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 +1402,60 @@ int proc_pid_arch_status(struct seq_file *m, struct pid_namespace *ns,
return 0;
}
#endif /* CONFIG_PROC_PID_ARCH_STATUS */
+
+#ifdef CONFIG_IOMMU_SUPPORT
+void update_pasid(void)
+{
+ u64 pasid_state;
+ u32 pasid;
+
+ if (!cpu_feature_enabled(X86_FEATURE_ENQCMD))
+ return;
+
+ if (!current->mm)
+ return;
+
+ pasid = READ_ONCE(current->mm->pasid);
+ /* Set the valid bit in the PASID MSR/state only for valid pasid. */
+ pasid_state = pasid == PASID_DISABLED ?
+ pasid : pasid | MSR_IA32_PASID_VALID;
+
+ /*
+ * No need to hold fregs_lock() since the task's fpstate won't
+ * be changed by others (e.g. ptrace) while the task is being
+ * switched to or is in IPI.
+ */
+ if (!test_thread_flag(TIF_NEED_FPU_LOAD)) {
+ /* The MSR is active and can be directly updated. */
+ wrmsrl(MSR_IA32_PASID, pasid_state);
+ } else {
+ struct fpu *fpu = &current->thread.fpu;
+ struct ia32_pasid_state *ppasid_state;
+ struct xregs_state *xsave;
+
+ /*
+ * The CPU's xstate registers are not currently active. Just
+ * update the PASID state in the memory buffer here. The
+ * PASID MSR will be loaded when returning to user mode.
+ */
+ xsave = &fpu->state.xsave;
+ xsave->header.xfeatures |= XFEATURE_MASK_PASID;
+ ppasid_state = get_xsave_addr(xsave, XFEATURE_PASID);
+ /*
+ * Since XFEATURE_MASK_PASID is set in xfeatures, ppasid_state
+ * won't be NULL and no need to check its value.
+ *
+ * Only update the task's PASID state when it's different
+ * from the mm's pasid.
+ */
+ if (ppasid_state->pasid != pasid_state) {
+ /*
+ * Invalid fpregs so that state restoring will pick up
+ * the PASID state.
+ */
+ __fpu_invalidate_fpregs_state(fpu);
+ ppasid_state->pasid = pasid_state;
+ }
+ }
+}
+#endif /* CONFIG_IOMMU_SUPPORT */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index ffe149aafc39..dfef5a7e0f5a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -207,11 +207,11 @@ uint8_t amdgpu_amdkfd_get_xgmi_hops_count(struct kgd_dev *dst, struct kgd_dev *s
})
/* GPUVM API */
-int amdgpu_amdkfd_gpuvm_create_process_vm(struct kgd_dev *kgd, unsigned int pasid,
+int amdgpu_amdkfd_gpuvm_create_process_vm(struct kgd_dev *kgd, u32 pasid,
void **vm, void **process_info,
struct dma_fence **ef);
int amdgpu_amdkfd_gpuvm_acquire_process_vm(struct kgd_dev *kgd,
- struct file *filp, unsigned int pasid,
+ struct file *filp, u32 pasid,
void **vm, void **process_info,
struct dma_fence **ef);
void amdgpu_amdkfd_gpuvm_destroy_cb(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
index bf927f432506..ee531c3988d1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
@@ -105,7 +105,7 @@ static void kgd_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid,
unlock_srbm(kgd);
}
-static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid,
+static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, u32 pasid,
unsigned int vmid)
{
struct amdgpu_device *adev = get_amdgpu_device(kgd);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
index 744366c7ee85..4d41317b9292 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
@@ -139,7 +139,7 @@ static void kgd_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid,
unlock_srbm(kgd);
}
-static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid,
+static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, u32 pasid,
unsigned int vmid)
{
struct amdgpu_device *adev = get_amdgpu_device(kgd);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
index feab4cc6e836..35917d4b50f6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
@@ -96,7 +96,7 @@ static void kgd_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid,
unlock_srbm(kgd);
}
-static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid,
+static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, u32 pasid,
unsigned int vmid)
{
struct amdgpu_device *adev = get_amdgpu_device(kgd);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
index 1102de76d876..1abfe63c80fe 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
@@ -110,7 +110,7 @@ void kgd_gfx_v9_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid,
unlock_srbm(kgd);
}
-int kgd_gfx_v9_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid,
+int kgd_gfx_v9_set_pasid_vmid_mapping(struct kgd_dev *kgd, u32 pasid,
unsigned int vmid)
{
struct amdgpu_device *adev = get_amdgpu_device(kgd);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h
index aedf67d57449..ff2bc72e6646 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h
@@ -26,7 +26,7 @@ void kgd_gfx_v9_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid,
uint32_t sh_mem_config,
uint32_t sh_mem_ape1_base, uint32_t sh_mem_ape1_limit,
uint32_t sh_mem_bases);
-int kgd_gfx_v9_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid,
+int kgd_gfx_v9_set_pasid_vmid_mapping(struct kgd_dev *kgd, u32 pasid,
unsigned int vmid);
int kgd_gfx_v9_init_interrupts(struct kgd_dev *kgd, uint32_t pipe_id);
int kgd_gfx_v9_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index a58af513c952..d02c5c177a98 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -992,7 +992,7 @@ create_evict_fence_fail:
return ret;
}
-int amdgpu_amdkfd_gpuvm_create_process_vm(struct kgd_dev *kgd, unsigned int pasid,
+int amdgpu_amdkfd_gpuvm_create_process_vm(struct kgd_dev *kgd, u32 pasid,
void **vm, void **process_info,
struct dma_fence **ef)
{
@@ -1028,7 +1028,7 @@ amdgpu_vm_init_fail:
}
int amdgpu_amdkfd_gpuvm_acquire_process_vm(struct kgd_dev *kgd,
- struct file *filp, unsigned int pasid,
+ struct file *filp, u32 pasid,
void **vm, void **process_info,
struct dma_fence **ef)
{
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
index 7521f4ab55de..6e9a9e5dbea0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
@@ -43,7 +43,7 @@ static DEFINE_IDA(amdgpu_pasid_ida);
/* Helper to free pasid from a fence callback */
struct amdgpu_pasid_cb {
struct dma_fence_cb cb;
- unsigned int pasid;
+ u32 pasid;
};
/**
@@ -79,7 +79,7 @@ int amdgpu_pasid_alloc(unsigned int bits)
* amdgpu_pasid_free - Free a PASID
* @pasid: PASID to free
*/
-void amdgpu_pasid_free(unsigned int pasid)
+void amdgpu_pasid_free(u32 pasid)
{
trace_amdgpu_pasid_freed(pasid);
ida_simple_remove(&amdgpu_pasid_ida, pasid);
@@ -105,7 +105,7 @@ static void amdgpu_pasid_free_cb(struct dma_fence *fence,
* Free the pasid only after all the fences in resv are signaled.
*/
void amdgpu_pasid_free_delayed(struct dma_resv *resv,
- unsigned int pasid)
+ u32 pasid)
{
struct dma_fence *fence, **fences;
struct amdgpu_pasid_cb *cb;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h
index 8e58325bbca2..0c3b4fa1f936 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h
@@ -71,9 +71,9 @@ struct amdgpu_vmid_mgr {
};
int amdgpu_pasid_alloc(unsigned int bits);
-void amdgpu_pasid_free(unsigned int pasid);
+void amdgpu_pasid_free(u32 pasid);
void amdgpu_pasid_free_delayed(struct dma_resv *resv,
- unsigned int pasid);
+ u32 pasid);
bool amdgpu_vmid_had_gpu_reset(struct amdgpu_device *adev,
struct amdgpu_vmid *id);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 414548064648..b403b2a88ee5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -1084,7 +1084,7 @@ void amdgpu_driver_postclose_kms(struct drm_device *dev,
struct amdgpu_fpriv *fpriv = file_priv->driver_priv;
struct amdgpu_bo_list *list;
struct amdgpu_bo *pd;
- unsigned int pasid;
+ u32 pasid;
int handle;
if (!fpriv)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 71e005cf2952..cb1d7cddebc3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -2785,7 +2785,7 @@ long amdgpu_vm_wait_idle(struct amdgpu_vm *vm, long timeout)
* 0 for success, error for failure.
*/
int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
- int vm_context, unsigned int pasid)
+ int vm_context, u32 pasid)
{
struct amdgpu_bo_param bp;
struct amdgpu_bo *root;
@@ -2956,7 +2956,7 @@ static int amdgpu_vm_check_clean_reserved(struct amdgpu_device *adev,
* 0 for success, -errno for errors.
*/
int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm,
- unsigned int pasid)
+ u32 pasid)
{
bool pte_support_ats = (adev->asic_type == CHIP_RAVEN);
int r;
@@ -3254,7 +3254,7 @@ int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
* @pasid: PASID identifier for VM
* @task_info: task_info to fill.
*/
-void amdgpu_vm_get_task_info(struct amdgpu_device *adev, unsigned int pasid,
+void amdgpu_vm_get_task_info(struct amdgpu_device *adev, u32 pasid,
struct amdgpu_task_info *task_info)
{
struct amdgpu_vm *vm;
@@ -3298,7 +3298,7 @@ void amdgpu_vm_set_task_info(struct amdgpu_vm *vm)
* Try to gracefully handle a VM fault. Return true if the fault was handled and
* shouldn't be reported any more.
*/
-bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, unsigned int pasid,
+bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid,
uint64_t addr)
{
struct amdgpu_bo *root;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index 770025a5e500..ffbc0cc87ccf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -372,8 +372,8 @@ void amdgpu_vm_manager_fini(struct amdgpu_device *adev);
long amdgpu_vm_wait_idle(struct amdgpu_vm *vm, long timeout);
int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
- int vm_context, unsigned int pasid);
-int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm, unsigned int pasid);
+ int vm_context, u32 pasid);
+int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm, u32 pasid);
void amdgpu_vm_release_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm);
void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm);
void amdgpu_vm_get_pd_bo(struct amdgpu_vm *vm,
@@ -430,9 +430,9 @@ bool amdgpu_vm_need_pipeline_sync(struct amdgpu_ring *ring,
struct amdgpu_job *job);
void amdgpu_vm_check_compute_bug(struct amdgpu_device *adev);
-void amdgpu_vm_get_task_info(struct amdgpu_device *adev, unsigned int pasid,
+void amdgpu_vm_get_task_info(struct amdgpu_device *adev, u32 pasid,
struct amdgpu_task_info *task_info);
-bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, unsigned int pasid,
+bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid,
uint64_t addr);
void amdgpu_vm_set_task_info(struct amdgpu_vm *vm);
diff --git a/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c b/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c
index 24b471734117..dcb1d89d776e 100644
--- a/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c
+++ b/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c
@@ -91,7 +91,7 @@ static void cik_event_interrupt_wq(struct kfd_dev *dev,
(const struct cik_ih_ring_entry *)ih_ring_entry;
uint32_t context_id = ihre->data & 0xfffffff;
unsigned int vmid = (ihre->ring_id & 0x0000ff00) >> 8;
- unsigned int pasid = (ihre->ring_id & 0xffff0000) >> 16;
+ u32 pasid = (ihre->ring_id & 0xffff0000) >> 16;
if (pasid == 0)
return;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
index 27bcc5b472f6..b258a3dae767 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
@@ -45,7 +45,7 @@ static void dbgdev_address_watch_disable_nodiq(struct kfd_dev *dev)
}
static int dbgdev_diq_submit_ib(struct kfd_dbgdev *dbgdev,
- unsigned int pasid, uint64_t vmid0_address,
+ u32 pasid, uint64_t vmid0_address,
uint32_t *packet_buff, size_t size_in_bytes)
{
struct pm4__release_mem *rm_packet;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.h b/drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.h
index a04a1fe1d0d9..f9c6df1fdc5c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.h
@@ -275,7 +275,7 @@ struct kfd_dbgdev {
};
struct kfd_dbgmgr {
- unsigned int pasid;
+ u32 pasid;
struct kfd_dev *dev;
struct kfd_dbgdev *dbgdev;
};
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 0f4508b4903e..a8d316711625 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -40,7 +40,7 @@
#define CIK_HPD_EOP_BYTES (1U << CIK_HPD_EOP_BYTES_LOG2)
static int set_pasid_vmid_mapping(struct device_queue_manager *dqm,
- unsigned int pasid, unsigned int vmid);
+ u32 pasid, unsigned int vmid);
static int execute_queues_cpsch(struct device_queue_manager *dqm,
enum kfd_unmap_queues_filter filter,
@@ -948,7 +948,7 @@ out:
}
static int
-set_pasid_vmid_mapping(struct device_queue_manager *dqm, unsigned int pasid,
+set_pasid_vmid_mapping(struct device_queue_manager *dqm, u32 pasid,
unsigned int vmid)
{
return dqm->dev->kfd2kgd->set_pasid_vmid_mapping(
@@ -1981,8 +1981,7 @@ void device_queue_manager_uninit(struct device_queue_manager *dqm)
kfree(dqm);
}
-int kfd_process_vm_fault(struct device_queue_manager *dqm,
- unsigned int pasid)
+int kfd_process_vm_fault(struct device_queue_manager *dqm, u32 pasid)
{
struct kfd_process_device *pdd;
struct kfd_process *p = kfd_lookup_process_by_pasid(pasid);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
index a9583b95fcc1..ba2c2ce0c55a 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
@@ -460,7 +460,7 @@ static void set_event_from_interrupt(struct kfd_process *p,
}
}
-void kfd_signal_event_interrupt(unsigned int pasid, uint32_t partial_id,
+void kfd_signal_event_interrupt(u32 pasid, uint32_t partial_id,
uint32_t valid_id_bits)
{
struct kfd_event *ev = NULL;
@@ -872,7 +872,7 @@ static void lookup_events_by_type_and_signal(struct kfd_process *p,
}
#ifdef KFD_SUPPORT_IOMMU_V2
-void kfd_signal_iommu_event(struct kfd_dev *dev, unsigned int pasid,
+void kfd_signal_iommu_event(struct kfd_dev *dev, u32 pasid,
unsigned long address, bool is_write_requested,
bool is_execute_requested)
{
@@ -950,7 +950,7 @@ void kfd_signal_iommu_event(struct kfd_dev *dev, unsigned int pasid,
}
#endif /* KFD_SUPPORT_IOMMU_V2 */
-void kfd_signal_hw_exception_event(unsigned int pasid)
+void kfd_signal_hw_exception_event(u32 pasid)
{
/*
* Because we are called from arbitrary context (workqueue) as opposed
@@ -971,7 +971,7 @@ void kfd_signal_hw_exception_event(unsigned int pasid)
kfd_unref_process(p);
}
-void kfd_signal_vm_fault_event(struct kfd_dev *dev, unsigned int pasid,
+void kfd_signal_vm_fault_event(struct kfd_dev *dev, u32 pasid,
struct kfd_vm_fault_info *info)
{
struct kfd_event *ev;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.h b/drivers/gpu/drm/amd/amdkfd/kfd_events.h
index c7ac6c73af86..c8fe5dbdad55 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.h
@@ -79,7 +79,7 @@ struct kfd_event {
#define KFD_EVENT_TYPE_DEBUG 5
#define KFD_EVENT_TYPE_MEMORY 8
-extern void kfd_signal_event_interrupt(unsigned int pasid, uint32_t partial_id,
- uint32_t valid_id_bits);
+extern void kfd_signal_event_interrupt(u32 pasid, uint32_t partial_id,
+ uint32_t valid_id_bits);
#endif
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
index 7c8786b9eb0a..e8ef3886688b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
@@ -139,7 +139,7 @@ void kfd_iommu_unbind_process(struct kfd_process *p)
}
/* Callback for process shutdown invoked by the IOMMU driver */
-static void iommu_pasid_shutdown_callback(struct pci_dev *pdev, int pasid)
+static void iommu_pasid_shutdown_callback(struct pci_dev *pdev, u32 pasid)
{
struct kfd_dev *dev = kfd_device_by_pci_dev(pdev);
struct kfd_process *p;
@@ -185,8 +185,8 @@ static void iommu_pasid_shutdown_callback(struct pci_dev *pdev, int pasid)
}
/* This function called by IOMMU driver on PPR failure */
-static int iommu_invalid_ppr_cb(struct pci_dev *pdev, int pasid,
- unsigned long address, u16 flags)
+static int iommu_invalid_ppr_cb(struct pci_dev *pdev, u32 pasid,
+ unsigned long address, u16 flags)
{
struct kfd_dev *dev;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c b/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c
index 2a07c4f2cd0d..af5816f51e55 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c
@@ -51,7 +51,7 @@ unsigned int kfd_get_pasid_limit(void)
return 1U << pasid_bits;
}
-unsigned int kfd_pasid_alloc(void)
+u32 kfd_pasid_alloc(void)
{
int r = amdgpu_pasid_alloc(pasid_bits);
@@ -63,7 +63,7 @@ unsigned int kfd_pasid_alloc(void)
return 0;
}
-void kfd_pasid_free(unsigned int pasid)
+void kfd_pasid_free(u32 pasid)
{
amdgpu_pasid_free(pasid);
}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 6727e9de5b8b..922ae138ab85 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -723,7 +723,7 @@ struct kfd_process {
/* We want to receive a notification when the mm_struct is destroyed */
struct mmu_notifier mmu_notifier;
- uint16_t pasid;
+ u32 pasid;
unsigned int doorbell_index;
/*
@@ -800,7 +800,7 @@ int kfd_process_create_wq(void);
void kfd_process_destroy_wq(void);
struct kfd_process *kfd_create_process(struct file *filep);
struct kfd_process *kfd_get_process(const struct task_struct *);
-struct kfd_process *kfd_lookup_process_by_pasid(unsigned int pasid);
+struct kfd_process *kfd_lookup_process_by_pasid(u32 pasid);
struct kfd_process *kfd_lookup_process_by_mm(const struct mm_struct *mm);
void kfd_unref_process(struct kfd_process *p);
int kfd_process_evict_queues(struct kfd_process *p);
@@ -841,8 +841,8 @@ int kfd_pasid_init(void);
void kfd_pasid_exit(void);
bool kfd_set_pasid_limit(unsigned int new_limit);
unsigned int kfd_get_pasid_limit(void);
-unsigned int kfd_pasid_alloc(void);
-void kfd_pasid_free(unsigned int pasid);
+u32 kfd_pasid_alloc(void);
+void kfd_pasid_free(u32 pasid);
/* Doorbells */
size_t kfd_doorbell_process_slice(struct kfd_dev *kfd);
@@ -927,7 +927,7 @@ void device_queue_manager_uninit(struct device_queue_manager *dqm);
struct kernel_queue *kernel_queue_init(struct kfd_dev *dev,
enum kfd_queue_type type);
void kernel_queue_uninit(struct kernel_queue *kq, bool hanging);
-int kfd_process_vm_fault(struct device_queue_manager *dqm, unsigned int pasid);
+int kfd_process_vm_fault(struct device_queue_manager *dqm, u32 pasid);
/* Process Queue Manager */
struct process_queue_node {
@@ -1049,12 +1049,12 @@ int kfd_wait_on_events(struct kfd_process *p,
uint32_t num_events, void __user *data,
bool all, uint32_t user_timeout_ms,
uint32_t *wait_result);
-void kfd_signal_event_interrupt(unsigned int pasid, uint32_t partial_id,
+void kfd_signal_event_interrupt(u32 pasid, uint32_t partial_id,
uint32_t valid_id_bits);
void kfd_signal_iommu_event(struct kfd_dev *dev,
- unsigned int pasid, unsigned long address,
- bool is_write_requested, bool is_execute_requested);
-void kfd_signal_hw_exception_event(unsigned int pasid);
+ u32 pasid, unsigned long address,
+ bool is_write_requested, bool is_execute_requested);
+void kfd_signal_hw_exception_event(u32 pasid);
int kfd_set_event(struct kfd_process *p, uint32_t event_id);
int kfd_reset_event(struct kfd_process *p, uint32_t event_id);
int kfd_event_page_set(struct kfd_process *p, void *kernel_address,
@@ -1065,7 +1065,7 @@ int kfd_event_create(struct file *devkfd, struct kfd_process *p,
uint64_t *event_page_offset, uint32_t *event_slot_index);
int kfd_event_destroy(struct kfd_process *p, uint32_t event_id);
-void kfd_signal_vm_fault_event(struct kfd_dev *dev, unsigned int pasid,
+void kfd_signal_vm_fault_event(struct kfd_dev *dev, u32 pasid,
struct kfd_vm_fault_info *info);
void kfd_signal_reset_event(struct kfd_dev *dev);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 40695d52e9a8..627793029033 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -1306,7 +1306,7 @@ void kfd_process_device_remove_obj_handle(struct kfd_process_device *pdd,
}
/* This increments the process->ref counter. */
-struct kfd_process *kfd_lookup_process_by_pasid(unsigned int pasid)
+struct kfd_process *kfd_lookup_process_by_pasid(u32 pasid)
{
struct kfd_process *p, *ret_p = NULL;
unsigned int temp;
diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
index a3c238c39ef5..301de493377a 100644
--- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
@@ -226,7 +226,7 @@ struct kfd2kgd_calls {
uint32_t sh_mem_config, uint32_t sh_mem_ape1_base,
uint32_t sh_mem_ape1_limit, uint32_t sh_mem_bases);
- int (*set_pasid_vmid_mapping)(struct kgd_dev *kgd, unsigned int pasid,
+ int (*set_pasid_vmid_mapping)(struct kgd_dev *kgd, u32 pasid,
unsigned int vmid);
int (*init_interrupts)(struct kgd_dev *kgd, uint32_t pipe_id);
diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h
index 57309716fd18..030ee90197a1 100644
--- a/drivers/iommu/amd/amd_iommu.h
+++ b/drivers/iommu/amd/amd_iommu.h
@@ -45,12 +45,12 @@ extern int amd_iommu_register_ppr_notifier(struct notifier_block *nb);
extern int amd_iommu_unregister_ppr_notifier(struct notifier_block *nb);
extern void amd_iommu_domain_direct_map(struct iommu_domain *dom);
extern int amd_iommu_domain_enable_v2(struct iommu_domain *dom, int pasids);
-extern int amd_iommu_flush_page(struct iommu_domain *dom, int pasid,
+extern int amd_iommu_flush_page(struct iommu_domain *dom, u32 pasid,
u64 address);
-extern int amd_iommu_flush_tlb(struct iommu_domain *dom, int pasid);
-extern int amd_iommu_domain_set_gcr3(struct iommu_domain *dom, int pasid,
+extern int amd_iommu_flush_tlb(struct iommu_domain *dom, u32 pasid);
+extern int amd_iommu_domain_set_gcr3(struct iommu_domain *dom, u32 pasid,
unsigned long cr3);
-extern int amd_iommu_domain_clear_gcr3(struct iommu_domain *dom, int pasid);
+extern int amd_iommu_domain_clear_gcr3(struct iommu_domain *dom, u32 pasid);
extern struct iommu_domain *amd_iommu_get_v2_domain(struct pci_dev *pdev);
#ifdef CONFIG_IRQ_REMAP
@@ -66,7 +66,7 @@ static inline int amd_iommu_create_irq_domain(struct amd_iommu *iommu)
#define PPR_INVALID 0x1
#define PPR_FAILURE 0xf
-extern int amd_iommu_complete_ppr(struct pci_dev *pdev, int pasid,
+extern int amd_iommu_complete_ppr(struct pci_dev *pdev, u32 pasid,
int status, int tag);
static inline bool is_rd890_iommu(struct pci_dev *pdev)
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 10e4200d3552..d05943b5e7c7 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -513,10 +513,11 @@ static void amd_iommu_report_page_fault(u16 devid, u16 domain_id,
static void iommu_print_event(struct amd_iommu *iommu, void *__evt)
{
struct device *dev = iommu->iommu.dev;
- int type, devid, pasid, flags, tag;
+ int type, devid, flags, tag;
volatile u32 *event = __evt;
int count = 0;
u64 address;
+ u32 pasid;
retry:
type = (event[1] >> EVENT_TYPE_SHIFT) & EVENT_TYPE_MASK;
@@ -909,7 +910,7 @@ static void build_inv_iotlb_pages(struct iommu_cmd *cmd, u16 devid, int qdep,
cmd->data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK;
}
-static void build_inv_iommu_pasid(struct iommu_cmd *cmd, u16 domid, int pasid,
+static void build_inv_iommu_pasid(struct iommu_cmd *cmd, u16 domid, u32 pasid,
u64 address, bool size)
{
memset(cmd, 0, sizeof(*cmd));
@@ -927,7 +928,7 @@ static void build_inv_iommu_pasid(struct iommu_cmd *cmd, u16 domid, int pasid,
CMD_SET_TYPE(cmd, CMD_INV_IOMMU_PAGES);
}
-static void build_inv_iotlb_pasid(struct iommu_cmd *cmd, u16 devid, int pasid,
+static void build_inv_iotlb_pasid(struct iommu_cmd *cmd, u16 devid, u32 pasid,
int qdep, u64 address, bool size)
{
memset(cmd, 0, sizeof(*cmd));
@@ -947,7 +948,7 @@ static void build_inv_iotlb_pasid(struct iommu_cmd *cmd, u16 devid, int pasid,
CMD_SET_TYPE(cmd, CMD_INV_IOTLB_PAGES);
}
-static void build_complete_ppr(struct iommu_cmd *cmd, u16 devid, int pasid,
+static void build_complete_ppr(struct iommu_cmd *cmd, u16 devid, u32 pasid,
int status, int tag, bool gn)
{
memset(cmd, 0, sizeof(*cmd));
@@ -2786,7 +2787,7 @@ out:
}
EXPORT_SYMBOL(amd_iommu_domain_enable_v2);
-static int __flush_pasid(struct protection_domain *domain, int pasid,
+static int __flush_pasid(struct protection_domain *domain, u32 pasid,
u64 address, bool size)
{
struct iommu_dev_data *dev_data;
@@ -2847,13 +2848,13 @@ out:
return ret;
}
-static int __amd_iommu_flush_page(struct protection_domain *domain, int pasid,
+static int __amd_iommu_flush_page(struct protection_domain *domain, u32 pasid,
u64 address)
{
return __flush_pasid(domain, pasid, address, false);
}
-int amd_iommu_flush_page(struct iommu_domain *dom, int pasid,
+int amd_iommu_flush_page(struct iommu_domain *dom, u32 pasid,
u64 address)
{
struct protection_domain *domain = to_pdomain(dom);
@@ -2868,13 +2869,13 @@ int amd_iommu_flush_page(struct iommu_domain *dom, int pasid,
}
EXPORT_SYMBOL(amd_iommu_flush_page);
-static int __amd_iommu_flush_tlb(struct protection_domain *domain, int pasid)
+static int __amd_iommu_flush_tlb(struct protection_domain *domain, u32 pasid)
{
return __flush_pasid(domain, pasid, CMD_INV_IOMMU_ALL_PAGES_ADDRESS,
true);
}
-int amd_iommu_flush_tlb(struct iommu_domain *dom, int pasid)
+int amd_iommu_flush_tlb(struct iommu_domain *dom, u32 pasid)
{
struct protection_domain *domain = to_pdomain(dom);
unsigned long flags;
@@ -2888,7 +2889,7 @@ int amd_iommu_flush_tlb(struct iommu_domain *dom, int pasid)
}
EXPORT_SYMBOL(amd_iommu_flush_tlb);
-static u64 *__get_gcr3_pte(u64 *root, int level, int pasid, bool alloc)
+static u64 *__get_gcr3_pte(u64 *root, int level, u32 pasid, bool alloc)
{
int index;
u64 *pte;
@@ -2920,7 +2921,7 @@ static u64 *__get_gcr3_pte(u64 *root, int level, int pasid, bool alloc)
return pte;
}
-static int __set_gcr3(struct protection_domain *domain, int pasid,
+static int __set_gcr3(struct protection_domain *domain, u32 pasid,
unsigned long cr3)
{
struct domain_pgtable pgtable;
@@ -2939,7 +2940,7 @@ static int __set_gcr3(struct protection_domain *domain, int pasid,
return __amd_iommu_flush_tlb(domain, pasid);
}
-static int __clear_gcr3(struct protection_domain *domain, int pasid)
+static int __clear_gcr3(struct protection_domain *domain, u32 pasid)
{
struct domain_pgtable pgtable;
u64 *pte;
@@ -2957,7 +2958,7 @@ static int __clear_gcr3(struct protection_domain *domain, int pasid)
return __amd_iommu_flush_tlb(domain, pasid);
}
-int amd_iommu_domain_set_gcr3(struct iommu_domain *dom, int pasid,
+int amd_iommu_domain_set_gcr3(struct iommu_domain *dom, u32 pasid,
unsigned long cr3)
{
struct protection_domain *domain = to_pdomain(dom);
@@ -2972,7 +2973,7 @@ int amd_iommu_domain_set_gcr3(struct iommu_domain *dom, int pasid,
}
EXPORT_SYMBOL(amd_iommu_domain_set_gcr3);
-int amd_iommu_domain_clear_gcr3(struct iommu_domain *dom, int pasid)
+int amd_iommu_domain_clear_gcr3(struct iommu_domain *dom, u32 pasid)
{
struct protection_domain *domain = to_pdomain(dom);
unsigned long flags;
@@ -2986,7 +2987,7 @@ int amd_iommu_domain_clear_gcr3(struct iommu_domain *dom, int pasid)
}
EXPORT_SYMBOL(amd_iommu_domain_clear_gcr3);
-int amd_iommu_complete_ppr(struct pci_dev *pdev, int pasid,
+int amd_iommu_complete_ppr(struct pci_dev *pdev, u32 pasid,
int status, int tag)
{
struct iommu_dev_data *dev_data;
diff --git a/drivers/iommu/amd/iommu_v2.c b/drivers/iommu/amd/iommu_v2.c
index 0d175aed1d92..5ecc0bc608ec 100644
--- a/drivers/iommu/amd/iommu_v2.c
+++ b/drivers/iommu/amd/iommu_v2.c
@@ -40,7 +40,7 @@ struct pasid_state {
struct mmu_notifier mn; /* mmu_notifier handle */
struct pri_queue pri[PRI_QUEUE_SIZE]; /* PRI tag states */
struct device_state *device_state; /* Link to our device_state */
- int pasid; /* PASID index */
+ u32 pasid; /* PASID index */
bool invalid; /* Used during setup and
teardown of the pasid */
spinlock_t lock; /* Protect pri_queues and
@@ -70,7 +70,7 @@ struct fault {
struct mm_struct *mm;
u64 address;
u16 devid;
- u16 pasid;
+ u32 pasid;
u16 tag;
u16 finish;
u16 flags;
@@ -150,7 +150,7 @@ static void put_device_state(struct device_state *dev_state)
/* Must be called under dev_state->lock */
static struct pasid_state **__get_pasid_state_ptr(struct device_state *dev_state,
- int pasid, bool alloc)
+ u32 pasid, bool alloc)
{
struct pasid_state **root, **ptr;
int level, index;
@@ -184,7 +184,7 @@ static struct pasid_state **__get_pasid_state_ptr(struct device_state *dev_state
static int set_pasid_state(struct device_state *dev_state,
struct pasid_state *pasid_state,
- int pasid)
+ u32 pasid)
{
struct pasid_state **ptr;
unsigned long flags;
@@ -211,7 +211,7 @@ out_unlock:
return ret;
}
-static void clear_pasid_state(struct device_state *dev_state, int pasid)
+static void clear_pasid_state(struct device_state *dev_state, u32 pasid)
{
struct pasid_state **ptr;
unsigned long flags;
@@ -229,7 +229,7 @@ out_unlock:
}
static struct pasid_state *get_pasid_state(struct device_state *dev_state,
- int pasid)
+ u32 pasid)
{
struct pasid_state **ptr, *ret = NULL;
unsigned long flags;
@@ -594,7 +594,7 @@ static struct notifier_block ppr_nb = {
.notifier_call = ppr_notifier,
};
-int amd_iommu_bind_pasid(struct pci_dev *pdev, int pasid,
+int amd_iommu_bind_pasid(struct pci_dev *pdev, u32 pasid,
struct task_struct *task)
{
struct pasid_state *pasid_state;
@@ -615,7 +615,7 @@ int amd_iommu_bind_pasid(struct pci_dev *pdev, int pasid,
return -EINVAL;
ret = -EINVAL;
- if (pasid < 0 || pasid >= dev_state->max_pasids)
+ if (pasid >= dev_state->max_pasids)
goto out;
ret = -ENOMEM;
@@ -679,7 +679,7 @@ out:
}
EXPORT_SYMBOL(amd_iommu_bind_pasid);
-void amd_iommu_unbind_pasid(struct pci_dev *pdev, int pasid)
+void amd_iommu_unbind_pasid(struct pci_dev *pdev, u32 pasid)
{
struct pasid_state *pasid_state;
struct device_state *dev_state;
@@ -695,7 +695,7 @@ void amd_iommu_unbind_pasid(struct pci_dev *pdev, int pasid)
if (dev_state == NULL)
return;
- if (pasid < 0 || pasid >= dev_state->max_pasids)
+ if (pasid >= dev_state->max_pasids)
goto out;
pasid_state = get_pasid_state(dev_state, pasid);
diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c
index 93e6345f3414..e4cfa7355fc6 100644
--- a/drivers/iommu/intel/dmar.c
+++ b/drivers/iommu/intel/dmar.c
@@ -1482,7 +1482,7 @@ void qi_flush_dev_iotlb_pasid(struct intel_iommu *iommu, u16 sid, u16 pfsid,
}
void qi_flush_pasid_cache(struct intel_iommu *iommu, u16 did,
- u64 granu, int pasid)
+ u64 granu, u32 pasid)
{
struct qi_desc desc = {.qw1 = 0, .qw2 = 0, .qw3 = 0};
@@ -1796,7 +1796,7 @@ void dmar_msi_read(int irq, struct msi_msg *msg)
}
static int dmar_fault_do_one(struct intel_iommu *iommu, int type,
- u8 fault_reason, int pasid, u16 source_id,
+ u8 fault_reason, u32 pasid, u16 source_id,
unsigned long long addr)
{
const char *reason;
@@ -1846,7 +1846,8 @@ irqreturn_t dmar_fault(int irq, void *dev_id)
u8 fault_reason;
u16 source_id;
u64 guest_addr;
- int type, pasid;
+ u32 pasid;
+ int type;
u32 data;
bool pasid_present;
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 2239c211178b..342e42e9c977 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -2527,7 +2527,7 @@ dmar_search_domain_by_dev_info(int segment, int bus, int devfn)
static int domain_setup_first_level(struct intel_iommu *iommu,
struct dmar_domain *domain,
struct device *dev,
- int pasid)
+ u32 pasid)
{
int flags = PASID_FLAG_SUPERVISOR_MODE;
struct dma_pte *pgd = domain->pgd;
@@ -5173,7 +5173,7 @@ static int aux_domain_add_dev(struct dmar_domain *domain,
return -ENODEV;
if (domain->default_pasid <= 0) {
- int pasid;
+ u32 pasid;
/* No private data needed for the default pasid */
pasid = ioasid_alloc(NULL, PASID_MIN,
diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c
index e6faedf42fd4..b92af83b79bd 100644
--- a/drivers/iommu/intel/pasid.c
+++ b/drivers/iommu/intel/pasid.c
@@ -27,7 +27,7 @@
static DEFINE_SPINLOCK(pasid_lock);
u32 intel_pasid_max_id = PASID_MAX;
-int vcmd_alloc_pasid(struct intel_iommu *iommu, unsigned int *pasid)
+int vcmd_alloc_pasid(struct intel_iommu *iommu, u32 *pasid)
{
unsigned long flags;
u8 status_code;
@@ -58,7 +58,7 @@ int vcmd_alloc_pasid(struct intel_iommu *iommu, unsigned int *pasid)
return ret;
}
-void vcmd_free_pasid(struct intel_iommu *iommu, unsigned int pasid)
+void vcmd_free_pasid(struct intel_iommu *iommu, u32 pasid)
{
unsigned long flags;
u8 status_code;
@@ -146,7 +146,7 @@ int intel_pasid_alloc_table(struct device *dev)
struct pasid_table *pasid_table;
struct pasid_table_opaque data;
struct page *pages;
- int max_pasid = 0;
+ u32 max_pasid = 0;
int ret, order;
int size;
@@ -168,7 +168,7 @@ int intel_pasid_alloc_table(struct device *dev)
INIT_LIST_HEAD(&pasid_table->dev);
if (info->pasid_supported)
- max_pasid = min_t(int, pci_max_pasids(to_pci_dev(dev)),
+ max_pasid = min_t(u32, pci_max_pasids(to_pci_dev(dev)),
intel_pasid_max_id);
size = max_pasid >> (PASID_PDE_SHIFT - 3);
@@ -242,7 +242,7 @@ int intel_pasid_get_dev_max_id(struct device *dev)
return info->pasid_table->max_pasid;
}
-struct pasid_entry *intel_pasid_get_entry(struct device *dev, int pasid)
+struct pasid_entry *intel_pasid_get_entry(struct device *dev, u32 pasid)
{
struct device_domain_info *info;
struct pasid_table *pasid_table;
@@ -251,8 +251,7 @@ struct pasid_entry *intel_pasid_get_entry(struct device *dev, int pasid)
int dir_index, index;
pasid_table = intel_pasid_get_table(dev);
- if (WARN_ON(!pasid_table || pasid < 0 ||
- pasid >= intel_pasid_get_dev_max_id(dev)))
+ if (WARN_ON(!pasid_table || pasid >= intel_pasid_get_dev_max_id(dev)))
return NULL;
dir = pasid_table->table;
@@ -305,7 +304,7 @@ static inline void pasid_clear_entry_with_fpd(struct pasid_entry *pe)
}
static void
-intel_pasid_clear_entry(struct device *dev, int pasid, bool fault_ignore)
+intel_pasid_clear_entry(struct device *dev, u32 pasid, bool fault_ignore)
{
struct pasid_entry *pe;
@@ -444,7 +443,7 @@ pasid_set_eafe(struct pasid_entry *pe)
static void
pasid_cache_invalidation_with_pasid(struct intel_iommu *iommu,
- u16 did, int pasid)
+ u16 did, u32 pasid)
{
struct qi_desc desc;
@@ -473,7 +472,7 @@ iotlb_invalidation_with_pasid(struct intel_iommu *iommu, u16 did, u32 pasid)
static void
devtlb_invalidation_with_pasid(struct intel_iommu *iommu,
- struct device *dev, int pasid)
+ struct device *dev, u32 pasid)
{
struct device_domain_info *info;
u16 sid, qdep, pfsid;
@@ -499,7 +498,7 @@ devtlb_invalidation_with_pasid(struct intel_iommu *iommu,
}
void intel_pasid_tear_down_entry(struct intel_iommu *iommu, struct device *dev,
- int pasid, bool fault_ignore)
+ u32 pasid, bool fault_ignore)
{
struct pasid_entry *pte;
u16 did;
@@ -524,7 +523,7 @@ void intel_pasid_tear_down_entry(struct intel_iommu *iommu, struct device *dev,
static void pasid_flush_caches(struct intel_iommu *iommu,
struct pasid_entry *pte,
- int pasid, u16 did)
+ u32 pasid, u16 did)
{
if (!ecap_coherent(iommu->ecap))
clflush_cache_range(pte, sizeof(*pte));
@@ -543,7 +542,7 @@ static void pasid_flush_caches(struct intel_iommu *iommu,
*/
int intel_pasid_setup_first_level(struct intel_iommu *iommu,
struct device *dev, pgd_t *pgd,
- int pasid, u16 did, int flags)
+ u32 pasid, u16 did, int flags)
{
struct pasid_entry *pte;
@@ -616,7 +615,7 @@ static inline int iommu_skip_agaw(struct dmar_domain *domain,
*/
int intel_pasid_setup_second_level(struct intel_iommu *iommu,
struct dmar_domain *domain,
- struct device *dev, int pasid)
+ struct device *dev, u32 pasid)
{
struct pasid_entry *pte;
struct dma_pte *pgd;
@@ -674,7 +673,7 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu,
*/
int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
struct dmar_domain *domain,
- struct device *dev, int pasid)
+ struct device *dev, u32 pasid)
{
u16 did = FLPT_DEFAULT_DID;
struct pasid_entry *pte;
@@ -760,7 +759,7 @@ intel_pasid_setup_bind_data(struct intel_iommu *iommu, struct pasid_entry *pte,
* @addr_width: Address width of the first level (guest)
*/
int intel_pasid_setup_nested(struct intel_iommu *iommu, struct device *dev,
- pgd_t *gpgd, int pasid,
+ pgd_t *gpgd, u32 pasid,
struct iommu_gpasid_bind_data_vtd *pasid_data,
struct dmar_domain *domain, int addr_width)
{
diff --git a/drivers/iommu/intel/pasid.h b/drivers/iommu/intel/pasid.h
index c9850766c3a9..97dfcffbf495 100644
--- a/drivers/iommu/intel/pasid.h
+++ b/drivers/iommu/intel/pasid.h
@@ -72,7 +72,7 @@ struct pasid_entry {
struct pasid_table {
void *table; /* pasid table pointer */
int order; /* page order of pasid table */
- int max_pasid; /* max pasid */
+ u32 max_pasid; /* max pasid */
struct list_head dev; /* device list */
};
@@ -98,31 +98,31 @@ static inline bool pasid_pte_is_present(struct pasid_entry *pte)
return READ_ONCE(pte->val[0]) & PASID_PTE_PRESENT;
}
-extern u32 intel_pasid_max_id;
+extern unsigned int intel_pasid_max_id;
int intel_pasid_alloc_id(void *ptr, int start, int end, gfp_t gfp);
-void intel_pasid_free_id(int pasid);
-void *intel_pasid_lookup_id(int pasid);
+void intel_pasid_free_id(u32 pasid);
+void *intel_pasid_lookup_id(u32 pasid);
int intel_pasid_alloc_table(struct device *dev);
void intel_pasid_free_table(struct device *dev);
struct pasid_table *intel_pasid_get_table(struct device *dev);
int intel_pasid_get_dev_max_id(struct device *dev);
-struct pasid_entry *intel_pasid_get_entry(struct device *dev, int pasid);
+struct pasid_entry *intel_pasid_get_entry(struct device *dev, u32 pasid);
int intel_pasid_setup_first_level(struct intel_iommu *iommu,
struct device *dev, pgd_t *pgd,
- int pasid, u16 did, int flags);
+ u32 pasid, u16 did, int flags);
int intel_pasid_setup_second_level(struct intel_iommu *iommu,
struct dmar_domain *domain,
- struct device *dev, int pasid);
+ struct device *dev, u32 pasid);
int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
struct dmar_domain *domain,
- struct device *dev, int pasid);
+ struct device *dev, u32 pasid);
int intel_pasid_setup_nested(struct intel_iommu *iommu,
- struct device *dev, pgd_t *pgd, int pasid,
+ struct device *dev, pgd_t *pgd, u32 pasid,
struct iommu_gpasid_bind_data_vtd *pasid_data,
struct dmar_domain *domain, int addr_width);
void intel_pasid_tear_down_entry(struct intel_iommu *iommu,
- struct device *dev, int pasid,
+ struct device *dev, u32 pasid,
bool fault_ignore);
-int vcmd_alloc_pasid(struct intel_iommu *iommu, unsigned int *pasid);
-void vcmd_free_pasid(struct intel_iommu *iommu, unsigned int pasid);
+int vcmd_alloc_pasid(struct intel_iommu *iommu, u32 *pasid);
+void vcmd_free_pasid(struct intel_iommu *iommu, u32 pasid);
#endif /* __INTEL_PASID_H */
diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index 95c3164a2302..60ffe083b6d6 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -19,11 +19,12 @@
#include <linux/mm_types.h>
#include <linux/ioasid.h>
#include <asm/page.h>
+#include <asm/fpu/api.h>
#include "pasid.h"
static irqreturn_t prq_event_thread(int irq, void *d);
-static void intel_svm_drain_prq(struct device *dev, int pasid);
+static void intel_svm_drain_prq(struct device *dev, u32 pasid);
#define PRQ_ORDER 0
@@ -399,7 +400,7 @@ int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev,
return ret;
}
-int intel_svm_unbind_gpasid(struct device *dev, int pasid)
+int intel_svm_unbind_gpasid(struct device *dev, u32 pasid)
{
struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL);
struct intel_svm_dev *sdev;
@@ -444,9 +445,28 @@ out:
return ret;
}
+static void _load_pasid(void *unused)
+{
+ update_pasid();
+}
+
+static void load_pasid(struct mm_struct *mm, u32 pasid)
+{
+ mutex_lock(&mm->context.lock);
+
+ /* Synchronize with READ_ONCE in update_pasid(). */
+ smp_store_release(&mm->pasid, pasid);
+
+ /* Update PASID MSR on all CPUs running the mm's tasks. */
+ on_each_cpu_mask(mm_cpumask(mm), _load_pasid, NULL, true);
+
+ mutex_unlock(&mm->context.lock);
+}
+
/* Caller must hold pasid_mutex, mm reference */
static int
-intel_svm_bind_mm(struct device *dev, int flags, struct svm_dev_ops *ops,
+intel_svm_bind_mm(struct device *dev, unsigned int flags,
+ struct svm_dev_ops *ops,
struct mm_struct *mm, struct intel_svm_dev **sd)
{
struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL);
@@ -590,6 +610,10 @@ intel_svm_bind_mm(struct device *dev, int flags, struct svm_dev_ops *ops,
}
list_add_tail(&svm->list, &global_svm_list);
+ if (mm) {
+ /* The newly allocated pasid is loaded to the mm. */
+ load_pasid(mm, svm->pasid);
+ }
} else {
/*
* Binding a new device with existing PASID, need to setup
@@ -620,7 +644,7 @@ out:
}
/* Caller must hold pasid_mutex */
-static int intel_svm_unbind_mm(struct device *dev, int pasid)
+static int intel_svm_unbind_mm(struct device *dev, u32 pasid)
{
struct intel_svm_dev *sdev;
struct intel_iommu *iommu;
@@ -653,8 +677,11 @@ static int intel_svm_unbind_mm(struct device *dev, int pasid)
if (list_empty(&svm->devs)) {
ioasid_free(svm->pasid);
- if (svm->mm)
+ if (svm->mm) {
mmu_notifier_unregister(&svm->notifier, svm->mm);
+ /* Clear mm's pasid. */
+ load_pasid(svm->mm, PASID_DISABLED);
+ }
list_del(&svm->list);
/* We mandate that no page faults may be outstanding
* for the PASID when intel_svm_unbind_mm() is called.
@@ -739,7 +766,7 @@ static bool is_canonical_address(u64 addr)
* described in VT-d spec CH7.10 to drain all page requests and page
* responses pending in the hardware.
*/
-static void intel_svm_drain_prq(struct device *dev, int pasid)
+static void intel_svm_drain_prq(struct device *dev, u32 pasid)
{
struct device_domain_info *info;
struct dmar_domain *domain;
@@ -1033,7 +1060,7 @@ intel_svm_bind(struct device *dev, struct mm_struct *mm, void *drvdata)
{
struct iommu_sva *sva = ERR_PTR(-EINVAL);
struct intel_svm_dev *sdev = NULL;
- int flags = 0;
+ unsigned int flags = 0;
int ret;
/*
@@ -1042,7 +1069,7 @@ intel_svm_bind(struct device *dev, struct mm_struct *mm, void *drvdata)
* and intel_svm etc.
*/
if (drvdata)
- flags = *(int *)drvdata;
+ flags = *(unsigned int *)drvdata;
mutex_lock(&pasid_mutex);
ret = intel_svm_bind_mm(dev, flags, NULL, mm, &sdev);
if (ret)
@@ -1067,10 +1094,10 @@ void intel_svm_unbind(struct iommu_sva *sva)
mutex_unlock(&pasid_mutex);
}
-int intel_svm_get_pasid(struct iommu_sva *sva)
+u32 intel_svm_get_pasid(struct iommu_sva *sva)
{
struct intel_svm_dev *sdev;
- int pasid;
+ u32 pasid;
mutex_lock(&pasid_mutex);
sdev = to_intel_svm_dev(sva);
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 609bd25bf154..0e4fbdc0f5e5 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -2839,7 +2839,7 @@ void iommu_sva_unbind_device(struct iommu_sva *handle)
}
EXPORT_SYMBOL_GPL(iommu_sva_unbind_device);
-int iommu_sva_get_pasid(struct iommu_sva *handle)
+u32 iommu_sva_get_pasid(struct iommu_sva *handle)
{
const struct iommu_ops *ops = handle->dev->bus->iommu_ops;
diff --git a/drivers/misc/uacce/uacce.c b/drivers/misc/uacce/uacce.c
index a5b8dab80c76..4cb7a5b19467 100644
--- a/drivers/misc/uacce/uacce.c
+++ b/drivers/misc/uacce/uacce.c
@@ -93,7 +93,7 @@ static long uacce_fops_compat_ioctl(struct file *filep,
static int uacce_bind_queue(struct uacce_device *uacce, struct uacce_queue *q)
{
- int pasid;
+ u32 pasid;
struct iommu_sva *handle;
if (!(uacce->flags & UACCE_DEV_SVA))
diff --git a/include/linux/amd-iommu.h b/include/linux/amd-iommu.h
index 21e950e4ab62..450717299928 100644
--- a/include/linux/amd-iommu.h
+++ b/include/linux/amd-iommu.h
@@ -76,7 +76,7 @@ extern void amd_iommu_free_device(struct pci_dev *pdev);
*
* The function returns 0 on success or a negative value on error.
*/
-extern int amd_iommu_bind_pasid(struct pci_dev *pdev, int pasid,
+extern int amd_iommu_bind_pasid(struct pci_dev *pdev, u32 pasid,
struct task_struct *task);
/**
@@ -88,7 +88,7 @@ extern int amd_iommu_bind_pasid(struct pci_dev *pdev, int pasid,
* When this function returns the device is no longer using the PASID
* and the PASID is no longer bound to its task.
*/
-extern void amd_iommu_unbind_pasid(struct pci_dev *pdev, int pasid);
+extern void amd_iommu_unbind_pasid(struct pci_dev *pdev, u32 pasid);
/**
* amd_iommu_set_invalid_ppr_cb() - Register a call-back for failed
@@ -114,7 +114,7 @@ extern void amd_iommu_unbind_pasid(struct pci_dev *pdev, int pasid);
#define AMD_IOMMU_INV_PRI_RSP_FAIL 2
typedef int (*amd_iommu_invalid_ppr_cb)(struct pci_dev *pdev,
- int pasid,
+ u32 pasid,
unsigned long address,
u16);
@@ -166,7 +166,7 @@ extern int amd_iommu_device_info(struct pci_dev *pdev,
* @cb: The call-back function
*/
-typedef void (*amd_iommu_invalidate_ctx)(struct pci_dev *pdev, int pasid);
+typedef void (*amd_iommu_invalidate_ctx)(struct pci_dev *pdev, u32 pasid);
extern int amd_iommu_set_invalidate_ctx_cb(struct pci_dev *pdev,
amd_iommu_invalidate_ctx cb);
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index b1ed2f25f7c0..9c3e8337442a 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -549,7 +549,7 @@ struct dmar_domain {
2 == 1GiB, 3 == 512GiB, 4 == 1TiB */
u64 max_addr; /* maximum mapped address */
- int default_pasid; /*
+ u32 default_pasid; /*
* The default pasid used for non-SVM
* traffic on mediated devices.
*/
@@ -708,7 +708,7 @@ void qi_flush_dev_iotlb_pasid(struct intel_iommu *iommu, u16 sid, u16 pfsid,
u32 pasid, u16 qdep, u64 addr,
unsigned int size_order);
void qi_flush_pasid_cache(struct intel_iommu *iommu, u16 did, u64 granu,
- int pasid);
+ u32 pasid);
int qi_submit_sync(struct intel_iommu *iommu, struct qi_desc *desc,
unsigned int count, unsigned long options);
@@ -737,11 +737,11 @@ extern int intel_svm_enable_prq(struct intel_iommu *iommu);
extern int intel_svm_finish_prq(struct intel_iommu *iommu);
int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev,
struct iommu_gpasid_bind_data *data);
-int intel_svm_unbind_gpasid(struct device *dev, int pasid);
+int intel_svm_unbind_gpasid(struct device *dev, u32 pasid);
struct iommu_sva *intel_svm_bind(struct device *dev, struct mm_struct *mm,
void *drvdata);
void intel_svm_unbind(struct iommu_sva *handle);
-int intel_svm_get_pasid(struct iommu_sva *handle);
+u32 intel_svm_get_pasid(struct iommu_sva *handle);
int intel_svm_page_response(struct device *dev, struct iommu_fault_event *evt,
struct iommu_page_response *msg);
@@ -753,7 +753,7 @@ struct intel_svm_dev {
struct device *dev;
struct svm_dev_ops *ops;
struct iommu_sva sva;
- int pasid;
+ u32 pasid;
int users;
u16 did;
u16 dev_iotlb:1;
@@ -765,8 +765,8 @@ struct intel_svm {
struct mm_struct *mm;
struct intel_iommu *iommu;
- int flags;
- int pasid;
+ unsigned int flags;
+ u32 pasid;
int gpasid; /* In case that guest PASID is different from host PASID */
struct list_head devs;
struct list_head list;
diff --git a/include/linux/intel-svm.h b/include/linux/intel-svm.h
index c9e7e601950d..39d368a810b8 100644
--- a/include/linux/intel-svm.h
+++ b/include/linux/intel-svm.h
@@ -11,7 +11,7 @@
struct device;
struct svm_dev_ops {
- void (*fault_cb)(struct device *dev, int pasid, u64 address,
+ void (*fault_cb)(struct device *dev, u32 pasid, u64 address,
void *private, int rwxp, int response);
};
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index fee209efb756..e57e819aaf2e 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -286,7 +286,7 @@ struct iommu_ops {
struct iommu_sva *(*sva_bind)(struct device *dev, struct mm_struct *mm,
void *drvdata);
void (*sva_unbind)(struct iommu_sva *handle);
- int (*sva_get_pasid)(struct iommu_sva *handle);
+ u32 (*sva_get_pasid)(struct iommu_sva *handle);
int (*page_response)(struct device *dev,
struct iommu_fault_event *evt,
@@ -296,7 +296,7 @@ struct iommu_ops {
int (*sva_bind_gpasid)(struct iommu_domain *domain,
struct device *dev, struct iommu_gpasid_bind_data *data);
- int (*sva_unbind_gpasid)(struct device *dev, int pasid);
+ int (*sva_unbind_gpasid)(struct device *dev, u32 pasid);
int (*def_domain_type)(struct device *dev);
@@ -634,7 +634,7 @@ struct iommu_sva *iommu_sva_bind_device(struct device *dev,
struct mm_struct *mm,
void *drvdata);
void iommu_sva_unbind_device(struct iommu_sva *handle);
-int iommu_sva_get_pasid(struct iommu_sva *handle);
+u32 iommu_sva_get_pasid(struct iommu_sva *handle);
#else /* CONFIG_IOMMU_API */
@@ -1027,7 +1027,7 @@ static inline void iommu_sva_unbind_device(struct iommu_sva *handle)
{
}
-static inline int iommu_sva_get_pasid(struct iommu_sva *handle)
+static inline u32 iommu_sva_get_pasid(struct iommu_sva *handle)
{
return IOMMU_PASID_INVALID;
}
@@ -1046,7 +1046,7 @@ static inline int iommu_sva_bind_gpasid(struct iommu_domain *domain,
}
static inline int iommu_sva_unbind_gpasid(struct iommu_domain *domain,
- struct device *dev, int pasid)
+ struct device *dev, u32 pasid)
{
return -ENODEV;
}
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index ed028af3cb19..5a9238f6caad 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -552,6 +552,10 @@ struct mm_struct {
atomic_long_t hugetlb_usage;
#endif
struct work_struct async_put_work;
+
+#ifdef CONFIG_IOMMU_SUPPORT
+ u32 pasid;
+#endif
} __randomize_layout;
/*
diff --git a/include/linux/uacce.h b/include/linux/uacce.h
index 454c2f6672d7..48e319f40275 100644
--- a/include/linux/uacce.h
+++ b/include/linux/uacce.h
@@ -81,7 +81,7 @@ struct uacce_queue {
struct list_head list;
struct uacce_qfile_region *qfrs[UACCE_MAX_REGION];
enum uacce_q_state state;
- int pasid;
+ u32 pasid;
struct iommu_sva *handle;
};