summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--Documentation/x86/index.rst1
-rw-r--r--Documentation/x86/sva.rst257
-rw-r--r--arch/x86/include/asm/cpufeatures.h1
-rw-r--r--arch/x86/include/asm/disabled-features.h9
-rw-r--r--arch/x86/include/asm/fpu/api.h12
-rw-r--r--arch/x86/include/asm/fpu/internal.h7
-rw-r--r--arch/x86/include/asm/fpu/types.h11
-rw-r--r--arch/x86/include/asm/fpu/xstate.h2
-rw-r--r--arch/x86/include/asm/io.h17
-rw-r--r--arch/x86/include/asm/msr-index.h3
-rw-r--r--arch/x86/include/asm/special_insns.h64
-rw-r--r--arch/x86/kernel/cpu/cpuid-deps.c1
-rw-r--r--arch/x86/kernel/fpu/xstate.c63
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h4
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c4
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c6
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h4
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c8
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h8
-rw-r--r--drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c2
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c2
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.h2
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c7
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_events.c8
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_events.h4
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_iommu.c6
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_pasid.c4
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_priv.h20
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_process.c2
-rw-r--r--drivers/gpu/drm/amd/include/kgd_kfd_interface.h2
-rw-r--r--drivers/iommu/amd/amd_iommu.h10
-rw-r--r--drivers/iommu/amd/iommu.c31
-rw-r--r--drivers/iommu/amd/iommu_v2.c20
-rw-r--r--drivers/iommu/intel/dmar.c7
-rw-r--r--drivers/iommu/intel/iommu.c4
-rw-r--r--drivers/iommu/intel/pasid.c31
-rw-r--r--drivers/iommu/intel/pasid.h24
-rw-r--r--drivers/iommu/intel/svm.c47
-rw-r--r--drivers/iommu/iommu.c2
-rw-r--r--drivers/misc/uacce/uacce.c2
-rw-r--r--include/linux/amd-iommu.h8
-rw-r--r--include/linux/intel-iommu.h14
-rw-r--r--include/linux/intel-svm.h2
-rw-r--r--include/linux/iommu.h10
-rw-r--r--include/linux/mm_types.h4
-rw-r--r--include/linux/uacce.h2
52 files changed, 607 insertions, 164 deletions
diff --git a/Documentation/x86/index.rst b/Documentation/x86/index.rst
index 265d9e9a093b..e5d5ff096685 100644
--- a/Documentation/x86/index.rst
+++ b/Documentation/x86/index.rst
@@ -30,3 +30,4 @@ x86-specific Documentation
usb-legacy-support
i386/index
x86_64/index
+ sva
diff --git a/Documentation/x86/sva.rst b/Documentation/x86/sva.rst
new file mode 100644
index 000000000000..076efd51ef1f
--- /dev/null
+++ b/Documentation/x86/sva.rst
@@ -0,0 +1,257 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===========================================
+Shared Virtual Addressing (SVA) with ENQCMD
+===========================================
+
+Background
+==========
+
+Shared Virtual Addressing (SVA) allows the processor and device to use the
+same virtual addresses avoiding the need for software to translate virtual
+addresses to physical addresses. SVA is what PCIe calls Shared Virtual
+Memory (SVM).
+
+In addition to the convenience of using application virtual addresses
+by the device, it also doesn't require pinning pages for DMA.
+PCIe Address Translation Services (ATS) along with Page Request Interface
+(PRI) allow devices to function much the same way as the CPU handling
+application page-faults. For more information please refer to the PCIe
+specification Chapter 10: ATS Specification.
+
+Use of SVA requires IOMMU support in the platform. IOMMU is also
+required to support the PCIe features ATS and PRI. ATS allows devices
+to cache translations for virtual addresses. The IOMMU driver uses the
+mmu_notifier() support to keep the device TLB cache and the CPU cache in
+sync. When an ATS lookup fails for a virtual address, the device should
+use the PRI in order to request the virtual address to be paged into the
+CPU page tables. The device must use ATS again in order the fetch the
+translation before use.
+
+Shared Hardware Workqueues
+==========================
+
+Unlike Single Root I/O Virtualization (SR-IOV), Scalable IOV (SIOV) permits
+the use of Shared Work Queues (SWQ) by both applications and Virtual
+Machines (VM's). This allows better hardware utilization vs. hard
+partitioning resources that could result in under utilization. In order to
+allow the hardware to distinguish the context for which work is being
+executed in the hardware by SWQ interface, SIOV uses Process Address Space
+ID (PASID), which is a 20-bit number defined by the PCIe SIG.
+
+PASID value is encoded in all transactions from the device. This allows the
+IOMMU to track I/O on a per-PASID granularity in addition to using the PCIe
+Resource Identifier (RID) which is the Bus/Device/Function.
+
+
+ENQCMD
+======
+
+ENQCMD is a new instruction on Intel platforms that atomically submits a
+work descriptor to a device. The descriptor includes the operation to be
+performed, virtual addresses of all parameters, virtual address of a completion
+record, and the PASID (process address space ID) of the current process.
+
+ENQCMD works with non-posted semantics and carries a status back if the
+command was accepted by hardware. This allows the submitter to know if the
+submission needs to be retried or other device specific mechanisms to
+implement fairness or ensure forward progress should be provided.
+
+ENQCMD is the glue that ensures applications can directly submit commands
+to the hardware and also permits hardware to be aware of application context
+to perform I/O operations via use of PASID.
+
+Process Address Space Tagging
+=============================
+
+A new thread-scoped MSR (IA32_PASID) provides the connection between
+user processes and the rest of the hardware. When an application first
+accesses an SVA-capable device, this MSR is initialized with a newly
+allocated PASID. The driver for the device calls an IOMMU-specific API
+that sets up the routing for DMA and page-requests.
+
+For example, the Intel Data Streaming Accelerator (DSA) uses
+iommu_sva_bind_device(), which will do the following:
+
+- Allocate the PASID, and program the process page-table (%cr3 register) in the
+ PASID context entries.
+- Register for mmu_notifier() to track any page-table invalidations to keep
+ the device TLB in sync. For example, when a page-table entry is invalidated,
+ the IOMMU propagates the invalidation to the device TLB. This will force any
+ future access by the device to this virtual address to participate in
+ ATS. If the IOMMU responds with proper response that a page is not
+ present, the device would request the page to be paged in via the PCIe PRI
+ protocol before performing I/O.
+
+This MSR is managed with the XSAVE feature set as "supervisor state" to
+ensure the MSR is updated during context switch.
+
+PASID Management
+================
+
+The kernel must allocate a PASID on behalf of each process which will use
+ENQCMD and program it into the new MSR to communicate the process identity to
+platform hardware. ENQCMD uses the PASID stored in this MSR to tag requests
+from this process. When a user submits a work descriptor to a device using the
+ENQCMD instruction, the PASID field in the descriptor is auto-filled with the
+value from MSR_IA32_PASID. Requests for DMA from the device are also tagged
+with the same PASID. The platform IOMMU uses the PASID in the transaction to
+perform address translation. The IOMMU APIs setup the corresponding PASID
+entry in IOMMU with the process address used by the CPU (e.g. %cr3 register in
+x86).
+
+The MSR must be configured on each logical CPU before any application
+thread can interact with a device. Threads that belong to the same
+process share the same page tables, thus the same MSR value.
+
+PASID is cleared when a process is created. The PASID allocation and MSR
+programming may occur long after a process and its threads have been created.
+One thread must call iommu_sva_bind_device() to allocate the PASID for the
+process. If a thread uses ENQCMD without the MSR first being populated, a #GP
+will be raised. The kernel will update the PASID MSR with the PASID for all
+threads in the process. A single process PASID can be used simultaneously
+with multiple devices since they all share the same address space.
+
+One thread can call iommu_sva_unbind_device() to free the allocated PASID.
+The kernel will clear the PASID MSR for all threads belonging to the process.
+
+New threads inherit the MSR value from the parent.
+
+Relationships
+=============
+
+ * Each process has many threads, but only one PASID.
+ * Devices have a limited number (~10's to 1000's) of hardware workqueues.
+ The device driver manages allocating hardware workqueues.
+ * A single mmap() maps a single hardware workqueue as a "portal" and
+ each portal maps down to a single workqueue.
+ * For each device with which a process interacts, there must be
+ one or more mmap()'d portals.
+ * Many threads within a process can share a single portal to access
+ a single device.
+ * Multiple processes can separately mmap() the same portal, in
+ which case they still share one device hardware workqueue.
+ * The single process-wide PASID is used by all threads to interact
+ with all devices. There is not, for instance, a PASID for each
+ thread or each thread<->device pair.
+
+FAQ
+===
+
+* What is SVA/SVM?
+
+Shared Virtual Addressing (SVA) permits I/O hardware and the processor to
+work in the same address space, i.e., to share it. Some call it Shared
+Virtual Memory (SVM), but Linux community wanted to avoid confusing it with
+POSIX Shared Memory and Secure Virtual Machines which were terms already in
+circulation.
+
+* What is a PASID?
+
+A Process Address Space ID (PASID) is a PCIe-defined Transaction Layer Packet
+(TLP) prefix. A PASID is a 20-bit number allocated and managed by the OS.
+PASID is included in all transactions between the platform and the device.
+
+* How are shared workqueues different?
+
+Traditionally, in order for userspace applications to interact with hardware,
+there is a separate hardware instance required per process. For example,
+consider doorbells as a mechanism of informing hardware about work to process.
+Each doorbell is required to be spaced 4k (or page-size) apart for process
+isolation. This requires hardware to provision that space and reserve it in
+MMIO. This doesn't scale as the number of threads becomes quite large. The
+hardware also manages the queue depth for Shared Work Queues (SWQ), and
+consumers don't need to track queue depth. If there is no space to accept
+a command, the device will return an error indicating retry.
+
+A user should check Deferrable Memory Write (DMWr) capability on the device
+and only submits ENQCMD when the device supports it. In the new DMWr PCIe
+terminology, devices need to support DMWr completer capability. In addition,
+it requires all switch ports to support DMWr routing and must be enabled by
+the PCIe subsystem, much like how PCIe atomic operations are managed for
+instance.
+
+SWQ allows hardware to provision just a single address in the device. When
+used with ENQCMD to submit work, the device can distinguish the process
+submitting the work since it will include the PASID assigned to that
+process. This helps the device scale to a large number of processes.
+
+* Is this the same as a user space device driver?
+
+Communicating with the device via the shared workqueue is much simpler
+than a full blown user space driver. The kernel driver does all the
+initialization of the hardware. User space only needs to worry about
+submitting work and processing completions.
+
+* Is this the same as SR-IOV?
+
+Single Root I/O Virtualization (SR-IOV) focuses on providing independent
+hardware interfaces for virtualizing hardware. Hence, it's required to be
+almost fully functional interface to software supporting the traditional
+BARs, space for interrupts via MSI-X, its own register layout.
+Virtual Functions (VFs) are assisted by the Physical Function (PF)
+driver.
+
+Scalable I/O Virtualization builds on the PASID concept to create device
+instances for virtualization. SIOV requires host software to assist in
+creating virtual devices; each virtual device is represented by a PASID
+along with the bus/device/function of the device. This allows device
+hardware to optimize device resource creation and can grow dynamically on
+demand. SR-IOV creation and management is very static in nature. Consult
+references below for more details.
+
+* Why not just create a virtual function for each app?
+
+Creating PCIe SR-IOV type Virtual Functions (VF) is expensive. VFs require
+duplicated hardware for PCI config space and interrupts such as MSI-X.
+Resources such as interrupts have to be hard partitioned between VFs at
+creation time, and cannot scale dynamically on demand. The VFs are not
+completely independent from the Physical Function (PF). Most VFs require
+some communication and assistance from the PF driver. SIOV, in contrast,
+creates a software-defined device where all the configuration and control
+aspects are mediated via the slow path. The work submission and completion
+happen without any mediation.
+
+* Does this support virtualization?
+
+ENQCMD can be used from within a guest VM. In these cases, the VMM helps
+with setting up a translation table to translate from Guest PASID to Host
+PASID. Please consult the ENQCMD instruction set reference for more
+details.
+
+* Does memory need to be pinned?
+
+When devices support SVA along with platform hardware such as IOMMU
+supporting such devices, there is no need to pin memory for DMA purposes.
+Devices that support SVA also support other PCIe features that remove the
+pinning requirement for memory.
+
+Device TLB support - Device requests the IOMMU to lookup an address before
+use via Address Translation Service (ATS) requests. If the mapping exists
+but there is no page allocated by the OS, IOMMU hardware returns that no
+mapping exists.
+
+Device requests the virtual address to be mapped via Page Request
+Interface (PRI). Once the OS has successfully completed the mapping, it
+returns the response back to the device. The device requests again for
+a translation and continues.
+
+IOMMU works with the OS in managing consistency of page-tables with the
+device. When removing pages, it interacts with the device to remove any
+device TLB entry that might have been cached before removing the mappings from
+the OS.
+
+References
+==========
+
+VT-D:
+https://01.org/blogs/ashokraj/2018/recent-enhancements-intel-virtualization-technology-directed-i/o-intel-vt-d
+
+SIOV:
+https://01.org/blogs/2019/assignable-interfaces-intel-scalable-i/o-virtualization-linux
+
+ENQCMD in ISE:
+https://software.intel.com/sites/default/files/managed/c5/15/architecture-instruction-set-extensions-programming-reference.pdf
+
+DSA spec:
+https://software.intel.com/sites/default/files/341204-intel-data-streaming-accelerator-spec.pdf
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 50b2a8d85ef0..a48458b04e1e 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -353,6 +353,7 @@
#define X86_FEATURE_CLDEMOTE (16*32+25) /* CLDEMOTE instruction */
#define X86_FEATURE_MOVDIRI (16*32+27) /* MOVDIRI instruction */
#define X86_FEATURE_MOVDIR64B (16*32+28) /* MOVDIR64B instruction */
+#define X86_FEATURE_ENQCMD (16*32+29) /* ENQCMD and ENQCMDS instructions */
/* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */
#define X86_FEATURE_OVERFLOW_RECOV (17*32+ 0) /* MCA overflow recovery support */
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index 4ea8584682f9..5861d34f9771 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -56,6 +56,12 @@
# define DISABLE_PTI (1 << (X86_FEATURE_PTI & 31))
#endif
+#ifdef CONFIG_IOMMU_SUPPORT
+# define DISABLE_ENQCMD 0
+#else
+# define DISABLE_ENQCMD (1 << (X86_FEATURE_ENQCMD & 31))
+#endif
+
/*
* Make sure to add features to the correct mask
*/
@@ -75,7 +81,8 @@
#define DISABLED_MASK13 0
#define DISABLED_MASK14 0
#define DISABLED_MASK15 0
-#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP)
+#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP| \
+ DISABLE_ENQCMD)
#define DISABLED_MASK17 0
#define DISABLED_MASK18 0
#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19)
diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
index b774c52e5411..dcd9503b1098 100644
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -62,4 +62,16 @@ extern void switch_fpu_return(void);
*/
extern int cpu_has_xfeatures(u64 xfeatures_mask, const char **feature_name);
+/*
+ * Tasks that are not using SVA have mm->pasid set to zero to note that they
+ * will not have the valid bit set in MSR_IA32_PASID while they are running.
+ */
+#define PASID_DISABLED 0
+
+#ifdef CONFIG_IOMMU_SUPPORT
+/* Update current's PASID MSR/state by mm's PASID. */
+void update_pasid(void);
+#else
+static inline void update_pasid(void) { }
+#endif
#endif /* _ASM_X86_FPU_API_H */
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 21a8b5259477..eb1ed3bd8d96 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -583,6 +583,13 @@ static inline void switch_fpu_finish(struct fpu *new_fpu)
pkru_val = pk->pkru;
}
__write_pkru(pkru_val);
+
+ /*
+ * Expensive PASID MSR write will be avoided in update_pasid() because
+ * TIF_NEED_FPU_LOAD was set. And the PASID state won't be updated
+ * unless it's different from mm->pasid to reduce overhead.
+ */
+ update_pasid();
}
/*
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index c87364ea6446..f5a38a5f3ae1 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -114,7 +114,7 @@ enum xfeature {
XFEATURE_Hi16_ZMM,
XFEATURE_PT_UNIMPLEMENTED_SO_FAR,
XFEATURE_PKRU,
- XFEATURE_RSRVD_COMP_10,
+ XFEATURE_PASID,
XFEATURE_RSRVD_COMP_11,
XFEATURE_RSRVD_COMP_12,
XFEATURE_RSRVD_COMP_13,
@@ -134,6 +134,7 @@ enum xfeature {
#define XFEATURE_MASK_Hi16_ZMM (1 << XFEATURE_Hi16_ZMM)
#define XFEATURE_MASK_PT (1 << XFEATURE_PT_UNIMPLEMENTED_SO_FAR)
#define XFEATURE_MASK_PKRU (1 << XFEATURE_PKRU)
+#define XFEATURE_MASK_PASID (1 << XFEATURE_PASID)
#define XFEATURE_MASK_LBR (1 << XFEATURE_LBR)
#define XFEATURE_MASK_FPSSE (XFEATURE_MASK_FP | XFEATURE_MASK_SSE)
@@ -256,6 +257,14 @@ struct arch_lbr_state {
struct lbr_entry entries[];
} __packed;
+/*
+ * State component 10 is supervisor state used for context-switching the
+ * PASID state.
+ */
+struct ia32_pasid_state {
+ u64 pasid;
+} __packed;
+
struct xstate_header {
u64 xfeatures;
u64 xcomp_bv;
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index 14ab815132d4..47a92232d595 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -35,7 +35,7 @@
XFEATURE_MASK_BNDCSR)
/* All currently supported supervisor features */
-#define XFEATURE_MASK_SUPERVISOR_SUPPORTED (0)
+#define XFEATURE_MASK_SUPERVISOR_SUPPORTED (XFEATURE_MASK_PASID)
/*
* A supervisor state component may not always contain valuable information,
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index e1aa17a468a8..d726459d08e5 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -401,7 +401,7 @@ extern bool phys_mem_access_encrypted(unsigned long phys_addr,
/**
* iosubmit_cmds512 - copy data to single MMIO location, in 512-bit units
- * @__dst: destination, in MMIO space (must be 512-bit aligned)
+ * @dst: destination, in MMIO space (must be 512-bit aligned)
* @src: source
* @count: number of 512 bits quantities to submit
*
@@ -412,25 +412,14 @@ extern bool phys_mem_access_encrypted(unsigned long phys_addr,
* Warning: Do not use this helper unless your driver has checked that the CPU
* instruction is supported on the platform.
*/
-static inline void iosubmit_cmds512(void __iomem *__dst, const void *src,
+static inline void iosubmit_cmds512(void __iomem *dst, const void *src,
size_t count)
{
- /*
- * Note that this isn't an "on-stack copy", just definition of "dst"
- * as a pointer to 64-bytes of stuff that is going to be overwritten.
- * In the MOVDIR64B case that may be needed as you can use the
- * MOVDIR64B instruction to copy arbitrary memory around. This trick
- * lets the compiler know how much gets clobbered.
- */
- volatile struct { char _[64]; } *dst = __dst;
const u8 *from = src;
const u8 *end = from + count * 64;
while (from < end) {
- /* MOVDIR64B [rdx], rax */
- asm volatile(".byte 0x66, 0x0f, 0x38, 0xf8, 0x02"
- : "=m" (dst)
- : "d" (from), "a" (dst));
+ movdir64b(dst, from);
from += 64;
}
}
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 2859ee4f39a8..aaddc6a9e237 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -257,6 +257,9 @@
#define MSR_IA32_LASTINTFROMIP 0x000001dd
#define MSR_IA32_LASTINTTOIP 0x000001de
+#define MSR_IA32_PASID 0x00000d93
+#define MSR_IA32_PASID_VALID BIT_ULL(31)
+
/* DEBUGCTLMSR bits (others vary by model): */
#define DEBUGCTLMSR_LBR (1UL << 0) /* last branch recording */
#define DEBUGCTLMSR_BTF_SHIFT 1
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index 5999b0b3dd4a..94624fb06fac 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -240,6 +240,70 @@ static inline void serialize(void)
asm volatile(".byte 0xf, 0x1, 0xe8" ::: "memory");
}
+/* The dst parameter must be 64-bytes aligned */
+static inline void movdir64b(void *dst, const void *src)
+{
+ const struct { char _[64]; } *__src = src;
+ struct { char _[64]; } *__dst = dst;
+
+ /*
+ * MOVDIR64B %(rdx), rax.
+ *
+ * Both __src and __dst must be memory constraints in order to tell the
+ * compiler that no other memory accesses should be reordered around
+ * this one.
+ *
+ * Also, both must be supplied as lvalues because this tells
+ * the compiler what the object is (its size) the instruction accesses.
+ * I.e., not the pointers but what they point to, thus the deref'ing '*'.
+ */
+ asm volatile(".byte 0x66, 0x0f, 0x38, 0xf8, 0x02"
+ : "+m" (*__dst)
+ : "m" (*__src), "a" (__dst), "d" (__src));
+}
+
+/**
+ * enqcmds - Enqueue a command in supervisor (CPL0) mode
+ * @dst: destination, in MMIO space (must be 512-bit aligned)
+ * @src: 512 bits memory operand
+ *
+ * The ENQCMDS instruction allows software to write a 512-bit command to
+ * a 512-bit-aligned special MMIO region that supports the instruction.
+ * A return status is loaded into the ZF flag in the RFLAGS register.
+ * ZF = 0 equates to success, and ZF = 1 indicates retry or error.
+ *
+ * This function issues the ENQCMDS instruction to submit data from
+ * kernel space to MMIO space, in a unit of 512 bits. Order of data access
+ * is not guaranteed, nor is a memory barrier performed afterwards. It
+ * returns 0 on success and -EAGAIN on failure.
+ *
+ * Warning: Do not use this helper unless your driver has checked that the
+ * ENQCMDS instruction is supported on the platform and the device accepts
+ * ENQCMDS.
+ */
+static inline int enqcmds(void __iomem *dst, const void *src)
+{
+ const struct { char _[64]; } *__src = src;
+ struct { char _[64]; } *__dst = dst;
+ int zf;
+
+ /*
+ * ENQCMDS %(rdx), rax
+ *
+ * See movdir64b()'s comment on operand specification.
+ */
+ asm volatile(".byte 0xf3, 0x0f, 0x38, 0xf8, 0x02, 0x66, 0x90"
+ CC_SET(z)
+ : CC_OUT(z) (zf), "+m" (*__dst)
+ : "m" (*__src), "a" (__dst), "d" (__src));
+
+ /* Submission failure is indicated via EFLAGS.ZF=1 */
+ if (zf)
+ return -EAGAIN;
+
+ return 0;
+}
+
#endif /* __KERNEL__ */
#endif /* _ASM_X86_SPECIAL_INSNS_H */
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index 3cbe24ca80ab..3a02707c1f4d 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -69,6 +69,7 @@ static const struct cpuid_dep cpuid_deps[] = {
{ X86_FEATURE_CQM_MBM_TOTAL, X86_FEATURE_CQM_LLC },
{ X86_FEATURE_CQM_MBM_LOCAL, X86_FEATURE_CQM_LLC },
{ X86_FEATURE_AVX512_BF16, X86_FEATURE_AVX512VL },
+ { X86_FEATURE_ENQCMD, X86_FEATURE_XSAVES },
{}
};
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 038e19c0019e..5d8047441a0a 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -37,6 +37,7 @@ static const char *xfeature_names[] =
"AVX-512 ZMM_Hi256" ,
"Processor Trace (unused)" ,
"Protection Keys User registers",
+ "PASID state",
"unknown xstate feature" ,
};
@@ -51,6 +52,7 @@ static short xsave_cpuid_features[] __initdata = {
X86_FEATURE_AVX512F,
X86_FEATURE_INTEL_PT,
X86_FEATURE_PKU,
+ X86_FEATURE_ENQCMD,
};
/*
@@ -318,6 +320,7 @@ static void __init print_xstate_features(void)
print_xstate_feature(XFEATURE_MASK_ZMM_Hi256);
print_xstate_feature(XFEATURE_MASK_Hi16_ZMM);
print_xstate_feature(XFEATURE_MASK_PKRU);
+ print_xstate_feature(XFEATURE_MASK_PASID);
}
/*
@@ -592,6 +595,7 @@ static void check_xstate_against_struct(int nr)
XCHECK_SZ(sz, nr, XFEATURE_ZMM_Hi256, struct avx_512_zmm_uppers_state);
XCHECK_SZ(sz, nr, XFEATURE_Hi16_ZMM, struct avx_512_hi16_state);
XCHECK_SZ(sz, nr, XFEATURE_PKRU, struct pkru_state);
+ XCHECK_SZ(sz, nr, XFEATURE_PASID, struct ia32_pasid_state);
/*
* Make *SURE* to add any feature numbers in below if
@@ -601,7 +605,7 @@ static void check_xstate_against_struct(int nr)
if ((nr < XFEATURE_YMM) ||
(nr >= XFEATURE_MAX) ||
(nr == XFEATURE_PT_UNIMPLEMENTED_SO_FAR) ||
- ((nr >= XFEATURE_RSRVD_COMP_10) && (nr <= XFEATURE_LBR))) {
+ ((nr >= XFEATURE_RSRVD_COMP_11) && (nr <= XFEATURE_LBR))) {
WARN_ONCE(1, "no structure for xstate: %d\n", nr);
XSTATE_WARN_ON(1);
}
@@ -1398,3 +1