From 312e3f8aefb5dc9c2f052ba0ee35a2fd6baa5bcd Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Thu, 11 Mar 2021 09:30:54 +0000 Subject: thermal: Fix spelling mistake "disabed" -> "disabled" There is a spelling mistake in a comment, fix it. Signed-off-by: Colin Ian King Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20210311093054.5338-1-colin.king@canonical.com --- include/uapi/linux/thermal.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/thermal.h b/include/uapi/linux/thermal.h index c105054cbb57..9aa2fedfa309 100644 --- a/include/uapi/linux/thermal.h +++ b/include/uapi/linux/thermal.h @@ -60,7 +60,7 @@ enum thermal_genl_event { THERMAL_GENL_EVENT_UNSPEC, THERMAL_GENL_EVENT_TZ_CREATE, /* Thermal zone creation */ THERMAL_GENL_EVENT_TZ_DELETE, /* Thermal zone deletion */ - THERMAL_GENL_EVENT_TZ_DISABLE, /* Thermal zone disabed */ + THERMAL_GENL_EVENT_TZ_DISABLE, /* Thermal zone disabled */ THERMAL_GENL_EVENT_TZ_ENABLE, /* Thermal zone enabled */ THERMAL_GENL_EVENT_TZ_TRIP_UP, /* Trip point crossed the way up */ THERMAL_GENL_EVENT_TZ_TRIP_DOWN, /* Trip point crossed the way down */ -- cgit v1.2.3 From 3093c3c7c136458af692d5c3d309a66c3c12d9f4 Mon Sep 17 00:00:00 2001 From: Arnaud Pouliquen Date: Thu, 11 Mar 2021 15:04:09 +0100 Subject: rpmsg: Move RPMSG_ADDR_ANY in user API As the RPMSG_ADDR_ANY is a valid src or dst address that can be set by user applications, migrate its definition in user API. Reviewed-by: Bjorn Andersson Reviewed-by: Mathieu Poirier Signed-off-by: Arnaud Pouliquen Link: https://lore.kernel.org/r/20210311140413.31725-3-arnaud.pouliquen@foss.st.com Signed-off-by: Bjorn Andersson --- include/uapi/linux/rpmsg.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/rpmsg.h b/include/uapi/linux/rpmsg.h index e14c6dab4223..5e00748da319 100644 --- a/include/uapi/linux/rpmsg.h +++ b/include/uapi/linux/rpmsg.h @@ -9,6 +9,8 @@ #include #include +#define RPMSG_ADDR_ANY 0xFFFFFFFF + /** * struct rpmsg_endpoint_info - endpoint info representation * @name: name of service -- cgit v1.2.3 From 809328b40cfb152f75541aa3dcbbe4903098963b Mon Sep 17 00:00:00 2001 From: Arnaud Pouliquen Date: Thu, 11 Mar 2021 15:04:10 +0100 Subject: rpmsg: Add short description of the IOCTL defined in UAPI. Add a description of the IOCTLs and provide information on the default value of the source and destination addresses. Reviewed-by: Bjorn Andersson Reviewed-by: Mathieu Poirier Signed-off-by: Arnaud Pouliquen Link: https://lore.kernel.org/r/20210311140413.31725-4-arnaud.pouliquen@foss.st.com Signed-off-by: Bjorn Andersson --- include/uapi/linux/rpmsg.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/rpmsg.h b/include/uapi/linux/rpmsg.h index 5e00748da319..f5ca8740f3fb 100644 --- a/include/uapi/linux/rpmsg.h +++ b/include/uapi/linux/rpmsg.h @@ -14,8 +14,8 @@ /** * struct rpmsg_endpoint_info - endpoint info representation * @name: name of service - * @src: local address - * @dst: destination address + * @src: local address. To set to RPMSG_ADDR_ANY if not used. + * @dst: destination address. To set to RPMSG_ADDR_ANY if not used. */ struct rpmsg_endpoint_info { char name[32]; @@ -23,7 +23,14 @@ struct rpmsg_endpoint_info { __u32 dst; }; +/** + * Instantiate a new rmpsg char device endpoint. + */ #define RPMSG_CREATE_EPT_IOCTL _IOW(0xb5, 0x1, struct rpmsg_endpoint_info) + +/** + * Destroy a rpmsg char device endpoint created by the RPMSG_CREATE_EPT_IOCTL. + */ #define RPMSG_DESTROY_EPT_IOCTL _IO(0xb5, 0x2) #endif -- cgit v1.2.3 From d83e682e301071313e390e2f5ba2f6ca2ebc1848 Mon Sep 17 00:00:00 2001 From: Nick Kossifidis Date: Mon, 19 Apr 2021 03:55:35 +0300 Subject: RISC-V: Add EM_RISCV to kexec UAPI header Add RISC-V to the list of supported kexec architectures, we need to add the definition early-on so that later patches can use it. EM_RISCV is 243 as per ELF psABI specification here: https://github.com/riscv/riscv-elf-psabi-doc/blob/master/riscv-elf.md Signed-off-by: Nick Kossifidis Signed-off-by: Palmer Dabbelt --- include/uapi/linux/kexec.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kexec.h b/include/uapi/linux/kexec.h index 05669c87a0af..778dc191c265 100644 --- a/include/uapi/linux/kexec.h +++ b/include/uapi/linux/kexec.h @@ -42,6 +42,7 @@ #define KEXEC_ARCH_MIPS_LE (10 << 16) #define KEXEC_ARCH_MIPS ( 8 << 16) #define KEXEC_ARCH_AARCH64 (183 << 16) +#define KEXEC_ARCH_RISCV (243 << 16) /* The artificial cap on the number of segments passed to kexec_load. */ #define KEXEC_SEGMENT_MAX 16 -- cgit v1.2.3 From 94604548aa7163fa14b837149bb0cb708bc613bc Mon Sep 17 00:00:00 2001 From: Andrea Mayer Date: Tue, 27 Apr 2021 17:44:04 +0200 Subject: seg6: add counters support for SRv6 Behaviors This patch provides counters for SRv6 Behaviors as defined in [1], section 6. For each SRv6 Behavior instance, counters defined in [1] are: - the total number of packets that have been correctly processed; - the total amount of traffic in bytes of all packets that have been correctly processed; In addition, this patch introduces a new counter that counts the number of packets that have NOT been properly processed (i.e. errors) by an SRv6 Behavior instance. Counters are not only interesting for network monitoring purposes (i.e. counting the number of packets processed by a given behavior) but they also provide a simple tool for checking whether a behavior instance is working as we expect or not. Counters can be useful for troubleshooting misconfigured SRv6 networks. Indeed, an SRv6 Behavior can silently drop packets for very different reasons (i.e. wrong SID configuration, interfaces set with SID addresses, etc) without any notification/message to the user. Due to the nature of SRv6 networks, diagnostic tools such as ping and traceroute may be ineffective: paths used for reaching a given router can be totally different from the ones followed by probe packets. In addition, paths are often asymmetrical and this makes it even more difficult to keep up with the journey of the packets and to understand which behaviors are actually processing our traffic. When counters are enabled on an SRv6 Behavior instance, it is possible to verify if packets are actually processed by such behavior and what is the outcome of the processing. Therefore, the counters for SRv6 Behaviors offer an non-invasive observability point which can be leveraged for both traffic monitoring and troubleshooting purposes. [1] https://www.rfc-editor.org/rfc/rfc8986.html#name-counters Troubleshooting using SRv6 Behavior counters -------------------------------------------- Let's make a brief example to see how helpful counters can be for SRv6 networks. Let's consider a node where an SRv6 End Behavior receives an SRv6 packet whose Segment Left (SL) is equal to 0. In this case, the End Behavior (which accepts only packets with SL >= 1) discards the packet and increases the error counter. This information can be leveraged by the network operator for troubleshooting. Indeed, the error counter is telling the user that the packet: (i) arrived at the node; (ii) the packet has been taken into account by the SRv6 End behavior; (iii) but an error has occurred during the processing. The error (iii) could be caused by different reasons, such as wrong route settings on the node or due to an invalid SID List carried by the SRv6 packet. Anyway, the error counter is used to exclude that the packet did not arrive at the node or it has not been processed by the behavior at all. Turning on/off counters for SRv6 Behaviors ------------------------------------------ Each SRv6 Behavior instance can be configured, at the time of its creation, to make use of counters. This is done through iproute2 which allows the user to create an SRv6 Behavior instance specifying the optional "count" attribute as shown in the following example: $ ip -6 route add 2001:db8::1 encap seg6local action End count dev eth0 per-behavior counters can be shown by adding "-s" to the iproute2 command line, i.e.: $ ip -s -6 route show 2001:db8::1 2001:db8::1 encap seg6local action End packets 0 bytes 0 errors 0 dev eth0 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Impact of counters for SRv6 Behaviors on performance ==================================================== To determine the performance impact due to the introduction of counters in the SRv6 Behavior subsystem, we have carried out extensive tests. We chose to test the throughput achieved by the SRv6 End.DX2 Behavior because, among all the other behaviors implemented so far, it reaches the highest throughput which is around 1.5 Mpps (per core at 2.4 GHz on a Xeon(R) CPU E5-2630 v3) on kernel 5.12-rc2 using packets of size ~ 100 bytes. Three different tests were conducted in order to evaluate the overall throughput of the SRv6 End.DX2 Behavior in the following scenarios: 1) vanilla kernel (without the SRv6 Behavior counters patch) and a single instance of an SRv6 End.DX2 Behavior; 2) patched kernel with SRv6 Behavior counters and a single instance of an SRv6 End.DX2 Behavior with counters turned off; 3) patched kernel with SRv6 Behavior counters and a single instance of SRv6 End.DX2 Behavior with counters turned on. All tests were performed on a testbed deployed on the CloudLab facilities [2], a flexible infrastructure dedicated to scientific research on the future of Cloud Computing. Results of tests are shown in the following table: Scenario (1): average 1504764,81 pps (~1504,76 kpps); std. dev 3956,82 pps Scenario (2): average 1501469,78 pps (~1501,47 kpps); std. dev 2979,85 pps Scenario (3): average 1501315,13 pps (~1501,32 kpps); std. dev 2956,00 pps As can be observed, throughputs achieved in scenarios (2),(3) did not suffer any observable degradation compared to scenario (1). Thanks to Jakub Kicinski and David Ahern for their valuable suggestions and comments provided during the discussion of the proposed RFCs. [2] https://www.cloudlab.us Signed-off-by: Andrea Mayer Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/uapi/linux/seg6_local.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/seg6_local.h b/include/uapi/linux/seg6_local.h index 3b39ef1dbb46..5ae3ace84de0 100644 --- a/include/uapi/linux/seg6_local.h +++ b/include/uapi/linux/seg6_local.h @@ -27,6 +27,7 @@ enum { SEG6_LOCAL_OIF, SEG6_LOCAL_BPF, SEG6_LOCAL_VRFTABLE, + SEG6_LOCAL_COUNTERS, __SEG6_LOCAL_MAX, }; #define SEG6_LOCAL_MAX (__SEG6_LOCAL_MAX - 1) @@ -78,4 +79,33 @@ enum { #define SEG6_LOCAL_BPF_PROG_MAX (__SEG6_LOCAL_BPF_PROG_MAX - 1) +/* SRv6 Behavior counters are encoded as netlink attributes guaranteeing the + * correct alignment. + * Each counter is identified by a different attribute type (i.e. + * SEG6_LOCAL_CNT_PACKETS). + * + * - SEG6_LOCAL_CNT_PACKETS: identifies a counter that counts the number of + * packets that have been CORRECTLY processed by an SRv6 Behavior instance + * (i.e., packets that generate errors or are dropped are NOT counted). + * + * - SEG6_LOCAL_CNT_BYTES: identifies a counter that counts the total amount + * of traffic in bytes of all packets that have been CORRECTLY processed by + * an SRv6 Behavior instance (i.e., packets that generate errors or are + * dropped are NOT counted). + * + * - SEG6_LOCAL_CNT_ERRORS: identifies a counter that counts the number of + * packets that have NOT been properly processed by an SRv6 Behavior instance + * (i.e., packets that generate errors or are dropped). + */ +enum { + SEG6_LOCAL_CNT_UNSPEC, + SEG6_LOCAL_CNT_PAD, /* pad for 64 bits values */ + SEG6_LOCAL_CNT_PACKETS, + SEG6_LOCAL_CNT_BYTES, + SEG6_LOCAL_CNT_ERRORS, + __SEG6_LOCAL_CNT_MAX, +}; + +#define SEG6_LOCAL_CNT_MAX (__SEG6_LOCAL_CNT_MAX - 1) + #endif -- cgit v1.2.3 From c7d13358b6a2f49f81a34aa323a2d0878a0532a2 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 30 Apr 2021 14:00:13 +0200 Subject: netfilter: xt_SECMARK: add new revision to fix structure layout This extension breaks when trying to delete rules, add a new revision to fix this. Fixes: 5e6874cdb8de ("[SECMARK]: Add xtables SECMARK target") Signed-off-by: Phil Sutter Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/xt_SECMARK.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/xt_SECMARK.h b/include/uapi/linux/netfilter/xt_SECMARK.h index 1f2a708413f5..beb2cadba8a9 100644 --- a/include/uapi/linux/netfilter/xt_SECMARK.h +++ b/include/uapi/linux/netfilter/xt_SECMARK.h @@ -20,4 +20,10 @@ struct xt_secmark_target_info { char secctx[SECMARK_SECCTX_MAX]; }; +struct xt_secmark_target_info_v1 { + __u8 mode; + char secctx[SECMARK_SECCTX_MAX]; + __u32 secid; +}; + #endif /*_XT_SECMARK_H_target */ -- cgit v1.2.3 From 77b8aeb9da0490357f1f5a2b0d12125e6332c37a Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Tue, 4 May 2021 09:52:02 -0600 Subject: vfio/pci: Revert nvlink removal uAPI breakage Revert the uAPI changes from the below commit with notice that these regions and capabilities are no longer provided. Fixes: b392a1989170 ("vfio/pci: remove vfio_pci_nvlink2") Reported-by: Greg Kurz Signed-off-by: Alex Williamson Reviewed-by: Cornelia Huck Reviewed-by: Greg Kurz Tested-by: Greg Kurz Reviewed-by: Christoph Hellwig Message-Id: <162014341432.3807030.11054087109120670135.stgit@omen> --- include/uapi/linux/vfio.h | 46 ++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 42 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 34b1f53a3901..ef33ea002b0b 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -333,10 +333,21 @@ struct vfio_region_info_cap_type { #define VFIO_REGION_SUBTYPE_INTEL_IGD_LPC_CFG (3) /* 10de vendor PCI sub-types */ -/* subtype 1 was VFIO_REGION_SUBTYPE_NVIDIA_NVLINK2_RAM, don't use */ +/* + * NVIDIA GPU NVlink2 RAM is coherent RAM mapped onto the host address space. + * + * Deprecated, region no longer provided + */ +#define VFIO_REGION_SUBTYPE_NVIDIA_NVLINK2_RAM (1) /* 1014 vendor PCI sub-types */ -/* subtype 1 was VFIO_REGION_SUBTYPE_IBM_NVLINK2_ATSD, don't use */ +/* + * IBM NPU NVlink2 ATSD (Address Translation Shootdown) register of NPU + * to do TLB invalidation on a GPU. + * + * Deprecated, region no longer provided + */ +#define VFIO_REGION_SUBTYPE_IBM_NVLINK2_ATSD (1) /* sub-types for VFIO_REGION_TYPE_GFX */ #define VFIO_REGION_SUBTYPE_GFX_EDID (1) @@ -630,9 +641,36 @@ struct vfio_device_migration_info { */ #define VFIO_REGION_INFO_CAP_MSIX_MAPPABLE 3 -/* subtype 4 was VFIO_REGION_INFO_CAP_NVLINK2_SSATGT, don't use */ +/* + * Capability with compressed real address (aka SSA - small system address) + * where GPU RAM is mapped on a system bus. Used by a GPU for DMA routing + * and by the userspace to associate a NVLink bridge with a GPU. + * + * Deprecated, capability no longer provided + */ +#define VFIO_REGION_INFO_CAP_NVLINK2_SSATGT 4 + +struct vfio_region_info_cap_nvlink2_ssatgt { + struct vfio_info_cap_header header; + __u64 tgt; +}; -/* subtype 5 was VFIO_REGION_INFO_CAP_NVLINK2_LNKSPD, don't use */ +/* + * Capability with an NVLink link speed. The value is read by + * the NVlink2 bridge driver from the bridge's "ibm,nvlink-speed" + * property in the device tree. The value is fixed in the hardware + * and failing to provide the correct value results in the link + * not working with no indication from the driver why. + * + * Deprecated, capability no longer provided + */ +#define VFIO_REGION_INFO_CAP_NVLINK2_LNKSPD 5 + +struct vfio_region_info_cap_nvlink2_lnkspd { + struct vfio_info_cap_header header; + __u32 link_speed; + __u32 __pad; +}; /** * VFIO_DEVICE_GET_IRQ_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 9, -- cgit v1.2.3 From 7677f7fd8be76659cd2d0db8ff4093bbb51c20e5 Mon Sep 17 00:00:00 2001 From: Axel Rasmussen Date: Tue, 4 May 2021 18:35:36 -0700 Subject: userfaultfd: add minor fault registration mode Patch series "userfaultfd: add minor fault handling", v9. Overview ======== This series adds a new userfaultfd feature, UFFD_FEATURE_MINOR_HUGETLBFS. When enabled (via the UFFDIO_API ioctl), this feature means that any hugetlbfs VMAs registered with UFFDIO_REGISTER_MODE_MISSING will *also* get events for "minor" faults. By "minor" fault, I mean the following situation: Let there exist two mappings (i.e., VMAs) to the same page(s) (shared memory). One of the mappings is registered with userfaultfd (in minor mode), and the other is not. Via the non-UFFD mapping, the underlying pages have already been allocated & filled with some contents. The UFFD mapping has not yet been faulted in; when it is touched for the first time, this results in what I'm calling a "minor" fault. As a concrete example, when working with hugetlbfs, we have huge_pte_none(), but find_lock_page() finds an existing page. We also add a new ioctl to resolve such faults: UFFDIO_CONTINUE. The idea is, userspace resolves the fault by either a) doing nothing if the contents are already correct, or b) updating the underlying contents using the second, non-UFFD mapping (via memcpy/memset or similar, or something fancier like RDMA, or etc...). In either case, userspace issues UFFDIO_CONTINUE to tell the kernel "I have ensured the page contents are correct, carry on setting up the mapping". Use Case ======== Consider the use case of VM live migration (e.g. under QEMU/KVM): 1. While a VM is still running, we copy the contents of its memory to a target machine. The pages are populated on the target by writing to the non-UFFD mapping, using the setup described above. The VM is still running (and therefore its memory is likely changing), so this may be repeated several times, until we decide the target is "up to date enough". 2. We pause the VM on the source, and start executing on the target machine. During this gap, the VM's user(s) will *see* a pause, so it is desirable to minimize this window. 3. Between the last time any page was copied from the source to the target, and when the VM was paused, the contents of that page may have changed - and therefore the copy we have on the target machine is out of date. Although we can keep track of which pages are out of date, for VMs with large amounts of memory, it is "slow" to transfer this information to the target machine. We want to resume execution before such a transfer would complete. 4. So, the guest begins executing on the target machine. The first time it touches its memory (via the UFFD-registered mapping), userspace wants to intercept this fault. Userspace checks whether or not the page is up to date, and if not, copies the updated page from the source machine, via the non-UFFD mapping. Finally, whether a copy was performed or not, userspace issues a UFFDIO_CONTINUE ioctl to tell the kernel "I have ensured the page contents are correct, carry on setting up the mapping". We don't have to do all of the final updates on-demand. The userfaultfd manager can, in the background, also copy over updated pages once it receives the map of which pages are up-to-date or not. Interaction with Existing APIs ============================== Because this is a feature, a registered VMA could potentially receive both missing and minor faults. I spent some time thinking through how the existing API interacts with the new feature: UFFDIO_CONTINUE cannot be used to resolve non-minor faults, as it does not allocate a new page. If UFFDIO_CONTINUE is used on a non-minor fault: - For non-shared memory or shmem, -EINVAL is returned. - For hugetlb, -EFAULT is returned. UFFDIO_COPY and UFFDIO_ZEROPAGE cannot be used to resolve minor faults. Without modifications, the existing codepath assumes a new page needs to be allocated. This is okay, since userspace must have a second non-UFFD-registered mapping anyway, thus there isn't much reason to want to use these in any case (just memcpy or memset or similar). - If UFFDIO_COPY is used on a minor fault, -EEXIST is returned. - If UFFDIO_ZEROPAGE is used on a minor fault, -EEXIST is returned (or -EINVAL in the case of hugetlb, as UFFDIO_ZEROPAGE is unsupported in any case). - UFFDIO_WRITEPROTECT simply doesn't work with shared memory, and returns -ENOENT in that case (regardless of the kind of fault). Future Work =========== This series only supports hugetlbfs. I have a second series in flight to support shmem as well, extending the functionality. This series is more mature than the shmem support at this point, and the functionality works fully on hugetlbfs, so this series can be merged first and then shmem support will follow. This patch (of 6): This feature allows userspace to intercept "minor" faults. By "minor" faults, I mean the following situation: Let there exist two mappings (i.e., VMAs) to the same page(s). One of the mappings is registered with userfaultfd (in minor mode), and the other is not. Via the non-UFFD mapping, the underlying pages have already been allocated & filled with some contents. The UFFD mapping has not yet been faulted in; when it is touched for the first time, this results in what I'm calling a "minor" fault. As a concrete example, when working with hugetlbfs, we have huge_pte_none(), but find_lock_page() finds an existing page. This commit adds the new registration mode, and sets the relevant flag on the VMAs being registered. In the hugetlb fault path, if we find that we have huge_pte_none(), but find_lock_page() does indeed find an existing page, then we have a "minor" fault, and if the VMA has the userfaultfd registration flag, we call into userfaultfd to handle it. This is implemented as a new registration mode, instead of an API feature. This is because the alternative implementation has significant drawbacks [1]. However, doing it this was requires we allocate a VM_* flag for the new registration mode. On 32-bit systems, there are no unused bits, so this feature is only supported on architectures with CONFIG_ARCH_USES_HIGH_VMA_FLAGS. When attempting to register a VMA in MINOR mode on 32-bit architectures, we return -EINVAL. [1] https://lore.kernel.org/patchwork/patch/1380226/ [peterx@redhat.com: fix minor fault page leak] Link: https://lkml.kernel.org/r/20210322175132.36659-1-peterx@redhat.com Link: https://lkml.kernel.org/r/20210301222728.176417-1-axelrasmussen@google.com Link: https://lkml.kernel.org/r/20210301222728.176417-2-axelrasmussen@google.com Signed-off-by: Axel Rasmussen Reviewed-by: Peter Xu Reviewed-by: Mike Kravetz Cc: Alexander Viro Cc: Alexey Dobriyan Cc: Andrea Arcangeli Cc: Anshuman Khandual Cc: Catalin Marinas Cc: Chinwen Chang Cc: Huang Ying Cc: Ingo Molnar Cc: Jann Horn Cc: Jerome Glisse Cc: Lokesh Gidra Cc: "Matthew Wilcox (Oracle)" Cc: Michael Ellerman Cc: "Michal Koutn" Cc: Michel Lespinasse Cc: Mike Rapoport Cc: Nicholas Piggin Cc: Peter Xu Cc: Shaohua Li Cc: Shawn Anastasio Cc: Steven Rostedt Cc: Steven Price Cc: Vlastimil Babka Cc: Adam Ruprecht Cc: Axel Rasmussen Cc: Cannon Matthews Cc: "Dr . David Alan Gilbert" Cc: David Rientjes Cc: Mina Almasry Cc: Oliver Upton Cc: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/uapi/linux/userfaultfd.h | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h index 5f2d88212f7c..f24dd4fcbad9 100644 --- a/include/uapi/linux/userfaultfd.h +++ b/include/uapi/linux/userfaultfd.h @@ -19,15 +19,19 @@ * means the userland is reading). */ #define UFFD_API ((__u64)0xAA) +#define UFFD_API_REGISTER_MODES (UFFDIO_REGISTER_MODE_MISSING | \ + UFFDIO_REGISTER_MODE_WP | \ + UFFDIO_REGISTER_MODE_MINOR) #define UFFD_API_FEATURES (UFFD_FEATURE_PAGEFAULT_FLAG_WP | \ UFFD_FEATURE_EVENT_FORK | \ UFFD_FEATURE_EVENT_REMAP | \ - UFFD_FEATURE_EVENT_REMOVE | \ + UFFD_FEATURE_EVENT_REMOVE | \ UFFD_FEATURE_EVENT_UNMAP | \ UFFD_FEATURE_MISSING_HUGETLBFS | \ UFFD_FEATURE_MISSING_SHMEM | \ UFFD_FEATURE_SIGBUS | \ - UFFD_FEATURE_THREAD_ID) + UFFD_FEATURE_THREAD_ID | \ + UFFD_FEATURE_MINOR_HUGETLBFS) #define UFFD_API_IOCTLS \ ((__u64)1 << _UFFDIO_REGISTER | \ (__u64)1 << _UFFDIO_UNREGISTER | \ @@ -127,6 +131,7 @@ struct uffd_msg { /* flags for UFFD_EVENT_PAGEFAULT */ #define UFFD_PAGEFAULT_FLAG_WRITE (1<<0) /* If this was a write fault */ #define UFFD_PAGEFAULT_FLAG_WP (1<<1) /* If reason is VM_UFFD_WP */ +#define UFFD_PAGEFAULT_FLAG_MINOR (1<<2) /* If reason is VM_UFFD_MINOR */ struct uffdio_api { /* userland asks for an API number and the features to enable */ @@ -171,6 +176,10 @@ struct uffdio_api { * * UFFD_FEATURE_THREAD_ID pid of the page faulted task_struct will * be returned, if feature is not requested 0 will be returned. + * + * UFFD_FEATURE_MINOR_HUGETLBFS indicates that minor faults + * can be intercepted (via REGISTER_MODE_MINOR) for + * hugetlbfs-backed pages. */ #define UFFD_FEATURE_PAGEFAULT_FLAG_WP (1<<0) #define UFFD_FEATURE_EVENT_FORK (1<<1) @@ -181,6 +190,7 @@ struct uffdio_api { #define UFFD_FEATURE_EVENT_UNMAP (1<<6) #define UFFD_FEATURE_SIGBUS (1<<7) #define UFFD_FEATURE_THREAD_ID (1<<8) +#define UFFD_FEATURE_MINOR_HUGETLBFS (1<<9) __u64 features; __u64 ioctls; @@ -195,6 +205,7 @@ struct uffdio_register { struct uffdio_range range; #define UFFDIO_REGISTER_MODE_MISSING ((__u64)1<<0) #define UFFDIO_REGISTER_MODE_WP ((__u64)1<<1) +#define UFFDIO_REGISTER_MODE_MINOR ((__u64)1<<2) __u64 mode; /* -- cgit v1.2.3 From f619147104c8ea71e120e4936d2b68ec11a1e527 Mon Sep 17 00:00:00 2001 From: Axel Rasmussen Date: Tue, 4 May 2021 18:35:49 -0700 Subject: userfaultfd: add UFFDIO_CONTINUE ioctl This ioctl is how userspace ought to resolve "minor" userfaults. The idea is, userspace is notified that a minor fault has occurred. It might change the contents of the page using its second non-UFFD mapping, or not. Then, it calls UFFDIO_CONTINUE to tell the kernel "I have ensured the page contents are correct, carry on setting up the mapping". Note that it doesn't make much sense to use UFFDIO_{COPY,ZEROPAGE} for MINOR registered VMAs. ZEROPAGE maps the VMA to the zero page; but in the minor fault case, we already have some pre-existing underlying page. Likewise, UFFDIO_COPY isn't useful if we have a second non-UFFD mapping. We'd just use memcpy() or similar instead. It turns out hugetlb_mcopy_atomic_pte() already does very close to what we want, if an existing page is provided via `struct page **pagep`. We already special-case the behavior a bit for the UFFDIO_ZEROPAGE case, so just extend that design: add an enum for the three modes of operation, and make the small adjustments needed for the MCOPY_ATOMIC_CONTINUE case. (Basically, look up the existing page, and avoid adding the existing page to the page cache or calling set_page_huge_active() on it.) Link: https://lkml.kernel.org/r/20210301222728.176417-5-axelrasmussen@google.com Signed-off-by: Axel Rasmussen Reviewed-by: Peter Xu Cc: Adam Ruprecht Cc: Alexander Viro Cc: Alexey Dobriyan Cc: Andrea Arcangeli Cc: Anshuman Khandual Cc: Cannon Matthews Cc: Catalin Marinas Cc: Chinwen Chang Cc: David Rientjes Cc: "Dr . David Alan Gilbert" Cc: Huang Ying Cc: Ingo Molnar Cc: Jann Horn Cc: Jerome Glisse Cc: Kirill A. Shutemov Cc: Lokesh Gidra Cc: "Matthew Wilcox (Oracle)" Cc: Michael Ellerman Cc: "Michal Koutn" Cc: Michel Lespinasse Cc: Mike Kravetz Cc: Mike Rapoport Cc: Mina Almasry Cc: Nicholas Piggin Cc: Oliver Upton Cc: Shaohua Li Cc: Shawn Anastasio Cc: Steven Price Cc: Steven Rostedt Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/uapi/linux/userfaultfd.h | 21 +++++++++++++++++++-- 1 file changed, 19 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h index f24dd4fcbad9..bafbeb1a2624 100644 --- a/include/uapi/linux/userfaultfd.h +++ b/include/uapi/linux/userfaultfd.h @@ -40,10 +40,12 @@ ((__u64)1 << _UFFDIO_WAKE | \ (__u64)1 << _UFFDIO_COPY | \ (__u64)1 << _UFFDIO_ZEROPAGE | \ - (__u64)1 << _UFFDIO_WRITEPROTECT) + (__u64)1 << _UFFDIO_WRITEPROTECT | \ + (__u64)1 << _UFFDIO_CONTINUE) #define UFFD_API_RANGE_IOCTLS_BASIC \ ((__u64)1 << _UFFDIO_WAKE | \ - (__u64)1 << _UFFDIO_COPY) + (__u64)1 << _UFFDIO_COPY | \ + (__u64)1 << _UFFDIO_CONTINUE) /* * Valid ioctl command number range with this API is from 0x00 to @@ -59,6 +61,7 @@ #define _UFFDIO_COPY (0x03) #define _UFFDIO_ZEROPAGE (0x04) #define _UFFDIO_WRITEPROTECT (0x06) +#define _UFFDIO_CONTINUE (0x07) #define _UFFDIO_API (0x3F) /* userfaultfd ioctl ids */ @@ -77,6 +80,8 @@ struct uffdio_zeropage) #define UFFDIO_WRITEPROTECT _IOWR(UFFDIO, _UFFDIO_WRITEPROTECT, \ struct uffdio_writeprotect) +#define UFFDIO_CONTINUE _IOR(UFFDIO, _UFFDIO_CONTINUE, \ + struct uffdio_continue) /* read() structure */ struct uffd_msg { @@ -268,6 +273,18 @@ struct uffdio_writeprotect { __u64 mode; }; +struct uffdio_continue { + struct uffdio_range range; +#define UFFDIO_CONTINUE_MODE_DONTWAKE ((__u64)1<<0) + __u64 mode; + + /* + * Fields below here are written by the ioctl and must be at the end: + * the copy_from_user will not read past here. + */ + __s64 mapped; +}; + /* * Flags for the userfaultfd(2) system call itself. */ -- cgit v1.2.3 From b6676de8d7b48724d4cd3a3742c62fa525baa904 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Tue, 4 May 2021 18:36:01 -0700 Subject: mm/vmscan: move RECLAIM* bits to uapi header It is currently not obvious that the RECLAIM_* bits are part of the uapi since they are defined in vmscan.c. Move them to a uapi header to make it obvious. This should have no functional impact. Link: https://lkml.kernel.org/r/20210219172557.08074910@viggo.jf.intel.com Signed-off-by: Dave Hansen Reviewed-by: Ben Widawsky Reviewed-by: Oscar Salvador Acked-by: David Rientjes Acked-by: Christoph Lameter Cc: Alex Shi Cc: Daniel Wagner Cc: "Tobin C. Harding" Cc: Christoph Lameter Cc: Huang Ying Cc: Dan Williams Cc: Qian Cai Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/uapi/linux/mempolicy.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mempolicy.h b/include/uapi/linux/mempolicy.h index 8948467b3992..4832fd0b5642 100644 --- a/include/uapi/linux/mempolicy.h +++ b/include/uapi/linux/mempolicy.h @@ -64,5 +64,12 @@ enum { #define MPOL_F_MOF (1 << 3) /* this policy wants migrate on fault */ #define MPOL_F_MORON (1 << 4) /* Migrate On protnone Reference On Node */ +/* + * These bit locations are exposed in the vm.zone_reclaim_mode sysctl + * ABI. New bits are OK, but existing bits can never change. + */ +#define RECLAIM_ZONE (1<<0) /* Run shrink_inactive_list on the zone */ +#define RECLAIM_WRITE (1<<1) /* Writeout pages during reclaim */ +#define RECLAIM_UNMAP (1<<2) /* Unmap pages during reclaim */ #endif /* _UAPI_LINUX_MEMPOLICY_H */ -- cgit v1.2.3 From fa60ce2cb4506701c43bd4cf3ca23d970daf1b9c Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 6 May 2021 18:06:44 -0700 Subject: treewide: remove editor modelines and cruft The section "19) Editor modelines and other cruft" in Documentation/process/coding-style.rst clearly says, "Do not include any of these in source files." I recently receive a patch to explicitly add a new one. Let's do treewide cleanups, otherwise some people follow the existing code and attempt to upstream their favoriate editor setups. It is even nicer if scripts/checkpatch.pl can check it. If we like to impose coding style in an editor-independent manner, I think editorconfig (patch [1]) is a saner solution. [1] https://lore.kernel.org/lkml/20200703073143.423557-1-danny@kdrag0n.dev/ Link: https://lkml.kernel.org/r/20210324054457.1477489-1-masahiroy@kernel.org Signed-off-by: Masahiro Yamada Acked-by: Geert Uytterhoeven Reviewed-by: Miguel Ojeda [auxdisplay] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/uapi/linux/if_bonding.h | 11 ----------- include/uapi/linux/nfs4.h | 6 ------ 2 files changed, 17 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_bonding.h b/include/uapi/linux/if_bonding.h index e8eb4ad03cf1..d174914a837d 100644 --- a/include/uapi/linux/if_bonding.h +++ b/include/uapi/linux/if_bonding.h @@ -153,14 +153,3 @@ enum { #define BOND_3AD_STAT_MAX (__BOND_3AD_STAT_MAX - 1) #endif /* _LINUX_IF_BONDING_H */ - -/* - * Local variables: - * version-control: t - * kept-new-versions: 5 - * c-indent-level: 8 - * c-basic-offset: 8 - * tab-width: 8 - * End: - */ - diff --git a/include/uapi/linux/nfs4.h b/include/uapi/linux/nfs4.h index ed5415e0f1c1..800bb0ffa6e6 100644 --- a/include/uapi/linux/nfs4.h +++ b/include/uapi/linux/nfs4.h @@ -178,9 +178,3 @@ #define NFS4_MAX_BACK_CHANNEL_OPS 2 #endif /* _UAPI_LINUX_NFS4_H */ - -/* - * Local variables: - * c-basic-offset: 8 - * End: - */ -- cgit v1.2.3