr, buf, length); - ret = 0; + ret = zpci_memcpy_toio(io_addr, buf, length); out: if (buf != local_buf) kfree(buf); @@ -98,16 +97,16 @@ SYSCALL_DEFINE3(s390_pci_mmio_read, unsigned long, mmio_addr, goto out; io_addr = (void __iomem *)((pfn << PAGE_SHIFT) | (mmio_addr & ~PAGE_MASK)); - ret = -EFAULT; - if ((unsigned long) io_addr < ZPCI_IOMAP_ADDR_BASE) + if ((unsigned long) io_addr < ZPCI_IOMAP_ADDR_BASE) { + ret = -EFAULT; goto out; - - memcpy_fromio(buf, io_addr, length); - - if (copy_to_user(user_buffer, buf, length)) + } + ret = zpci_memcpy_fromio(buf, io_addr, length); + if (ret) goto out; + if (copy_to_user(user_buffer, buf, length)) + ret = -EFAULT; - ret = 0; out: if (buf != local_buf) kfree(buf); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index c2fb8a87dccb..b7d31ca55187 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -499,6 +499,7 @@ config X86_INTEL_QUARK depends on X86_IO_APIC select IOSF_MBI select INTEL_IMR + select COMMON_CLK ---help--- Select to include support for Quark X1000 SoC. Say Y here if you have a Quark based system such as the Arduino diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index a236e39cc385..30b28dc76411 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -81,11 +81,6 @@ static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level) (base_gfn >> KVM_HPAGE_GFN_SHIFT(level)); } -#define SELECTOR_TI_MASK (1 << 2) -#define SELECTOR_RPL_MASK 0x03 - -#define IOPL_SHIFT 12 - #define KVM_PERMILLE_MMU_PAGES 20 #define KVM_MIN_ALLOC_MMU_PAGES 64 #define KVM_MMU_HASH_SHIFT 10 @@ -933,6 +928,7 @@ struct x86_emulate_ctxt; int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port); void kvm_emulate_cpuid(struct kvm_vcpu *vcpu); int kvm_emulate_halt(struct kvm_vcpu *vcpu); +int kvm_vcpu_halt(struct kvm_vcpu *vcpu); int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu); void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index e62cf897f781..c1adf33fdd0d 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -115,7 +115,7 @@ static inline void kvm_spinlock_init(void) static inline bool kvm_para_available(void) { - return 0; + return false; } static inline unsigned int kvm_arch_para_features(void) diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index d6b078e9fa28..25b1cc07d496 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -95,6 +95,7 @@ unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src, struct pvclock_vsyscall_time_info { struct pvclock_vcpu_time_info pvti; + u32 migrate_count; } __attribute__((__aligned__(SMP_CACHE_BYTES))); #define PVTI_SIZE sizeof(struct pvclock_vsyscall_time_info) diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h index 5fa9770035dc..c9a6d68b8d62 100644 --- a/arch/x86/include/asm/xsave.h +++ b/arch/x86/include/asm/xsave.h @@ -82,18 +82,15 @@ static inline int xsave_state_booting(struct xsave_struct *fx, u64 mask) if (boot_cpu_has(X86_FEATURE_XSAVES)) asm volatile("1:"XSAVES"\n\t" "2:\n\t" - : : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) + xstate_fault + : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) : "memory"); else asm volatile("1:"XSAVE"\n\t" "2:\n\t" - : : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) + xstate_fault + : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) : "memory"); - - asm volatile(xstate_fault - : "0" (0) - : "memory"); - return err; } @@ -112,18 +109,15 @@ static inline int xrstor_state_booting(struct xsave_struct *fx, u64 mask) if (boot_cpu_has(X86_FEATURE_XSAVES)) asm volatile("1:"XRSTORS"\n\t" "2:\n\t" - : : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) + xstate_fault + : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) : "memory"); else asm volatile("1:"XRSTOR"\n\t" "2:\n\t" - : : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) + xstate_fault + : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) : "memory"); - - asm volatile(xstate_fault - : "0" (0) - : "memory"); - return err; } @@ -149,9 +143,9 @@ static inline int xsave_state(struct xsave_struct *fx, u64 mask) */ alternative_input_2( "1:"XSAVE, - "1:"XSAVEOPT, + XSAVEOPT, X86_FEATURE_XSAVEOPT, - "1:"XSAVES, + XSAVES, X86_FEATURE_XSAVES, [fx] "D" (fx), "a" (lmask), "d" (hmask) : "memory"); @@ -178,7 +172,7 @@ static inline int xrstor_state(struct xsave_struct *fx, u64 mask) */ alternative_input( "1: " XRSTOR, - "1: " XRSTORS, + XRSTORS, X86_FEATURE_XSAVES, "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) : "memory"); diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h index c5f1a1deb91a..1fe92181ee9e 100644 --- a/arch/x86/include/uapi/asm/vmx.h +++ b/arch/x86/include/uapi/asm/vmx.h @@ -67,6 +67,7 @@ #define EXIT_REASON_EPT_VIOLATION 48 #define EXIT_REASON_EPT_MISCONFIG 49 #define EXIT_REASON_INVEPT 50 +#define EXIT_REASON_RDTSCP 51 #define EXIT_REASON_PREEMPTION_TIMER 52 #define EXIT_REASON_INVVPID 53 #define EXIT_REASON_WBINVD 54 diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index b5c8ff5e9dfc..2346c95c6ab1 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1396,6 +1396,12 @@ void cpu_init(void) wait_for_master_cpu(cpu); + /* + * Initialize the CR4 shadow before doing anything that could + * try to read it. + */ + cr4_init_shadow(); + show_ucode_info_early(); printk(KERN_INFO "Initializing CPU#%d\n", cpu); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 94d7dcb12145..50163fa9034f 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -565,8 +565,8 @@ static const struct _tlb_table intel_tlb_table[] = { { 0xb2, TLB_INST_4K, 64, " TLB_INST 4KByte pages, 4-way set associative" }, { 0xb3, TLB_DATA_4K, 128, " TLB_DATA 4 KByte pages, 4-way set associative" }, { 0xb4, TLB_DATA_4K, 256, " TLB_DATA 4 KByte pages, 4-way associative" }, - { 0xb5, TLB_INST_4K, 64, " TLB_INST 4 KByte pages, 8-way set ssociative" }, - { 0xb6, TLB_INST_4K, 128, " TLB_INST 4 KByte pages, 8-way set ssociative" }, + { 0xb5, TLB_INST_4K, 64, " TLB_INST 4 KByte pages, 8-way set associative" }, + { 0xb6, TLB_INST_4K, 128, " TLB_INST 4 KByte pages, 8-way set associative" }, { 0xba, TLB_DATA_4K, 64, " TLB_DATA 4 KByte pages, 4-way associative" }, { 0xc0, TLB_DATA_4K_4M, 8, " TLB_DATA 4 KByte and 4 MByte pages, 4-way associative" }, { 0xc1, STLB_4K_2M, 1024, " STLB 4 KByte and 2 MByte pages, 8-way associative" }, diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 000d4199b03e..31e2d5bf3e38 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -982,6 +982,9 @@ ENTRY(xen_hypervisor_callback) ENTRY(xen_do_upcall) 1: mov %esp, %eax call xen_evtchn_do_upcall +#ifndef CONFIG_PREEMPT + call xen_maybe_preempt_hcall +#endif jmp ret_from_intr CFI_ENDPROC ENDPROC(xen_hypervisor_callback) diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index db13655c3a2a..1d74d161687c 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -269,11 +269,14 @@ ENTRY(ret_from_fork) testl $3, CS-ARGOFFSET(%rsp) # from kernel_thread? jz 1f - testl $_TIF_IA32, TI_flags(%rcx) # 32-bit compat task needs IRET - jnz int_ret_from_sys_call - - RESTORE_TOP_OF_STACK %rdi, -ARGOFFSET - jmp ret_from_sys_call # go to the SYSRET fastpath + /* + * By the time we get here, we have no idea whether our pt_regs, + * ti flags, and ti status came from the 64-bit SYSCALL fast path, + * the slow path, or one of the ia32entry paths. + * Use int_ret_from_sys_call to return, since it can safely handle + * all of the above. + */ + jmp int_ret_from_sys_call 1: subq $REST_SKIP, %rsp # leave space for volatiles @@ -1208,6 +1211,9 @@ ENTRY(xen_do_hypervisor_callback) # do_hypervisor_callback(struct *pt_regs) popq %rsp CFI_DEF_CFA_REGISTER rsp decl PER_CPU_VAR(irq_count) +#ifndef CONFIG_PREEMPT + call xen_maybe_preempt_hcall +#endif jmp error_exit CFI_ENDPROC END(xen_do_hypervisor_callback) diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 6a1146ea4d4d..4e3d5a9621fe 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -223,27 +223,48 @@ static unsigned long __recover_probed_insn(kprobe_opcode_t *buf, unsigned long addr) { struct kprobe *kp; + unsigned long faddr; kp = get_kprobe((void *)addr); - /* There is no probe, return original address */ - if (!kp) + faddr = ftrace_location(addr); + /* + * Addresses inside the ftrace location are refused by + * arch_check_ftrace_location(). Something went terribly wrong + * if such an address is checked here. + */ + if (WARN_ON(faddr && faddr != addr)) + return 0UL; + /* + * Use the current code if it is not modified by Kprobe + * and it cannot be modified by ftrace. + */ + if (!kp && !faddr) return addr; /* - * Basically, kp->ainsn.insn has an original instruction. - * However, RIP-relative instruction can not do single-stepping - * at different place, __copy_instruction() tweaks the displacement of - * that instruction. In that case, we can't recover the instruction - * from the kp->ainsn.insn. + * Basically, kp->ainsn.insn has an original instruction. + * However, RIP-relative instruction can not do single-stepping + * at different place, __copy_instruction() tweaks the displacement of + * that instruction. In that case, we can't recover the instruction + * from the kp->ainsn.insn. * - * On the other hand, kp->opcode has a copy of the first byte of - * the probed instruction, which is overwritten by int3. And - * the instruction at kp->addr is not modified by kprobes except - * for the first byte, we can recover the original instruction - * from it and kp->opcode. + * On the other hand, in case on normal Kprobe, kp->opcode has a copy + * of the first byte of the probed instruction, which is overwritten + * by int3. And the instruction at kp->addr is not modified by kprobes + * except for the first byte, we can recover the original instruction + * from it and kp->opcode. + * + * In case of Kprobes using ftrace, we do not have a copy of + * the original instruction. In fact, the ftrace location might + * be modified at anytime and even could be in an inconsistent state. + * Fortunately, we know that the original code is the ideal 5-byte + * long NOP. */ - memcpy(buf, kp->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t)); - buf[0] = kp->opcode; + memcpy(buf, (void *)addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t)); + if (faddr) + memcpy(buf, ideal_nops[NOP_ATOMIC5], 5); + else + buf[0] = kp->opcode; return (unsigned long)buf; } @@ -251,6 +272,7 @@ __recover_probed_insn(kprobe_opcode_t *buf, unsigned long addr) * Recover the probed instruction at addr for further analysis. * Caller must lock kprobes by kprobe_mutex, or disable preemption * for preventing to release referencing kprobes. + * Returns zero if the instruction can not get recovered. */ unsigned long recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr) { @@ -285,6 +307,8 @@ static int can_probe(unsigned long paddr) * normally used, we just go through if there is no kprobe. */ __addr = recover_probed_instruction(buf, addr); + if (!__addr) + return 0; kernel_insn_init(&insn, (void *)__addr, MAX_INSN_SIZE); insn_get_length(&insn); @@ -333,6 +357,8 @@ int __copy_instruction(u8 *dest, u8 *src) unsigned long recovered_insn = recover_probed_instruction(buf, (unsigned long)src); + if (!recovered_insn) + return 0; kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE); insn_get_length(&insn); /* Another subsystem puts a breakpoint, failed to recover */ diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 0dd8d089c315..7b3b9d15c47a 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -259,6 +259,8 @@ static int can_optimize(unsigned long paddr) */ return 0; recovered_insn = recover_probed_instruction(buf, addr); + if (!recovered_insn) + return 0; kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE); insn_get_length(&insn); /* Another subsystem puts a breakpoint */ diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 2f355d229a58..e5ecd20e72dd 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -141,7 +141,46 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock, set_normalized_timespec(ts, now.tv_sec, now.tv_nsec); } +static struct pvclock_vsyscall_time_info *pvclock_vdso_info; + +static struct pvclock_vsyscall_time_info * +pvclock_get_vsyscall_user_time_info(int cpu) +{ + if (!pvclock_vdso_info) { + BUG(); + return NULL; + } + + return &pvclock_vdso_info[cpu]; +} + +struct pvclock_vcpu_time_info *pvclock_get_vsyscall_time_info(int cpu) +{ + return &pvclock_get_vsyscall_user_time_info(cpu)->pvti; +} + #ifdef CONFIG_X86_64 +static int pvclock_task_migrate(struct notifier_block *nb, unsigned long l, + void *v) +{ + struct task_migration_notifier *mn = v; + struct pvclock_vsyscall_time_info *pvti; + + pvti = pvclock_get_vsyscall_user_time_info(mn->from_cpu); + + /* this is NULL when pvclock vsyscall is not initialized */ + if (unlikely(pvti == NULL)) + return NOTIFY_DONE; + + pvti->migrate_count++; + + return NOTIFY_DONE; +} + +static struct notifier_block pvclock_migrate = { + .notifier_call = pvclock_task_migrate, +}; + /* * Initialize the generic pvclock vsyscall state. This will allocate * a/some page(s) for the per-vcpu pvclock information, set up a @@ -155,12 +194,17 @@ int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i, WARN_ON (size != PVCLOCK_VSYSCALL_NR_PAGES*PAGE_SIZE); + pvclock_vdso_info = i; + for (idx = 0; idx <= (PVCLOCK_FIXMAP_END-PVCLOCK_FIXMAP_BEGIN); idx++) { __set_fixmap(PVCLOCK_FIXMAP_BEGIN + idx, __pa(i) + (idx*PAGE_SIZE), PAGE_KERNEL_VVAR); } + + register_task_migration_notifier(&pvclock_migrate); + return 0; } #endif diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 08f790dfadc9..16e8f962eaad 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -1,5 +1,5 @@ -ccflags-y += -Ivirt/kvm -Iarch/x86/kvm +ccflags-y += -Iarch/x86/kvm CFLAGS_x86.o := -I. CFLAGS_svm.o := -I. diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 4452eedfaedd..26228466f3f8 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -26,7 +26,7 @@ static inline bool guest_cpuid_has_xsave(struct kvm_vcpu *vcpu) struct kvm_cpuid_entry2 *best; if (!static_cpu_has(X86_FEATURE_XSAVE)) - return 0; + return false; best = kvm_find_cpuid_entry(vcpu, 1, 0); return best && (best->ecx & bit(X86_FEATURE_XSAVE)); diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index e0b794a84c35..b304728aabe3 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -248,27 +248,7 @@ struct mode_dual { struct opcode mode64; }; -/* EFLAGS bit definitions. */ -#define EFLG_ID (1<<21) -#define EFLG_VIP (1<<20) -#define EFLG_VIF (1<<19) -#define EFLG_AC (1<<18) -#define EFLG_VM (1<<17) -#define EFLG_RF (1<<16) -#define EFLG_IOPL (3<<12) -#define EFLG_NT (1<<14) -#define EFLG_OF (1<<11) -#define EFLG_DF (1<<10) -#define EFLG_IF (1<<9) -#define EFLG_TF (1<<8) -#define EFLG_SF (1<<7) -#define EFLG_ZF (1<<6) -#define EFLG_AF (1<<4) -#define EFLG_PF (1<<2) -#define EFLG_CF (1<<0) - #define EFLG_RESERVED_ZEROS_MASK 0xffc0802a -#define EFLG_RESERVED_ONE_MASK 2 enum x86_transfer_type { X86_TRANSFER_NONE, @@ -317,7 +297,8 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt) * These EFLAGS bits are restored from saved value during emulation, and * any changes are written back to the saved value after emulation. */ -#define EFLAGS_MASK (EFLG_OF|EFLG_SF|EFLG_ZF|EFLG_AF|EFLG_PF|EFLG_CF) +#define EFLAGS_MASK (X86_EFLAGS_OF|X86_EFLAGS_SF|X86_EFLAGS_ZF|X86_EFLAGS_AF|\ + X86_EFLAGS_PF|X86_EFLAGS_CF) #ifdef CONFIG_X86_64 #define ON64(x) x @@ -478,6 +459,25 @@ static void assign_masked(ulong *dest, ulong src, ulong mask) *dest = (*dest & ~mask) | (src & mask); } +static void assign_register(unsigned long *reg, u64 val, int bytes) +{ + /* The 4-byte case *is* correct: in 64-bit mode we zero-extend. */ + switch (bytes) { + case 1: + *(u8 *)reg = (u8)val; + break; + case 2: + *(u16 *)reg = (u16)val; + break; + case 4: + *reg = (u32)val; + break; /* 64b: zero-extend */ + case 8: + *reg = val; + break; + } +} + static inline unsigned long ad_mask(struct x86_emulate_ctxt *ctxt) { return (1UL << (ctxt->ad_bytes << 3)) - 1; @@ -943,6 +943,22 @@ FASTOP2(xadd); FASTOP2R(cmp, cmp_r); +static int em_bsf_c(struct x86_emulate_ctxt *ctxt) +{ + /* If src is zero, do not writeback, but update flags */ + if (ctxt->src.val == 0) + ctxt->dst.type = OP_NONE; + return fastop(ctxt, em_bsf); +} + +static int em_bsr_c(struct x86_emulate_ctxt *ctxt) +{ + /* If src is zero, do not writeback, but update flags */ + if (ctxt->src.val == 0) + ctxt->dst.type = OP_NONE; + return fastop(ctxt, em_bsr); +} + static u8 test_cc(unsigned int condition, unsigned long flags) { u8 rc; @@ -1399,7 +1415,7 @@ static int pio_in_emulated(struct x86_emulate_ctxt *ctxt, unsigned int in_page, n; unsigned int count = ctxt->rep_prefix ? address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) : 1; - in_page = (ctxt->eflags & EFLG_DF) ? + in_page = (ctxt->eflags & X86_EFLAGS_DF) ? offset_in_page(reg_read(ctxt, VCPU_REGS_RDI)) : PAGE_SIZE - offset_in_page(reg_read(ctxt, VCPU_REGS_RDI)); n = min3(in_page, (unsigned int)sizeof(rc->data) / size, count); @@ -1412,7 +1428,7 @@ static int pio_in_emulated(struct x86_emulate_ctxt *ctxt, } if (ctxt->rep_prefix && (ctxt->d & String) && - !(ctxt->eflags & EFLG_DF)) { + !(ctxt->eflags & X86_EFLAGS_DF)) { ctxt->dst.data = rc->data + rc->pos; ctxt->dst.type = OP_MEM_STR; ctxt->dst.count = (rc->end - rc->pos) / size; @@ -1691,21 +1707,7 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, static void write_register_operand(struct operand *op) { - /* The 4-byte case *is* correct: in 64-bit mode we zero-extend. */ - switch (op->bytes) { - case 1: - *(u8 *)op->addr.reg = (u8)op->val; - break; - case 2: - *(u16 *)op->addr.reg = (u16)op->val; - break; - case 4: - *op->addr.reg = (u32)op->val; - break; /* 64b: zero-extend */ - case 8: - *op->addr.reg = op->val; - break; - } + return assign_register(op->addr.reg, op->val, op->bytes); } static int writeback(struct x86_emulate_ctxt *ctxt, struct operand *op) @@ -1792,32 +1794,34 @@ static int emulate_popf(struct x86_emulate_ctxt *ctxt, { int rc; unsigned long val, change_mask; - int iopl = (ctxt->eflags & X86_EFLAGS_IOPL) >> IOPL_SHIFT; + int iopl = (ctxt->eflags & X86_EFLAGS_IOPL) >> X86_EFLAGS_IOPL_BIT; int cpl = ctxt->ops->cpl(ctxt); rc = emulate_pop(ctxt, &val, len); if (rc != X86EMUL_CONTINUE) return rc; - change_mask = EFLG_CF | EFLG_PF | EFLG_AF | EFLG_ZF | EFLG_SF | EFLG_OF - | EFLG_TF | EFLG_DF | EFLG_NT | EFLG_AC | EFLG_ID; + change_mask = X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF | + X86_EFLAGS_ZF | X86_EFLAGS_SF | X86_EFLAGS_OF | + X86_EFLAGS_TF | X86_EFLAGS_DF | X86_EFLAGS_NT | + X86_EFLAGS_AC | X86_EFLAGS_ID; switch(ctxt->mode) { case X86EMUL_MODE_PROT64: case X86EMUL_MODE_PROT32: case X86EMUL_MODE_PROT16: if (cpl == 0) - change_mask |= EFLG_IOPL; + change_mask |= X86_EFLAGS_IOPL; if (cpl <= iopl) - change_mask |= EFLG_IF; + change_mask |= X86_EFLAGS_IF; break; case X86EMUL_MODE_VM86: if (iopl < 3) return emulate_gp(ctxt, 0); - change_mask |= EFLG_IF; + change_mask |= X86_EFLAGS_IF; break; default: /* real mode */ - change_mask |= (EFLG_IOPL | EFLG_IF); + change_mask |= (X86_EFLAGS_IOPL | X86_EFLAGS_IF); break; } @@ -1918,7 +1922,7 @@ static int em_pusha(struct x86_emulate_ctxt *ctxt) static int em_pushf(struct x86_emulate_ctxt *ctxt) { - ctxt->src.val = (unsigned long)ctxt->eflags & ~EFLG_VM; + ctxt->src.val = (unsigned long)ctxt->eflags & ~X86_EFLAGS_VM; return em_push(ctxt); } @@ -1926,6 +1930,7 @@ static int em_popa(struct x86_emulate_ctxt *ctxt) { int rc = X86EMUL_CONTINUE; int reg = VCPU_REGS_RDI; + u32 val; while (reg >= VCPU_REGS_RAX) { if (reg == VCPU_REGS_RSP) { @@ -1933,9 +1938,10 @@ static int em_popa(struct x86_emulate_ctxt *ctxt) --reg; } - rc = emulate_pop(ctxt, reg_rmw(ctxt, reg), ctxt->op_bytes); + rc = emulate_pop(ctxt, &val, ctxt->op_bytes); if (rc != X86EMUL_CONTINUE) break; + assign_register(reg_rmw(ctxt, reg), val, ctxt->op_bytes); --reg; } return rc; @@ -1956,7 +1962,7 @@ static int __emulate_int_real(struct x86_emulate_ctxt *ctxt, int irq) if (rc != X86EMUL_CONTINUE) return rc; - ctxt->eflags &= ~(EFLG_IF | EFLG_TF | EFLG_AC); + ctxt->eflags &= ~(X86_EFLAGS_IF | X86_EFLAGS_TF | X86_EFLAGS_AC); ctxt->src.val = get_segment_selector(ctxt, VCPU_SREG_CS); rc = em_push(ctxt); @@ -2022,10 +2028,14 @@ static int emulate_iret_real(struct x86_emulate_ctxt *ctxt) unsigned long temp_eip = 0; unsigned long temp_eflags = 0; unsigned long cs = 0; - unsigned long mask = EFLG_CF | EFLG_PF | EFLG_AF | EFLG_ZF | EFLG_SF | EFLG_TF | - EFLG_IF | EFLG_DF | EFLG_OF | EFLG_IOPL | EFLG_NT | EFLG_RF | - EFLG_AC | EFLG_ID | (1 << 1); /* Last one is the reserved bit */ - unsigned long vm86_mask = EFLG_VM | EFLG_VIF | EFLG_VIP; + unsigned long mask = X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF | + X86_EFLAGS_ZF | X86_EFLAGS_SF | X86_EFLAGS_TF | + X86_EFLAGS_IF | X86_EFLAGS_DF | X86_EFLAGS_OF | + X86_EFLAGS_IOPL | X86_EFLAGS_NT | X86_EFLAGS_RF | + X86_EFLAGS_AC | X86_EFLAGS_ID | + X86_EFLAGS_FIXED_BIT; + unsigned long vm86_mask = X86_EFLAGS_VM | X86_EFLAGS_VIF | + X86_EFLAGS_VIP; /* TODO: Add stack limit check */ @@ -2054,7 +2064,6 @@ static int emulate_iret_real(struct x86_emulate_ctxt *ctxt) ctxt->_eip = temp_eip; - if (ctxt->op_bytes == 4) ctxt->eflags = ((temp_eflags & mask) | (ctxt->eflags & vm86_mask)); else if (ctxt->op_bytes == 2) { @@ -2063,7 +2072,7 @@ static int emulate_iret_real(struct x86_emulate_ctxt *ctxt) } ctxt->eflags &= ~EFLG_RESERVED_ZEROS_MASK; /* Clear reserved zeros */ - ctxt->eflags |= EFLG_RESERVED_ONE_MASK; + ctxt->eflags |= X86_EFLAGS_FIXED_BIT; ctxt->ops->set_nmi_mask(ctxt, false); return rc; @@ -2145,12 +2154,12 @@ static int em_cmpxchg8b(struct x86_emulate_ctxt *ctxt) ((u32) (old >> 32) != (u32) reg_read(ctxt, VCPU_REGS_RDX))) { *reg_write(ctxt, VCPU_REGS_RAX) = (u32) (old >> 0); *reg_write(ctxt, VCPU_REGS_RDX) = (u32) (old >> 32); - ctxt->eflags &= ~EFLG_ZF; + ctxt->eflags &= ~X86_EFLAGS_ZF; } else { ctxt->dst.val64 = ((u64)reg_read(ctxt, VCPU_REGS_RCX) << 32) | (u32) reg_read(ctxt, VCPU_REGS_RBX); - ctxt->eflags |= EFLG_ZF; + ctxt->eflags |= X86_EFLAGS_ZF; } return X86EMUL_CONTINUE; } @@ -2222,7 +2231,7 @@ static int em_cmpxchg(struct x86_emulate_ctxt *ctxt) ctxt->src.val = ctxt->dst.orig_val; fastop(ctxt, em_cmp); - if (ctxt->eflags & EFLG_ZF) { + if (ctxt->eflags & X86_EFLAGS_ZF) { /* Success: write back to memory; no update of EAX */ ctxt->src.type = OP_NONE; ctxt->dst.val = ctxt->src.orig_val; @@ -2381,14 +2390,14 @@ static int em_syscall(struct x86_emulate_ctxt *ctxt) ops->get_msr(ctxt, MSR_SYSCALL_MASK, &msr_data); ctxt->eflags &= ~msr_data; - ctxt->eflags |= EFLG_RESERVED_ONE_MASK; + ctxt->eflags |= X86_EFLAGS_FIXED_BIT; #endif } else { /* legacy mode */ ops->get_msr(ctxt, MSR_STAR, &msr_data); ctxt->_eip = (u32)msr_data; - ctxt->eflags &= ~(EFLG_VM | EFLG_IF); + ctxt->eflags &= ~(X86_EFLAGS_VM | X86_EFLAGS_IF); } return X86EMUL_CONTINUE; @@ -2425,8 +2434,8 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt) if ((msr_data & 0xfffc) == 0x0) return emulate_gp(ctxt, 0); - ctxt->eflags &= ~(EFLG_VM | EFLG_IF); - cs_sel = (u16)msr_data & ~SELECTOR_RPL_MASK; + ctxt->eflags &= ~(X86_EFLAGS_VM | X86_EFLAGS_IF); + cs_sel = (u16)msr_data & ~SEGMENT_RPL_MASK; ss_sel = cs_sel + 8; if (efer & EFER_LMA) { cs.d = 0; @@ -2493,8 +2502,8 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt) return emulate_gp(ctxt, 0); break; } - cs_sel |= SELECTOR_RPL_MASK; - ss_sel |= SELECTOR_RPL_MASK; + cs_sel |= SEGMENT_RPL_MASK; + ss_sel |= SEGMENT_RPL_MASK; ops->set_segment(ctxt, cs_sel, &cs, 0, VCPU_SREG_CS); ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS); @@ -2512,7 +2521,7 @@ static bool emulator_bad_iopl(struct x86_emulate_ctxt *ctxt) return false; if (ctxt->mode == X86EMUL_MODE_VM86) return true; - iopl = (ctxt->eflags & X86_EFLAGS_IOPL) >> IOPL_SHIFT; + iopl = (ctxt->eflags & X86_EFLAGS_IOPL) >> X86_EFLAGS_IOPL_BIT; return ctxt->ops->cpl(ctxt) > iopl; } @@ -2782,10 +2791,8 @@ static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt, return ret; ret = __load_segment_descriptor(ctxt, tss->gs, VCPU_SREG_GS, cpl, X86_TRANSFER_TASK_SWITCH, NULL); - if (ret != X86EMUL_CONTINUE) - return ret; - return X86EMUL_CONTINUE; + return ret; } static int task_switch_32(struct x86_emulate_ctxt *ctxt, @@ -2954,7 +2961,7 @@ int emulator_task_switch(struct x86_emulate_ctxt *ctxt, static void string_addr_inc(struct x86_emulate_ctxt *ctxt, int reg, struct operand *op) { - int df = (ctxt->eflags & EFLG_DF) ? -op->count : op->count; + int df = (ctxt->eflags & X86_EFLAGS_DF) ? -op->count : op->count; register_address_increment(ctxt, reg, df * op->bytes); op->addr.mem.ea = register_address(ctxt, reg); @@ -3323,7 +3330,7 @@ static int em_clts(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } -static int em_vmcall(struct x86_emulate_ctxt *ctxt) +static int em_hypercall(struct x86_emulate_ctxt *ctxt) { int rc = ctxt->ops->fix_hypercall(ctxt); @@ -3395,17 +3402,6 @@ static int em_lgdt(struct x86_emulate_ctxt *ctxt) return em_lgdt_lidt(ctxt, true); } -static int em_vmmcall(struct x86_emulate_ctxt *ctxt) -{ - int rc; - - rc = ctxt->ops->fix_hypercall(ctxt); - - /* Disable writeback. */ - ctxt->dst.type = OP_NONE; - return rc; -} - static int em_lidt(struct x86_emulate_ctxt *ctxt) { return em_lgdt_lidt(ctxt, false); @@ -3504,7 +3500,8 @@ static int em_sahf(struct x86_emulate_ctxt *ctxt) { u32 flags; - flags = EFLG_CF | EFLG_PF | EFLG_AF | EFLG_ZF | EFLG_SF; + flags = X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF | X86_EFLAGS_ZF | + X86_EFLAGS_SF; flags &= *reg_rmw(ctxt, VCPU_REGS_RAX) >> 8; ctxt->eflags &= ~0xffUL; @@ -3769,7 +3766,7 @@ static int check_perm_out(struct x86_emulate_ctxt *ctxt) static const struct opcode group7_rm0[] = { N, - I(SrcNone | Priv | EmulateOnUD, em_vmcall), + I(SrcNone | Priv | EmulateOnUD, em_hypercall), N, N, N, N, N, N, }; @@ -3781,7 +3778,7 @@ static const struct opcode group7_rm1[] = { static const struct opcode group7_rm3[] = { DIP(SrcNone | Prot | Priv, vmrun, check_svme_pa), - II(SrcNone | Prot | EmulateOnUD, em_vmmcall, vmmcall), + II(SrcNone | Prot | EmulateOnUD, em_hypercall, vmmcall), DIP(SrcNone | Prot | Priv, vmload, check_svme_pa), DIP(SrcNone | Prot | Priv, vmsave, check_svme_pa), DIP(SrcNone | Prot | Priv, stgi, check_svme), @@ -4192,7 +4189,8 @@ static const struct opcode twobyte_table[256] = { N, N, G(BitOp, group8), F(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_btc), - F(DstReg | SrcMem | ModRM, em_bsf), F(DstReg | SrcMem | ModRM, em_bsr), + I(DstReg | SrcMem | ModRM, em_bsf_c), + I(DstReg | SrcMem | ModRM, em_bsr_c), D(DstReg | SrcMem8 | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov), /* 0xC0 - 0xC7 */ F2bv(DstMem | SrcReg | ModRM | SrcWrite | Lock, em_xadd), @@ -4759,9 +4757,9 @@ static bool string_insn_completed(struct x86_emulate_ctxt *ctxt) if (((ctxt->b == 0xa6) || (ctxt->b == 0xa7) || (ctxt->b == 0xae) || (ctxt->b == 0xaf)) && (((ctxt->rep_prefix == REPE_PREFIX) && - ((ctxt->eflags & EFLG_ZF) == 0)) + ((ctxt->eflags & X86_EFLAGS_ZF) == 0)) || ((ctxt->rep_prefix == REPNE_PREFIX) && - ((ctxt->eflags & EFLG_ZF) == EFLG_ZF)))) + ((ctxt->eflags & X86_EFLAGS_ZF) == X86_EFLAGS_ZF)))) return true; return false; @@ -4913,7 +4911,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) /* All REP prefixes have the same first termination condition */ if (address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) == 0) { ctxt->eip = ctxt->_eip; - ctxt->eflags &= ~EFLG_RF; + ctxt->eflags &= ~X86_EFLAGS_RF; goto done; } } @@ -4950,7 +4948,8 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) goto done; } } - ctxt->dst.orig_val = ctxt->dst.val; + /* Copy full 64-bit value for CMPXCHG8B. */ + ctxt->dst.orig_val64 = ctxt->dst.val64; special_insn: @@ -4962,9 +4961,9 @@ special_insn: } if (ctxt->rep_prefix && (ctxt->d & String)) - ctxt->eflags |= EFLG_RF; + ctxt->eflags |= X86_EFLAGS_RF; else - ctxt->eflags &= ~EFLG_RF; + ctxt->eflags &= ~X86_EFLAGS_RF; if (ctxt->execute) { if (ctxt->d & Fastop) { @@ -5013,7 +5012,7 @@ special_insn: rc = emulate_int(ctxt, ctxt->src.val); break; case 0xce: /* into */ - if (ctxt->eflags & EFLG_OF) + if (ctxt->eflags & X86_EFLAGS_OF) rc = emulate_int(ctxt, 4); break; case 0xe9: /* jmp rel */ @@ -5026,19 +5025,19 @@ special_insn: break; case 0xf5: /* cmc */ /* complement carry flag from eflags reg */ - ctxt->eflags ^= EFLG_CF; + ctxt->eflags ^= X86_EFLAGS_CF; break; case 0xf8: /* clc */ - ctxt->eflags &= ~EFLG_CF; + ctxt->eflags &= ~X86_EFLAGS_CF; break; case 0xf9: /* stc */ - ctxt->eflags |= EFLG_CF; + ctxt->eflags |= X86_EFLAGS_CF; break; case 0xfc: /* cld */ - ctxt->eflags &= ~EFLG_DF; + ctxt->eflags &= ~X86_EFLAGS_DF; break; case 0xfd: /* std */ - ctxt->eflags |= EFLG_DF; + ctxt->eflags |= X86_EFLAGS_DF; break; default: goto cannot_emulate; @@ -5099,7 +5098,7 @@ writeback: } goto done; /* skip rip writeback */ } - ctxt->eflags &= ~EFLG_RF; + ctxt->eflags &= ~X86_EFLAGS_RF; } ctxt->eip = ctxt->_eip; @@ -5136,8 +5135,7 @@ twobyte_insn: case 0x40 ... 0x4f: /* cmov */ if (test_cc(ctxt->b, ctxt->eflags)) ctxt->dst.val = ctxt->src.val; - else if (ctxt->mode != X86EMUL_MODE_PROT64 || - ctxt->op_bytes != 4) + else if (ctxt->op_bytes != 4) ctxt->dst.type = OP_NONE; /* no writeback */ break; case 0x80 ... 0x8f: /* jnz rel, etc*/ diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 298781d4cfb4..4dce6f8b6129 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -443,7 +443,8 @@ static inline int pit_in_range(gpa_t addr) (addr < KVM_PIT_BASE_ADDRESS + KVM_PIT_MEM_LENGTH)); } -static int pit_ioport_write(struct kvm_io_device *this, +static int pit_ioport_write(struct kvm_vcpu *vcpu, + struct kvm_io_device *this, gpa_t addr, int len, const void *data) { struct kvm_pit *pit = dev_to_pit(this); @@ -519,7 +520,8 @@ static int pit_ioport_write(struct kvm_io_device *this, return 0; } -static int pit_ioport_read(struct kvm_io_device *this, +static int pit_ioport_read(struct kvm_vcpu *vcpu, + struct kvm_io_device *this, gpa_t addr, int len, void *data) { struct kvm_pit *pit = dev_to_pit(this); @@ -589,7 +591,8 @@ static int pit_ioport_read(struct kvm_io_device *this, return 0; } -static int speaker_ioport_write(struct kvm_io_device *this, +static int speaker_ioport_write(struct kvm_vcpu *vcpu, + struct kvm_io_device *this, gpa_t addr, int len, const void *data) { struct kvm_pit *pit = speaker_to_pit(this); @@ -606,8 +609,9 @@ static int speaker_ioport_write(struct kvm_io_device *this, return 0; } -static int speaker_ioport_read(struct kvm_io_device *this, - gpa_t addr, int len, void *data) +static int speaker_ioport_read(struct kvm_vcpu *vcpu, + struct kvm_io_device *this, + gpa_t addr, int len, void *data) { struct kvm_pit *pit = speaker_to_pit(this); struct kvm_kpit_state *pit_state = &pit->pit_state; diff --git a/arch/x86/kvm/i8254.h b/arch/x86/kvm/i8254.h index dd1b16b611b0..c84990b42b5b 100644 --- a/arch/x86/kvm/i8254.h +++ b/arch/x86/kvm/i8254.h @@ -3,7 +3,7 @@ #include <linux/kthread.h> -#include "iodev.h" +#include <kvm/iodev.h> struct kvm_kpit_channel_state { u32 count; /* can be 65536 */ diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index cc31f7c06d3d..fef922ff2635 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -507,6 +507,7 @@ static int picdev_read(struct kvm_pic *s, return -EOPNOTSUPP; if (len != 1) { + memset(val, 0, len); pr_pic_unimpl("non byte read\n"); return 0; } @@ -528,42 +529,42 @@ static int picdev_read(struct kvm_pic *s, return 0; } -static int picdev_master_write(struct kvm_io_device *dev, +static int picdev_master_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int len, const void *val) { return picdev_write(container_of(dev, struct kvm_pic, dev_master), addr, len, val); } -static int picdev_master_read(struct kvm_io_device *dev, +static int picdev_master_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int len, void *val) { return picdev_read(container_of(dev, struct kvm_pic, dev_master), addr, len, val); } -static int picdev_slave_write(struct kvm_io_device *dev, +static int picdev_slave_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int len, const void *val) { return picdev_write(container_of(dev, struct kvm_pic, dev_slave), addr, len, val); } -static int picdev_slave_read(struct kvm_io_device *dev, +static int picdev_slave_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int len, void *val) { return picdev_read(container_of(dev, struct kvm_pic, dev_slave), addr, len, val); } -static int picdev_eclr_write(struct kvm_io_device *dev, +static int picdev_eclr_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int len, const void *val) { return picdev_write(container_of(dev, struct kvm_pic, dev_eclr), addr, len, val); } -static int picdev_eclr_read(struct kvm_io_device *dev, +static int picdev_eclr_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int len, void *val) { return picdev_read(container_of(dev, struct kvm_pic, dev_eclr), diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index b1947e0f3e10..51889ec847b0 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -206,6 +206,8 @@ static int ioapic_set_irq(struct kvm_ioapic *ioapic, unsigned int irq, old_irr = ioapic->irr; ioapic->irr |= mask; + if (edge) + ioapic->irr_delivered &= ~mask; if ((edge && old_irr == ioapic->irr) || (!edge && entry.fields.remote_irr)) { ret = 0; @@ -349,7 +351,7 @@ static int ioapic_service(struct kvm_ioapic *ioapic, int irq, bool line_status) irqe.shorthand = 0; if (irqe.trig_mode == IOAPIC_EDGE_TRIG) - ioapic->irr &= ~(1 << irq); + ioapic->irr_delivered |= 1 << irq; if (irq == RTC_GSI && line_status) { /* @@ -471,13 +473,6 @@ static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, } } -bool kvm_ioapic_handles_vector(struct kvm *kvm, int vector) -{ - struct kvm_ioapic *ioapic = kvm->arch.vioapic; - smp_rmb(); - return test_bit(vector, ioapic->handled_vectors); -} - void kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, int vector, int trigger_mode) { struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic; @@ -498,8 +493,8 @@ static inline int ioapic_in_range(struct kvm_ioapic *ioapic, gpa_t addr) (addr < ioapic->base_address + IOAPIC_MEM_LENGTH))); } -static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len, - void *val) +static int ioapic_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *this, + gpa_t addr, int len, void *val) { struct kvm_ioapic *ioapic = to_ioapic(this); u32 result; @@ -541,8 +536,8 @@ static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len, return 0; } -static int ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len, - const void *val) +static int ioapic_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this, + gpa_t addr, int len, const void *val) { struct kvm_ioapic *ioapic = to_ioapic(this); u32 data; @@ -597,6 +592,7 @@ static void kvm_ioapic_reset(struct kvm_ioapic *ioapic) ioapic->base_address = IOAPIC_DEFAULT_BASE_ADDRESS; ioapic->ioregsel = 0; ioapic->irr = 0; + ioapic->irr_delivered = 0; ioapic->id = 0; memset(ioapic->irq_eoi, 0x00, IOAPIC_NUM_PINS); rtc_irq_eoi_tracking_reset(ioapic); @@ -654,6 +650,7 @@ int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state) spin_lock(&ioapic->lock); memcpy(state, ioapic, sizeof(struct kvm_ioapic_state)); + state->irr &= ~ioapic->irr_delivered; spin_unlock(&ioapic->lock); return 0; } @@ -667,6 +664,7 @@ int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state) spin_lock(&ioapic->lock); memcpy(ioapic, state, sizeof(struct kvm_ioapic_state)); ioapic->irr = 0; + ioapic->irr_delivered = 0; update_handled_vectors(ioapic); kvm_vcpu_request_scan_ioapic(kvm); kvm_ioapic_inject_all(ioapic, state->irr); diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h index c2e36d934af4..ca0b0b4e6256 100644 --- a/arch/x86/kvm/ioapic.h +++ b/arch/x86/kvm/ioapic.h @@ -3,7 +3,7 @@ #include <linux/kvm_host.h> -#include "iodev.h" +#include <kvm/iodev.h> struct kvm; struct kvm_vcpu; @@ -77,6 +77,7 @@ struct kvm_ioapic { struct rtc_status rtc_status; struct delayed_work eoi_inject; u32 irq_eoi[IOAPIC_NUM_PINS]; + u32 irr_delivered; }; #ifdef DEBUG @@ -97,13 +98,19 @@ static inline struct kvm_ioapic *ioapic_irqchip(struct kvm *kvm) return kvm->arch.vioapic; } +static inline bool kvm_ioapic_handles_vector(struct kvm *kvm, int vector) +{ + struct kvm_ioapic *ioapic = kvm->arch.vioapic; + smp_rmb(); + return test_bit(vector, ioapic->handled_vectors); +} + void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu); bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, int short_hand, unsigned int dest, int dest_mode); int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2); void kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, int vector, int trigger_mode); -bool kvm_ioapic_handles_vector(struct kvm *kvm, int vector); int kvm_ioapic_init(struct kvm *kvm); void kvm_ioapic_destroy(struct kvm *kvm); int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id, diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index 2d03568e9498..ad68c73008c5 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -27,7 +27,7 @@ #include <linux/kvm_host.h> #include <linux/spinlock.h> -#include "iodev.h" +#include <kvm/iodev.h> #include "ioapic.h" #include "lapic.h" diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index e55b5fc344eb..44f7b9afbedb 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1038,7 +1038,7 @@ static int apic_mmio_in_range(struct kvm_lapic *apic, gpa_t addr) addr < apic->base_address + LAPIC_MMIO_LENGTH; } -static int apic_mmio_read(struct kvm_io_device *this, +static int apic_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *this, gpa_t address, int len, void *data) { struct kvm_lapic *apic = to_lapic(this); @@ -1358,7 +1358,7 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) return ret; } -static int apic_mmio_write(struct kvm_io_device *this, +static int apic_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this, gpa_t address, int len, const void *data) { struct kvm_lapic *apic = to_lapic(this); @@ -1572,7 +1572,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu) apic_set_reg(apic, APIC_TMR + 0x10 * i, 0); } apic->irr_pending = kvm_apic_vid_enabled(vcpu->kvm); - apic->isr_count = kvm_apic_vid_enabled(vcpu->kvm); + apic->isr_count = kvm_x86_ops->hwapic_isr_update ? 1 : 0; apic->highest_isr_cache = -1; update_divide_count(apic); atomic_set(&apic->lapic_timer.pending, 0); @@ -1782,7 +1782,7 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu, update_divide_count(apic); start_apic_timer(apic); apic->irr_pending = true; - apic->isr_count = kvm_apic_vid_enabled(vcpu->kvm) ? + apic->isr_count = kvm_x86_ops->hwapic_isr_update ? 1 : count_vectors(apic->regs + APIC_ISR); apic->highest_isr_cache = -1; if (kvm_x86_ops->hwapic_irr_update) diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 0bc6c656625b..e284c2880c56 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -1,7 +1,7 @@ #ifndef __KVM_X86_LAPIC_H #define __KVM_X86_LAPIC_H -#include "iodev.h" +#include <kvm/iodev.h> #include <linux/kvm_host.h> diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 8e6b7d869d2f..29fbf9dfdc54 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -38,7 +38,7 @@ static struct kvm_arch_event_perf_mapping { }; /* mapping between fixed pmc index and arch_events array */ -int fixed_pmc_events[] = {1, 0, 7}; +static int fixed_pmc_events[] = {1, 0, 7}; static bool pmc_is_gp(struct kvm_pmc *pmc) { diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index d319e0c24758..155534c0f5e8 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1929,14 +1929,12 @@ static int nop_on_interception(struct vcpu_svm *svm) static int halt_interception(struct vcpu_svm *svm) { svm->next_rip = kvm_rip_read(&svm->vcpu) + 1; - skip_emulated_instruction(&svm->vcpu); return kvm_emulate_halt(&svm->vcpu); } static int vmmcall_interception(struct vcpu_svm *svm) { svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; - skip_emulated_instruction(&svm->vcpu); kvm_emulate_hypercall(&svm->vcpu); return 1; } @@ -2757,11 +2755,11 @@ static int invlpga_interception(struct vcpu_svm *svm) { struct kvm_vcpu *vcpu = &svm->vcpu; - trace_kvm_invlpga(svm->vmcb->save.rip, vcpu->arch.regs[VCPU_REGS_RCX], - vcpu->arch.regs[VCPU_REGS_RAX]); + trace_kvm_invlpga(svm->vmcb->save.rip, kvm_register_read(&svm->vcpu, VCPU_REGS_RCX), + kvm_register_read(&svm->vcpu, VCPU_REGS_RAX)); /* Let's treat INVLPGA the same as INVLPG (can be optimized!) */ - kvm_mmu_invlpg(vcpu, vcpu->arch.regs[VCPU_REGS_RAX]); + kvm_mmu_invlpg(vcpu, kvm_register_read(&svm->vcpu, VCPU_REGS_RAX)); svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; skip_emulated_instruction(&svm->vcpu); @@ -2770,12 +2768,18 @@ static int invlpga_interception(struct vcpu_svm *svm) static int skinit_interception(struct vcpu_svm *svm) { - trace_kvm_skinit(svm->vmcb->save.rip, svm->vcpu.arch.regs[VCPU_REGS_RAX]); + trace_kvm_skinit(svm->vmcb->save.rip, kvm_register_read(&svm->vcpu, VCPU_REGS_RAX)); kvm_queue_exception(&svm->vcpu, UD_VECTOR); return 1; } +static int wbinvd_interception(struct vcpu_svm *svm) +{ + kvm_emulate_wbinvd(&svm->vcpu); + return 1; +} + static int xsetbv_interception(struct vcpu_svm *svm) { u64 new_bv = kvm_read_edx_eax(&svm->vcpu); @@ -2902,7 +2906,8 @@ static int rdpmc_interception(struct vcpu_svm *svm) return 1; } -bool check_selective_cr0_intercepted(struct vcpu_svm *svm, unsigned long val) +static bool check_selective_cr0_intercepted(struct vcpu_svm *svm, + unsigned long val) { unsigned long cr0 = svm->vcpu.arch.cr0; bool ret = false; @@ -2940,7 +2945,10 @@ static int cr_interception(struct vcpu_svm *svm) return emulate_on_interception(svm); reg = svm->vmcb->control.exit_info_1 & SVM_EXITINFO_REG_MASK; - cr = svm->vmcb->control.exit_code - SVM_EXIT_READ_CR0; + if (svm->vmcb->control.exit_code == SVM_EXIT_CR0_SEL_WRITE) + cr = SVM_EXIT_WRITE_CR0 - SVM_EXIT_READ_CR0; + else + cr = svm->vmcb->control.exit_code - SVM_EXIT_READ_CR0; err = 0; if (cr >= 16) { /* mov to cr */ @@ -3133,7 +3141,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) static int rdmsr_interception(struct vcpu_svm *svm) { - u32 ecx = svm->vcpu.arch.regs[VCPU_REGS_RCX]; + u32 ecx = kvm_register_read(&svm->vcpu, VCPU_REGS_RCX); u64 data; if (svm_get_msr(&svm->vcpu, ecx, &data)) { @@ -3142,8 +3150,8 @@ static int rdmsr_interception(struct vcpu_svm *svm) } else { trace_kvm_msr_read(ecx, data); - svm->vcpu.arch.regs[VCPU_REGS_RAX] = data & 0xffffffff; - svm->vcpu.arch.regs[VCPU_REGS_RDX] = data >> 32; + kvm_register_write(&svm->vcpu, VCPU_REGS_RAX, data & 0xffffffff); + kvm_register_write(&svm->vcpu, VCPU_REGS_RDX, data >> 32); svm->next_rip = kvm_rip_read(&svm->vcpu) + 2; skip_emulated_instruction(&svm->vcpu); } @@ -3246,9 +3254,8 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) static int wrmsr_interception(struct vcpu_svm *svm) { struct msr_data msr; - u32 ecx = svm->vcpu.arch.regs[VCPU_REGS_RCX]; - u64 data = (svm->vcpu.arch.regs[VCPU_REGS_RAX] & -1u) - | ((u64)(svm->vcpu.arch.regs[VCPU_REGS_RDX] & -1u) << 32); + u32 ecx = kvm_register_read(&svm->vcpu, VCPU_REGS_RCX); + u64 data = kvm_read_edx_eax(&svm->vcpu); msr.data = data; msr.index = ecx; @@ -3325,7 +3332,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_READ_CR3] = cr_interception, [SVM_EXIT_READ_CR4] = cr_interception, [SVM_EXIT_READ_CR8] = cr_interception, - [SVM_EXIT_CR0_SEL_WRITE] = emulate_on_interception, + [SVM_EXIT_CR0_SEL_WRITE] = cr_interception, [SVM_EXIT_WRITE_CR0] = cr_interception, [SVM_EXIT_WRITE_CR3] = cr_interception, [SVM_EXIT_WRITE_CR4] = cr_interception, @@ -3376,7 +3383,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_STGI] = stgi_interception, [SVM_EXIT_CLGI] = clgi_interception, [SVM_EXIT_SKINIT] = skinit_interception, - [SVM_EXIT_WBINVD] = emulate_on_interception, + [SVM_EXIT_WBINVD] = wbinvd_interception, [SVM_EXIT_MONITOR] = monitor_interception, [SVM_EXIT_MWAIT] = mwait_interception, [SVM_EXIT_XSETBV] = xsetbv_interception, @@ -3555,7 +3562,7 @@ static int handle_exit(struct kvm_vcpu *vcpu) if (exit_code >= ARRAY_SIZE(svm_exit_handlers) || !svm_exit_handlers[exit_code]) { - WARN_ONCE(1, "vmx: unexpected exit reason 0x%x\n", exit_code); + WARN_ONCE(1, "svm: unexpected exit reason 0x%x\n", exit_code); kvm_queue_exception(vcpu, UD_VECTOR); return 1; } @@ -3649,11 +3656,6 @@ static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) return; } -static void svm_hwapic_isr_update(struct kvm *kvm, int isr) -{ - return; -} - static void svm_sync_pir_to_irr(struct kvm_vcpu *vcpu) { return; @@ -4403,7 +4405,6 @@ static struct kvm_x86_ops svm_x86_ops = { .set_virtual_x2apic_mode = svm_set_virtual_x2apic_mode, .vm_has_apicv = svm_vm_has_apicv, .load_eoi_exitmap = svm_load_eoi_exitmap, - .hwapic_isr_update = svm_hwapic_isr_update, .sync_pir_to_irr = svm_sync_pir_to_irr, .set_tss_addr = svm_set_tss_addr, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 14c1a18d206a..b5a6425d8d97 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2467,6 +2467,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) vmx->nested.nested_vmx_secondary_ctls_low = 0; vmx->nested.nested_vmx_secondary_ctls_high &= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | + SECONDARY_EXEC_RDTSCP | SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | @@ -3262,8 +3263,8 @@ static void fix_pmode_seg(struct kvm_vcpu *vcpu, int seg, * default value. */ if (seg == VCPU_SREG_CS || seg == VCPU_SREG_SS) - save->selector &= ~SELECTOR_RPL_MASK; - save->dpl = save->selector & SELECTOR_RPL_MASK; + save->selector &= ~SEGMENT_RPL_MASK; + save->dpl = save->selector & SEGMENT_RPL_MASK; save->s = 1; } vmx_set_segment(vcpu, save, seg); @@ -3836,7 +3837,7 @@ static bool code_segment_valid(struct kvm_vcpu *vcpu) unsigned int cs_rpl; vmx_get_segment(vcpu, &cs, VCPU_SREG_CS); - cs_rpl = cs.selector & SELECTOR_RPL_MASK; + cs_rpl = cs.selector & SEGMENT_RPL_MASK; if (cs.unusable) return false; @@ -3864,7 +3865,7 @@ static bool stack_segment_valid(struct kvm_vcpu *vcpu) unsigned int ss_rpl; vmx_get_segment(vcpu, &ss, VCPU_SREG_SS); - ss_rpl = ss.selector & SELECTOR_RPL_MASK; + ss_rpl = ss.selector & SEGMENT_RPL_MASK; if (ss.unusable) return true; @@ -3886,7 +3887,7 @@ static bool data_segment_valid(struct kvm_vcpu *vcpu, int seg) unsigned int rpl; vmx_get_segment(vcpu, &var, seg); - rpl = var.selector & SELECTOR_RPL_MASK; + rpl = var.selector & SEGMENT_RPL_MASK; if (var.unusable) return true; @@ -3913,7 +3914,7 @@ static bool tr_valid(struct kvm_vcpu *vcpu) if (tr.unusable) return false; - if (tr.selector & SELECTOR_TI_MASK) /* TI = 1 */ + if (tr.selector & SEGMENT_TI_MASK) /* TI = 1 */ return false; if (tr.type != 3 && tr.type != 11) /* TODO: Check if guest is in IA32e mode */ return false; @@ -3931,7 +3932,7 @@ static bool ldtr_valid(struct kvm_vcpu *vcpu) if (ldtr.unusable) return true; - if (ldtr.selector & SELECTOR_TI_MASK) /* TI = 1 */ + if (ldtr.selector & SEGMENT_TI_MASK) /* TI = 1 */ return false; if (ldtr.type != 2) return false; @@ -3948,8 +3949,8 @@ static bool cs_ss_rpl_check(struct kvm_vcpu *vcpu) vmx_get_segment(vcpu, &cs, VCPU_SREG_CS); vmx_get_segment(vcpu, &ss, VCPU_SREG_SS); - return ((cs.selector & SELECTOR_RPL_MASK) == - (ss.selector & SELECTOR_RPL_MASK)); + return ((cs.selector & SEGMENT_RPL_MASK) == + (ss.selector & SEGMENT_RPL_MASK)); } /* @@ -4367,6 +4368,18 @@ static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) return 0; } +static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu) +{ +#ifdef CONFIG_SMP + if (vcpu->mode == IN_GUEST_MODE) { + apic->send_IPI_mask(get_cpu_mask(vcpu->cpu), + POSTED_INTR_VECTOR); + return true; + } +#endif + return false; +} + static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu, int vector) { @@ -4375,9 +4388,7 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu, if (is_guest_mode(vcpu) && vector == vmx->nested.posted_intr_nv) { /* the PIR and ON have been set by L1. */ - if (vcpu->mode == IN_GUEST_MODE) - apic->send_IPI_mask(get_cpu_mask(vcpu->cpu), - POSTED_INTR_VECTOR); + kvm_vcpu_trigger_posted_interrupt(vcpu); /* * If a posted intr is not recognized by hardware, * we will accomplish it in the next vmentry. @@ -4409,12 +4420,7 @@ static void vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) r = pi_test_and_set_on(&vmx->pi_desc); kvm_make_request(KVM_REQ_EVENT, vcpu); -#ifdef CONFIG_SMP - if (!r && (vcpu->mode == IN_GUEST_MODE)) - apic->send_IPI_mask(get_cpu_mask(vcpu->cpu), - POSTED_INTR_VECTOR); - else -#endif + if (r || !kvm_vcpu_trigger_posted_interrupt(vcpu)) kvm_vcpu_kick(vcpu); } @@ -4995,7 +5001,7 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu, if (emulate_instruction(vcpu, 0) == EMULATE_DONE) { if (vcpu->arch.halt_request) { vcpu->arch.halt_request = 0; - return kvm_emulate_halt(vcpu); + return kvm_vcpu_halt(vcpu); } return 1; } @@ -5060,6 +5066,10 @@ static int handle_exception(struct kvm_vcpu *vcpu) } if (is_invalid_opcode(intr_info)) { + if (is_guest_mode(vcpu)) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } er = emulate_instruction(vcpu, EMULTYPE_TRAP_UD); if (er != EMULATE_DONE) kvm_queue_exception(vcpu, UD_VECTOR); @@ -5522,13 +5532,11 @@ static int handle_interrupt_window(struct kvm_vcpu *vcpu) static int handle_halt(struct kvm_vcpu *vcpu) { - skip_emulated_instruction(vcpu); return kvm_emulate_halt(vcpu); } static int handle_vmcall(struct kvm_vcpu *vcpu) { - skip_emulated_instruction(vcpu); kvm_emulate_hypercall(vcpu); return 1; } @@ -5559,7 +5567,6 @@ static int handle_rdpmc(struct kvm_vcpu *vcpu) static int handle_wbinvd(struct kvm_vcpu *vcpu) { - skip_emulated_instruction(vcpu); kvm_emulate_wbinvd(vcpu); return 1; } @@ -5817,7 +5824,7 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) gpa_t gpa; gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); - if (!kvm_io_bus_write(vcpu->kvm, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) { + if (!kvm_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) { skip_emulated_instruction(vcpu); return 1; } @@ -5898,7 +5905,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) if (vcpu->arch.halt_request) { vcpu->arch.halt_request = 0; - ret = kvm_emulate_halt(vcpu); + ret = kvm_vcpu_halt(vcpu); goto out; } @@ -7307,21 +7314,21 @@ static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu, else if (port < 0x10000) bitmap = vmcs12->io_bitmap_b; else - return 1; + return true; bitmap += (port & 0x7fff) / 8; if (last_bitmap != bitmap) if (kvm_read_guest(vcpu->kvm, bitmap, &b, 1)) - return 1; + return true; if (b & (1 << (port & 7))) - return 1; + return true; port++; size--; last_bitmap = bitmap; } - return 0; + return false; } /* @@ -7337,7 +7344,7 @@ static bool nested_vmx_exit_handled_msr(struct kvm_vcpu *vcpu, gpa_t bitmap; if (!nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS)) - return 1; + return true; /* * The MSR_BITMAP page is divided into four 1024-byte bitmaps, @@ -7356,10 +7363,10 @@ static bool nested_vmx_exit_handled_msr(struct kvm_vcpu *vcpu, if (msr_index < 1024*8) { unsigned char b; if (kvm_read_guest(vcpu->kvm, bitmap + msr_index/8, &b, 1)) - return 1; + return true; return 1 & (b >> (msr_index & 7)); } else - return 1; /* let L1 handle the wrong parameter */ + return true; /* let L1 handle the wrong parameter */ } /* @@ -7381,7 +7388,7 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu, case 0: if (vmcs12->cr0_guest_host_mask & (val ^ vmcs12->cr0_read_shadow)) - return 1; + return true; break; case 3: if ((vmcs12->cr3_target_count >= 1 && @@ -7392,37 +7399,37 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu, vmcs12->cr3_target_value2 == val) || (vmcs12->cr3_target_count >= 4 && vmcs12->cr3_target_value3 == val)) - return 0; + return false; if (nested_cpu_has(vmcs12, CPU_BASED_CR3_LOAD_EXITING)) - return 1; + return true; break; case 4: if (vmcs12->cr4_guest_host_mask & (vmcs12->cr4_read_shadow ^ val)) - return 1; + return true; break; case 8: if (nested_cpu_has(vmcs12, CPU_BASED_CR8_LOAD_EXITING)) - return 1; + return true; break; } break; case 2: /* clts */ if ((vmcs12->cr0_guest_host_mask & X86_CR0_TS) && (vmcs12->cr0_read_shadow & X86_CR0_TS)) - return 1; + return true; break; case 1: /* mov from cr */ switch (cr) { case 3: if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_CR3_STORE_EXITING) - return 1; + return true; break; case 8: if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_CR8_STORE_EXITING) - return 1; + return true; break; } break; @@ -7433,14 +7440,14 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu, */ if (vmcs12->cr0_guest_host_mask & 0xe & (val ^ vmcs12->cr0_read_shadow)) - return 1; + return true; if ((vmcs12->cr0_guest_host_mask & 0x1) && !(vmcs12->cr0_read_shadow & 0x1) && (val & 0x1)) - return 1; + return true; break; } - return 0; + return false; } /* @@ -7463,48 +7470,48 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) KVM_ISA_VMX); if (vmx->nested.nested_run_pending) - return 0; + return false; if (unlikely(vmx->fail)) { pr_info_ratelimited("%s failed vm entry %x\n", __func__, vmcs_read32(VM_INSTRUCTION_ERROR)); - return 1; + return true; } switch (exit_reason) { case EXIT_REASON_EXCEPTION_NMI: if (!is_exception(intr_info)) - return 0; + return false; else if (is_page_fault(intr_info)) return enable_ept; else if (is_no_device(intr_info) && !(vmcs12->guest_cr0 & X86_CR0_TS)) - return 0; + return false; return vmcs12->exception_bitmap & (1u << (intr_info & INTR_INFO_VECTOR_MASK)); case EXIT_REASON_EXTERNAL_INTERRUPT: - return 0; + return false; case EXIT_REASON_TRIPLE_FAULT: - return 1; + return true; case EXIT_REASON_PENDING_INTERRUPT: return nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_INTR_PENDING); case EXIT_REASON_NMI_WINDOW: return nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_NMI_PENDING); case EXIT_REASON_TASK_SWITCH: - return 1; + return true; case EXIT_REASON_CPUID: if (kvm_register_read(vcpu, VCPU_REGS_RAX) == 0xa) - return 0; - return 1; + return false; + return true; case EXIT_REASON_HLT: return nested_cpu_has(vmcs12, CPU_BASED_HLT_EXITING); case EXIT_REASON_INVD: - return 1; + return true; case EXIT_REASON_INVLPG: return nested_cpu_has(vmcs12, CPU_BASED_INVLPG_EXITING); case EXIT_REASON_RDPMC: return nested_cpu_has(vmcs12, CPU_BASED_RDPMC_EXITING); - case EXIT_REASON_RDTSC: + case EXIT_REASON_RDTSC: case EXIT_REASON_RDTSCP: return nested_cpu_has(vmcs12, CPU_BASED_RDTSC_EXITING); case EXIT_REASON_VMCALL: case EXIT_REASON_VMCLEAR: case EXIT_REASON_VMLAUNCH: case EXIT_REASON_VMPTRLD: @@ -7516,7 +7523,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) * VMX instructions trap unconditionally. This allows L1 to * emulate them for its L2 guest, i.e., allows 3-level nesting! */ - return 1; + return true; case EXIT_REASON_CR_ACCESS: return nested_vmx_exit_handled_cr(vcpu, vmcs12); case EXIT_REASON_DR_ACCESS: @@ -7527,7 +7534,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) case EXIT_REASON_MSR_WRITE: return nested_vmx_exit_handled_msr(vcpu, vmcs12, exit_reason); case EXIT_REASON_INVALID_STATE: - return 1; + return true; case EXIT_REASON_MWAIT_INSTRUCTION: return nested_cpu_has(vmcs12, CPU_BASED_MWAIT_EXITING); case EXIT_REASON_MONITOR_INSTRUCTION: @@ -7537,7 +7544,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) nested_cpu_has2(vmcs12, SECONDARY_EXEC_PAUSE_LOOP_EXITING); case EXIT_REASON_MCE_DURING_VMENTRY: - return 0; + return false; case EXIT_REASON_TPR_BELOW_THRESHOLD: return nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW); case EXIT_REASON_APIC_ACCESS: @@ -7546,7 +7553,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) case EXIT_REASON_APIC_WRITE: case EXIT_REASON_EOI_INDUCED: /* apic_write and eoi_induced should exit unconditionally. */ - return 1; + return true; case EXIT_REASON_EPT_VIOLATION: /* * L0 always deals with the EPT violation. If nested EPT is @@ -7554,7 +7561,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) * missing in the guest EPT table (EPT12), the EPT violation * will be injected with nested_ept_inject_page_fault() */ - return 0; + return false; case EXIT_REASON_EPT_MISCONFIG: /* * L2 never uses directly L1's EPT, but rather L0's own EPT @@ -7562,11 +7569,11 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) * (EPT on EPT). So any problems with the structure of the * table is L0's fault. */ - return 0; + return false; case EXIT_REASON_WBINVD: return nested_cpu_has2(vmcs12, SECONDARY_EXEC_WBINVD_EXITING); case EXIT_REASON_XSETBV: - return 1; + return true; case EXIT_REASON_XSAVES: case EXIT_REASON_XRSTORS: /* * This should never happen, since it is not possible to @@ -7576,7 +7583,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) */ return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES); default: - return 1; + return true; } } @@ -8511,6 +8518,9 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) exec_control); } } + if (nested && !vmx->rdtscp_enabled) + vmx->nested.nested_vmx_secondary_ctls_high &= + ~SECONDARY_EXEC_RDTSCP; } /* Exposing INVPCID only when PCID is exposed */ @@ -9140,8 +9150,9 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) exec_control &= ~SECONDARY_EXEC_RDTSCP; /* Take the following fields only from vmcs12 */ exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | + SECONDARY_EXEC_RDTSCP | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | - SECONDARY_EXEC_APIC_REGISTER_VIRT); + SECONDARY_EXEC_APIC_REGISTER_VIRT); if (nested_cpu_has(vmcs12, CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)) exec_control |= vmcs12->secondary_vm_exec_control; @@ -9513,7 +9524,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) vmcs12->launch_state = 1; if (vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) - return kvm_emulate_halt(vcpu); + return kvm_vcpu_halt(vcpu); vmx->nested.nested_run_pending = 1; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index bd7a70be41b3..a284c927551e 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4115,8 +4115,8 @@ static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len, do { n = min(len, 8); if (!(vcpu->arch.apic && - !kvm_iodevice_write(&vcpu->arch.apic->dev, addr, n, v)) - && kvm_io_bus_write(vcpu->kvm, KVM_MMIO_BUS, addr, n, v)) + !kvm_iodevice_write(vcpu, &vcpu->arch.apic->dev, addr, n, v)) + && kvm_io_bus_write(vcpu, KVM_MMIO_BUS, addr, n, v)) break; handled += n; addr += n; @@ -4135,8 +4135,9 @@ static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v) do { n = min(len, 8); if (!(vcpu->arch.apic && - !kvm_iodevice_read(&vcpu->arch.apic->dev, addr, n, v)) - && kvm_io_bus_read(vcpu->kvm, KVM_MMIO_BUS, addr, n, v)) + !kvm_iodevice_read(vcpu, &vcpu->arch.apic->dev, + addr, n, v)) + && kvm_io_bus_read(vcpu, KVM_MMIO_BUS, addr, n, v)) break; trace_kvm_mmio(KVM_TRACE_MMIO_READ, n, addr, *(u64 *)v); handled += n; @@ -4476,7 +4477,8 @@ mmio: return X86EMUL_CONTINUE; } -int emulator_read_write(struct x86_emulate_ctxt *ctxt, unsigned long addr, +static int emulator_read_write(struct x86_emulate_ctxt *ctxt, + unsigned long addr, void *val, unsigned int bytes, struct x86_exception *exception, const struct read_write_emulator_ops *ops) @@ -4539,7 +4541,7 @@ static int emulator_read_emulated(struct x86_emulate_ctxt *ctxt, exception, &read_emultor); } -int emulator_write_emulated(struct x86_emulate_ctxt *ctxt, +static int emulator_write_emulated(struct x86_emulate_ctxt *ctxt, unsigned long addr, const void *val, unsigned int bytes, @@ -4630,10 +4632,10 @@ static int kernel_pio(struct kvm_vcpu *vcpu, void *pd) int r; if (vcpu->arch.pio.in) - r = kvm_io_bus_read(vcpu->kvm, KVM_PIO_BUS, vcpu->arch.pio.port, + r = kvm_io_bus_read(vcpu, KVM_PIO_BUS, vcpu->arch.pio.port, vcpu->arch.pio.size, pd); else - r = kvm_io_bus_write(vcpu->kvm, KVM_PIO_BUS, + r = kvm_io_bus_write(vcpu, KVM_PIO_BUS, vcpu->arch.pio.port, vcpu->arch.pio.size, pd); return r; @@ -4706,7 +4708,7 @@ static void emulator_invlpg(struct x86_emulate_ctxt *ctxt, ulong address) kvm_mmu_invlpg(emul_to_vcpu(ctxt), address); } -int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu) +int kvm_emulate_wbinvd_noskip(struct kvm_vcpu *vcpu) { if (!need_emulate_wbinvd(vcpu)) return X86EMUL_CONTINUE; @@ -4723,19 +4725,29 @@ int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu) wbinvd(); return X86EMUL_CONTINUE; } + +int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu) +{ + kvm_x86_ops->skip_emulated_instruction(vcpu); + return kvm_emulate_wbinvd_noskip(vcpu); +} EXPORT_SYMBOL_GPL(kvm_emulate_wbinvd); + + static void emulator_wbinvd(struct x86_emulate_ctxt *ctxt) { - kvm_emulate_wbinvd(emul_to_vcpu(ctxt)); + kvm_emulate_wbinvd_noskip(emul_to_vcpu(ctxt)); } -int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long *dest) +static int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, + unsigned long *dest) { return kvm_get_dr(emul_to_vcpu(ctxt), dr, dest); } -int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long value) +static int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, + unsigned long value) { return __kvm_set_dr(emul_to_vcpu(ctxt), dr, value); @@ -5817,7 +5829,7 @@ void kvm_arch_exit(void) free_percpu(shared_msrs); } -int kvm_emulate_halt(struct kvm_vcpu *vcpu) +int kvm_vcpu_halt(struct kvm_vcpu *vcpu) { ++vcpu->stat.halt_exits; if (irqchip_in_kernel(vcpu->kvm)) { @@ -5828,6 +5840,13 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu) return 0; } } +EXPORT_SYMBOL_GPL(kvm_vcpu_halt); + +int kvm_emulate_halt(struct kvm_vcpu *vcpu) +{ + kvm_x86_ops->skip_emulated_instruction(vcpu); + return kvm_vcpu_halt(vcpu); +} EXPORT_SYMBOL_GPL(kvm_emulate_halt); int kvm_hv_hypercall(struct kvm_vcpu *vcpu) @@ -5904,7 +5923,7 @@ static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid) lapic_irq.dest_id = apicid; lapic_irq.delivery_mode = APIC_DM_REMRD; - kvm_irq_delivery_to_apic(kvm, 0, &lapic_irq, NULL); + kvm_irq_delivery_to_apic(kvm, NULL, &lapic_irq, NULL); } int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) @@ -5912,6 +5931,8 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) unsigned long nr, a0, a1, a2, a3, ret; int op_64_bit, r = 1; + kvm_x86_ops->skip_emulated_instruction(vcpu); + if (kvm_hv_hypercall_enabled(vcpu->kvm)) return kvm_hv_hypercall(vcpu); @@ -7429,7 +7450,7 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { if (!dont || free->arch.rmap[i] != dont->arch.rmap[i]) { - kvm_kvfree(free->arch.rmap[i]); + kvfree(free->arch.rmap[i]); free->arch.rmap[i] = NULL; } if (i == 0) @@ -7437,7 +7458,7 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, if (!dont || free->arch.lpage_info[i - 1] != dont->arch.lpage_info[i - 1]) { - kvm_kvfree(free->arch.lpage_info[i - 1]); + kvfree(free->arch.lpage_info[i - 1]); free->arch.lpage_info[i - 1] = NULL; } } @@ -7491,12 +7512,12 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, out_free: for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { - kvm_kvfree(slot->arch.rmap[i]); + kvfree(slot->arch.rmap[i]); slot->arch.rmap[i] = NULL; if (i == 0) continue; - kvm_kvfree(slot->arch.lpage_info[i - 1]); + kvfree(slot->arch.lpage_info[i - 1]); slot->arch.lpage_info[i - 1] = NULL; } return -ENOMEM; diff --git a/arch/x86/lguest/Kconfig b/arch/x86/lguest/Kconfig index 4a0890f815c4..08f41caada45 100644 --- a/arch/x86/lguest/Kconfig +++ b/arch/x86/lguest/Kconfig @@ -1,6 +1,6 @@ config LGUEST_GUEST bool "Lguest guest support" - depends on X86_32 && PARAVIRT + depends on X86_32 && PARAVIRT && PCI select TTY select VIRTUALIZATION select VIRTIO @@ -8,7 +8,7 @@ config LGUEST_GUEST help Lguest is a tiny in-kernel hypervisor. Selecting this will allow your kernel to boot under lguest. This option will increase - your kernel size by about 6k. If in doubt, say N. + your kernel size by about 10k. If in doubt, say N. If you say Y here, make sure you say Y (or M) to the virtio block and net drivers which lguest needs. diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index 6ac273832f28..e4695985f9de 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -331,7 +331,7 @@ static void probe_pci_root_info(struct pci_root_info *info, struct list_head *list) { int ret; - struct resource_entry *entry; + struct resource_entry *entry, *tmp; sprintf(info->name, "PCI Bus %04x:%02x", domain, busnum); info->bridge = device; @@ -345,8 +345,13 @@ static void probe_pci_root_info(struct pci_root_info *info, dev_dbg(&device->dev, "no IO and memory resources present in _CRS\n"); else - resource_list_for_each_entry(entry, list) - entry->res->name = info->name; + resource_list_for_each_entry_safe(entry, tmp, list) { + if ((entry->res->flags & IORESOURCE_WINDOW) == 0 || + (entry->res->flags & IORESOURCE_DISABLED)) + resource_list_destroy_entry(entry); + else + entry->res->name = info->name; + } } struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c index 1bbedc4b0f88..3005f0c89f2e 100644 --- a/arch/x86/platform/intel-mid/intel-mid.c +++ b/arch/x86/platform/intel-mid/intel-mid.c @@ -130,7 +130,7 @@ static void intel_mid_arch_setup(void) intel_mid_ops = get_intel_mid_ops[__intel_mid_cpu_chip](); else { intel_mid_ops = get_intel_mid_ops[INTEL_MID_CPU_CHIP_PENWELL](); - pr_info("ARCH: Uknown SoC, assuming PENWELL!\n"); + pr_info("ARCH: Unknown SoC, assuming PENWELL!\n"); } out: diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c index 9793322751e0..30933760ee5f 100644 --- a/arch/x86/vdso/vclock_gettime.c +++ b/arch/x86/vdso/vclock_gettime.c @@ -82,18 +82,15 @@ static notrace cycle_t vread_pvclock(int *mode) cycle_t ret; u64 last; u32 version; + u32 migrate_count; u8 flags; unsigned cpu, cpu1; /* - * Note: hypervisor must guarantee that: - * 1. cpu ID number maps 1:1 to per-CPU pvclock time info. - * 2. that per-CPU pvclock time info is updated if the - * underlying CPU changes. - * 3. that version is increased whenever underlying CPU - * changes. - * + * When looping to get a consistent (time-info, tsc) pair, we + * also need to deal with the possibility we can switch vcpus, + * so make sure we always re-fetch time-info for the current vcpu. */ do { cpu = __getcpu() & VGETCPU_CPU_MASK; @@ -104,6 +101,8 @@ static notrace cycle_t vread_pvclock(int *mode) pvti = get_pvti(cpu); + migrate_count = pvti->migrate_count; + version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags); /* @@ -115,7 +114,8 @@ static notrace cycle_t vread_pvclock(int *mode) cpu1 = __getcpu() & VGETCPU_CPU_MASK; } while (unlikely(cpu != cpu1 || (pvti->pvti.version & 1) || - pvti->pvti.version != version)); + pvti->pvti.version != version || + pvti->migrate_count != migrate_count)); if (unlikely(!(flags & PVCLOCK_TSC_STABLE_BIT))) *mode = VCLOCK_NONE; diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index bd8b8459c3d0..5240f563076d 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1070,6 +1070,23 @@ static inline void xen_write_cr8(unsigned long val) BUG_ON(val); } #endif + +static u64 xen_read_msr_safe(unsigned int msr, int *err) +{ + u64 val; + + val = native_read_msr_safe(msr, err); + switch (msr) { + case MSR_IA32_APICBASE: +#ifdef CONFIG_X86_X2APIC + if (!(cpuid_ecx(1) & (1 << (X86_FEATURE_X2APIC & 31)))) +#endif + val &= ~X2APIC_ENABLE; + break; + } + return val; +} + static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high) { int ret; @@ -1240,7 +1257,7 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { .wbinvd = native_wbinvd, - .read_msr = native_read_msr_safe, + .read_msr = xen_read_msr_safe, .write_msr = xen_write_msr_safe, .read_tsc = native_read_tsc, @@ -1741,6 +1758,7 @@ asmlinkage __visible void __init xen_start_kernel(void) #ifdef CONFIG_X86_32 i386_start_kernel(); #else + cr4_init_shadow(); /* 32b kernel does this in i386_start_kernel() */ x86_64_start_reservations((char *)__pa_symbol(&boot_params)); #endif } diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index c723668e3e27..5589a6e2a023 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -42,8 +42,10 @@ static bool acpi_dev_resource_len_valid(u64 start, u64 end, u64 len, bool io) * CHECKME: len might be required to check versus a minimum * length as well. 1 for io is fine, but for memory it does * not make any sense at all. + * Note: some BIOSes report incorrect length for ACPI address space + * descriptor, so remove check of 'reslen == len' to avoid regression. */ - if (len && reslen && reslen == len && start <= end) + if (len && reslen && start <= end) return true; pr_debug("ACPI: invalid or unassigned resource %s [%016llx - %016llx] length [%016llx]\n", diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c index debd30917010..26eb70c8f518 100644 --- a/drivers/acpi/video.c +++ b/drivers/acpi/video.c @@ -2110,7 +2110,8 @@ static int __init intel_opregion_present(void) int acpi_video_register(void) { - int result = 0; + int ret; + if (register_count) { /* * if the function of acpi_video_register is already called, @@ -2122,9 +2123,9 @@ int acpi_video_register(void) mutex_init(&video_list_lock); INIT_LIST_HEAD(&video_bus_head); - result = acpi_bus_register_driver(&acpi_video_bus); - if (result < 0) - return -ENODEV; + ret = acpi_bus_register_driver(&acpi_video_bus); + if (ret) + return ret; /* * When the acpi_video_bus is loaded successfully, increase @@ -2176,6 +2177,17 @@ EXPORT_SYMBOL(acpi_video_unregister_backlight); static int __init acpi_video_init(void) { + /* + * Let the module load even if ACPI is disabled (e.g. due to + * a broken BIOS) so that i915.ko can still be loaded on such + * old systems without an AcpiOpRegion. + * + * acpi_video_register() will report -ENODEV later as well due + * to acpi_disabled when i915.ko tries to register itself afterwards. + */ + if (acpi_disabled) + return 0; + dmi_check_system(video_dmi_table); if (intel_opregion_present()) diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 33b09b6568a4..6607f3c6ace1 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -551,7 +551,6 @@ static int binder_update_page_range(struct binder_proc *proc, int allocate, { void *page_addr; unsigned long user_page_addr; - struct vm_struct tmp_area; struct page **page; struct mm_struct *mm; @@ -600,10 +599,11 @@ static int binder_update_page_range(struct binder_proc *proc, int allocate, proc->pid, page_addr); goto err_alloc_page_failed; } - tmp_area.addr = page_addr; - tmp_area.size = PAGE_SIZE + PAGE_SIZE /* guard page? */; - ret = map_vm_area(&tmp_area, PAGE_KERNEL, page); - if (ret) { + ret = map_kernel_range_noflush((unsigned long)page_addr, + PAGE_SIZE, PAGE_KERNEL, page); + flush_cache_vmap((unsigned long)page_addr, + (unsigned long)page_addr + PAGE_SIZE); + if (ret != 1) { pr_err("%d: binder_alloc_buf failed to map page at %p in kernel\n", proc->pid, page_addr); goto err_map_kernel_failed; diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c index f9054cd36a72..5389579c5120 100644 --- a/drivers/ata/sata_fsl.c +++ b/drivers/ata/sata_fsl.c @@ -869,6 +869,8 @@ try_offline_again: */ ata_msleep(ap, 1); + sata_set_spd(link); + /* * Now, bring the host controller online again, this can take time * as PHY reset and communication establishment, 1st D2H FIS and diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index ba4abbe4693c..45937f88e77c 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -2242,7 +2242,7 @@ static void rtpm_status_str(struct seq_file *s, struct device *dev) } static int pm_genpd_summary_one(struct seq_file *s, - struct generic_pm_domain *gpd) + struct generic_pm_domain *genpd) { static const char * const status_lookup[] = { [GPD_STATE_ACTIVE] = "on", @@ -2256,26 +2256,26 @@ static int pm_genpd_summary_one(struct seq_file *s, struct gpd_link *link; int ret; - ret = mutex_lock_interruptible(&gpd->lock); + ret = mutex_lock_interruptible(&genpd->lock); if (ret) return -ERESTARTSYS; - if (WARN_ON(gpd->status >= ARRAY_SIZE(status_lookup))) + if (WARN_ON(genpd->status >= ARRAY_SIZE(status_lookup))) goto exit; - seq_printf(s, "%-30s %-15s ", gpd->name, status_lookup[gpd->status]); + seq_printf(s, "%-30s %-15s ", genpd->name, status_lookup[genpd->status]); /* * Modifications on the list require holding locks on both * master and slave, so we are safe. - * Also gpd->name is immutable. + * Also genpd->name is immutable. */ - list_for_each_entry(link, &gpd->master_links, master_node) { + list_for_each_entry(link, &genpd->master_links, master_node) { seq_printf(s, "%s", link->slave->name); - if (!list_is_last(&link->master_node, &gpd->master_links)) + if (!list_is_last(&link->master_node, &genpd->master_links)) seq_puts(s, ", "); } - list_for_each_entry(pm_data, &gpd->dev_list, list_node) { + list_for_each_entry(pm_data, &genpd->dev_list, list_node) { kobj_path = kobject_get_path(&pm_data->dev->kobj, GFP_KERNEL); if (kobj_path == NULL) continue; @@ -2287,14 +2287,14 @@ static int pm_genpd_summary_one(struct seq_file *s, seq_puts(s, "\n"); exit: - mutex_unlock(&gpd->lock); + mutex_unlock(&genpd->lock); return 0; } static int pm_genpd_summary_show(struct seq_file *s, void *data) { - struct generic_pm_domain *gpd; + struct generic_pm_domain *genpd; int ret = 0; seq_puts(s, " domain status slaves\n"); @@ -2305,8 +2305,8 @@ static int pm_genpd_summary_show(struct seq_file *s, void *data) if (ret) return -ERESTARTSYS; - list_for_each_entry(gpd, &gpd_list, gpd_list_node) { - ret = pm_genpd_summary_one(s, gpd); + list_for_each_entry(genpd, &gpd_list, gpd_list_node) { + ret = pm_genpd_summary_one(s, genpd); if (ret) break; } diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c index c2744b30d5d9..aab7158d2afe 100644 --- a/drivers/base/power/wakeup.c +++ b/drivers/base/power/wakeup.c @@ -730,6 +730,7 @@ void pm_system_wakeup(void) pm_abort_suspend = true; freeze_wake(); } +EXPORT_SYMBOL_GPL(pm_system_wakeup); void pm_wakeup_clear(void) { diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c index b64bccbb78c9..ceb32dd52a6c 100644 --- a/drivers/block/nvme-core.c +++ b/drivers/block/nvme-core.c @@ -482,6 +482,7 @@ static int nvme_error_status(u16 status) } } +#ifdef CONFIG_BLK_DEV_INTEGRITY static void nvme_dif_prep(u32 p, u32 v, struct t10_pi_tuple *pi) { if (be32_to_cpu(pi->ref_tag) == v) @@ -538,6 +539,58 @@ static void nvme_dif_remap(struct request *req, kunmap_atomic(pmap); } +static int nvme_noop_verify(struct blk_integrity_iter *iter) +{ + return 0; +} + +static int nvme_noop_generate(struct blk_integrity_iter *iter) +{ + return 0; +} + +struct blk_integrity nvme_meta_noop = { + .name = "NVME_META_NOOP", + .generate_fn = nvme_noop_generate, + .verify_fn = nvme_noop_verify, +}; + +static void nvme_init_integrity(struct nvme_ns *ns) +{ + struct blk_integrity integrity; + + switch (ns->pi_type) { + case NVME_NS_DPS_PI_TYPE3: + integrity = t10_pi_type3_crc; + break; + case NVME_NS_DPS_PI_TYPE1: + case NVME_NS_DPS_PI_TYPE2: + integrity = t10_pi_type1_crc; + break; + default: + integrity = nvme_meta_noop; + break; + } + integrity.tuple_size = ns->ms; + blk_integrity_register(ns->disk, &integrity); + blk_queue_max_integrity_segments(ns->queue, 1); +} +#else /* CONFIG_BLK_DEV_INTEGRITY */ +static void nvme_dif_remap(struct request *req, + void (*dif_swap)(u32 p, u32 v, struct t10_pi_tuple *pi)) +{ +} +static void nvme_dif_prep(u32 p, u32 v, struct t10_pi_tuple *pi) +{ +} +static void nvme_dif_complete(u32 p, u32 v, struct t10_pi_tuple *pi) +{ +} +static void nvme_init_integrity(struct nvme_ns *ns) +{ +} +#endif + static void req_completion(struct nvme_queue *nvmeq, void *ctx, struct nvme_completion *cqe) { @@ -1959,43 +2012,6 @@ static void nvme_config_discard(struct nvme_ns *ns) queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, ns->queue); } -static int nvme_noop_verify(struct blk_integrity_iter *iter) -{ - return 0; -} - -static int nvme_noop_generate(struct blk_integrity_iter *iter) -{ - return 0; -} - -struct blk_integrity nvme_meta_noop = { - .name = "NVME_META_NOOP", - .generate_fn = nvme_noop_generate, - .verify_fn = nvme_noop_verify, -}; - -static void nvme_init_integrity(struct nvme_ns *ns) -{ - struct blk_integrity integrity; - - switch (ns->pi_type) { - case NVME_NS_DPS_PI_TYPE3: - integrity = t10_pi_type3_crc; - break; - case NVME_NS_DPS_PI_TYPE1: - case NVME_NS_DPS_PI_TYPE2: - integrity = t10_pi_type1_crc; - break; - default: - integrity = nvme_meta_noop; - break; - } - integrity.tuple_size = ns->ms; - blk_integrity_register(ns->disk, &integrity); - blk_queue_max_integrity_segments(ns->queue, 1); -} - static int nvme_revalidate_disk(struct gendisk *disk) { struct nvme_ns *ns = disk->private_data; @@ -2036,7 +2052,8 @@ static int nvme_revalidate_disk(struct gendisk *disk) pi_type = ns->ms == sizeof(struct t10_pi_tuple) ? id->dps & NVME_NS_DPS_PI_MASK : 0; - if (disk->integrity && (ns->pi_type != pi_type || ns->ms != old_ms || + if (blk_get_integrity(disk) && (ns->pi_type != pi_type || + ns->ms != old_ms || bs != queue_logical_block_size(disk->queue) || (ns->ms && id->flbas & NVME_NS_FLBAS_META_EXT))) blk_integrity_unregister(disk); @@ -2044,11 +2061,11 @@ static int nvme_revalidate_disk(struct gendisk *disk) ns->pi_type = pi_type; blk_queue_logical_block_size(ns->queue, bs); - if (ns->ms && !disk->integrity && (disk->flags & GENHD_FL_UP) && + if (ns->ms && !blk_get_integrity(disk) && (disk->flags & GENHD_FL_UP) && !(id->flbas & NVME_NS_FLBAS_META_EXT)) nvme_init_integrity(ns); - if (id->ncap == 0 || (ns->ms && !disk->integrity)) + if (id->ncap == 0 || (ns->ms && !blk_get_integrity(disk))) set_capacity(disk, 0); else set_capacity(disk, le64_to_cpup(&id->nsze) << (ns->lba_shift - 9)); @@ -2652,7 +2669,7 @@ static void nvme_dev_remove(struct nvme_dev *dev) list_for_each_entry(ns, &dev->namespaces, list) { if (ns->disk->flags & GENHD_FL_UP) { - if (ns->disk->integrity) + if (blk_get_integrity(ns->disk)) blk_integrity_unregister(ns->disk); del_gendisk(ns->disk); } diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 8e233edd7a09..871bd3550cb0 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -528,7 +528,7 @@ out_cleanup: static inline void update_used_max(struct zram *zram, const unsigned long pages) { - int old_max, cur_max; + unsigned long old_max, cur_max; old_max = atomic_long_read(&zram->stats.max_used_pages); diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index b87688881143..8bfc4c2bba87 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -272,6 +272,7 @@ static const struct usb_device_id blacklist_table[] = { { USB_DEVICE(0x1286, 0x2046), .driver_info = BTUSB_MARVELL }, /* Intel Bluetooth devices */ + { USB_DEVICE(0x8087, 0x07da), .driver_info = BTUSB_CSR }, { USB_DEVICE(0x8087, 0x07dc), .driver_info = BTUSB_INTEL }, { USB_DEVICE(0x8087, 0x0a2a), .driver_info = BTUSB_INTEL }, { USB_DEVICE(0x8087, 0x0a2b), .driver_info = BTUSB_INTEL_NEW }, diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c index 1d278ccd751f..e096e9cddb40 100644 --- a/drivers/char/tpm/tpm-chip.c +++ b/drivers/char/tpm/tpm-chip.c @@ -140,24 +140,24 @@ static int tpm_dev_add_device(struct tpm_chip *chip) { int rc; - rc = device_add(&chip->dev); + rc = cdev_add(&chip->cdev, chip->dev.devt, 1); if (rc) { dev_err(&chip->dev, - "unable to device_register() %s, major %d, minor %d, err=%d\n", + "unable to cdev_add() %s, major %d, minor %d, err=%d\n", chip->devname, MAJOR(chip->dev.devt), MINOR(chip->dev.devt), rc); + device_unregister(&chip->dev); return rc; } - rc = cdev_add(&chip->cdev, chip->dev.devt, 1); + rc = device_add(&chip->dev); if (rc) { dev_err(&chip->dev, - "unable to cdev_add() %s, major %d, minor %d, err=%d\n", + "unable to device_register() %s, major %d, minor %d, err=%d\n", chip->devname, MAJOR(chip->dev.devt), MINOR(chip->dev.devt), rc); - device_unregister(&chip->dev); return rc; } @@ -174,27 +174,17 @@ static void tpm_dev_del_device(struct tpm_chip *chip) * tpm_chip_register() - create a character device for the TPM chip * @chip: TPM chip to use. * - * Creates a character device for the TPM chip and adds sysfs interfaces for - * the device, PPI and TCPA. As the last step this function adds the - * chip to the list of TPM chips available for use. + * Creates a character device for the TPM chip and adds sysfs attributes for + * the device. As the last step this function adds the chip to the list of TPM + * chips available for in-kernel use. * - * NOTE: This function should be only called after the chip initialization - * is complete. - * - * Called from tpm_<specific>.c probe function only for devices - * the driver has determined it should claim. Prior to calling - * this function the specific probe function has called pci_enable_device - * upon errant exit from this function specific probe function should call - * pci_disable_device + * This function should be only called after the chip initialization is + * complete. */ int tpm_chip_register(struct tpm_chip *chip) { int rc; - rc = tpm_dev_add_device(chip); - if (rc) - return rc; - /* Populate sysfs for TPM1 devices. */ if (!(chip->flags & TPM_CHIP_FLAG_TPM2)) { rc = tpm_sysfs_add_device(chip); @@ -208,6 +198,10 @@ int tpm_chip_register(struct tpm_chip *chip) chip->bios_dir = tpm_bios_log_setup(chip->devname); } + rc = tpm_dev_add_device(chip); + if (rc) + return rc; + /* Make the chip available. */ spin_lock(&driver_lock); list_add_rcu(&chip->list, &tpm_chip_list); diff --git a/drivers/char/tpm/tpm_ibmvtpm.c b/drivers/char/tpm/tpm_ibmvtpm.c index b1e53e3aece5..42ffa5e7a1e0 100644 --- a/drivers/char/tpm/tpm_ibmvtpm.c +++ b/drivers/char/tpm/tpm_ibmvtpm.c @@ -124,7 +124,7 @@ static int tpm_ibmvtpm_send(struct tpm_chip *chip, u8 *buf, size_t count) { struct ibmvtpm_dev *ibmvtpm; struct ibmvtpm_crq crq; - u64 *word = (u64 *) &crq; + __be64 *word = (__be64 *)&crq; int rc; ibmvtpm = (struct ibmvtpm_dev *)TPM_VPRIV(chip); @@ -145,11 +145,11 @@ static int tpm_ibmvtpm_send(struct tpm_chip *chip, u8 *buf, size_t count) memcpy((void *)ibmvtpm->rtce_buf, (void *)buf, count); crq.valid = (u8)IBMVTPM_VALID_CMD; crq.msg = (u8)VTPM_TPM_COMMAND; - crq.len = (u16)count; - crq.data = ibmvtpm->rtce_dma_handle; + crq.len = cpu_to_be16(count); + crq.data = cpu_to_be32(ibmvtpm->rtce_dma_handle); - rc = ibmvtpm_send_crq(ibmvtpm->vdev, cpu_to_be64(word[0]), - cpu_to_be64(word[1])); + rc = ibmvtpm_send_crq(ibmvtpm->vdev, be64_to_cpu(word[0]), + be64_to_cpu(word[1])); if (rc != H_SUCCESS) { dev_err(ibmvtpm->dev, "tpm_ibmvtpm_send failed rc=%d\n", rc); rc = 0; diff --git a/drivers/char/tpm/tpm_ibmvtpm.h b/drivers/char/tpm/tpm_ibmvtpm.h index f595f14426bf..6af92890518f 100644 --- a/drivers/char/tpm/tpm_ibmvtpm.h +++ b/drivers/char/tpm/tpm_ibmvtpm.h @@ -22,9 +22,9 @@ struct ibmvtpm_crq { u8 valid; u8 msg; - u16 len; - u32 data; - u64 reserved; + __be16 len; + __be32 data; + __be64 reserved; } __attribute__((packed, aligned(8))); struct ibmvtpm_crq_queue { diff --git a/drivers/clk/at91/pmc.c b/drivers/clk/at91/pmc.c index f07c8152e5cc..3f27d21fb729 100644 --- a/drivers/clk/at91/pmc.c +++ b/drivers/clk/at91/pmc.c @@ -89,12 +89,29 @@ static int pmc_irq_set_type(struct irq_data *d, unsigned type) return 0; } +static void pmc_irq_suspend(struct irq_data *d) +{ + struct at91_pmc *pmc = irq_data_get_irq_chip_data(d); + + pmc->imr = pmc_read(pmc, AT91_PMC_IMR); + pmc_write(pmc, AT91_PMC_IDR, pmc->imr); +} + +static void pmc_irq_resume(struct irq_data *d) +{ + struct at91_pmc *pmc = irq_data_get_irq_chip_data(d); + + pmc_write(pmc, AT91_PMC_IER, pmc->imr); +} + static struct irq_chip pmc_irq = { .name = "PMC", .irq_disable = pmc_irq_mask, .irq_mask = pmc_irq_mask, .irq_unmask = pmc_irq_unmask, .irq_set_type = pmc_irq_set_type, + .irq_suspend = pmc_irq_suspend, + .irq_resume = pmc_irq_resume, }; static struct lock_class_key pmc_lock_class; @@ -224,7 +241,8 @@ static struct at91_pmc *__init at91_pmc_init(struct device_node *np, goto out_free_pmc; pmc_write(pmc, AT91_PMC_IDR, 0xffffffff); - if (request_irq(pmc->virq, pmc_irq_handler, IRQF_SHARED, "pmc", pmc)) + if (request_irq(pmc->virq, pmc_irq_handler, + IRQF_SHARED | IRQF_COND_SUSPEND, "pmc", pmc)) goto out_remove_irqdomain; return pmc; diff --git a/drivers/clk/at91/pmc.h b/drivers/clk/at91/pmc.h index 52d2041fa3f6..69abb08cf146 100644 --- a/drivers/clk/at91/pmc.h +++ b/drivers/clk/at91/pmc.h @@ -33,6 +33,7 @@ struct at91_pmc { spinlock_t lock; const struct at91_pmc_caps *caps; struct irq_domain *irqdomain; + u32 imr; }; static inline void pmc_lock(struct at91_pmc *pmc) diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig index 1c2506f68122..68161f7a07d6 100644 --- a/drivers/clocksource/Kconfig +++ b/drivers/clocksource/Kconfig @@ -63,6 +63,11 @@ config VT8500_TIMER config CADENCE_TTC_TIMER bool +config ASM9260_TIMER + bool + select CLKSRC_MMIO + select CLKSRC_OF + config CLKSRC_NOMADIK_MTU bool depends on (ARCH_NOMADIK || ARCH_U8500) @@ -245,15 +250,4 @@ config CLKSRC_PXA help This enables OST0 support available on PXA and SA-11x0 platforms. - -config ASM9260_TIMER - bool "Alphascale ASM9260 timer driver" - depends on GENERIC_CLOCKEVENTS - select CLKSRC_MMIO - select CLKSRC_OF - default y if MACH_ASM9260 - help - This enables build of a clocksource and clockevent driver for - the 32-bit System Timer hardware available on a Alphascale ASM9260. - endmenu diff --git a/drivers/clocksource/mtk_timer.c b/drivers/clocksource/mtk_timer.c index 32a3d25795d3..68ab42356d0e 100644 --- a/drivers/clocksource/mtk_timer.c +++ b/drivers/clocksource/mtk_timer.c @@ -224,6 +224,8 @@ static void __init mtk_timer_init(struct device_node *node) } rate = clk_get_rate(clk); + mtk_timer_global_reset(evt); + if (request_irq(evt->dev.irq, mtk_timer_interrupt, IRQF_TIMER | IRQF_IRQPOLL, "mtk_timer", evt)) { pr_warn("failed to setup irq %d\n", evt->dev.irq); @@ -232,8 +234,6 @@ static void __init mtk_timer_init(struct device_node *node) evt->ticks_per_jiffy = DIV_ROUND_UP(rate, HZ); - mtk_timer_global_reset(evt); - /* Configure clock source */ mtk_timer_setup(evt, GPT_CLK_SRC, TIMER_CTRL_OP_FREERUN); clocksource_mmio_init(evt->gpt_base + TIMER_CNT_REG(GPT_CLK_SRC), @@ -241,10 +241,11 @@ static void __init mtk_timer_init(struct device_node *node) /* Configure clock event */ mtk_timer_setup(evt, GPT_CLK_EVT, TIMER_CTRL_OP_REPEAT); - mtk_timer_enable_irq(evt, GPT_CLK_EVT); - clockevents_config_and_register(&evt->dev, rate, 0x3, 0xffffffff); + + mtk_timer_enable_irq(evt, GPT_CLK_EVT); + return; err_clk_disable: diff --git a/drivers/clocksource/pxa_timer.c b/drivers/clocksource/pxa_timer.c index 941f3f344e08..d9438af2bbd6 100644 --- a/drivers/clocksource/pxa_timer.c +++ b/drivers/clocksource/pxa_timer.c @@ -163,7 +163,7 @@ static struct irqaction pxa_ost0_irq = { .dev_id = &ckevt_pxa_osmr0, }; -static void pxa_timer_common_init(int irq, unsigned long clock_tick_rate) +static void __init pxa_timer_common_init(int irq, unsigned long clock_tick_rate) { timer_writel(0, OIER); timer_writel(OSSR_M0 | OSSR_M1 | OSSR_M2 | OSSR_M3, OSSR); diff --git a/drivers/cpufreq/exynos-cpufreq.c b/drivers/cpufreq/exynos-cpufreq.c index 5e98c6b1f284..82d2fbb20f7e 100644 --- a/drivers/cpufreq/exynos-cpufreq.c +++ b/drivers/cpufreq/exynos-cpufreq.c @@ -159,7 +159,7 @@ static struct cpufreq_driver exynos_driver = { static int exynos_cpufreq_probe(struct platform_device *pdev) { - struct device_node *cpus, *np; + struct device_node *cpu0; int ret = -EINVAL; exynos_info = kzalloc(sizeof(*exynos_info), GFP_KERNEL); @@ -206,28 +206,19 @@ static int exynos_cpufreq_probe(struct platform_device *pdev) if (ret) goto err_cpufreq_reg; - cpus = of_find_node_by_path("/cpus"); - if (!cpus) { - pr_err("failed to find cpus node\n"); + cpu0 = of_get_cpu_node(0, NULL); + if (!cpu0) { + pr_err("failed to find cpu0 node\n"); return 0; } - np = of_get_next_child(cpus, NULL); - if (!np) { - pr_err("failed to find cpus child node\n"); - of_node_put(cpus); - return 0; - } - - if (of_find_property(np, "#cooling-cells", NULL)) { - cdev = of_cpufreq_cooling_register(np, + if (of_find_property(cpu0, "#cooling-cells", NULL)) { + cdev = of_cpufreq_cooling_register(cpu0, cpu_present_mask); if (IS_ERR(cdev)) pr_err("running cpufreq without cooling device: %ld\n", PTR_ERR(cdev)); } - of_node_put(np); - of_node_put(cpus); return 0; diff --git a/drivers/cpufreq/ppc-corenet-cpufreq.c b/drivers/cpufreq/ppc-corenet-cpufreq.c index bee5df7794d3..7cb4b766cf94 100644 --- a/drivers/cpufreq/ppc-corenet-cpufreq.c +++ b/drivers/cpufreq/ppc-corenet-cpufreq.c @@ -22,6 +22,8 @@ #include <linux/smp.h> #include <sysdev/fsl_soc.h> +#include <asm/smp.h> /* for get_hard_smp_processor_id() in UP configs */ + /** * struct cpu_data - per CPU data struct * @parent: the parent node of cpu clock diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 4d534582514e..080bd2dbde4b 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -44,6 +44,12 @@ void disable_cpuidle(void) off = 1; } +bool cpuidle_not_available(struct cpuidle_driver *drv, + struct cpuidle_device *dev) +{ + return off || !initialized || !drv || !dev || !dev->enabled; +} + /** * cpuidle_play_dead - cpu off-lining * @@ -66,14 +72,8 @@ int cpuidle_play_dead(void) return -ENODEV; } -/** - * cpuidle_find_deepest_state - Find deepest state meeting specific conditions. - * @drv: cpuidle driver for the given CPU. - * @dev: cpuidle device for the given CPU. - * @freeze: Whether or not the state should be suitable for suspend-to-idle. - */ -static int cpuidle_find_deepest_state(struct cpuidle_driver *drv, - struct cpuidle_device *dev, bool freeze) +static int find_deepest_state(struct cpuidle_driver *drv, + struct cpuidle_device *dev, bool freeze) { unsigned int latency_req = 0; int i, ret = freeze ? -1 : CPUIDLE_DRIVER_STATE_START - 1; @@ -92,6 +92,17 @@ static int cpuidle_find_deepest_state(struct cpuidle_driver *drv, return ret; } +/** + * cpuidle_find_deepest_state - Find the deepest available idle state. + * @drv: cpuidle driver for the given CPU. + * @dev: cpuidle device for the given CPU. + */ +int cpuidle_find_deepest_state(struct cpuidle_driver *drv, + struct cpuidle_device *dev) +{ + return find_deepest_state(drv, dev, false); +} + static void enter_freeze_proper(struct cpuidle_driver *drv, struct cpuidle_device *dev, int index) { @@ -113,15 +124,14 @@ static void enter_freeze_proper(struct cpuidle_driver *drv, /** * cpuidle_enter_freeze - Enter an idle state suitable for suspend-to-idle. + * @drv: cpuidle driver for the given CPU. + * @dev: cpuidle device for the given CPU. * * If there are states with the ->enter_freeze callback, find the deepest of - * them and enter it with frozen tick. Otherwise, find the deepest state - * available and enter it normally. + * them and enter it with frozen tick. */ -void cpuidle_enter_freeze(void) +int cpuidle_enter_freeze(struct cpuidle_driver *drv, struct cpuidle_device *dev) { - struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices); - struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev); int index; /* @@ -129,24 +139,11 @@ void cpuidle_enter_freeze(void) * that interrupts won't be enabled when it exits and allows the tick to * be frozen safely. */ - index = cpuidle_find_deepest_state(drv, dev, true); - if (index >= 0) { - enter_freeze_proper(drv, dev, index); - return; - } - - /* - * It is not safe to freeze the tick, find the deepest state available - * at all and try to enter it normally. - */ - index = cpuidle_find_deepest_state(drv, dev, false); + index = find_deepest_state(drv, dev, true); if (index >= 0) - cpuidle_enter(drv, dev, index); - else - arch_cpu_idle(); + enter_freeze_proper(drv, dev, index); - /* Interrupts are enabled again here. */ - local_irq_disable(); + return index; } /** @@ -205,12 +202,6 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, */ int cpuidle_select(struct cpuidle_driver *drv, struct cpuidle_device *dev) { - if (off || !initialized) - return -ENODEV; - - if (!drv || !dev || !dev->enabled) - return -EBUSY; - return cpuidle_curr_governor->select(drv, dev); } diff --git a/drivers/dma-buf/fence.c b/drivers/dma-buf/fence.c index e5541117b3e9..50ef8bd8708b 100644 --- a/drivers/dma-buf/fence.c +++ b/drivers/dma-buf/fence.c @@ -159,6 +159,9 @@ fence_wait_timeout(struct fence *fence, bool intr, signed long timeout) if (WARN_ON(timeout < 0)) return -EINVAL; + if (timeout == 0) + return fence_is_signaled(fence); + trace_fence_wait_start(fence); ret = fence->ops->wait(fence, intr, timeout); trace_fence_wait_end(fence); diff --git a/drivers/dma-buf/reservation.c b/drivers/dma-buf/reservation.c index 3c97c8fa8d02..39920d77f288 100644 --- a/drivers/dma-buf/reservation.c +++ b/drivers/dma-buf/reservation.c @@ -327,6 +327,9 @@ long reservation_object_wait_timeout_rcu(struct reservation_object *obj, unsigned seq, shared_count, i = 0; long ret = timeout; + if (!timeout) + return reservation_object_test_signaled_rcu(obj, wait_all); + retry: fence = NULL; shared_count = 0; @@ -402,8 +405,6 @@ reservation_object_test_signaled_single(struct fence *passed_fence) int ret = 1; if (!test_bit(FENCE_FLAG_SIGNALED_BIT, &lfence->flags)) { - int ret; - fence = fence_get_rcu(lfence); if (!fence) return -1; diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index 09e2825a547a..d9891d3461f6 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -664,7 +664,6 @@ at_xdmac_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr, struct at_xdmac_desc *first = NULL, *prev = NULL; unsigned int periods = buf_len / period_len; int i; - u32 cfg; dev_dbg(chan2dev(chan), "%s: buf_addr=%pad, buf_len=%zd, period_len=%zd, dir=%s, flags=0x%lx\n", __func__, &buf_addr, buf_len, period_len, @@ -700,17 +699,17 @@ at_xdmac_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr, if (direction == DMA_DEV_TO_MEM) { desc->lld.mbr_sa = atchan->per_src_addr; desc->lld.mbr_da = buf_addr + i * period_len; - cfg = atchan->cfg[AT_XDMAC_DEV_TO_MEM_CFG]; + desc->lld.mbr_cfg = atchan->cfg[AT_XDMAC_DEV_TO_MEM_CFG]; } else { desc->lld.mbr_sa = buf_addr + i * period_len; desc->lld.mbr_da = atchan->per_dst_addr; - cfg = atchan->cfg[AT_XDMAC_MEM_TO_DEV_CFG]; + desc->lld.mbr_cfg = atchan->cfg[AT_XDMAC_MEM_TO_DEV_CFG]; } desc->lld.mbr_ubc = AT_XDMAC_MBR_UBC_NDV1 | AT_XDMAC_MBR_UBC_NDEN | AT_XDMAC_MBR_UBC_NSEN | AT_XDMAC_MBR_UBC_NDE - | period_len >> at_xdmac_get_dwidth(cfg); + | period_len >> at_xdmac_get_dwidth(desc->lld.mbr_cfg); dev_dbg(chan2dev(chan), "%s: lld: mbr_sa=%pad, mbr_da=%pad, mbr_ubc=0x%08x\n", diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c index 455b7a4f1e87..a8ad05291b27 100644 --- a/drivers/dma/dw/core.c +++ b/drivers/dma/dw/core.c @@ -626,7 +626,7 @@ static irqreturn_t dw_dma_interrupt(int irq, void *dev_id) dev_vdbg(dw->dma.dev, "%s: status=0x%x\n", __func__, status); /* Check if we have any interrupt from the DMAC */ - if (!status) + if (!status || !dw->in_use) return IRQ_NONE; /* diff --git a/drivers/dma/ioat/dma_v3.c b/drivers/dma/ioat/dma_v3.c index 77a6dcf25b98..194ec20c9408 100644 --- a/drivers/dma/ioat/dma_v3.c +++ b/drivers/dma/ioat/dma_v3.c @@ -230,6 +230,10 @@ static bool is_bwd_noraid(struct pci_dev *pdev) switch (pdev->device) { case PCI_DEVICE_ID_INTEL_IOAT_BWD2: case PCI_DEVICE_ID_INTEL_IOAT_BWD3: + case PCI_DEVICE_ID_INTEL_IOAT_BDXDE0: + case PCI_DEVICE_ID_INTEL_IOAT_BDXDE1: + case PCI_DEVICE_ID_INTEL_IOAT_BDXDE2: + case PCI_DEVICE_ID_INTEL_IOAT_BDXDE3: return true; default: return false; diff --git a/drivers/dma/mmp_pdma.c b/drivers/dma/mmp_pdma.c index 8926f271904e..eb410044e1af 100644 --- a/drivers/dma/mmp_pdma.c +++ b/drivers/dma/mmp_pdma.c @@ -219,6 +219,9 @@ static irqreturn_t mmp_pdma_int_handler(int irq, void *dev_id) while (dint) { i = __ffs(dint); + /* only handle interrupts belonging to pdma driver*/ + if (i >= pdev->dma_channels) + break; dint &= (dint - 1); phy = &pdev->phy[i]; ret = mmp_pdma_chan_handler(irq, phy); @@ -999,6 +1002,9 @@ static int mmp_pdma_probe(struct platform_device *op) struct resource *iores; int i, ret, irq = 0; int dma_channels = 0, irq_num = 0; + const enum dma_slave_buswidth widths = + DMA_SLAVE_BUSWIDTH_1_BYTE | DMA_SLAVE_BUSWIDTH_2_BYTES | + DMA_SLAVE_BUSWIDTH_4_BYTES; pdev = devm_kzalloc(&op->dev, sizeof(*pdev), GFP_KERNEL); if (!pdev) @@ -1066,6 +1072,10 @@ static int mmp_pdma_probe(struct platform_device *op) pdev->device.device_config = mmp_pdma_config; pdev->device.device_terminate_all = mmp_pdma_terminate_all; pdev->device.copy_align = PDMA_ALIGNMENT; + pdev->device.src_addr_widths = widths; + pdev->device.dst_addr_widths = widths; + pdev->device.directions = BIT(DMA_MEM_TO_DEV) | BIT(DMA_DEV_TO_MEM); + pdev->device.residue_granularity = DMA_RESIDUE_GRANULARITY_DESCRIPTOR; if (pdev->dev->coherent_dma_mask) dma_set_mask(pdev->dev, pdev->dev->coherent_dma_mask); diff --git a/drivers/dma/mmp_tdma.c b/drivers/dma/mmp_tdma.c index 70c2fa9963cd..b6f4e1fc9c78 100644 --- a/drivers/dma/mmp_tdma.c +++ b/drivers/dma/mmp_tdma.c @@ -110,7 +110,7 @@ struct mmp_tdma_chan { struct tasklet_struct tasklet; struct mmp_tdma_desc *desc_arr; - phys_addr_t desc_arr_phys; + dma_addr_t desc_arr_phys; int desc_num; enum dma_transfer_direction dir; dma_addr_t dev_addr; @@ -166,9 +166,12 @@ static void mmp_tdma_enable_chan(struct mmp_tdma_chan *tdmac) static int mmp_tdma_disable_chan(struct dma_chan *chan) { struct mmp_tdma_chan *tdmac = to_mmp_tdma_chan(chan); + u32 tdcr; - writel(readl(tdmac->reg_base + TDCR) & ~TDCR_CHANEN, - tdmac->reg_base + TDCR); + tdcr = readl(tdmac->reg_base + TDCR); + tdcr |= TDCR_ABR; + tdcr &= ~TDCR_CHANEN; + writel(tdcr, tdmac->reg_base + TDCR); tdmac->status = DMA_COMPLETE; @@ -296,12 +299,27 @@ static int mmp_tdma_clear_chan_irq(struct mmp_tdma_chan *tdmac) return -EAGAIN; } +static size_t mmp_tdma_get_pos(struct mmp_tdma_chan *tdmac) +{ + size_t reg; + + if (tdmac->idx == 0) { + reg = __raw_readl(tdmac->reg_base + TDSAR); + reg -= tdmac->desc_arr[0].src_addr; + } else if (tdmac->idx == 1) { + reg = __raw_readl(tdmac->reg_base + TDDAR); + reg -= tdmac->desc_arr[0].dst_addr; + } else + return -EINVAL; + + return reg; +} + static irqreturn_t mmp_tdma_chan_handler(int irq, void *dev_id) { struct mmp_tdma_chan *tdmac = dev_id; if (mmp_tdma_clear_chan_irq(tdmac) == 0) { - tdmac->pos = (tdmac->pos + tdmac->period_len) % tdmac->buf_len; tasklet_schedule(&tdmac->tasklet); return IRQ_HANDLED; } else @@ -343,7 +361,7 @@ static void mmp_tdma_free_descriptor(struct mmp_tdma_chan *tdmac) int size = tdmac->desc_num * sizeof(struct mmp_tdma_desc); gpool = tdmac->pool; - if (tdmac->desc_arr) + if (gpool && tdmac->desc_arr) gen_pool_free(gpool, (unsigned long)tdmac->desc_arr, size); tdmac->desc_arr = NULL; @@ -499,6 +517,7 @@ static enum dma_status mmp_tdma_tx_status(struct dma_chan *chan, { struct mmp_tdma_chan *tdmac = to_mmp_tdma_chan(chan); + tdmac->pos = mmp_tdma_get_pos(tdmac); dma_set_tx_state(txstate, chan->completed_cookie, chan->cookie, tdmac->buf_len - tdmac->pos); @@ -610,7 +629,7 @@ static int mmp_tdma_probe(struct platform_device *pdev) int i, ret; int irq = 0, irq_num = 0; int chan_num = TDMA_CHANNEL_NUM; - struct gen_pool *pool; + struct gen_pool *pool = NULL; of_id = of_match_device(mmp_tdma_dt_ids, &pdev->dev); if (of_id) diff --git a/drivers/dma/qcom_bam_dma.c b/drivers/dma/qcom_bam_dma.c index d7a33b3ac466..9c914d625906 100644 --- a/drivers/dma/qcom_bam_dma.c +++ b/drivers/dma/qcom_bam_dma.c @@ -162,9 +162,9 @@ static const struct reg_offset_data bam_v1_4_reg_info[] = { [BAM_P_IRQ_STTS] = { 0x1010, 0x1000, 0x00, 0x00 }, [BAM_P_IRQ_CLR] = { 0x1014, 0x1000, 0x00, 0x00 }, [BAM_P_IRQ_EN] = { 0x1018, 0x1000, 0x00, 0x00 }, - [BAM_P_EVNT_DEST_ADDR] = { 0x102C, 0x00, 0x1000, 0x00 }, - [BAM_P_EVNT_REG] = { 0x1018, 0x00, 0x1000, 0x00 }, - [BAM_P_SW_OFSTS] = { 0x1000, 0x00, 0x1000, 0x00 }, + [BAM_P_EVNT_DEST_ADDR] = { 0x182C, 0x00, 0x1000, 0x00 }, + [BAM_P_EVNT_REG] = { 0x1818, 0x00, 0x1000, 0x00 }, + [BAM_P_SW_OFSTS] = { 0x1800, 0x00, 0x1000, 0x00 }, [BAM_P_DATA_FIFO_ADDR] = { 0x1824, 0x00, 0x1000, 0x00 }, [BAM_P_DESC_FIFO_ADDR] = { 0x181C, 0x00, 0x1000, 0x00 }, [BAM_P_EVNT_GEN_TRSHLD] = { 0x1828, 0x00, 0x1000, 0x00 }, @@ -1143,6 +1143,10 @@ static int bam_dma_probe(struct platform_device *pdev) dma_cap_set(DMA_SLAVE, bdev->common.cap_mask); /* initialize dmaengine apis */ + bdev->common.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV); + bdev->common.residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT; + bdev->common.src_addr_widths = DMA_SLAVE_BUSWIDTH_4_BYTES; + bdev->common.dst_addr_widths = DMA_SLAVE_BUSWIDTH_4_BYTES; bdev->common.device_alloc_chan_resources = bam_alloc_chan; bdev->common.device_free_chan_resources = bam_free_chan; bdev->common.device_prep_slave_sg = bam_prep_slave_sg; diff --git a/drivers/dma/sh/shdmac.c b/drivers/dma/sh/shdmac.c index b2431aa30033..9f1d4c7dbab8 100644 --- a/drivers/dma/sh/shdmac.c +++ b/drivers/dma/sh/shdmac.c @@ -582,15 +582,12 @@ static void sh_dmae_chan_remove(struct sh_dmae_device *shdev) } } -static void sh_dmae_shutdown(struct platform_device *pdev) -{ - struct sh_dmae_device *shdev = platform_get_drvdata(pdev); - sh_dmae_ctl_stop(shdev); -} - #ifdef CONFIG_PM static int sh_dmae_runtime_suspend(struct device *dev) { + struct sh_dmae_device *shdev = dev_get_drvdata(dev); + + sh_dmae_ctl_stop(shdev); return 0; } @@ -605,6 +602,9 @@ static int sh_dmae_runtime_resume(struct device *dev) #ifdef CONFIG_PM_SLEEP static int sh_dmae_suspend(struct device *dev) { + struct sh_dmae_device *shdev = dev_get_drvdata(dev); + + sh_dmae_ctl_stop(shdev); return 0; } @@ -929,13 +929,12 @@ static int sh_dmae_remove(struct platform_device *pdev) } static struct platform_driver sh_dmae_driver = { - .driver = { + .driver = { .pm = &sh_dmae_pm, .name = SH_DMAE_DRV_NAME, .of_match_table = sh_dmae_of_match, }, .remove = sh_dmae_remove, - .shutdown = sh_dmae_shutdown, }; static int __init sh_dmae_init(void) diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c index c5f7b4e9eb6c..69fac068669f 100644 --- a/drivers/firmware/dmi_scan.c +++ b/drivers/firmware/dmi_scan.c @@ -78,7 +78,7 @@ static const char * __init dmi_string(const struct dmi_header *dm, u8 s) * We have to be cautious here. We have seen BIOSes with DMI pointers * pointing to completely the wrong place for example */ -static void dmi_table(u8 *buf, int len, int num, +static void dmi_table(u8 *buf, u32 len, int num, void (*decode)(const struct dmi_header *, void *), void *private_data) { @@ -93,12 +93,6 @@ static void dmi_table(u8 *buf, int len, int num, const struct dmi_header *dm = (const struct dmi_header *)data; /* - * 7.45 End-of-Table (Type 127) [SMBIOS reference spec v3.0.0] - */ - if (dm->type == DMI_ENTRY_END_OF_TABLE) - break; - - /* * We want to know the total length (formatted area and * strings) before decoding to make sure we won't run off the * table in dmi_decode or dmi_string @@ -108,13 +102,20 @@ static void dmi_table(u8 *buf, int len, int num, data++; if (data - buf < len - 1) decode(dm, private_data); + + /* + * 7.45 End-of-Table (Type 127) [SMBIOS reference spec v3.0.0] + */ + if (dm->type == DMI_ENTRY_END_OF_TABLE) + break; + data += 2; i++; } } static phys_addr_t dmi_base; -static u16 dmi_len; +static u32 dmi_len; static u16 dmi_num; static int __init dmi_walk_early(void (*decode)(const struct dmi_header *, diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c index 2fe195002021..f07d4a67fa76 100644 --- a/drivers/firmware/efi/libstub/efi-stub-helper.c +++ b/drivers/firmware/efi/libstub/efi-stub-helper.c @@ -179,12 +179,12 @@ again: start = desc->phys_addr; end = start + desc->num_pages * (1UL << EFI_PAGE_SHIFT); - if ((start + size) > end || (start + size) > max) - continue; - - if (end - size > max) + if (end > max) end = max; + if ((start + size) > end) + continue; + if (round_down(end - size, align) < start) continue; diff --git a/drivers/gpio/gpio-tps65912.c b/drivers/gpio/gpio-tps65912.c index 472fb5b8779f..9cdbc0c9cb2d 100644 --- a/drivers/gpio/gpio-tps65912.c +++ b/drivers/gpio/gpio-tps65912.c @@ -26,9 +26,12 @@ struct tps65912_gpio_data { struct gpio_chip gpio_chip; }; +#define to_tgd(gc) container_of(gc, struct tps65912_gpio_data, gpio_chip) + static int tps65912_gpio_get(struct gpio_chip *gc, unsigned offset) { - struct tps65912 *tps65912 = container_of(gc, struct tps65912, gpio); + struct tps65912_gpio_data *tps65912_gpio = to_tgd(gc); + struct tps65912 *tps65912 = tps65912_gpio->tps65912; int val; val = tps65912_reg_read(tps65912, TPS65912_GPIO1 + offset); @@ -42,7 +45,8 @@ static int tps65912_gpio_get(struct gpio_chip *gc, unsigned offset) static void tps65912_gpio_set(struct gpio_chip *gc, unsigned offset, int value) { - struct tps65912 *tps65912 = container_of(gc, struct tps65912, gpio); + struct tps65912_gpio_data *tps65912_gpio = to_tgd(gc); + struct tps65912 *tps65912 = tps65912_gpio->tps65912; if (value) tps65912_set_bits(tps65912, TPS65912_GPIO1 + offset, @@ -55,7 +59,8 @@ static void tps65912_gpio_set(struct gpio_chip *gc, unsigned offset, static int tps65912_gpio_output(struct gpio_chip *gc, unsigned offset, int value) { - struct tps65912 *tps65912 = container_of(gc, struct tps65912, gpio); + struct tps65912_gpio_data *tps65912_gpio = to_tgd(gc); + struct tps65912 *tps65912 = tps65912_gpio->tps65912; /* Set the initial value */ tps65912_gpio_set(gc, offset, value); @@ -66,7 +71,8 @@ static int tps65912_gpio_output(struct gpio_chip *gc, unsigned offset, static int tps65912_gpio_input(struct gpio_chip *gc, unsigned offset) { - struct tps65912 *tps65912 = container_of(gc, struct tps65912, gpio); + struct tps65912_gpio_data *tps65912_gpio = to_tgd(gc); + struct tps65912 *tps65912 = tps65912_gpio->tps65912; return tps65912_clear_bits(tps65912, TPS65912_GPIO1 + offset, GPIO_CFG_MASK); diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c index 8cad8e400b44..4650bf830d6b 100644 --- a/drivers/gpio/gpiolib-of.c +++ b/drivers/gpio/gpiolib-of.c @@ -46,12 +46,13 @@ static int of_gpiochip_find_and_xlate(struct gpio_chip *gc, void *data) ret = gc->of_xlate(gc, &gg_data->gpiospec, gg_data->flags); if (ret < 0) { - /* We've found the gpio chip, but the translation failed. - * Return true to stop looking and return the translation - * error via out_gpio + /* We've found a gpio chip, but the translation failed. + * Store translation error in out_gpio. + * Return false to keep looking, as more than one gpio chip + * could be registered per of-node. */ gg_data->out_gpio = ERR_PTR(ret); - return true; + return false; } gg_data->out_gpio = gpiochip_get_desc(gc, ret); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index b3589d0e39b9..910ff8ab9c9c 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -62,12 +62,18 @@ enum KFD_MQD_TYPE get_mqd_type_from_queue_type(enum kfd_queue_type type) return KFD_MQD_TYPE_CP; } -static inline unsigned int get_first_pipe(struct device_queue_manager *dqm) +unsigned int get_first_pipe(struct device_queue_manager *dqm) { - BUG_ON(!dqm); + BUG_ON(!dqm || !dqm->dev); return dqm->dev->shared_resources.first_compute_pipe; } +unsigned int get_pipes_num(struct device_queue_manager *dqm) +{ + BUG_ON(!dqm || !dqm->dev); + return dqm->dev->shared_resources.compute_pipe_count; +} + static inline unsigned int get_pipes_num_cpsch(void) { return PIPE_PER_ME_CP_SCHEDULING; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h index d64f86cda34f..488f51d19427 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h @@ -163,6 +163,8 @@ void program_sh_mem_settings(struct device_queue_manager *dqm, struct qcm_process_device *qpd); int init_pipelines(struct device_queue_manager *dqm, unsigned int pipes_num, unsigned int first_pipe); +unsigned int get_first_pipe(struct device_queue_manager *dqm); +unsigned int get_pipes_num(struct device_queue_manager *dqm); extern inline unsigned int get_sh_mem_bases_32(struct kfd_process_device *pdd) { @@ -175,10 +177,4 @@ get_sh_mem_bases_nybble_64(struct kfd_process_device *pdd) return (pdd->lds_base >> 60) & 0x0E; } -extern inline unsigned int get_pipes_num(struct device_queue_manager *dqm) -{ - BUG_ON(!dqm || !dqm->dev); - return dqm->dev->shared_resources.compute_pipe_count; -} - #endif /* KFD_DEVICE_QUEUE_MANAGER_H_ */ diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_cik.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_cik.c index 6b072466e2a6..5469efe0523e 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_cik.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_cik.c @@ -131,5 +131,5 @@ static int register_process_cik(struct device_queue_manager *dqm, static int initialize_cpsch_cik(struct device_queue_manager *dqm) { - return init_pipelines(dqm, get_pipes_num(dqm), 0); + return init_pipelines(dqm, get_pipes_num(dqm), get_first_pipe(dqm)); } diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c index 0409b907de5d..b3e3068c6ec0 100644 --- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c +++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c @@ -153,7 +153,7 @@ static int atmel_hlcdc_crtc_mode_set(struct drm_crtc *c, (adj->crtc_hdisplay - 1) | ((adj->crtc_vdisplay - 1) << 16)); - cfg = ATMEL_HLCDC_CLKPOL; + cfg = 0; prate = clk_get_rate(crtc->dc->hlcdc->sys_clk); mode_rate = mode->crtc_clock * 1000; diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c index 7320a6c6613f..c1cb17493e0d 100644 --- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c +++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c @@ -311,8 +311,6 @@ static int atmel_hlcdc_dc_load(struct drm_device *dev) pm_runtime_enable(dev->dev); - pm_runtime_put_sync(dev->dev); - ret = atmel_hlcdc_dc_modeset_init(dev); if (ret < 0) { dev_err(dev->dev, "failed to initialize mode setting\n"); diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_layer.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_layer.c index 063d2a7b941f..e79bd9ba474b 100644 --- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_layer.c +++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_layer.c @@ -311,7 +311,8 @@ int atmel_hlcdc_layer_disable(struct atmel_hlcdc_layer *layer) /* Disable the layer */ regmap_write(regmap, desc->regs_offset + ATMEL_HLCDC_LAYER_CHDR, - ATMEL_HLCDC_LAYER_RST); + ATMEL_HLCDC_LAYER_RST | ATMEL_HLCDC_LAYER_A2Q | + ATMEL_HLCDC_LAYER_UPDATE); /* Clear all pending interrupts */ regmap_read(regmap, desc->regs_offset + ATMEL_HLCDC_LAYER_ISR, &isr); diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index 6b00173d1be4..6b6b07ff720b 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -2127,7 +2127,6 @@ int drm_mode_getconnector(struct drm_device *dev, void *data, DRM_DEBUG_KMS("[CONNECTOR:%d:?]\n", out_resp->connector_id); mutex_lock(&dev->mode_config.mutex); - drm_modeset_lock(&dev->mode_config.connection_mutex, NULL); connector = drm_connector_find(dev, out_resp->connector_id); if (!connector) { @@ -2157,6 +2156,8 @@ int drm_mode_getconnector(struct drm_device *dev, void *data, out_resp->mm_height = connector->display_info.height_mm; out_resp->subpixel = connector->display_info.subpixel_order; out_resp->connection = connector->status; + + drm_modeset_lock(&dev->mode_config.connection_mutex, NULL); encoder = drm_connector_get_encoder(connector); if (encoder) out_resp->encoder_id = encoder->base.id; diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c index 04a209e2b66d..7fc6f8bd4821 100644 --- a/drivers/gpu/drm/drm_mm.c +++ b/drivers/gpu/drm/drm_mm.c @@ -91,29 +91,29 @@ */ static struct drm_mm_node *drm_mm_search_free_generic(const struct drm_mm *mm, - unsigned long size, + u64 size, unsigned alignment, unsigned long color, enum drm_mm_search_flags flags); static struct drm_mm_node *drm_mm_search_free_in_range_generic(const struct drm_mm *mm, - unsigned long size, + u64 size, unsigned alignment, unsigned long color, - unsigned long start, - unsigned long end, + u64 start, + u64 end, enum drm_mm_search_flags flags); static void drm_mm_insert_helper(struct drm_mm_node *hole_node, struct drm_mm_node *node, - unsigned long size, unsigned alignment, + u64 size, unsigned alignment, unsigned long color, enum drm_mm_allocator_flags flags) { struct drm_mm *mm = hole_node->mm; - unsigned long hole_start = drm_mm_hole_node_start(hole_node); - unsigned long hole_end = drm_mm_hole_node_end(hole_node); - unsigned long adj_start = hole_start; - unsigned long adj_end = hole_end; + u64 hole_start = drm_mm_hole_node_start(hole_node); + u64 hole_end = drm_mm_hole_node_end(hole_node); + u64 adj_start = hole_start; + u64 adj_end = hole_end; BUG_ON(node->allocated); @@ -124,12 +124,15 @@ static void drm_mm_insert_helper(struct drm_mm_node *hole_node, adj_start = adj_end - size; if (alignment) { - unsigned tmp = adj_start % alignment; - if (tmp) { + u64 tmp = adj_start; + unsigned rem; + + rem = do_div(tmp, alignment); + if (rem) { if (flags & DRM_MM_CREATE_TOP) - adj_start -= tmp; + adj_start -= rem; else - adj_start += alignment - tmp; + adj_start += alignment - rem; } } @@ -176,9 +179,9 @@ static void drm_mm_insert_helper(struct drm_mm_node *hole_node, int drm_mm_reserve_node(struct drm_mm *mm, struct drm_mm_node *node) { struct drm_mm_node *hole; - unsigned long end = node->start + node->size; - unsigned long hole_start; - unsigned long hole_end; + u64 end = node->start + node->size; + u64 hole_start; + u64 hole_end; BUG_ON(node == NULL); @@ -227,7 +230,7 @@ EXPORT_SYMBOL(drm_mm_reserve_node); * 0 on success, -ENOSPC if there's no suitable hole. */ int drm_mm_insert_node_generic(struct drm_mm *mm, struct drm_mm_node *node, - unsigned long size, unsigned alignment, + u64 size, unsigned alignment, unsigned long color, enum drm_mm_search_flags sflags, enum drm_mm_allocator_flags aflags) @@ -246,16 +249,16 @@ EXPORT_SYMBOL(drm_mm_insert_node_generic); static void drm_mm_insert_helper_range(struct drm_mm_node *hole_node, struct drm_mm_node *node, - unsigned long size, unsigned alignment, + u64 size, unsigned alignment, unsigned long color, - unsigned long start, unsigned long end, + u64 start, u64 end, enum drm_mm_allocator_flags flags) { struct drm_mm *mm = hole_node->mm; - unsigned long hole_start = drm_mm_hole_node_start(hole_node); - unsigned long hole_end = drm_mm_hole_node_end(hole_node); - unsigned long adj_start = hole_start; - unsigned long adj_end = hole_end; + u64 hole_start = drm_mm_hole_node_start(hole_node); + u64 hole_end = drm_mm_hole_node_end(hole_node); + u64 adj_start = hole_start; + u64 adj_end = hole_end; BUG_ON(!hole_node->hole_follows || node->allocated); @@ -271,12 +274,15 @@ static void drm_mm_insert_helper_range(struct drm_mm_node *hole_node, mm->color_adjust(hole_node, color, &adj_start, &adj_end); if (alignment) { - unsigned tmp = adj_start % alignment; - if (tmp) { + u64 tmp = adj_start; + unsigned rem; + + rem = do_div(tmp, alignment); + if (rem) { if (flags & DRM_MM_CREATE_TOP) - adj_start -= tmp; + adj_start -= rem; else - adj_start += alignment - tmp; + adj_start += alignment - rem; } } @@ -324,9 +330,9 @@ static void drm_mm_insert_helper_range(struct drm_mm_node *hole_node, * 0 on success, -ENOSPC if there's no suitable hole. */ int drm_mm_insert_node_in_range_generic(struct drm_mm *mm, struct drm_mm_node *node, - unsigned long size, unsigned alignment, + u64 size, unsigned alignment, unsigned long color, - unsigned long start, unsigned long end, + u64 start, u64 end, enum drm_mm_search_flags sflags, enum drm_mm_allocator_flags aflags) { @@ -387,32 +393,34 @@ void drm_mm_remove_node(struct drm_mm_node *node) } EXPORT_SYMBOL(drm_mm_remove_node); -static int check_free_hole(unsigned long start, unsigned long end, - unsigned long size, unsigned alignment) +static int check_free_hole(u64 start, u64 end, u64 size, unsigned alignment) { if (end - start < size) return 0; if (alignment) { - unsigned tmp = start % alignment; + u64 tmp = start; + unsigned rem; + + rem = do_div(tmp, alignment); if (tmp) - start += alignment - tmp; + start += alignment - rem; } return end >= start + size; } static struct drm_mm_node *drm_mm_search_free_generic(const struct drm_mm *mm, - unsigned long size, + u64 size, unsigned alignment, unsigned long color, enum drm_mm_search_flags flags) { struct drm_mm_node *entry; struct drm_mm_node *best; - unsigned long adj_start; - unsigned long adj_end; - unsigned long best_size; + u64 adj_start; + u64 adj_end; + u64 best_size; BUG_ON(mm->scanned_blocks); @@ -421,7 +429,7 @@ static struct drm_mm_node *drm_mm_search_free_generic(const struct drm_mm *mm, __drm_mm_for_each_hole(entry, mm, adj_start, adj_end, flags & DRM_MM_SEARCH_BELOW) { - unsigned long hole_size = adj_end - adj_start; + u64 hole_size = adj_end - adj_start; if (mm->color_adjust) { mm->color_adjust(entry, color, &adj_start, &adj_end); @@ -445,18 +453,18 @@ static struct drm_mm_node *drm_mm_search_free_generic(const struct drm_mm *mm, } static struct drm_mm_node *drm_mm_search_free_in_range_generic(const struct drm_mm *mm, - unsigned long size, + u64 size, unsigned alignment, unsigned long color, - unsigned long start, - unsigned long end, + u64 start, + u64 end, enum drm_mm_search_flags flags) { struct drm_mm_node *entry; struct drm_mm_node *best; - unsigned long adj_start; - unsigned long adj_end; - unsigned long best_size; + u64 adj_start; + u64 adj_end; + u64 best_size; BUG_ON(mm->scanned_blocks); @@ -465,7 +473,7 @@ static struct drm_mm_node *drm_mm_search_free_in_range_generic(const struct drm_ __drm_mm_for_each_hole(entry, mm, adj_start, adj_end, flags & DRM_MM_SEARCH_BELOW) { - unsigned long hole_size = adj_end - adj_start; + u64 hole_size = adj_end - adj_start; if (adj_start < start) adj_start = start; @@ -561,7 +569,7 @@ EXPORT_SYMBOL(drm_mm_replace_node); * adding/removing nodes to/from the scan list are allowed. */ void drm_mm_init_scan(struct drm_mm *mm, - unsigned long size, + u64 size, unsigned alignment, unsigned long color) { @@ -594,11 +602,11 @@ EXPORT_SYMBOL(drm_mm_init_scan); * adding/removing nodes to/from the scan list are allowed. */ void drm_mm_init_scan_with_range(struct drm_mm *mm, - unsigned long size, + u64 size, unsigned alignment, unsigned long color, - unsigned long start, - unsigned long end) + u64 start, + u64 end) { mm->scan_color = color; mm->scan_alignment = alignment; @@ -627,8 +635,8 @@ bool drm_mm_scan_add_block(struct drm_mm_node *node) { struct drm_mm *mm = node->mm; struct drm_mm_node *prev_node; - unsigned long hole_start, hole_end; - unsigned long adj_start, adj_end; + u64 hole_start, hole_end; + u64 adj_start, adj_end; mm->scanned_blocks++; @@ -731,7 +739,7 @@ EXPORT_SYMBOL(drm_mm_clean); * * Note that @mm must be cleared to 0 before calling this function. */ -void drm_mm_init(struct drm_mm * mm, unsigned long start, unsigned long size) +void drm_mm_init(struct drm_mm * mm, u64 start, u64 size) { INIT_LIST_HEAD(&mm->hole_stack); mm->scanned_blocks = 0; @@ -766,18 +774,17 @@ void drm_mm_takedown(struct drm_mm * mm) } EXPORT_SYMBOL(drm_mm_takedown); -static unsigned long drm_mm_debug_hole(struct drm_mm_node *entry, - const char *prefix) +static u64 drm_mm_debug_hole(struct drm_mm_node *entry, + const char *prefix) { - unsigned long hole_start, hole_end, hole_size; + u64 hole_start, hole_end, hole_size; if (entry->hole_follows) { hole_start = drm_mm_hole_node_start(entry); hole_end = drm_mm_hole_node_end(entry); hole_size = hole_end - hole_start; - printk(KERN_DEBUG "%s 0x%08lx-0x%08lx: %8lu: free\n", - prefix, hole_start, hole_end, - hole_size); + pr_debug("%s %#llx-%#llx: %llu: free\n", prefix, hole_start, + hole_end, hole_size); return hole_size; } @@ -792,35 +799,34 @@ static unsigned long drm_mm_debug_hole(struct drm_mm_node *entry, void drm_mm_debug_table(struct drm_mm *mm, const char *prefix) { struct drm_mm_node *entry; - unsigned long total_used = 0, total_free = 0, total = 0; + u64 total_used = 0, total_free = 0, total = 0; total_free += drm_mm_debug_hole(&mm->head_node, prefix); drm_mm_for_each_node(entry, mm) { - printk(KERN_DEBUG "%s 0x%08lx-0x%08lx: %8lu: used\n", - prefix, entry->start, entry->start + entry->size, - entry->size); + pr_debug("%s %#llx-%#llx: %llu: used\n", prefix, entry->start, + entry->start + entry->size, entry->size); total_used += entry->size; total_free += drm_mm_debug_hole(entry, prefix); } total = total_free + total_used; - printk(KERN_DEBUG "%s total: %lu, used %lu free %lu\n", prefix, total, - total_used, total_free); + pr_debug("%s total: %llu, used %llu free %llu\n", prefix, total, + total_used, total_free); } EXPORT_SYMBOL(drm_mm_debug_table); #if defined(CONFIG_DEBUG_FS) -static unsigned long drm_mm_dump_hole(struct seq_file *m, struct drm_mm_node *entry) +static u64 drm_mm_dump_hole(struct seq_file *m, struct drm_mm_node *entry) { - unsigned long hole_start, hole_end, hole_size; + u64 hole_start, hole_end, hole_size; if (entry->hole_follows) { hole_start = drm_mm_hole_node_start(entry); hole_end = drm_mm_hole_node_end(entry); hole_size = hole_end - hole_start; - seq_printf(m, "0x%08lx-0x%08lx: 0x%08lx: free\n", - hole_start, hole_end, hole_size); + seq_printf(m, "%#llx-%#llx: %llu: free\n", hole_start, + hole_end, hole_size); return hole_size; } @@ -835,20 +841,20 @@ static unsigned long drm_mm_dump_hole(struct seq_file *m, struct drm_mm_node *en int drm_mm_dump_table(struct seq_file *m, struct drm_mm *mm) { struct drm_mm_node *entry; - unsigned long total_used = 0, total_free = 0, total = 0; + u64 total_used = 0, total_free = 0, total = 0; total_free += drm_mm_dump_hole(m, &mm->head_node); drm_mm_for_each_node(entry, mm) { - seq_printf(m, "0x%08lx-0x%08lx: 0x%08lx: used\n", - entry->start, entry->start + entry->size, - entry->size); + seq_printf(m, "%#016llx-%#016llx: %llu: used\n", entry->start, + entry->start + entry->size, entry->size); total_used += entry->size; total_free += drm_mm_dump_hole(m, entry); } total = total_free + total_used; - seq_printf(m, "total: %lu, used %lu free %lu\n", total, total_used, total_free); + seq_printf(m, "total: %llu, used %llu free %llu\n", total, + total_used, total_free); return 0; } EXPORT_SYMBOL(drm_mm_dump_table); diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index 96e811fe24ca..e8b18e542da4 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -152,12 +152,12 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj) seq_puts(m, " (pp"); else seq_puts(m, " (g"); - seq_printf(m, "gtt offset: %08lx, size: %08lx, type: %u)", + seq_printf(m, "gtt offset: %08llx, size: %08llx, type: %u)", vma->node.start, vma->node.size, vma->ggtt_view.type); } if (obj->stolen) - seq_printf(m, " (stolen: %08lx)", obj->stolen->start); + seq_printf(m, " (stolen: %08llx)", obj->stolen->start); if (obj->pin_mappable || obj->fault_mappable) { char s[3], *t = s; if (obj->pin_mappable) diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 8039cec71fc2..cc6ea53d2b81 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -622,7 +622,7 @@ static int i915_drm_suspend(struct drm_device *dev) return 0; } -static int i915_drm_suspend_late(struct drm_device *drm_dev) +static int i915_drm_suspend_late(struct drm_device *drm_dev, bool hibernation) { struct drm_i915_private *dev_priv = drm_dev->dev_private; int ret; @@ -636,7 +636,17 @@ static int i915_drm_suspend_late(struct drm_device *drm_dev) } pci_disable_device(drm_dev->pdev); - pci_set_power_state(drm_dev->pdev, PCI_D3hot); + /* + * During hibernation on some GEN4 platforms the BIOS may try to access + * the device even though it's already in D3 and hang the machine. So + * leave the device in D0 on those platforms and hope the BIOS will + * power down the device properly. Platforms where this was seen: + * Lenovo Thinkpad X301, X61s + */ + if (!(hibernation && + drm_dev->pdev->subsystem_vendor == PCI_VENDOR_ID_LENOVO && + INTEL_INFO(dev_priv)->gen == 4)) + pci_set_power_state(drm_dev->pdev, PCI_D3hot); return 0; } @@ -662,7 +672,7 @@ int i915_suspend_legacy(struct drm_device *dev, pm_message_t state) if (error) return error; - return i915_drm_suspend_late(dev); + return i915_drm_suspend_late(dev, false); } static int i915_drm_resume(struct drm_device *dev) @@ -950,7 +960,17 @@ static int i915_pm_suspend_late(struct device *dev) if (drm_dev->switch_power_state == DRM_SWITCH_POWER_OFF) return 0; - return i915_drm_suspend_late(drm_dev); + return i915_drm_suspend_late(drm_dev, false); +} + +static int i915_pm_poweroff_late(struct device *dev) +{ + struct drm_device *drm_dev = dev_to_i915(dev)->dev; + + if (drm_dev->switch_power_state == DRM_SWITCH_POWER_OFF) + return 0; + + return i915_drm_suspend_late(drm_dev, true); } static int i915_pm_resume_early(struct device *dev) @@ -1520,7 +1540,7 @@ static const struct dev_pm_ops i915_pm_ops = { .thaw_early = i915_pm_resume_early, .thaw = i915_pm_resume, .poweroff = i915_pm_suspend, - .poweroff_late = i915_pm_suspend_late, + .poweroff_late = i915_pm_poweroff_late, .restore_early = i915_pm_resume_early, .restore = i915_pm_resume, diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index f2a825e39646..8727086cf48c 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -2114,6 +2114,9 @@ void i915_gem_track_fb(struct drm_i915_gem_object *old, * number comparisons on buffer last_read|write_seqno. It also allows an * emission time to be associated with the request for tracking how far ahead * of the GPU the submission is. + * + * The requests are reference counted, so upon creation they should have an + * initial reference taken using kref_init */ struct drm_i915_gem_request { struct kref ref; @@ -2137,7 +2140,16 @@ struct drm_i915_gem_request { /** Position in the ringbuffer of the end of the whole request */ u32 tail; - /** Context related to this request */ + /** + * Context related to this request + * Contexts are refcounted, so when this request is associated with a + * context, we must increment the context's refcount, to guarantee that + * it persists while any request is linked to it. Requests themselves + * are also refcounted, so the request will only be freed when the last + * reference to it is dismissed, and the code in + * i915_gem_request_free() will then decrement the refcount on the + * context. + */ struct intel_context *ctx; /** Batch buffer related to this request if any */ @@ -2374,6 +2386,7 @@ struct drm_i915_cmd_table { (INTEL_DEVID(dev) & 0xFF00) == 0x0C00) #define IS_BDW_ULT(dev) (IS_BROADWELL(dev) && \ ((INTEL_DEVID(dev) & 0xf) == 0x6 || \ + (INTEL_DEVID(dev) & 0xf) == 0xb || \ (INTEL_DEVID(dev) & 0xf) == 0xe)) #define IS_BDW_GT3(dev) (IS_BROADWELL(dev) && \ (INTEL_DEVID(dev) & 0x00F0) == 0x0020) diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index c26d36cc4b31..e5daad5f75fb 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -2659,8 +2659,7 @@ static void i915_gem_reset_ring_cleanup(struct drm_i915_private *dev_priv, if (submit_req->ctx != ring->default_context) intel_lr_context_unpin(ring, submit_req->ctx); - i915_gem_context_unreference(submit_req->ctx); - kfree(submit_req); + i915_gem_request_unreference(submit_req); } /* diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 746f77fb57a3..dccdc8aad2e2 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -1145,7 +1145,7 @@ static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt) ppgtt->base.clear_range(&ppgtt->base, 0, ppgtt->base.total, true); - DRM_DEBUG_DRIVER("Allocated pde space (%ldM) at GTT entry: %lx\n", + DRM_DEBUG_DRIVER("Allocated pde space (%lldM) at GTT entry: %llx\n", ppgtt->node.size >> 20, ppgtt->node.start / PAGE_SIZE); @@ -1713,8 +1713,8 @@ void i915_gem_gtt_finish_object(struct drm_i915_gem_object *obj) static void i915_gtt_color_adjust(struct drm_mm_node *node, unsigned long color, - unsigned long *start, - unsigned long *end) + u64 *start, + u64 *end) { if (node->color != color) *start += 4096; diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c index a2045848bd1a..9c6f93ec886b 100644 --- a/drivers/gpu/drm/i915/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/i915_gem_stolen.c @@ -485,10 +485,8 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev, stolen_offset, gtt_offset, size); /* KISS and expect everything to be page-aligned */ - BUG_ON(stolen_offset & 4095); - BUG_ON(size & 4095); - - if (WARN_ON(size == 0)) + if (WARN_ON(size == 0) || WARN_ON(size & 4095) || + WARN_ON(stolen_offset & 4095)) return NULL; stolen = kzalloc(sizeof(*stolen), GFP_KERNEL); diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c index 7a24bd1a51f6..6377b22269ad 100644 --- a/drivers/gpu/drm/i915/i915_gem_tiling.c +++ b/drivers/gpu/drm/i915/i915_gem_tiling.c @@ -335,9 +335,10 @@ i915_gem_set_tiling(struct drm_device *dev, void *data, return -EINVAL; } + mutex_lock(&dev->struct_mutex); if (i915_gem_obj_is_pinned(obj) || obj->framebuffer_references) { - drm_gem_object_unreference_unlocked(&obj->base); - return -EBUSY; + ret = -EBUSY; + goto err; } if (args->tiling_mode == I915_TILING_NONE) { @@ -369,7 +370,6 @@ i915_gem_set_tiling(struct drm_device *dev, void *data, } } - mutex_lock(&dev->struct_mutex); if (args->tiling_mode != obj->tiling_mode || args->stride != obj->stride) { /* We need to rebind the object if its current allocation @@ -424,6 +424,7 @@ i915_gem_set_tiling(struct drm_device *dev, void *data, obj->bit_17 = NULL; } +err: drm_gem_object_unreference(&obj->base); mutex_unlock(&dev->struct_mutex); diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 4145d95902f5..ede5bbbd8a08 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -1892,6 +1892,9 @@ static irqreturn_t valleyview_irq_handler(int irq, void *arg) u32 iir, gt_iir, pm_iir; irqreturn_t ret = IRQ_NONE; + if (!intel_irqs_enabled(dev_priv)) + return IRQ_NONE; + while (true) { /* Find, clear, then process each source of interrupt */ @@ -1936,6 +1939,9 @@ static irqreturn_t cherryview_irq_handler(int irq, void *arg) u32 master_ctl, iir; irqreturn_t ret = IRQ_NONE; + if (!intel_irqs_enabled(dev_priv)) + return IRQ_NONE; + for (;;) { master_ctl = I915_READ(GEN8_MASTER_IRQ) & ~GEN8_MASTER_IRQ_CONTROL; iir = I915_READ(VLV_IIR); @@ -2208,6 +2214,9 @@ static irqreturn_t ironlake_irq_handler(int irq, void *arg) u32 de_iir, gt_iir, de_ier, sde_ier = 0; irqreturn_t ret = IRQ_NONE; + if (!intel_irqs_enabled(dev_priv)) + return IRQ_NONE; + /* We get interrupts on unclaimed registers, so check for this before we * do any I915_{READ,WRITE}. */ intel_uncore_check_errors(dev); @@ -2279,6 +2288,9 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg) enum pipe pipe; u32 aux_mask = GEN8_AUX_CHANNEL_A; + if (!intel_irqs_enabled(dev_priv)) + return IRQ_NONE; + if (IS_GEN9(dev)) aux_mask |= GEN9_AUX_CHANNEL_B | GEN9_AUX_CHANNEL_C | GEN9_AUX_CHANNEL_D; @@ -3771,6 +3783,9 @@ static irqreturn_t i8xx_irq_handler(int irq, void *arg) I915_DISPLAY_PLANE_A_FLIP_PENDING_INTERRUPT | I915_DISPLAY_PLANE_B_FLIP_PENDING_INTERRUPT; + if (!intel_irqs_enabled(dev_priv)) + return IRQ_NONE; + iir = I915_READ16(IIR); if (iir == 0) return IRQ_NONE; @@ -3951,6 +3966,9 @@ static irqreturn_t i915_irq_handler(int irq, void *arg) I915_DISPLAY_PLANE_B_FLIP_PENDING_INTERRUPT; int pipe, ret = IRQ_NONE; + if (!intel_irqs_enabled(dev_priv)) + return IRQ_NONE; + iir = I915_READ(IIR); do { bool irq_received = (iir & ~flip_mask) != 0; @@ -4171,6 +4189,9 @@ static irqreturn_t i965_irq_handler(int irq, void *arg) I915_DISPLAY_PLANE_A_FLIP_PENDING_INTERRUPT | I915_DISPLAY_PLANE_B_FLIP_PENDING_INTERRUPT; + if (!intel_irqs_enabled(dev_priv)) + return IRQ_NONE; + iir = I915_READ(IIR); for (;;) { @@ -4520,6 +4541,7 @@ void intel_runtime_pm_disable_interrupts(struct drm_i915_private *dev_priv) { dev_priv->dev->driver->irq_uninstall(dev_priv->dev); dev_priv->pm.irqs_enabled = false; + synchronize_irq(dev_priv->dev->irq); } /** diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 3d220a67f865..e730789b53b7 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -2371,13 +2371,19 @@ intel_alloc_plane_obj(struct intel_crtc *crtc, struct drm_device *dev = crtc->base.dev; struct drm_i915_gem_object *obj = NULL; struct drm_mode_fb_cmd2 mode_cmd = { 0 }; - u32 base = plane_config->base; + u32 base_aligned = round_down(plane_config->base, PAGE_SIZE); + u32 size_aligned = round_up(plane_config->base + plane_config->size, + PAGE_SIZE); + + size_aligned -= base_aligned; if (plane_config->size == 0) return false; - obj = i915_gem_object_create_stolen_for_preallocated(dev, base, base, - plane_config->size); + obj = i915_gem_object_create_stolen_for_preallocated(dev, + base_aligned, + base_aligned, + size_aligned); if (!obj) return false; @@ -2725,10 +2731,19 @@ static void skylake_update_primary_plane(struct drm_crtc *crtc, case DRM_FORMAT_XRGB8888: plane_ctl |= PLANE_CTL_FORMAT_XRGB_8888; break; + case DRM_FORMAT_ARGB8888: + plane_ctl |= PLANE_CTL_FORMAT_XRGB_8888; + plane_ctl |= PLANE_CTL_ALPHA_SW_PREMULTIPLY; + break; case DRM_FORMAT_XBGR8888: plane_ctl |= PLANE_CTL_ORDER_RGBX; plane_ctl |= PLANE_CTL_FORMAT_XRGB_8888; break; + case DRM_FORMAT_ABGR8888: + plane_ctl |= PLANE_CTL_ORDER_RGBX; + plane_ctl |= PLANE_CTL_FORMAT_XRGB_8888; + plane_ctl |= PLANE_CTL_ALPHA_SW_PREMULTIPLY; + break; case DRM_FORMAT_XRGB2101010: plane_ctl |= PLANE_CTL_FORMAT_XRGB_2101010; break; @@ -6627,7 +6642,7 @@ i9xx_get_initial_plane_config(struct intel_crtc *crtc, aligned_height = intel_fb_align_height(dev, fb->height, plane_config->tiling); - plane_config->size = PAGE_ALIGN(fb->pitches[0] * aligned_height); + plane_config->size = fb->pitches[0] * aligned_height; DRM_DEBUG_KMS("pipe/plane %c/%d with fb: size=%dx%d@%d, offset=%x, pitch %d, size 0x%x\n", pipe_name(pipe), plane, fb->width, fb->height, @@ -7664,7 +7679,7 @@ skylake_get_initial_plane_config(struct intel_crtc *crtc, aligned_height = intel_fb_align_height(dev, fb->height, plane_config->tiling); - plane_config->size = ALIGN(fb->pitches[0] * aligned_height, PAGE_SIZE); + plane_config->size = fb->pitches[0] * aligned_height; DRM_DEBUG_KMS("pipe %c with fb: size=%dx%d@%d, offset=%x, pitch %d, size 0x%x\n", pipe_name(pipe), fb->width, fb->height, @@ -7755,7 +7770,7 @@ ironlake_get_initial_plane_config(struct intel_crtc *crtc, aligned_height = intel_fb_align_height(dev, fb->height, plane_config->tiling); - plane_config->size = PAGE_ALIGN(fb->pitches[0] * aligned_height); + plane_config->size = fb->pitches[0] * aligned_height; DRM_DEBUG_KMS("pipe %c with fb: size=%dx%d@%d, offset=%x, pitch %d, size 0x%x\n", pipe_name(pipe), fb->width, fb->height, @@ -8698,6 +8713,7 @@ retry: old->release_fb->funcs->destroy(old->release_fb); goto fail; } + crtc->primary->crtc = crtc; /* let the connector get through one full cycle before testing */ intel_wait_for_vblank(dev, intel_crtc->pipe); @@ -12182,9 +12198,6 @@ intel_check_cursor_plane(struct drm_plane *plane, return -ENOMEM; } - if (fb == crtc->cursor->fb) - return 0; - /* we only need to pin inside GTT if cursor is non-phy */ mutex_lock(&dev->struct_mutex); if (!INTEL_INFO(dev)->cursor_needs_physical && obj->tiling_mode) { @@ -13096,6 +13109,9 @@ static struct intel_quirk intel_quirks[] = { /* HP Chromebook 14 (Celeron 2955U) */ { 0x0a06, 0x103c, 0x21ed, quirk_backlight_present }, + + /* Dell Chromebook 11 */ + { 0x0a06, 0x1028, 0x0a35, quirk_backlight_present }, }; static void intel_init_quirks(struct drm_device *dev) diff --git a/drivers/gpu/drm/i915/intel_fifo_underrun.c b/drivers/gpu/drm/i915/intel_fifo_underrun.c index 04e248dd2259..54daa66c6970 100644 --- a/drivers/gpu/drm/i915/intel_fifo_underrun.c +++ b/drivers/gpu/drm/i915/intel_fifo_underrun.c @@ -282,16 +282,6 @@ bool intel_set_cpu_fifo_underrun_reporting(struct drm_i915_private *dev_priv, return ret; } -static bool -__cpu_fifo_underrun_reporting_enabled(struct drm_i915_private *dev_priv, - enum pipe pipe) -{ - struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe]; - struct intel_crtc *intel_crtc = to_intel_crtc(crtc); - - return !intel_crtc->cpu_fifo_underrun_disabled; -} - /** * intel_set_pch_fifo_underrun_reporting - set PCH fifo underrun reporting state * @dev_priv: i915 device instance @@ -352,9 +342,15 @@ bool intel_set_pch_fifo_underrun_reporting(struct drm_i915_private *dev_priv, void intel_cpu_fifo_underrun_irq_handler(struct drm_i915_private *dev_priv, enum pipe pipe) { + struct drm_crtc *crtc = dev_priv->pipe_to_crtc_mapping[pipe]; + + /* We may be called too early in init, thanks BIOS! */ + if (crtc == NULL) + return; + /* GMCH can't disable fifo underruns, filter them. */ if (HAS_GMCH_DISPLAY(dev_priv->dev) && - !__cpu_fifo_underrun_reporting_enabled(dev_priv, pipe)) + to_intel_crtc(crtc)->cpu_fifo_underrun_disabled) return; if (intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false)) diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index 0f358c5999ec..e8d3da9f3373 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -503,18 +503,19 @@ static int execlists_context_queue(struct intel_engine_cs *ring, * If there isn't a request associated with this submission, * create one as a temporary holder. */ - WARN(1, "execlist context submission without request"); request = kzalloc(sizeof(*request), GFP_KERNEL); if (request == NULL) return -ENOMEM; request->ring = ring; request->ctx = to; + kref_init(&request->ref); + request->uniq = dev_priv->request_uniq++; + i915_gem_context_reference(request->ctx); } else { + i915_gem_request_reference(request); WARN_ON(to != request->ctx); } request->tail = tail; - i915_gem_request_reference(request); - i915_gem_context_reference(request->ctx); intel_runtime_pm_get(dev_priv); @@ -731,7 +732,6 @@ void intel_execlists_retire_requests(struct intel_engine_cs *ring) if (ctx_obj && (ctx != ring->default_context)) intel_lr_context_unpin(ring, ctx); intel_runtime_pm_put(dev_priv); - i915_gem_context_unreference(ctx); list_del(&req->execlist_link); i915_gem_request_unreference(req); } diff --git a/drivers/gpu/drm/imx/dw_hdmi-imx.c b/drivers/gpu/drm/imx/dw_hdmi-imx.c index 121d30ca2d44..87fe8ed92ebe 100644 --- a/drivers/gpu/drm/imx/dw_hdmi-imx.c +++ b/drivers/gpu/drm/imx/dw_hdmi-imx.c @@ -70,7 +70,9 @@ static const struct dw_hdmi_curr_ctrl imx_cur_ctr[] = { 118800000, { 0x091c, 0x091c, 0x06dc }, }, { 216000000, { 0x06dc, 0x0b5c, 0x091c }, - } + }, { + ~0UL, { 0x0000, 0x0000, 0x0000 }, + }, }; static const struct dw_hdmi_sym_term imx_sym_term[] = { @@ -136,11 +138,34 @@ static struct drm_encoder_funcs dw_hdmi_imx_encoder_funcs = { .destroy = drm_encoder_cleanup, }; +static enum drm_mode_status imx6q_hdmi_mode_valid(struct drm_connector *con, + struct drm_display_mode *mode) +{ + if (mode->clock < 13500) + return MODE_CLOCK_LOW; + if (mode->clock > 266000) + return MODE_CLOCK_HIGH; + + return MODE_OK; +} + +static enum drm_mode_status imx6dl_hdmi_mode_valid(struct drm_connector *con, + struct drm_display_mode *mode) +{ + if (mode->clock < 13500) + return MODE_CLOCK_LOW; + if (mode->clock > 270000) + return MODE_CLOCK_HIGH; + + return MODE_OK; +} + static struct dw_hdmi_plat_data imx6q_hdmi_drv_data = { - .mpll_cfg = imx_mpll_cfg, - .cur_ctr = imx_cur_ctr, - .sym_term = imx_sym_term, - .dev_type = IMX6Q_HDMI, + .mpll_cfg = imx_mpll_cfg, + .cur_ctr = imx_cur_ctr, + .sym_term = imx_sym_term, + .dev_type = IMX6Q_HDMI, + .mode_valid = imx6q_hdmi_mode_valid, }; static struct dw_hdmi_plat_data imx6dl_hdmi_drv_data = { @@ -148,6 +173,7 @@ static struct dw_hdmi_plat_data imx6dl_hdmi_drv_data = { .cur_ctr = imx_cur_ctr, .sym_term = imx_sym_term, .dev_type = IMX6DL_HDMI, + .mode_valid = imx6dl_hdmi_mode_valid, }; static const struct of_device_id dw_hdmi_imx_dt_ids[] = { diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c index 1b86aac0b341..2d6dc94e1e64 100644 --- a/drivers/gpu/drm/imx/imx-ldb.c +++ b/drivers/gpu/drm/imx/imx-ldb.c @@ -163,22 +163,7 @@ static void imx_ldb_encoder_prepare(struct drm_encoder *encoder) { struct imx_ldb_channel *imx_ldb_ch = enc_to_imx_ldb_ch(encoder); struct imx_ldb *ldb = imx_ldb_ch->ldb; - struct drm_display_mode *mode = &encoder->crtc->hwmode; u32 pixel_fmt; - unsigned long serial_clk; - unsigned long di_clk = mode->clock * 1000; - int mux = imx_drm_encoder_get_mux_id(imx_ldb_ch->child, encoder); - - if (ldb->ldb_ctrl & LDB_SPLIT_MODE_EN) { - /* dual channel LVDS mode */ - serial_clk = 3500UL * mode->clock; - imx_ldb_set_clock(ldb, mux, 0, serial_clk, di_clk); - imx_ldb_set_clock(ldb, mux, 1, serial_clk, di_clk); - } else { - serial_clk = 7000UL * mode->clock; - imx_ldb_set_clock(ldb, mux, imx_ldb_ch->chno, serial_clk, - di_clk); - } switch (imx_ldb_ch->chno) { case 0: @@ -247,6 +232,9 @@ static void imx_ldb_encoder_mode_set(struct drm_encoder *encoder, struct imx_ldb_channel *imx_ldb_ch = enc_to_imx_ldb_ch(encoder); struct imx_ldb *ldb = imx_ldb_ch->ldb; int dual = ldb->ldb_ctrl & LDB_SPLIT_MODE_EN; + unsigned long serial_clk; + unsigned long di_clk = mode->clock * 1000; + int mux = imx_drm_encoder_get_mux_id(imx_ldb_ch->child, encoder); if (mode->clock > 170000) { dev_warn(ldb->dev, @@ -257,6 +245,16 @@ static void imx_ldb_encoder_mode_set(struct drm_encoder *encoder, "%s: mode exceeds 85 MHz pixel clock\n", __func__); } + if (dual) { + serial_clk = 3500UL * mode->clock; + imx_ldb_set_clock(ldb, mux, 0, serial_clk, di_clk); + imx_ldb_set_clock(ldb, mux, 1, serial_clk, di_clk); + } else { + serial_clk = 7000UL * mode->clock; + imx_ldb_set_clock(ldb, mux, imx_ldb_ch->chno, serial_clk, + di_clk); + } + /* FIXME - assumes straight connections DI0 --> CH0, DI1 --> CH1 */ if (imx_ldb_ch == &ldb->channel[0]) { if (mode->flags & DRM_MODE_FLAG_NVSYNC) diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c index 5e83e007080f..900dda6a8e71 100644 --- a/drivers/gpu/drm/imx/parallel-display.c +++ b/drivers/gpu/drm/imx/parallel-display.c @@ -236,8 +236,11 @@ static int imx_pd_bind(struct device *dev, struct device *master, void *data) } panel_node = of_parse_phandle(np, "fsl,panel", 0); - if (panel_node) + if (panel_node) { imxpd->panel = of_drm_find_panel(panel_node); + if (!imxpd->panel) + return -EPROBE_DEFER; + } imxpd->dev = dev; diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_irq.c b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_irq.c index 8edd531cb621..7369ee7f0c55 100644 --- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_irq.c +++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_irq.c @@ -32,7 +32,10 @@ static void mdp4_irq_error_handler(struct mdp_irq *irq, uint32_t irqstatus) void mdp4_irq_preinstall(struct msm_kms *kms) { struct mdp4_kms *mdp4_kms = to_mdp4_kms(to_mdp_kms(kms)); + mdp4_enable(mdp4_kms); mdp4_write(mdp4_kms, REG_MDP4_INTR_CLEAR, 0xffffffff); + mdp4_write(mdp4_kms, REG_MDP4_INTR_ENABLE, 0x00000000); + mdp4_disable(mdp4_kms); } int mdp4_irq_postinstall(struct msm_kms *kms) @@ -53,7 +56,9 @@ int mdp4_irq_postinstall(struct msm_kms *kms) void mdp4_irq_uninstall(struct msm_kms *kms) { struct mdp4_kms *mdp4_kms = to_mdp4_kms(to_mdp_kms(kms)); + mdp4_enable(mdp4_kms); mdp4_write(mdp4_kms, REG_MDP4_INTR_ENABLE, 0x00000000); + mdp4_disable(mdp4_kms); } irqreturn_t mdp4_irq(struct msm_kms *kms) diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5.xml.h b/drivers/gpu/drm/msm/mdp/mdp5/mdp5.xml.h index 09b4a25eb553..c276624290af 100644 --- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5.xml.h +++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5.xml.h @@ -8,17 +8,9 @@ http://github.com/freedreno/envytools/ git clone https://github.com/freedreno/envytools.git The rules-ng-ng source files this header was generated from are: -- /home/robclark/src/freedreno/envytools/rnndb/msm.xml ( 676 bytes, from 2014-12-05 15:34:49) -- /home/robclark/src/freedreno/envytools/rnndb/freedreno_copyright.xml ( 1453 bytes, from 2013-03-31 16:51:27) -- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp4.xml ( 20908 bytes, from 2014-12-08 16:13:00) -- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp_common.xml ( 2357 bytes, from 2014-12-08 16:13:00) -- /home/robclark/src/freedreno/envytools/rnndb/mdp/mdp5.xml ( 27208 bytes, from 2015-01-13 23:56:11) -- /home/robclark/src/freedreno/envytools/rnndb/dsi/dsi.xml ( 11712 bytes, from 2013-08-17 17:13:43) -- /home/robclark/src/freedreno/envytools/rnndb/dsi/sfpb.xml ( 344 bytes, from 2013-08-11 19:26:32) -- /home/robclark/src/freedreno/envytools/rnndb/dsi/mmss_cc.xml ( 1686 bytes, from 2014-10-31 16:48:57) -- /home/robclark/src/freedreno/envytools/rnndb/hdmi/qfprom.xml ( 600 bytes, from 2013-07-05 19:21:12) -- /home/robclark/src/freedreno/envytools/rnndb/hdmi/hdmi.xml ( 26848 bytes, from 2015-01-13 23:55:57) -- /home/robclark/src/freedreno/envytools/rnndb/edp/edp.xml ( 8253 bytes, from 2014-12-08 16:13:00) +- /local/mnt2/workspace2/sviau/envytools/rnndb/mdp/mdp5.xml ( 27229 bytes, from 2015-02-10 17:00:41) +- /local/mnt2/workspace2/sviau/envytools/rnndb/freedreno_copyright.xml ( 1453 bytes, from 2014-06-02 18:31:15) +- /local/mnt2/workspace2/sviau/envytools/rnndb/mdp/mdp_common.xml ( 2357 bytes, from 2015-01-23 16:20:19) Copyright (C) 2013-2015 by the following authors: - Rob Clark <robdclark@gmail.com> (robclark) @@ -910,6 +902,7 @@ static inline uint32_t __offset_LM(uint32_t idx) case 2: return (mdp5_cfg->lm.base[2]); case 3: return (mdp5_cfg->lm.base[3]); case 4: return (mdp5_cfg->lm.base[4]); + case 5: return (mdp5_cfg->lm.base[5]); default: return INVALID_IDX(idx); } } diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c index 46fac545dc2b..2f2863cf8b45 100644 --- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c +++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_crtc.c @@ -62,8 +62,8 @@ struct mdp5_crtc { /* current cursor being scanned out: */ struct drm_gem_object *scanout_bo; - uint32_t width; - uint32_t height; + uint32_t width, height; + uint32_t x, y; } cursor; }; #define to_mdp5_crtc(x) container_of(x, struct mdp5_crtc, base) @@ -103,8 +103,8 @@ static void crtc_flush_all(struct drm_crtc *crtc) struct drm_plane *plane; uint32_t flush_mask = 0; - /* we could have already released CTL in the disable path: */ - if (!mdp5_crtc->ctl) + /* this should not happen: */ + if (WARN_ON(!mdp5_crtc->ctl)) return; drm_atomic_crtc_for_each_plane(plane, crtc) { @@ -143,6 +143,11 @@ static void complete_flip(struct drm_crtc *crtc, struct drm_file *file) drm_atomic_crtc_for_each_plane(plane, crtc) { mdp5_plane_complete_flip(plane); } + + if (mdp5_crtc->ctl && !crtc->state->enable) { + mdp5_ctl_release(mdp5_crtc->ctl); + mdp5_crtc->ctl = NULL; + } } static void unref_cursor_worker(struct drm_flip_work *work, void *val) @@ -386,14 +391,17 @@ static void mdp5_crtc_atomic_flush(struct drm_crtc *crtc) mdp5_crtc->event = crtc->state->event; spin_unlock_irqrestore(&dev->event_lock, flags); + /* + * If no CTL has been allocated in mdp5_crtc_atomic_check(), + * it means we are trying to flush a CRTC whose state is disabled: + * nothing else needs to be done. + */ + if (unlikely(!mdp5_crtc->ctl)) + return; + blend_setup(crtc); crtc_flush_all(crtc); request_pending(crtc, PENDING_FLIP); - - if (mdp5_crtc->ctl && !crtc->state->enable) { - mdp5_ctl_release(mdp5_crtc->ctl); - mdp5_crtc->ctl = NULL; - } } static int mdp5_crtc_set_property(struct drm_crtc *crtc, @@ -403,6 +411,32 @@ static int mdp5_crtc_set_property(struct drm_crtc *crtc, return -EINVAL; } +static void get_roi(struct drm_crtc *crtc, uint32_t *roi_w, uint32_t *roi_h) +{ + struct mdp5_crtc *mdp5_crtc = to_mdp5_crtc(crtc); + uint32_t xres = crtc->mode.hdisplay; + uint32_t yres = crtc->mode.vdisplay; + + /* + * Cursor Region Of Interest (ROI) is a plane read from cursor + * buffer to render. The ROI region is determined by the visibility of + * the cursor point. In the default Cursor image the cursor point will + * be at the top left of the cursor image, unless it is specified + * otherwise using hotspot feature. + * + * If the cursor point reaches the right (xres - x < cursor.width) or + * bottom (yres - y < cursor.height) boundary of the screen, then ROI + * width and ROI height need to be evaluated to crop the cursor image + * accordingly. + * (xres-x) will be new cursor width when x > (xres - cursor.width) + * (yres-y) will be new cursor height when y > (yres - cursor.height) + */ + *roi_w = min(mdp5_crtc->cursor.width, xres - + mdp5_crtc->cursor.x); + *roi_h = min(mdp5_crtc->cursor.height, yres - + mdp5_crtc->cursor.y); +} + static int mdp5_crtc_cursor_set(struct drm_crtc *crtc, struct drm_file *file, uint32_t handle, uint32_t width, uint32_t height) @@ -416,6 +450,7 @@ static int mdp5_crtc_cursor_set(struct drm_crtc *crtc, unsigned int depth; enum mdp5_cursor_alpha cur_alpha = CURSOR_ALPHA_PER_PIXEL; uint32_t flush_mask = mdp_ctl_flush_mask_cursor(0); + uint32_t roi_w, roi_h; unsigned long flags; if ((width > CURSOR_WIDTH) || (height > CURSOR_HEIGHT)) { @@ -446,6 +481,12 @@ static int mdp5_crtc_cursor_set(struct drm_crtc *crtc, spin_lock_irqsave(&mdp5_crtc->cursor.lock, flags); old_bo = mdp5_crtc->cursor.scanout_bo; + mdp5_crtc->cursor.scanout_bo = cursor_bo; + mdp5_crtc->cursor.width = width; + mdp5_crtc->cursor.height = height; + + get_roi(crtc, &roi_w, &roi_h); + mdp5_write(mdp5_kms, REG_MDP5_LM_CURSOR_STRIDE(lm), stride); mdp5_write(mdp5_kms, REG_MDP5_LM_CURSOR_FORMAT(lm), MDP5_LM_CURSOR_FORMAT_FORMAT(CURSOR_FMT_ARGB8888)); @@ -453,19 +494,14 @@ static int mdp5_crtc_cursor_set(struct drm_crtc *crtc, MDP5_LM_CURSOR_IMG_SIZE_SRC_H(height) | MDP5_LM_CURSOR_IMG_SIZE_SRC_W(width)); mdp5_write(mdp5_kms, REG_MDP5_LM_CURSOR_SIZE(lm), - MDP5_LM_CURSOR_SIZE_ROI_H(height) | - MDP5_LM_CURSOR_SIZE_ROI_W(width)); + MDP5_LM_CURSOR_SIZE_ROI_H(roi_h) | + MDP5_LM_CURSOR_SIZE_ROI_W(roi_w)); mdp5_write(mdp5_kms, REG_MDP5_LM_CURSOR_BASE_ADDR(lm), cursor_addr); - blendcfg = MDP5_LM_CURSOR_BLEND_CONFIG_BLEND_EN; - blendcfg |= MDP5_LM_CURSOR_BLEND_CONFIG_BLEND_TRANSP_EN; blendcfg |= MDP5_LM_CURSOR_BLEND_CONFIG_BLEND_ALPHA_SEL(cur_alpha); mdp5_write(mdp5_kms, REG_MDP5_LM_CURSOR_BLEND_CONFIG(lm), blendcfg); - mdp5_crtc->cursor.scanout_bo = cursor_bo; - mdp5_crtc->cursor.width = width; - mdp5_crtc->cursor.height = height; spin_unlock_irqrestore(&mdp5_crtc->cursor.lock, flags); ret = mdp5_ctl_set_cursor(mdp5_crtc->ctl, true); @@ -489,31 +525,18 @@ static int mdp5_crtc_cursor_move(struct drm_crtc *crtc, int x, int y) struct mdp5_kms *mdp5_kms = get_kms(crtc); struct mdp5_crtc *mdp5_crtc = to_mdp5_crtc(crtc); uint32_t flush_mask = mdp_ctl_flush_mask_cursor(0); - uint32_t xres = crtc->mode.hdisplay; - uint32_t yres = crtc->mode.vdisplay; uint32_t roi_w; uint32_t roi_h; unsigned long flags; - x = (x > 0) ? x : 0; - y = (y > 0) ? y : 0; + /* In case the CRTC is disabled, just drop the cursor update */ + if (unlikely(!crtc->state->enable)) + return 0; - /* - * Cursor Region Of Interest (ROI) is a plane read from cursor - * buffer to render. The ROI region is determined by the visiblity of - * the cursor point. In the default Cursor image the cursor point will - * be at the top left of the cursor image, unless it is specified - * otherwise using hotspot feature. - * - * If the cursor point reaches the right (xres - x < cursor.width) or - * bottom (yres - y < cursor.height) boundary of the screen, then ROI - * width and ROI height need to be evaluated to crop the cursor image - * accordingly. - * (xres-x) will be new cursor width when x > (xres - cursor.width) - * (yres-y) will be new cursor height when y > (yres - cursor.height) - */ - roi_w = min(mdp5_crtc->cursor.width, xres - x); - roi_h = min(mdp5_crtc->cursor.height, yres - y); + mdp5_crtc->cursor.x = x = max(x, 0); + mdp5_crtc->cursor.y = y = max(y, 0); + + get_roi(crtc, &roi_w, &roi_h); spin_lock_irqsave(&mdp5_crtc->cursor.lock, flags); mdp5_write(mdp5_kms, REG_MDP5_LM_CURSOR_SIZE(mdp5_crtc->lm), @@ -544,8 +567,8 @@ static const struct drm_crtc_funcs mdp5_crtc_funcs = { static const struct drm_crtc_helper_funcs mdp5_crtc_helper_funcs = { .mode_fixup = mdp5_crtc_mode_fixup, .mode_set_nofb = mdp5_crtc_mode_set_nofb, - .prepare = mdp5_crtc_disable, - .commit = mdp5_crtc_enable, + .disable = mdp5_crtc_disable, + .enable = mdp5_crtc_enable, .atomic_check = mdp5_crtc_atomic_check, .atomic_begin = mdp5_crtc_atomic_begin, .atomic_flush = mdp5_crtc_atomic_flush, diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_encoder.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_encoder.c index d6a14bb99988..af0e02fa4f48 100644 --- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_encoder.c +++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_encoder.c @@ -267,14 +267,14 @@ static void mdp5_encoder_enable(struct drm_encoder *encoder) mdp5_write(mdp5_kms, REG_MDP5_INTF_TIMING_ENGINE_EN(intf), 1); spin_unlock_irqrestore(&mdp5_encoder->intf_lock, flags); - mdp5_encoder->enabled = false; + mdp5_encoder->enabled = true; } static const struct drm_encoder_helper_funcs mdp5_encoder_helper_funcs = { .mode_fixup = mdp5_encoder_mode_fixup, .mode_set = mdp5_encoder_mode_set, - .prepare = mdp5_encoder_disable, - .commit = mdp5_encoder_enable, + .disable = mdp5_encoder_disable, + .enable = mdp5_encoder_enable, }; /* initialize encoder */ diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_irq.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_irq.c index 70ac81edd40f..a9407105b9b7 100644 --- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_irq.c +++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_irq.c @@ -34,7 +34,10 @@ static void mdp5_irq_error_handler(struct mdp_irq *irq, uint32_t irqstatus) void mdp5_irq_preinstall(struct msm_kms *kms) { struct mdp5_kms *mdp5_kms = to_mdp5_kms(to_mdp_kms(kms)); + mdp5_enable(mdp5_kms); mdp5_write(mdp5_kms, REG_MDP5_INTR_CLEAR, 0xffffffff); + mdp5_write(mdp5_kms, REG_MDP5_INTR_EN, 0x00000000); + mdp5_disable(mdp5_kms); } int mdp5_irq_postinstall(struct msm_kms *kms) @@ -57,7 +60,9 @@ int mdp5_irq_postinstall(struct msm_kms *kms) void mdp5_irq_uninstall(struct msm_kms *kms) { struct mdp5_kms *mdp5_kms = to_mdp5_kms(to_mdp_kms(kms)); + mdp5_enable(mdp5_kms); mdp5_write(mdp5_kms, REG_MDP5_INTR_EN, 0x00000000); + mdp5_disable(mdp5_kms); } static void mdp5_irq_mdp(struct mdp_kms *mdp_kms) diff --git a/drivers/gpu/drm/msm/msm_atomic.c b/drivers/gpu/drm/msm/msm_atomic.c index 871aa2108dc6..18fd643b6e69 100644 --- a/drivers/gpu/drm/msm/msm_atomic.c +++ b/drivers/gpu/drm/msm/msm_atomic.c @@ -219,8 +219,10 @@ int msm_atomic_commit(struct drm_device *dev, * mark our set of crtc's as busy: */ ret = start_atomic(dev->dev_private, c->crtc_mask); - if (ret) + if (ret) { + kfree(c); return ret; + } /* * This is the point of no return - everything below never fails except diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c index 79924e4b1b49..6751553abe4a 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c +++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c @@ -418,7 +418,7 @@ nouveau_fbcon_create(struct drm_fb_helper *helper, nouveau_fbcon_zfill(dev, fbcon); /* To allow resizeing without swapping buffers */ - NV_INFO(drm, "allocated %dx%d fb: 0x%lx, bo %p\n", + NV_INFO(drm, "allocated %dx%d fb: 0x%llx, bo %p\n", nouveau_fb->base.width, nouveau_fb->base.height, nvbo->bo.offset, nvbo); diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c index ed644a4f6f57..86807ee91bd1 100644 --- a/drivers/gpu/drm/radeon/atombios_crtc.c +++ b/drivers/gpu/drm/radeon/atombios_crtc.c @@ -1405,6 +1405,9 @@ static int dce4_crtc_do_set_base(struct drm_crtc *crtc, (x << 16) | y); viewport_w = crtc->mode.hdisplay; viewport_h = (crtc->mode.vdisplay + 1) & ~1; + if ((rdev->family >= CHIP_BONAIRE) && + (crtc->mode.flags & DRM_MODE_FLAG_INTERLACE)) + viewport_h *= 2; WREG32(EVERGREEN_VIEWPORT_SIZE + radeon_crtc->crtc_offset, (viewport_w << 16) | viewport_h); diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c index 5bf825dfaa09..8d74de82456e 100644 --- a/drivers/gpu/drm/radeon/atombios_dp.c +++ b/drivers/gpu/drm/radeon/atombios_dp.c @@ -178,6 +178,13 @@ radeon_dp_aux_transfer(struct drm_dp_aux *aux, struct drm_dp_aux_msg *msg) switch (msg->request & ~DP_AUX_I2C_MOT) { case DP_AUX_NATIVE_WRITE: case DP_AUX_I2C_WRITE: + /* The atom implementation only supports writes with a max payload of + * 12 bytes since it uses 4 bits for the total count (header + payload) + * in the parameter space. The atom interface supports 16 byte + * payloads for reads. The hw itself supports up to 16 bytes of payload. + */ + if (WARN_ON_ONCE(msg->size > 12)) + return -E2BIG; /* tx_size needs to be 4 even for bare address packets since the atom * table needs the info in tx_buf[3]. */ diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c index 7c9df1eac065..c39c1d0d9d4e 100644 --- a/drivers/gpu/drm/radeon/atombios_encoders.c +++ b/drivers/gpu/drm/radeon/atombios_encoders.c @@ -731,7 +731,9 @@ atombios_get_encoder_mode(struct drm_encoder *encoder) dig_connector = radeon_connector->con_priv; if ((dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_DISPLAYPORT) || (dig_connector->dp_sink_type == CONNECTOR_OBJECT_ID_eDP)) { - if (radeon_audio != 0 && ASIC_IS_DCE4(rdev) && !ASIC_IS_DCE5(rdev)) + if (radeon_audio != 0 && + drm_detect_monitor_audio(radeon_connector_edid(connector)) && + ASIC_IS_DCE4(rdev) && !ASIC_IS_DCE5(rdev)) return ATOM_ENCODER_MODE_DP_AUDIO; return ATOM_ENCODER_MODE_DP; } else if (radeon_audio != 0) { @@ -747,7 +749,9 @@ atombios_get_encoder_mode(struct drm_encoder *encoder) } break; case DRM_MODE_CONNECTOR_eDP: - if (radeon_audio != 0 && ASIC_IS_DCE4(rdev) && !ASIC_IS_DCE5(rdev)) + if (radeon_audio != 0 && + drm_detect_monitor_audio(radeon_connector_edid(connector)) && + ASIC_IS_DCE4(rdev) && !ASIC_IS_DCE5(rdev)) return ATOM_ENCODER_MODE_DP_AUDIO; return ATOM_ENCODER_MODE_DP; case DRM_MODE_CONNECTOR_DVIA: @@ -1622,7 +1626,6 @@ radeon_atom_encoder_dpms_dig(struct drm_encoder *encoder, int mode) struct radeon_connector *radeon_connector = NULL; struct radeon_connector_atom_dig *radeon_dig_connector = NULL; bool travis_quirk = false; - int encoder_mode; if (connector) { radeon_connector = to_radeon_connector(connector); @@ -1718,11 +1721,6 @@ radeon_atom_encoder_dpms_dig(struct drm_encoder *encoder, int mode) } break; } - - encoder_mode = atombios_get_encoder_mode(encoder); - if (radeon_audio != 0 && - (encoder_mode == ATOM_ENCODER_MODE_HDMI || ENCODER_MODE_IS_DP(encoder_mode))) - radeon_audio_dpms(encoder, mode); } static void @@ -1731,10 +1729,19 @@ radeon_atom_encoder_dpms(struct drm_encoder *encoder, int mode) struct drm_device *dev = encoder->dev; struct radeon_device *rdev = dev->dev_private; struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); + struct drm_connector *connector = radeon_get_connector_for_encoder(encoder); + int encoder_mode = atombios_get_encoder_mode(encoder); DRM_DEBUG_KMS("encoder dpms %d to mode %d, devices %08x, active_devices %08x\n", radeon_encoder->encoder_id, mode, radeon_encoder->devices, radeon_encoder->active_device); + + if (connector && (radeon_audio != 0) && + ((encoder_mode == ATOM_ENCODER_MODE_HDMI) || + (ENCODER_MODE_IS_DP(encoder_mode) && + drm_detect_monitor_audio(radeon_connector_edid(connector))))) + radeon_audio_dpms(encoder, mode); + switch (radeon_encoder->encoder_id) { case ENCODER_OBJECT_ID_INTERNAL_TMDS1: case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_TMDS1: @@ -2136,6 +2143,7 @@ radeon_atom_encoder_mode_set(struct drm_encoder *encoder, struct drm_device *dev = encoder->dev; struct radeon_device *rdev = dev->dev_private; struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); + struct drm_connector *connector = radeon_get_connector_for_encoder(encoder); int encoder_mode; radeon_encoder->pixel_clock = adjusted_mode->clock; @@ -2163,10 +2171,6 @@ radeon_atom_encoder_mode_set(struct drm_encoder *encoder, case ENCODER_OBJECT_ID_INTERNAL_UNIPHY3: case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_LVTMA: /* handled in dpms */ - encoder_mode = atombios_get_encoder_mode(encoder); - if (radeon_audio != 0 && - (encoder_mode == ATOM_ENCODER_MODE_HDMI || ENCODER_MODE_IS_DP(encoder_mode))) - radeon_audio_mode_set(encoder, adjusted_mode); break; case ENCODER_OBJECT_ID_INTERNAL_DDI: case ENCODER_OBJECT_ID_INTERNAL_DVO1: @@ -2188,6 +2192,13 @@ radeon_atom_encoder_mode_set(struct drm_encoder *encoder, } atombios_apply_encoder_quirks(encoder, adjusted_mode); + + encoder_mode = atombios_get_encoder_mode(encoder); + if (connector && (radeon_audio != 0) && + ((encoder_mode == ATOM_ENCODER_MODE_HDMI) || + (ENCODER_MODE_IS_DP(encoder_mode) && + drm_detect_monitor_audio(radeon_connector_edid(connector))))) + radeon_audio_mode_set(encoder, adjusted_mode); } static bool diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c index e6a4ba236c70..3e670d344a20 100644 --- a/drivers/gpu/drm/radeon/cik.c +++ b/drivers/gpu/drm/radeon/cik.c @@ -3613,6 +3613,8 @@ static void cik_gpu_init(struct radeon_device *rdev) } WREG32(GRBM_CNTL, GRBM_READ_TIMEOUT(0xff)); + WREG32(SRBM_INT_CNTL, 0x1); + WREG32(SRBM_INT_ACK, 0x1); WREG32(BIF_FB_EN, FB_READ_EN | FB_WRITE_EN); @@ -7230,6 +7232,8 @@ static void cik_disable_interrupt_state(struct radeon_device *rdev) WREG32(CP_ME2_PIPE3_INT_CNTL, 0); /* grbm */ WREG32(GRBM_INT_CNTL, 0); + /* SRBM */ + WREG32(SRBM_INT_CNTL, 0); /* vline/vblank, etc. */ WREG32(LB_INTERRUPT_MASK + EVERGREEN_CRTC0_REGISTER_OFFSET, 0); WREG32(LB_INTERRUPT_MASK + EVERGREEN_CRTC1_REGISTER_OFFSET, 0); @@ -7551,6 +7555,9 @@ int cik_irq_set(struct radeon_device *rdev) WREG32(DC_HPD5_INT_CONTROL, hpd5); WREG32(DC_HPD6_INT_CONTROL, hpd6); + /* posting read */ + RREG32(SRBM_STATUS); + return 0; } @@ -8046,6 +8053,10 @@ restart_ih: break; } break; + case 96: + DRM_ERROR("SRBM_READ_ERROR: 0x%x\n", RREG32(SRBM_READ_ERROR)); + WREG32(SRBM_INT_ACK, 0x1); + break; case 124: /* UVD */ DRM_DEBUG("IH: UVD int: 0x%08x\n", src_data); radeon_fence_process(rdev, R600_RING_TYPE_UVD_INDEX); diff --git a/drivers/gpu/drm/radeon/cikd.h b/drivers/gpu/drm/radeon/cikd.h index 03003f8a6de6..c648e1996dab 100644 --- a/drivers/gpu/drm/radeon/cikd.h +++ b/drivers/gpu/drm/radeon/cikd.h @@ -482,6 +482,10 @@ #define SOFT_RESET_ORB (1 << 23) #define SOFT_RESET_VCE (1 << 24) +#define SRBM_READ_ERROR 0xE98 +#define SRBM_INT_CNTL 0xEA0 +#define SRBM_INT_ACK 0xEA8 + #define VM_L2_CNTL 0x1400 #define ENABLE_L2_CACHE (1 << 0) #define ENABLE_L2_FRAGMENT_PROCESSING (1 << 1) diff --git a/drivers/gpu/drm/radeon/dce6_afmt.c b/drivers/gpu/drm/radeon/dce6_afmt.c index 192c80389151..3adc2afe32aa 100644 --- a/drivers/gpu/drm/radeon/dce6_afmt.c +++ b/drivers/gpu/drm/radeon/dce6_afmt.c @@ -26,6 +26,9 @@ #include "radeon_audio.h" #include "sid.h" +#define DCE8_DCCG_AUDIO_DTO1_PHASE 0x05b8 +#define DCE8_DCCG_AUDIO_DTO1_MODULE 0x05bc + u32 dce6_endpoint_rreg(struct radeon_device *rdev, u32 block_offset, u32 reg) { @@ -252,72 +255,67 @@ void dce6_audio_enable(struct radeon_device *rdev, void dce6_hdmi_audio_set_dto(struct radeon_device *rdev, struct radeon_crtc *crtc, unsigned int clock) { - /* Two dtos; generally use dto0 for HDMI */ + /* Two dtos; generally use dto0 for HDMI */ u32 value = 0; - if (crtc) + if (crtc) value |= DCCG_AUDIO_DTO0_SOURCE_SEL(crtc->crtc_id); WREG32(DCCG_AUDIO_DTO_SOURCE, value); - /* Express [24MHz / target pixel clock] as an exact rational - * number (coefficient of two integer numbers. DCCG_AUDIO_DTOx_PHASE - * is the numerator, DCCG_AUDIO_DTOx_MODULE is the denominator - */ - WREG32(DCCG_AUDIO_DTO0_PHASE, 24000); - WREG32(DCCG_AUDIO_DTO0_MODULE, clock); + /* Express [24MHz / target pixel clock] as an exact rational + * number (coefficient of two integer numbers. DCCG_AUDIO_DTOx_PHASE + * is the numerator, DCCG_AUDIO_DTOx_MODULE is the denominator + */ + WREG32(DCCG_AUDIO_DTO0_PHASE, 24000); + WREG32(DCCG_AUDIO_DTO0_MODULE, clock); } void dce6_dp_audio_set_dto(struct radeon_device *rdev, struct radeon_crtc *crtc, unsigned int clock) { - /* Two dtos; generally use dto1 for DP */ + /* Two dtos; generally use dto1 for DP */ u32 value = 0; value |= DCCG_AUDIO_DTO_SEL; - if (crtc) + if (crtc) value |= DCCG_AUDIO_DTO0_SOURCE_SEL(crtc->crtc_id); WREG32(DCCG_AUDIO_DTO_SOURCE, value); - /* Express [24MHz / target pixel clock] as an exact rational - * number (coefficient of two integer numbers. DCCG_AUDIO_DTOx_PHASE - * is the numerator, DCCG_AUDIO_DTOx_MODULE is the denominator - */ - WREG32(DCCG_AUDIO_DTO1_PHASE, 24000); - WREG32(DCCG_AUDIO_DTO1_MODULE, clock); + /* Express [24MHz / target pixel clock] as an exact rational + * number (coefficient of two integer numbers. DCCG_AUDIO_DTOx_PHASE + * is the numerator, DCCG_AUDIO_DTOx_MODULE is the denominator + */ + if (ASIC_IS_DCE8(rdev)) { + WREG32(DCE8_DCCG_AUDIO_DTO1_PHASE, 24000); + WREG32(DCE8_DCCG_AUDIO_DTO1_MODULE, clock); + } else { + WREG32(DCCG_AUDIO_DTO1_PHASE, 24000); + WREG32(DCCG_AUDIO_DTO1_MODULE, clock); + } } -void dce6_enable_dp_audio_packets(struct drm_encoder *encoder, bool enable) +void dce6_dp_enable(struct drm_encoder *encoder, bool enable) { struct drm_device *dev = encoder->dev; struct radeon_device *rdev = dev->dev_private; struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv; - uint32_t offset; if (!dig || !dig->afmt) return; - offset = dig->afmt->offset; - if (enable) { - if (dig->afmt->enabled) - return; - - WREG32(EVERGREEN_DP_SEC_TIMESTAMP + offset, EVERGREEN_DP_SEC_TIMESTAMP_MODE(1)); - WREG32(EVERGREEN_DP_SEC_CNTL + offset, - EVERGREEN_DP_SEC_ASP_ENABLE | /* Audio packet transmission */ - EVERGREEN_DP_SEC_ATP_ENABLE | /* Audio timestamp packet transmission */ - EVERGREEN_DP_SEC_AIP_ENABLE | /* Audio infoframe packet transmission */ - EVERGREEN_DP_SEC_STREAM_ENABLE); /* Master enable for secondary stream engine */ - radeon_audio_enable(rdev, dig->afmt->pin, true); + WREG32(EVERGREEN_DP_SEC_TIMESTAMP + dig->afmt->offset, + EVERGREEN_DP_SEC_TIMESTAMP_MODE(1)); + WREG32(EVERGREEN_DP_SEC_CNTL + dig->afmt->offset, + EVERGREEN_DP_SEC_ASP_ENABLE | /* Audio packet transmission */ + EVERGREEN_DP_SEC_ATP_ENABLE | /* Audio timestamp packet transmission */ + EVERGREEN_DP_SEC_AIP_ENABLE | /* Audio infoframe packet transmission */ + EVERGREEN_DP_SEC_STREAM_ENABLE); /* Master enable for secondary stream engine */ } else { - if (!dig->afmt->enabled) - return; - - WREG32(EVERGREEN_DP_SEC_CNTL + offset, 0); - radeon_audio_enable(rdev, dig->afmt->pin, false); + WREG32(EVERGREEN_DP_SEC_CNTL + dig->afmt->offset, 0); } dig->afmt->enabled = enable; diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c index 78600f534c80..973df064c14f 100644 --- a/drivers/gpu/drm/radeon/evergreen.c +++ b/drivers/gpu/drm/radeon/evergreen.c @@ -3253,6 +3253,8 @@ static void evergreen_gpu_init(struct radeon_device *rdev) } WREG32(GRBM_CNTL, GRBM_READ_TIMEOUT(0xff)); + WREG32(SRBM_INT_CNTL, 0x1); + WREG32(SRBM_INT_ACK, 0x1); evergreen_fix_pci_max_read_req_size(rdev); @@ -4324,6 +4326,7 @@ void evergreen_disable_interrupt_state(struct radeon_device *rdev) tmp = RREG32(DMA_CNTL) & ~TRAP_ENABLE; WREG32(DMA_CNTL, tmp); WREG32(GRBM_INT_CNTL, 0); + WREG32(SRBM_INT_CNTL, 0); WREG32(INT_MASK + EVERGREEN_CRTC0_REGISTER_OFFSET, 0); WREG32(INT_MASK + EVERGREEN_CRTC1_REGISTER_OFFSET, 0); if (rdev->num_crtc >= 4) { @@ -4590,6 +4593,9 @@ int evergreen_irq_set(struct radeon_device *rdev) WREG32(AFMT_AUDIO_PACKET_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET, afmt5); WREG32(AFMT_AUDIO_PACKET_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET, afmt6); + /* posting read */ + RREG32(SRBM_STATUS); + return 0; } @@ -5066,6 +5072,10 @@ restart_ih: DRM_ERROR("Unhandled interrupt: %d %d\n", src_id, src_data); break; } + case 96: + DRM_ERROR("SRBM_READ_ERROR: 0x%x\n", RREG32(SRBM_READ_ERROR)); + WREG32(SRBM_INT_ACK, 0x1); + break; case 124: /* UVD */ DRM_DEBUG("IH: UVD int: 0x%08x\n", src_data); radeon_fence_process(rdev, R600_RING_TYPE_UVD_INDEX); diff --git a/drivers/gpu/drm/radeon/evergreen_hdmi.c b/drivers/gpu/drm/radeon/evergreen_hdmi.c index 1d9aebc79595..c18d4ecbd95d 100644 --- a/drivers/gpu/drm/radeon/evergreen_hdmi.c +++ b/drivers/gpu/drm/radeon/evergreen_hdmi.c @@ -272,7 +272,7 @@ void dce4_hdmi_audio_set_dto(struct radeon_device *rdev, } void dce4_dp_audio_set_dto(struct radeon_device *rdev, - struct radeon_crtc *crtc, unsigned int clock) + struct radeon_crtc *crtc, unsigned int clock) { u32 value; @@ -294,7 +294,7 @@ void dce4_dp_audio_set_dto(struct radeon_device *rdev, * is the numerator, DCCG_AUDIO_DTOx_MODULE is the denominator */ WREG32(DCCG_AUDIO_DTO1_PHASE, 24000); - WREG32(DCCG_AUDIO_DTO1_MODULE, rdev->clock.max_pixel_clock * 10); + WREG32(DCCG_AUDIO_DTO1_MODULE, clock); } void dce4_set_vbi_packet(struct drm_encoder *encoder, u32 offset) @@ -350,20 +350,9 @@ void dce4_set_audio_packet(struct drm_encoder *encoder, u32 offset) struct drm_device *dev = encoder->dev; struct radeon_device *rdev = dev->dev_private; - WREG32(HDMI_INFOFRAME_CONTROL0 + offset, - HDMI_AUDIO_INFO_SEND | /* enable audio info frames (frames won't be set until audio is enabled) */ - HDMI_AUDIO_INFO_CONT); /* required for audio info values to be updated */ - WREG32(AFMT_INFOFRAME_CONTROL0 + offset, AFMT_AUDIO_INFO_UPDATE); /* required for audio info values to be updated */ - WREG32(HDMI_INFOFRAME_CONTROL1 + offset, - HDMI_AUDIO_INFO_LINE(2)); /* anything other than 0 */ - - WREG32(HDMI_AUDIO_PACKET_CONTROL + offset, - HDMI_AUDIO_DELAY_EN(1) | /* set the default audio delay */ - HDMI_AUDIO_PACKETS_PER_LINE(3)); /* should be suffient for all audio modes and small enough for all hblanks */ - WREG32(AFMT_60958_0 + offset, AFMT_60958_CS_CHANNEL_NUMBER_L(1)); @@ -408,15 +397,19 @@ void evergreen_hdmi_enable(struct drm_encoder *encoder, bool enable) if (!dig || !dig->afmt) return; - /* Silent, r600_hdmi_enable will raise WARN for us */ - if (enable && dig->afmt->enabled) - return; - if (!enable && !dig->afmt->enabled) - return; + if (enable) { + WREG32(HDMI_INFOFRAME_CONTROL1 + dig->afmt->offset, + HDMI_AUDIO_INFO_LINE(2)); /* anything other than 0 */ + + WREG32(HDMI_AUDIO_PACKET_CONTROL + dig->afmt->offset, + HDMI_AUDIO_DELAY_EN(1) | /* set the default audio delay */ + HDMI_AUDIO_PACKETS_PER_LINE(3)); /* should be suffient for all audio modes and small enough for all hblanks */ - if (!enable && dig->afmt->pin) { - radeon_audio_enable(rdev, dig->afmt->pin, 0); - dig->afmt->pin = NULL; + WREG32(HDMI_INFOFRAME_CONTROL0 + dig->afmt->offset, + HDMI_AUDIO_INFO_SEND | /* enable audio info frames (frames won't be set until audio is enabled) */ + HDMI_AUDIO_INFO_CONT); /* required for audio info values to be updated */ + } else { + WREG32(HDMI_INFOFRAME_CONTROL0 + dig->afmt->offset, 0); } dig->afmt->enabled = enable; @@ -425,33 +418,28 @@ void evergreen_hdmi_enable(struct drm_encoder *encoder, bool enable) enable ? "En" : "Dis", dig->afmt->offset, radeon_encoder->encoder_id); } -void evergreen_enable_dp_audio_packets(struct drm_encoder *encoder, bool enable) +void evergreen_dp_enable(struct drm_encoder *encoder, bool enable) { struct drm_device *dev = encoder->dev; struct radeon_device *rdev = dev->dev_private; struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv; - uint32_t offset; if (!dig || !dig->afmt) return; - offset = dig->afmt->offset; - if (enable) { struct drm_connector *connector = radeon_get_connector_for_encoder(encoder); struct radeon_connector *radeon_connector = to_radeon_connector(connector); struct radeon_connector_atom_dig *dig_connector; uint32_t val; - if (dig->afmt->enabled) - return; - - WREG32(EVERGREEN_DP_SEC_TIMESTAMP + offset, EVERGREEN_DP_SEC_TIMESTAMP_MODE(1)); + WREG32(EVERGREEN_DP_SEC_TIMESTAMP + dig->afmt->offset, + EVERGREEN_DP_SEC_TIMESTAMP_MODE(1)); if (radeon_connector->con_priv) { dig_connector = radeon_connector->con_priv; - val = RREG32(EVERGREEN_DP_SEC_AUD_N + offset); + val = RREG32(EVERGREEN_DP_SEC_AUD_N + dig->afmt->offset); val &= ~EVERGREEN_DP_SEC_N_BASE_MULTIPLE(0xf); if (dig_connector->dp_clock == 162000) @@ -459,21 +447,16 @@ void evergreen_enable_dp_audio_packets(struct drm_encoder *encoder, bool enable) else val |= EVERGREEN_DP_SEC_N_BASE_MULTIPLE(5); - WREG32(EVERGREEN_DP_SEC_AUD_N + offset, val); + WREG32(EVERGREEN_DP_SEC_AUD_N + dig->afmt->offset, val); } - WREG32(EVERGREEN_DP_SEC_CNTL + offset, + WREG32(EVERGREEN_DP_SEC_CNTL + dig->afmt->offset, EVERGREEN_DP_SEC_ASP_ENABLE | /* Audio packet transmission */ EVERGREEN_DP_SEC_ATP_ENABLE | /* Audio timestamp packet transmission */ EVERGREEN_DP_SEC_AIP_ENABLE | /* Audio infoframe packet transmission */ EVERGREEN_DP_SEC_STREAM_ENABLE); /* Master enable for secondary stream engine */ - radeon_audio_enable(rdev, dig->afmt->pin, 0xf); } else { - if (!dig->afmt->enabled) - return; - - WREG32(EVERGREEN_DP_SEC_CNTL + offset, 0); - radeon_audio_enable(rdev, dig->afmt->pin, 0); + WREG32(EVERGREEN_DP_SEC_CNTL + dig->afmt->offset, 0); } dig->afmt->enabled = enable; diff --git a/drivers/gpu/drm/radeon/evergreend.h b/drivers/gpu/drm/radeon/evergreend.h index ee83d2a88750..a8d1d5240fcb 100644 --- a/drivers/gpu/drm/radeon/evergreend.h +++ b/drivers/gpu/drm/radeon/evergreend.h @@ -1191,6 +1191,10 @@ #define SOFT_RESET_REGBB (1 << 22) #define SOFT_RESET_ORB (1 << 23) +#define SRBM_READ_ERROR 0xE98 +#define SRBM_INT_CNTL 0xEA0 +#define SRBM_INT_ACK 0xEA8 + /* display watermarks */ #define DC_LB_MEMORY_SPLIT 0x6b0c #define PRIORITY_A_CNT 0x6b18 diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c index 24242a7f0ac3..dab00812abaa 100644 --- a/drivers/gpu/drm/radeon/ni.c +++ b/drivers/gpu/drm/radeon/ni.c @@ -962,6 +962,8 @@ static void cayman_gpu_init(struct radeon_device *rdev) } WREG32(GRBM_CNTL, GRBM_READ_TIMEOUT(0xff)); + WREG32(SRBM_INT_CNTL, 0x1); + WREG32(SRBM_INT_ACK, 0x1); evergreen_fix_pci_max_read_req_size(rdev); @@ -1086,12 +1088,12 @@ static void cayman_gpu_init(struct radeon_device *rdev) if ((rdev->config.cayman.max_backends_per_se == 1) && (rdev->flags & RADEON_IS_IGP)) { - if ((disabled_rb_mask & 3) == 1) { - /* RB0 disabled, RB1 enabled */ - tmp = 0x11111111; - } else { + if ((disabled_rb_mask & 3) == 2) { /* RB1 disabled, RB0 enabled */ tmp = 0x00000000; + } else { + /* RB0 disabled, RB1 enabled */ + tmp = 0x11111111; } } else { tmp = gb_addr_config & NUM_PIPES_MASK; diff --git a/drivers/gpu/drm/radeon/nid.h b/drivers/gpu/drm/radeon/nid.h index ad7125486894..6b44580440d0 100644 --- a/drivers/gpu/drm/radeon/nid.h +++ b/drivers/gpu/drm/radeon/nid.h @@ -82,6 +82,10 @@ #define SOFT_RESET_REGBB (1 << 22) #define SOFT_RESET_ORB (1 << 23) +#define SRBM_READ_ERROR 0xE98 +#define SRBM_INT_CNTL 0xEA0 +#define SRBM_INT_ACK 0xEA8 + #define SRBM_STATUS2 0x0EC4 #define DMA_BUSY (1 << 5) #define DMA1_BUSY (1 << 6) diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c index 279801ca5110..04f2514f7564 100644 --- a/drivers/gpu/drm/radeon/r100.c +++ b/drivers/gpu/drm/radeon/r100.c @@ -728,6 +728,10 @@ int r100_irq_set(struct radeon_device *rdev) tmp |= RADEON_FP2_DETECT_MASK; } WREG32(RADEON_GEN_INT_CNTL, tmp); + + /* read back to post the write */ + RREG32(RADEON_GEN_INT_CNTL); + return 0; } diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c index 07a71a2488c9..2fcad344492f 100644 --- a/drivers/gpu/drm/radeon/r600.c +++ b/drivers/gpu/drm/radeon/r600.c @@ -3784,6 +3784,9 @@ int r600_irq_set(struct radeon_device *rdev) WREG32(RV770_CG_THERMAL_INT, thermal_int); } + /* posting read */ + RREG32(R_000E50_SRBM_STATUS); + return 0; } diff --git a/drivers/gpu/drm/radeon/r600_dpm.c b/drivers/gpu/drm/radeon/r600_dpm.c index 843b65f46ece..fa2154493cf1 100644 --- a/drivers/gpu/drm/radeon/r600_dpm.c +++ b/drivers/gpu/drm/radeon/r600_dpm.c @@ -188,7 +188,7 @@ u32 r600_dpm_get_vrefresh(struct radeon_device *rdev) list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { radeon_crtc = to_radeon_crtc(crtc); if (crtc->enabled && radeon_crtc->enabled && radeon_crtc->hw_mode.clock) { - vrefresh = radeon_crtc->hw_mode.vrefresh; + vrefresh = drm_mode_vrefresh(&radeon_crtc->hw_mode); break; } } diff --git a/drivers/gpu/drm/radeon/r600_hdmi.c b/drivers/gpu/drm/radeon/r600_hdmi.c index 62c91ed669ce..dd6606b8e23c 100644 --- a/drivers/gpu/drm/radeon/r600_hdmi.c +++ b/drivers/gpu/drm/radeon/r600_hdmi.c @@ -476,17 +476,6 @@ void r600_hdmi_enable(struct drm_encoder *encoder, bool enable) if (!dig || !dig->afmt) return; - /* Silent, r600_hdmi_enable will raise WARN for us */ - if (enable && dig->afmt->enabled) - return; - if (!enable && !dig->afmt->enabled) - return; - - if (!enable && dig->afmt->pin) { - radeon_audio_enable(rdev, dig->afmt->pin, 0); - dig->afmt->pin = NULL; - } - /* Older chipsets require setting HDMI and routing manually */ if (!ASIC_IS_DCE3(rdev)) { if (enable) diff --git a/drivers/gpu/drm/radeon/radeon_audio.c b/drivers/gpu/drm/radeon/radeon_audio.c index a3ceef6d9632..b21ef69a34ac 100644 --- a/drivers/gpu/drm/radeon/rad |