delphix · prakashsurya · Sep 21, 2020 · Sep 21, 2020 · Sep 21, 2020 · Sep 21, 2020
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
@@ -225,14 +225,23 @@
 			For broken nForce2 BIOS resulting in XT-PIC timer.
 
 	acpi_sleep=	[HW,ACPI] Sleep options
-			Format: { s3_bios, s3_mode, s3_beep, s4_nohwsig,
-				  old_ordering, nonvs, sci_force_enable, nobl }
+			Format: { s3_bios, s3_mode, s3_beep, s4_hwsig,
+				  s4_nohwsig, old_ordering, nonvs,
+				  sci_force_enable, nobl }
 			See Documentation/power/video.rst for information on
 			s3_bios and s3_mode.
 			s3_beep is for debugging; it makes the PC's speaker beep
 			as soon as the kernel's real-mode entry point is called.
+			s4_hwsig causes the kernel to check the ACPI hardware
+			signature during resume from hibernation, and gracefully
+			refuse to resume if it has changed. This complies with
+			the ACPI specification but not with reality, since
+			Windows does not do this and many laptops do change it
+			on docking. So the default behaviour is to allow resume
+			and simply warn when the signature changes, unless the
+			s4_hwsig option is enabled.
 			s4_nohwsig prevents ACPI hardware signature from being
-			used during resume from hibernation.
+			used (or even warned about) during resume.
 			old_ordering causes the ACPI 1.0 ordering of the _PTS
 			control method, with respect to putting devices into
 			low power states, to be enforced (the ACPI 2.0 ordering
@@ -1843,13 +1852,13 @@
 
 	iommu.strict=	[ARM64] Configure TLB invalidation behaviour
 			Format: { "0" | "1" }
-			0 - Lazy mode.
+			0 - Lazy mode (default).
 			  Request that DMA unmap operations use deferred
 			  invalidation of hardware TLBs, for increased
 			  throughput at the cost of reduced device isolation.
 			  Will fall back to strict mode if not supported by
 			  the relevant IOMMU driver.
-			1 - Strict mode (default).
+			1 - Strict mode.
 			  DMA unmap operations invalidate IOMMU hardware TLBs
 			  synchronously.
 
@@ -3165,7 +3174,8 @@
 			disable unhandled interrupt sources.
 
 	no_timer_check	[X86,APIC] Disables the code which tests for
-			broken timer IRQ sources.
+			broken timer IRQ sources. For AWS, this is defaulted
+			to disabled, can be re-enabled using no_timer_check=0.
 
 	noisapnp	[ISAPNP] Disables ISA PnP code.
 
@@ -3191,9 +3201,9 @@
 			[X86,PV_OPS] Disable paravirtualized VMware scheduler
 			clock and use the default one.
 
-	no-steal-acc	[X86,KVM] Disable paravirtualized steal time accounting.
-			steal time is computed, but won't influence scheduler
-			behaviour
+	no-steal-acc	[X86,KVM,ARM64] Disable paravirtualized steal time
+			accounting. steal time is computed, but won't
+			influence scheduler behaviour
 
 	nolapic		[X86-32,APIC] Do not enable or use the local APIC.
 
@@ -5002,6 +5012,7 @@
 			as the stability checks done at bootup.	Used to enable
 			high-resolution timer mode on older hardware, and in
 			virtualized environment.
+			[x86] unreliable: mark tsc clocksource as unreliable.
 			[x86] noirqtime: Do not use TSC to do irq accounting.
 			Used to run time disable IRQ_TIME_ACCOUNTING on any
 			platforms where RDTSC is slow and this accounting

diff --git a/Documentation/ioctl/ioctl-number.rst b/Documentation/ioctl/ioctl-number.rst
@@ -326,8 +326,11 @@ Code  Seq#    Include File                                           Comments
 0xAC  00-1F  linux/raw.h
 0xAD  00                                                             Netfilter device in development:
                                                                      <mailto:rusty@rustcorp.com.au>
-0xAE  all    linux/kvm.h                                             Kernel-based Virtual Machine
+0xAE  00-1F  linux/kvm.h                                             Kernel-based Virtual Machine
                                                                      <mailto:kvm@vger.kernel.org>
+0xAE  40-FF  linux/kvm.h                                             Kernel-based Virtual Machine
+                                                                     <mailto:kvm@vger.kernel.org>
+0xAE  20-3F  linux/nitro_enclaves.h                                  Nitro Enclaves
 0xAF  00-1F  linux/fsl_hypervisor.h                                  Freescale hypervisor
 0xB0  all                                                            RATIO devices in development:
                                                                      <mailto:vgo@ratio.de>

diff --git a/Documentation/virt/index.rst b/Documentation/virt/index.rst
@@ -9,6 +9,7 @@ Linux Virtualization Support
 
    kvm/index
    paravirt_ops
+   ne_overview
 
 .. only:: html and subproject
 

diff --git a/Documentation/virt/kvm/arm/pvtime.rst b/Documentation/virt/kvm/arm/pvtime.rst
@@ -0,0 +1,80 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Paravirtualized time support for arm64
+======================================
+
+Arm specification DEN0057/A defines a standard for paravirtualised time
+support for AArch64 guests:
+
+https://developer.arm.com/docs/den0057/a
+
+KVM/arm64 implements the stolen time part of this specification by providing
+some hypervisor service calls to support a paravirtualized guest obtaining a
+view of the amount of time stolen from its execution.
+
+Two new SMCCC compatible hypercalls are defined:
+
+* PV_TIME_FEATURES: 0xC5000020
+* PV_TIME_ST:       0xC5000021
+
+These are only available in the SMC64/HVC64 calling convention as
+paravirtualized time is not available to 32 bit Arm guests. The existence of
+the PV_FEATURES hypercall should be probed using the SMCCC 1.1 ARCH_FEATURES
+mechanism before calling it.
+
+PV_TIME_FEATURES
+    ============= ========    ==========
+    Function ID:  (uint32)    0xC5000020
+    PV_call_id:   (uint32)    The function to query for support.
+                              Currently only PV_TIME_ST is supported.
+    Return value: (int64)     NOT_SUPPORTED (-1) or SUCCESS (0) if the relevant
+                              PV-time feature is supported by the hypervisor.
+    ============= ========    ==========
+
+PV_TIME_ST
+    ============= ========    ==========
+    Function ID:  (uint32)    0xC5000021
+    Return value: (int64)     IPA of the stolen time data structure for this
+                              VCPU. On failure:
+                              NOT_SUPPORTED (-1)
+    ============= ========    ==========
+
+The IPA returned by PV_TIME_ST should be mapped by the guest as normal memory
+with inner and outer write back caching attributes, in the inner shareable
+domain. A total of 16 bytes from the IPA returned are guaranteed to be
+meaningfully filled by the hypervisor (see structure below).
+
+PV_TIME_ST returns the structure for the calling VCPU.
+
+Stolen Time
+-----------
+
+The structure pointed to by the PV_TIME_ST hypercall is as follows:
+
++-------------+-------------+-------------+----------------------------+
+| Field       | Byte Length | Byte Offset | Description                |
++=============+=============+=============+============================+
+| Revision    |      4      |      0      | Must be 0 for version 1.0  |
++-------------+-------------+-------------+----------------------------+
+| Attributes  |      4      |      4      | Must be 0                  |
++-------------+-------------+-------------+----------------------------+
+| Stolen time |      8      |      8      | Stolen time in unsigned    |
+|             |             |             | nanoseconds indicating how |
+|             |             |             | much time this VCPU thread |
+|             |             |             | was involuntarily not      |
+|             |             |             | running on a physical CPU. |
++-------------+-------------+-------------+----------------------------+
+
+All values in the structure are stored little-endian.
+
+The structure will be updated by the hypervisor prior to scheduling a VCPU. It
+will be present within a reserved region of the normal memory given to the
+guest. The guest should not attempt to write into this memory. There is a
+structure per VCPU of the guest.
+
+It is advisable that one or more 64k pages are set aside for the purpose of
+these structures and not used for other purposes, this enables the guest to map
+the region using 64k pages and avoids conflicting attributes with other memory.
+
+For the user space interface see Documentation/virt/kvm/devices/vcpu.txt
+section "3. GROUP: KVM_ARM_VCPU_PVTIME_CTRL".
diff --git a/Documentation/virt/kvm/devices/vcpu.txt b/Documentation/virt/kvm/devices/vcpu.txt
@@ -60,3 +60,17 @@ time to use the number provided for a given timer, overwriting any previously
 configured values on other VCPUs.  Userspace should configure the interrupt
 numbers on at least one VCPU after creating all VCPUs and before running any
 VCPUs.
+
+3. GROUP: KVM_ARM_VCPU_PVTIME_CTRL
+Architectures: ARM64
+
+3.1 ATTRIBUTE: KVM_ARM_VCPU_PVTIME_IPA
+Parameters: 64-bit base address
+Returns: -ENXIO:  Stolen time not implemented
+         -EEXIST: Base address already set for this VCPU
+         -EINVAL: Base address not 64 byte aligned
+
+Specifies the base address of the stolen time structure for this VCPU. The
+base address must be 64 byte aligned and exist within a valid guest memory
+region. See Documentation/virt/kvm/arm/pvtime.txt for more information
+including the layout of the stolen time structure.
diff --git a/Documentation/virt/ne_overview.rst b/Documentation/virt/ne_overview.rst
@@ -0,0 +1,100 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==============
+Nitro Enclaves
+==============
+
+Overview
+========
+
+Nitro Enclaves (NE) is a new Amazon Elastic Compute Cloud (EC2) capability
+that allows customers to carve out isolated compute environments within EC2
+instances [1].
+
+For example, an application that processes sensitive data and runs in a VM,
+can be separated from other applications running in the same VM. This
+application then runs in a separate VM than the primary VM, namely an enclave.
+It runs alongside the VM that spawned it. This setup matches low latency
+applications needs.
+
+The current supported architectures for the NE kernel driver, available in the
+upstream Linux kernel, are x86 and ARM64.
+
+The resources that are allocated for the enclave, such as memory and CPUs, are
+carved out of the primary VM. Each enclave is mapped to a process running in the
+primary VM, that communicates with the NE kernel driver via an ioctl interface.
+
+In this sense, there are two components:
+
+1. An enclave abstraction process - a user space process running in the primary
+VM guest that uses the provided ioctl interface of the NE driver to spawn an
+enclave VM (that's 2 below).
+
+There is a NE emulated PCI device exposed to the primary VM. The driver for this
+new PCI device is included in the NE driver.
+
+The ioctl logic is mapped to PCI device commands e.g. the NE_START_ENCLAVE ioctl
+maps to an enclave start PCI command. The PCI device commands are then
+translated into  actions taken on the hypervisor side; that's the Nitro
+hypervisor running on the host where the primary VM is running. The Nitro
+hypervisor is based on core KVM technology.
+
+2. The enclave itself - a VM running on the same host as the primary VM that
+spawned it. Memory and CPUs are carved out of the primary VM and are dedicated
+for the enclave VM. An enclave does not have persistent storage attached.
+
+The memory regions carved out of the primary VM and given to an enclave need to
+be aligned 2 MiB / 1 GiB physically contiguous memory regions (or multiple of
+this size e.g. 8 MiB). The memory can be allocated e.g. by using hugetlbfs from
+user space [2][3][7]. The memory size for an enclave needs to be at least
+64 MiB. The enclave memory and CPUs need to be from the same NUMA node.
+
+An enclave runs on dedicated cores. CPU 0 and its CPU siblings need to remain
+available for the primary VM. A CPU pool has to be set for NE purposes by an
+user with admin capability. See the cpu list section from the kernel
+documentation [4] for how a CPU pool format looks.
+
+An enclave communicates with the primary VM via a local communication channel,
+using virtio-vsock [5]. The primary VM has virtio-pci vsock emulated device,
+while the enclave VM has a virtio-mmio vsock emulated device. The vsock device
+uses eventfd for signaling. The enclave VM sees the usual interfaces - local
+APIC and IOAPIC - to get interrupts from virtio-vsock device. The virtio-mmio
+device is placed in memory below the typical 4 GiB.
+
+The application that runs in the enclave needs to be packaged in an enclave
+image together with the OS ( e.g. kernel, ramdisk, init ) that will run in the
+enclave VM. The enclave VM has its own kernel and follows the standard Linux
+boot protocol [6][8].
+
+The kernel bzImage, the kernel command line, the ramdisk(s) are part of the
+Enclave Image Format (EIF); plus an EIF header including metadata such as magic
+number, eif version, image size and CRC.
+
+Hash values are computed for the entire enclave image (EIF), the kernel and
+ramdisk(s). That's used, for example, to check that the enclave image that is
+loaded in the enclave VM is the one that was intended to be run.
+
+These crypto measurements are included in a signed attestation document
+generated by the Nitro Hypervisor and further used to prove the identity of the
+enclave; KMS is an example of service that NE is integrated with and that checks
+the attestation doc.
+
+The enclave image (EIF) is loaded in the enclave memory at offset 8 MiB. The
+init process in the enclave connects to the vsock CID of the primary VM and a
+predefined port - 9000 - to send a heartbeat value - 0xb7. This mechanism is
+used to check in the primary VM that the enclave has booted. The CID of the
+primary VM is 3.
+
+If the enclave VM crashes or gracefully exits, an interrupt event is received by
+the NE driver. This event is sent further to the user space enclave process
+running in the primary VM via a poll notification mechanism. Then the user space
+enclave process can exit.
+
+[1] https://aws.amazon.com/ec2/nitro/nitro-enclaves/
+[2] https://www.kernel.org/doc/html/latest/admin-guide/mm/hugetlbpage.html
+[3] https://lwn.net/Articles/807108/
+[4] https://www.kernel.org/doc/html/latest/admin-guide/kernel-parameters.html
+[5] https://man7.org/linux/man-pages/man7/vsock.7.html
+[6] https://www.kernel.org/doc/html/latest/x86/boot.html
+[7] https://www.kernel.org/doc/html/latest/arm64/hugetlbpage.html
+[8] https://www.kernel.org/doc/html/latest/arm64/booting.html
diff --git a/MAINTAINERS b/MAINTAINERS
@@ -11569,6 +11569,19 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/lftan/nios2.git
 S:	Maintained
 F:	arch/nios2/
 
+NITRO ENCLAVES (NE)
+M:	Andra Paraschiv <andraprs@amazon.com>
+M:	Alexandru Vasile <lexnv@amazon.com>
+M:	Alexandru Ciobotaru <alcioa@amazon.com>
+L:	linux-kernel@vger.kernel.org
+S:	Supported
+W:	https://aws.amazon.com/ec2/nitro/nitro-enclaves/
+F:	Documentation/virt/ne_overview.rst
+F:	drivers/virt/nitro_enclaves/
+F:	include/linux/nitro_enclaves.h
+F:	include/uapi/linux/nitro_enclaves.h
+F:	samples/nitro_enclaves/
+
 NOHZ, DYNTICKS SUPPORT
 M:	Frederic Weisbecker <fweisbec@gmail.com>
 M:	Thomas Gleixner <tglx@linutronix.de>

diff --git a/Makefile b/Makefile
@@ -499,9 +499,6 @@ LINUXINCLUDE    := \
 		-I$(objtree)/include \
 		$(USERINCLUDE)
 
-# UBUNTU: Include our third party driver stuff too
-LINUXINCLUDE   += -Iubuntu/include $(if $(KBUILD_SRC),-I$(srctree)/ubuntu/include)
-
 KBUILD_AFLAGS   := -D__ASSEMBLY__ -fno-PIE
 KBUILD_CFLAGS   := -Wall -Wundef -Werror=strict-prototypes -Wno-trigraphs \
 		   -fno-strict-aliasing -fno-common -fshort-wchar -fno-PIE \
@@ -662,7 +659,7 @@ endif
 ifeq ($(KBUILD_EXTMOD),)
 # Objects we will link into vmlinux / subdirs we need to visit
 init-y		:= init/
-drivers-y	:= drivers/ sound/ ubuntu/
+drivers-y	:= drivers/ sound/
 drivers-$(CONFIG_SAMPLES) += samples/
 net-y		:= net/
 libs-y		:= lib/
@@ -1258,7 +1255,6 @@ headers: $(version_h) scripts_unifdef uapi-asm-generic archheaders archscripts
 	  $(error Headers not exportable for the $(SRCARCH) architecture))
 	$(Q)$(MAKE) $(hdr-inst)=include/uapi
 	$(Q)$(MAKE) $(hdr-inst)=arch/$(SRCARCH)/include/uapi
-	$(Q)$(MAKE) $(hdr-inst)=ubuntu/include dst=include oldheaders=
 
 # Deprecated. It is no-op now.
 PHONY += headers_check

diff --git a/Ubuntu.md b/Ubuntu.md
@@ -1,8 +1,8 @@
-Name:    linux
+Name:    linux-aws
 Version: 5.4.0
 Series:  20.04 (focal)
 Description:
     This is the source code for the Ubuntu linux kernel for the 20.04 series. This
-    source tree is used to produce the flavours: generic, generic-lpae, lowlatency.
+    source tree is used to produce the flavours: aws.
     This kernel is configured to support the widest range of desktop, laptop and
     server configurations.
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
@@ -7,6 +7,7 @@
 #ifndef __ARM_KVM_HOST_H__
 #define __ARM_KVM_HOST_H__
 
+#include <linux/arm-smccc.h>
 #include <linux/errno.h>
 #include <linux/types.h>
 #include <linux/kvm_types.h>
@@ -38,6 +39,7 @@
 	KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 #define KVM_REQ_IRQ_PENDING	KVM_ARCH_REQ(1)
 #define KVM_REQ_VCPU_RESET	KVM_ARCH_REQ(2)
+#define KVM_REQ_RECORD_STEAL	KVM_ARCH_REQ(3)
 
 DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
 
@@ -323,6 +325,29 @@ static inline int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 int kvm_perf_init(void);
 int kvm_perf_teardown(void);
 
+static inline long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu)
+{
+	return SMCCC_RET_NOT_SUPPORTED;
+}
+
+static inline gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu)
+{
+	return GPA_INVALID;
+}
+
+static inline void kvm_update_stolen_time(struct kvm_vcpu *vcpu)
+{
+}
+
+static inline void kvm_arm_pvtime_vcpu_init(struct kvm_vcpu_arch *vcpu_arch)
+{
+}
+
+static inline bool kvm_arm_is_pvtime_enabled(struct kvm_vcpu_arch *vcpu_arch)
+{
+	return false;
+}
+
 void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot);
 
 struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr);