diff options
author | Lee Jones <joneslee@google.com> | 2024-04-11 18:16:04 +0100 |
---|---|---|
committer | Treehugger Robot <android-test-infra-autosubmit@system.gserviceaccount.com> | 2024-04-23 19:17:23 +0000 |
commit | 04c42ae514afa3c1e07796f1198bc6a90cab1904 (patch) | |
tree | 574a2657b9c7ddbf5c39c6487c3ef8e290a9c26d | |
parent | a0436d5a158ed314a36e2c39b522d17816d8de69 (diff) | |
parent | 508f34f2381eb84b2335abb970b940aefef50a19 (diff) | |
download | common-04c42ae514afa3c1e07796f1198bc6a90cab1904.tar.gz |
Merge 508f34f2381e ("Merge tag 'm68k-for-v6.9-tag1' of git://git.kernel.org/pub/scm/linux/kernel/git/geert/linux-m68k") into android-mainline
Steps on the way to v6.9-rc1
Signed-off-by: Lee Jones <joneslee@google.com>
Change-Id: I947378404e1ff2daca861d32e2a43f19c1a1b382
406 files changed, 13836 insertions, 4328 deletions
diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index a1db6db47505..710d47be11e0 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -516,6 +516,7 @@ What: /sys/devices/system/cpu/vulnerabilities /sys/devices/system/cpu/vulnerabilities/mds /sys/devices/system/cpu/vulnerabilities/meltdown /sys/devices/system/cpu/vulnerabilities/mmio_stale_data + /sys/devices/system/cpu/vulnerabilities/reg_file_data_sampling /sys/devices/system/cpu/vulnerabilities/retbleed /sys/devices/system/cpu/vulnerabilities/spec_store_bypass /sys/devices/system/cpu/vulnerabilities/spectre_v1 diff --git a/Documentation/admin-guide/RAS/address-translation.rst b/Documentation/admin-guide/RAS/address-translation.rst new file mode 100644 index 000000000000..f0ca17b43cd3 --- /dev/null +++ b/Documentation/admin-guide/RAS/address-translation.rst @@ -0,0 +1,24 @@ +.. SPDX-License-Identifier: GPL-2.0 + +Address translation +=================== + +x86 AMD +------- + +Zen-based AMD systems include a Data Fabric that manages the layout of +physical memory. Devices attached to the Fabric, like memory controllers, +I/O, etc., may not have a complete view of the system physical memory map. +These devices may provide a "normalized", i.e. device physical, address +when reporting memory errors. Normalized addresses must be translated to +a system physical address for the kernel to action on the memory. + +AMD Address Translation Library (CONFIG_AMD_ATL) provides translation for +this case. + +Glossary of acronyms used in address translation for Zen-based systems + +* CCM = Cache Coherent Moderator +* COD = Cluster-on-Die +* COH_ST = Coherent Station +* DF = Data Fabric diff --git a/Documentation/RAS/ras.rst b/Documentation/admin-guide/RAS/error-decoding.rst index 2556b397cd27..26a72f3fe5de 100644 --- a/Documentation/RAS/ras.rst +++ b/Documentation/admin-guide/RAS/error-decoding.rst @@ -1,15 +1,10 @@ .. SPDX-License-Identifier: GPL-2.0 -Reliability, Availability and Serviceability features -===================================================== - -This documents different aspects of the RAS functionality present in the -kernel. - Error decoding ---------------- +============== -* x86 +x86 +--- Error decoding on AMD systems should be done using the rasdaemon tool: https://github.com/mchehab/rasdaemon/ diff --git a/Documentation/admin-guide/RAS/index.rst b/Documentation/admin-guide/RAS/index.rst new file mode 100644 index 000000000000..f4087040a7c0 --- /dev/null +++ b/Documentation/admin-guide/RAS/index.rst @@ -0,0 +1,7 @@ +.. SPDX-License-Identifier: GPL-2.0 +.. toctree:: + :maxdepth: 2 + + main + error-decoding + address-translation diff --git a/Documentation/admin-guide/ras.rst b/Documentation/admin-guide/RAS/main.rst index 8e03751d126d..7ac1d4ccc509 100644 --- a/Documentation/admin-guide/ras.rst +++ b/Documentation/admin-guide/RAS/main.rst @@ -1,8 +1,12 @@ +.. SPDX-License-Identifier: GPL-2.0 .. include:: <isonum.txt> -============================================ -Reliability, Availability and Serviceability -============================================ +================================================== +Reliability, Availability and Serviceability (RAS) +================================================== + +This documents different aspects of the RAS functionality present in the +kernel. RAS concepts ************ diff --git a/Documentation/admin-guide/hw-vuln/index.rst b/Documentation/admin-guide/hw-vuln/index.rst index de99caabf65a..ff0b440ef2dc 100644 --- a/Documentation/admin-guide/hw-vuln/index.rst +++ b/Documentation/admin-guide/hw-vuln/index.rst @@ -21,3 +21,4 @@ are configurable at compile, boot or run time. cross-thread-rsb srso gather_data_sampling + reg-file-data-sampling diff --git a/Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst b/Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst new file mode 100644 index 000000000000..0585d02b9a6c --- /dev/null +++ b/Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst @@ -0,0 +1,104 @@ +================================== +Register File Data Sampling (RFDS) +================================== + +Register File Data Sampling (RFDS) is a microarchitectural vulnerability that +only affects Intel Atom parts(also branded as E-cores). RFDS may allow +a malicious actor to infer data values previously used in floating point +registers, vector registers, or integer registers. RFDS does not provide the +ability to choose which data is inferred. CVE-2023-28746 is assigned to RFDS. + +Affected Processors +=================== +Below is the list of affected Intel processors [#f1]_: + + =================== ============ + Common name Family_Model + =================== ============ + ATOM_GOLDMONT 06_5CH + ATOM_GOLDMONT_D 06_5FH + ATOM_GOLDMONT_PLUS 06_7AH + ATOM_TREMONT_D 06_86H + ATOM_TREMONT 06_96H + ALDERLAKE 06_97H + ALDERLAKE_L 06_9AH + ATOM_TREMONT_L 06_9CH + RAPTORLAKE 06_B7H + RAPTORLAKE_P 06_BAH + ATOM_GRACEMONT 06_BEH + RAPTORLAKE_S 06_BFH + =================== ============ + +As an exception to this table, Intel Xeon E family parts ALDERLAKE(06_97H) and +RAPTORLAKE(06_B7H) codenamed Catlow are not affected. They are reported as +vulnerable in Linux because they share the same family/model with an affected +part. Unlike their affected counterparts, they do not enumerate RFDS_CLEAR or +CPUID.HYBRID. This information could be used to distinguish between the +affected and unaffected parts, but it is deemed not worth adding complexity as +the reporting is fixed automatically when these parts enumerate RFDS_NO. + +Mitigation +========== +Intel released a microcode update that enables software to clear sensitive +information using the VERW instruction. Like MDS, RFDS deploys the same +mitigation strategy to force the CPU to clear the affected buffers before an +attacker can extract the secrets. This is achieved by using the otherwise +unused and obsolete VERW instruction in combination with a microcode update. +The microcode clears the affected CPU buffers when the VERW instruction is +executed. + +Mitigation points +----------------- +VERW is executed by the kernel before returning to user space, and by KVM +before VMentry. None of the affected cores support SMT, so VERW is not required +at C-state transitions. + +New bits in IA32_ARCH_CAPABILITIES +---------------------------------- +Newer processors and microcode update on existing affected processors added new +bits to IA32_ARCH_CAPABILITIES MSR. These bits can be used to enumerate +vulnerability and mitigation capability: + +- Bit 27 - RFDS_NO - When set, processor is not affected by RFDS. +- Bit 28 - RFDS_CLEAR - When set, processor is affected by RFDS, and has the + microcode that clears the affected buffers on VERW execution. + +Mitigation control on the kernel command line +--------------------------------------------- +The kernel command line allows to control RFDS mitigation at boot time with the +parameter "reg_file_data_sampling=". The valid arguments are: + + ========== ================================================================= + on If the CPU is vulnerable, enable mitigation; CPU buffer clearing + on exit to userspace and before entering a VM. + off Disables mitigation. + ========== ================================================================= + +Mitigation default is selected by CONFIG_MITIGATION_RFDS. + +Mitigation status information +----------------------------- +The Linux kernel provides a sysfs interface to enumerate the current +vulnerability status of the system: whether the system is vulnerable, and +which mitigations are active. The relevant sysfs file is: + + /sys/devices/system/cpu/vulnerabilities/reg_file_data_sampling + +The possible values in this file are: + + .. list-table:: + + * - 'Not affected' + - The processor is not vulnerable + * - 'Vulnerable' + - The processor is vulnerable, but no mitigation enabled + * - 'Vulnerable: No microcode' + - The processor is vulnerable but microcode is not updated. + * - 'Mitigation: Clear Register File' + - The processor is vulnerable and the CPU buffer clearing mitigation is + enabled. + +References +---------- +.. [#f1] Affected Processors + https://www.intel.com/content/www/us/en/developer/topic-technology/software-security-guidance/processors-affected-consolidated-product-cpu-model.html diff --git a/Documentation/admin-guide/hw-vuln/spectre.rst b/Documentation/admin-guide/hw-vuln/spectre.rst index 32a8893e5617..cce768afec6b 100644 --- a/Documentation/admin-guide/hw-vuln/spectre.rst +++ b/Documentation/admin-guide/hw-vuln/spectre.rst @@ -473,8 +473,8 @@ Spectre variant 2 -mindirect-branch=thunk-extern -mindirect-branch-register options. If the kernel is compiled with a Clang compiler, the compiler needs to support -mretpoline-external-thunk option. The kernel config - CONFIG_RETPOLINE needs to be turned on, and the CPU needs to run with - the latest updated microcode. + CONFIG_MITIGATION_RETPOLINE needs to be turned on, and the CPU needs + to run with the latest updated microcode. On Intel Skylake-era systems the mitigation covers most, but not all, cases. See :ref:`[3] <spec_ref3>` for more details. @@ -609,8 +609,8 @@ kernel command line. Selecting 'on' will, and 'auto' may, choose a mitigation method at run time according to the CPU, the available microcode, the setting of the - CONFIG_RETPOLINE configuration option, and the - compiler with which the kernel was built. + CONFIG_MITIGATION_RETPOLINE configuration option, + and the compiler with which the kernel was built. Selecting 'on' will also enable the mitigation against user space to user space task attacks. diff --git a/Documentation/admin-guide/index.rst b/Documentation/admin-guide/index.rst index fb40a1f6f79e..dfc06fab9432 100644 --- a/Documentation/admin-guide/index.rst +++ b/Documentation/admin-guide/index.rst @@ -122,7 +122,7 @@ configure specific aspects of kernel behavior to your liking. pmf pnp rapidio - ras + RAS/index rtc serial-console svga diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 3d635962d3ca..85c061926293 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1136,6 +1136,26 @@ The filter can be disabled or changed to another driver later using sysfs. + reg_file_data_sampling= + [X86] Controls mitigation for Register File Data + Sampling (RFDS) vulnerability. RFDS is a CPU + vulnerability which may allow userspace to infer + kernel data values previously stored in floating point + registers, vector registers, or integer registers. + RFDS only affects Intel Atom processors. + + on: Turns ON the mitigation. + off: Turns OFF the mitigation. + + This parameter overrides the compile time default set + by CONFIG_MITIGATION_RFDS. Mitigation cannot be + disabled when other VERW based mitigations (like MDS) + are enabled. In order to disable RFDS mitigation all + VERW based mitigations need to be disabled. + + For details see: + Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst + driver_async_probe= [KNL] List of driver names to be probed asynchronously. * matches with all driver names. If * is specified, the @@ -3322,9 +3342,7 @@ mem_encrypt= [X86-64] AMD Secure Memory Encryption (SME) control Valid arguments: on, off - Default (depends on kernel configuration option): - on (CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT=y) - off (CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT=n) + Default: off mem_encrypt=on: Activate SME mem_encrypt=off: Do not activate SME @@ -3400,7 +3418,9 @@ nospectre_bhb [ARM64] nospectre_v1 [X86,PPC] nospectre_v2 [X86,PPC,S390,ARM64] + reg_file_data_sampling=off [X86] retbleed=off [X86] + spec_rstack_overflow=off [X86] spec_store_bypass_disable=off [X86,PPC] spectre_v2_user=off [X86] srbds=off [X86,INTEL] @@ -6041,8 +6061,8 @@ Selecting 'on' will, and 'auto' may, choose a mitigation method at run time according to the CPU, the available microcode, the setting of the - CONFIG_RETPOLINE configuration option, and the - compiler with which the kernel was built. + CONFIG_MITIGATION_RETPOLINE configuration option, + and the compiler with which the kernel was built. Selecting 'on' will also enable the mitigation against user space to user space task attacks. diff --git a/Documentation/arch/x86/amd-memory-encryption.rst b/Documentation/arch/x86/amd-memory-encryption.rst index 07caa8fff852..414bc7402ae7 100644 --- a/Documentation/arch/x86/amd-memory-encryption.rst +++ b/Documentation/arch/x86/amd-memory-encryption.rst @@ -87,14 +87,14 @@ The state of SME in the Linux kernel can be documented as follows: kernel is non-zero). SME can also be enabled and activated in the BIOS. If SME is enabled and -activated in the BIOS, then all memory accesses will be encrypted and it will -not be necessary to activate the Linux memory encryption support. If the BIOS -merely enables SME (sets bit 23 of the MSR_AMD64_SYSCFG), then Linux can activate -memory encryption by default (CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT=y) or -by supplying mem_encrypt=on on the kernel command line. However, if BIOS does -not enable SME, then Linux will not be able to activate memory encryption, even -if configured to do so by default or the mem_encrypt=on command line parameter -is specified. +activated in the BIOS, then all memory accesses will be encrypted and it +will not be necessary to activate the Linux memory encryption support. + +If the BIOS merely enables SME (sets bit 23 of the MSR_AMD64_SYSCFG), +then memory encryption can be enabled by supplying mem_encrypt=on on the +kernel command line. However, if BIOS does not enable SME, then Linux +will not be able to activate memory encryption, even if configured to do +so by default or the mem_encrypt=on command line parameter is specified. Secure Nested Paging (SNP) ========================== diff --git a/Documentation/arch/x86/boot.rst b/Documentation/arch/x86/boot.rst index c513855a54bb..4fd492cb4970 100644 --- a/Documentation/arch/x86/boot.rst +++ b/Documentation/arch/x86/boot.rst @@ -878,7 +878,8 @@ Protocol: 2.10+ address if possible. A non-relocatable kernel will unconditionally move itself and to run - at this address. + at this address. A relocatable kernel will move itself to this address if it + loaded below this address. ============ ======= Field name: init_size diff --git a/Documentation/arch/x86/pti.rst b/Documentation/arch/x86/pti.rst index e08d35177bc0..57e8392f61d3 100644 --- a/Documentation/arch/x86/pti.rst +++ b/Documentation/arch/x86/pti.rst @@ -26,9 +26,9 @@ comments in pti.c). This approach helps to ensure that side-channel attacks leveraging the paging structures do not function when PTI is enabled. It can be -enabled by setting CONFIG_PAGE_TABLE_ISOLATION=y at compile time. -Once enabled at compile-time, it can be disabled at boot with the -'nopti' or 'pti=' kernel parameters (see kernel-parameters.txt). +enabled by setting CONFIG_MITIGATION_PAGE_TABLE_ISOLATION=y at compile +time. Once enabled at compile-time, it can be disabled at boot with +the 'nopti' or 'pti=' kernel parameters (see kernel-parameters.txt). Page Table Management ===================== diff --git a/Documentation/index.rst b/Documentation/index.rst index 36e61783437c..9dfdc826618c 100644 --- a/Documentation/index.rst +++ b/Documentation/index.rst @@ -113,7 +113,6 @@ to ReStructured Text format, or are simply too old. :maxdepth: 1 staging/index - RAS/ras Translations diff --git a/Documentation/process/maintainer-tip.rst b/Documentation/process/maintainer-tip.rst index 08dd0f804410..497bb39727c8 100644 --- a/Documentation/process/maintainer-tip.rst +++ b/Documentation/process/maintainer-tip.rst @@ -304,13 +304,15 @@ following tag ordering scheme: - Reported-by: ``Reporter <reporter@mail>`` + - Closes: ``URL or Message-ID of the bug report this is fixing`` + - Originally-by: ``Original author <original-author@mail>`` - Suggested-by: ``Suggester <suggester@mail>`` - Co-developed-by: ``Co-author <co-author@mail>`` - Signed-off: ``Co-author <co-author@mail>`` + Signed-off-by: ``Co-author <co-author@mail>`` Note, that Co-developed-by and Signed-off-by of the co-author(s) must come in pairs. @@ -478,7 +480,7 @@ Multi-line comments:: * Larger multi-line comments should be split into paragraphs. */ -No tail comments: +No tail comments (see below): Please refrain from using tail comments. Tail comments disturb the reading flow in almost all contexts, but especially in code:: @@ -499,6 +501,34 @@ No tail comments: /* This magic initialization needs a comment. Maybe not? */ seed = MAGIC_CONSTANT; + Use C++ style, tail comments when documenting structs in headers to + achieve a more compact layout and better readability:: + + // eax + u32 x2apic_shift : 5, // Number of bits to shift APIC ID right + // for the topology ID at the next level + : 27; // Reserved + // ebx + u32 num_processors : 16, // Number of processors at current level + : 16; // Reserved + + versus:: + + /* eax */ + /* + * Number of bits to shift APIC ID right for the topology ID + * at the next level + */ + u32 x2apic_shift : 5, + /* Reserved */ + : 27; + + /* ebx */ + /* Number of processors at current level */ + u32 num_processors : 16, + /* Reserved */ + : 16; + Comment the important things: Comments should be added where the operation is not obvious. Documenting diff --git a/Documentation/virt/coco/sev-guest.rst b/Documentation/virt/coco/sev-guest.rst index 68b0d2363af8..e1eaf6a830ce 100644 --- a/Documentation/virt/coco/sev-guest.rst +++ b/Documentation/virt/coco/sev-guest.rst @@ -67,6 +67,23 @@ counter (e.g. counter overflow), then -EIO will be returned. }; }; +The host ioctls are issued to a file descriptor of the /dev/sev device. +The ioctl accepts the command ID/input structure documented below. + +:: + + struct sev_issue_cmd { + /* Command ID */ + __u32 cmd; + + /* Command request structure */ + __u64 data; + + /* Firmware error code on failure (see psp-sev.h) */ + __u32 error; + }; + + 2.1 SNP_GET_REPORT ------------------ @@ -124,6 +141,41 @@ be updated with the expected value. See GHCB specification for further detail on how to parse the certificate blob. +2.4 SNP_PLATFORM_STATUS +----------------------- +:Technology: sev-snp +:Type: hypervisor ioctl cmd +:Parameters (out): struct sev_user_data_snp_status +:Returns (out): 0 on success, -negative on error + +The SNP_PLATFORM_STATUS command is used to query the SNP platform status. The +status includes API major, minor version and more. See the SEV-SNP +specification for further details. + +2.5 SNP_COMMIT +-------------- +:Technology: sev-snp +:Type: hypervisor ioctl cmd +:Returns (out): 0 on success, -negative on error + +SNP_COMMIT is used to commit the currently installed firmware using the +SEV-SNP firmware SNP_COMMIT command. This prevents roll-back to a previously +committed firmware version. This will also update the reported TCB to match +that of the currently installed firmware. + +2.6 SNP_SET_CONFIG +------------------ +:Technology: sev-snp +:Type: hypervisor ioctl cmd +:Parameters (in): struct sev_user_data_snp_config +:Returns (out): 0 on success, -negative on error + +SNP_SET_CONFIG is used to set the system-wide configuration such as +reported TCB version in the attestation report. The command is similar +to SNP_CONFIG command defined in the SEV-SNP spec. The current values of +the firmware parameters affected by this command can be queried via +SNP_PLATFORM_STATUS. + 3. SEV-SNP CPUID Enforcement ============================ diff --git a/MAINTAINERS b/MAINTAINERS index 5574ceaa1a37..8423007e15f3 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -897,6 +897,12 @@ Q: https://patchwork.kernel.org/project/linux-rdma/list/ F: drivers/infiniband/hw/efa/ F: include/uapi/rdma/efa-abi.h +AMD ADDRESS TRANSLATION LIBRARY (ATL) +M: Yazen Ghannam <Yazen.Ghannam@amd.com> +L: linux-edac@vger.kernel.org +S: Supported +F: drivers/ras/amd/atl/* + AMD AXI W1 DRIVER M: Kris Chaplin <kris.chaplin@amd.com> R: Thomas Delev <thomas.delev@amd.com> @@ -7583,7 +7589,6 @@ R: Robert Richter <rric@kernel.org> L: linux-edac@vger.kernel.org S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/ras/ras.git edac-for-next -F: Documentation/admin-guide/ras.rst F: Documentation/driver-api/edac.rst F: drivers/edac/ F: include/linux/edac.h @@ -18386,11 +18391,17 @@ M: Tony Luck <tony.luck@intel.com> M: Borislav Petkov <bp@alien8.de> L: linux-edac@vger.kernel.org S: Maintained -F: Documentation/admin-guide/ras.rst +F: Documentation/admin-guide/RAS F: drivers/ras/ F: include/linux/ras.h F: include/ras/ras_event.h +RAS FRU MEMORY POISON MANAGER (FMPM) +M: Yazen Ghannam <Yazen.Ghannam@amd.com> +L: linux-edac@vger.kernel.org +S: Maintained +F: drivers/ras/amd/fmpm.c + RC-CORE / LIRC FRAMEWORK M: Sean Young <sean@mess.org> L: linux-media@vger.kernel.org diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c index 7439b2377df5..8e9dd63b220c 100644 --- a/arch/alpha/kernel/smp.c +++ b/arch/alpha/kernel/smp.c @@ -467,11 +467,6 @@ smp_prepare_cpus(unsigned int max_cpus) smp_num_cpus = smp_num_probed; } -void -smp_prepare_boot_cpu(void) -{ -} - int __cpu_up(unsigned int cpu, struct task_struct *tidle) { diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c index 8d9b188caa27..b2f2c59279a6 100644 --- a/arch/arc/kernel/smp.c +++ b/arch/arc/kernel/smp.c @@ -39,11 +39,6 @@ struct plat_smp_ops __weak plat_smp_ops; /* XXX: per cpu ? Only needed once in early secondary boot */ struct task_struct *secondary_idle_tsk; -/* Called from start_kernel */ -void __init smp_prepare_boot_cpu(void) -{ -} - static int __init arc_get_cpu_map(const char *name, struct cpumask *cpumask) { unsigned long dt_root = of_get_flat_dt_root(); diff --git a/arch/csky/kernel/smp.c b/arch/csky/kernel/smp.c index 8e42352cbf12..92dbbf3e0205 100644 --- a/arch/csky/kernel/smp.c +++ b/arch/csky/kernel/smp.c @@ -152,10 +152,6 @@ void arch_irq_work_raise(void) } #endif -void __init smp_prepare_boot_cpu(void) -{ -} - void __init smp_prepare_cpus(unsigned int max_cpus) { } diff --git a/arch/hexagon/kernel/smp.c b/arch/hexagon/kernel/smp.c index 608884bc3396..65e1fdf9fdb2 100644 --- a/arch/hexagon/kernel/smp.c +++ b/arch/hexagon/kernel/smp.c @@ -114,10 +114,6 @@ void send_ipi(const struct cpumask *cpumask, enum ipi_message_type msg) local_irq_restore(flags); } -void __init smp_prepare_boot_cpu(void) -{ -} - /* * interrupts should already be disabled from the VM * SP should already be correct; need to set THREADINFO_REG diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig index b4d71fea558f..a6f6607efe79 100644 --- a/arch/m68k/configs/amiga_defconfig +++ b/arch/m68k/configs/amiga_defconfig @@ -336,7 +336,6 @@ CONFIG_ATA=y CONFIG_PATA_GAYLE=y CONFIG_PATA_BUDDHA=y CONFIG_MD=y -CONFIG_MD_LINEAR=m CONFIG_BLK_DEV_DM=m CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m @@ -579,12 +578,10 @@ CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_ARC4=m -CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_HCTR2=m CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_LRW=m -CONFIG_CRYPTO_OFB=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m CONFIG_CRYPTO_AEGIS128=m diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig index 682d8cd3dd3c..0ca1f9f930bc 100644 --- a/arch/m68k/configs/apollo_defconfig +++ b/arch/m68k/configs/apollo_defconfig @@ -316,7 +316,6 @@ CONFIG_SCSI_SAS_ATTRS=m CONFIG_ISCSI_TCP=m CONFIG_ISCSI_BOOT_SYSFS=m CONFIG_MD=y -CONFIG_MD_LINEAR=m CONFIG_BLK_DEV_DM=m CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m @@ -536,12 +535,10 @@ CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_ARC4=m -CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_HCTR2=m CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_LRW=m -CONFIG_CRYPTO_OFB=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m CONFIG_CRYPTO_AEGIS128=m diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig index 15259ced8463..be030659d8d7 100644 --- a/arch/m68k/configs/atari_defconfig +++ b/arch/m68k/configs/atari_defconfig @@ -331,7 +331,6 @@ CONFIG_ATA=y # CONFIG_ATA_BMDMA is not set CONFIG_PATA_FALCON=y CONFIG_MD=y -CONFIG_MD_LINEAR=m CONFIG_BLK_DEV_DM=m CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m @@ -556,12 +555,10 @@ CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_ARC4=m -CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_HCTR2=m CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_LRW=m -CONFIG_CRYPTO_OFB=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m CONFIG_CRYPTO_AEGIS128=m diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig index 7395c12caef6..ad8f81fbb630 100644 --- a/arch/m68k/configs/bvme6000_defconfig +++ b/arch/m68k/configs/bvme6000_defconfig @@ -314,7 +314,6 @@ CONFIG_ISCSI_TCP=m CONFIG_ISCSI_BOOT_SYSFS=m CONFIG_BVME6000_SCSI=y CONFIG_MD=y -CONFIG_MD_LINEAR=m CONFIG_BLK_DEV_DM=m CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m @@ -528,12 +527,10 @@ CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_ARC4=m -CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_HCTR2=m CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_LRW=m -CONFIG_CRYPTO_OFB=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m CONFIG_CRYPTO_AEGIS128=m diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig index 92506bc7f78d..ff253b6accec 100644 --- a/arch/m68k/configs/hp300_defconfig +++ b/arch/m68k/configs/hp300_defconfig @@ -315,7 +315,6 @@ CONFIG_SCSI_SAS_ATTRS=m CONFIG_ISCSI_TCP=m CONFIG_ISCSI_BOOT_SYSFS=m CONFIG_MD=y -CONFIG_MD_LINEAR=m CONFIG_BLK_DEV_DM=m CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m @@ -538,12 +537,10 @@ CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_ARC4=m -CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_HCTR2=m CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_LRW=m -CONFIG_CRYPTO_OFB=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m CONFIG_CRYPTO_AEGIS128=m diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig index 144bc8c0d8b5..f92b866620a7 100644 --- a/arch/m68k/configs/mac_defconfig +++ b/arch/m68k/configs/mac_defconfig @@ -320,7 +320,6 @@ CONFIG_ATA=y # CONFIG_ATA_BMDMA is not set CONFIG_PATA_PLATFORM=y CONFIG_MD=y -CONFIG_MD_LINEAR=m CONFIG_BLK_DEV_DM=m CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m @@ -555,12 +554,10 @@ CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_ARC4=m -CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_HCTR2=m CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_LRW=m -CONFIG_CRYPTO_OFB=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m CONFIG_CRYPTO_AEGIS128=m diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig index 07594c729497..bd813beaa8a7 100644 --- a/arch/m68k/configs/multi_defconfig +++ b/arch/m68k/configs/multi_defconfig @@ -363,7 +363,6 @@ CONFIG_PATA_GAYLE=y CONFIG_PATA_BUDDHA=y CONFIG_PATA_PLATFORM=y CONFIG_MD=y -CONFIG_MD_LINEAR=m CONFIG_BLK_DEV_DM=m CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m @@ -641,12 +640,10 @@ CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_ARC4=m -CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_HCTR2=m CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_LRW=m -CONFIG_CRYPTO_OFB=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m CONFIG_CRYPTO_AEGIS128=m diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig index c34de6c1de20..2237ee0fe433 100644 --- a/arch/m68k/configs/mvme147_defconfig +++ b/arch/m68k/configs/mvme147_defconfig @@ -313,7 +313,6 @@ CONFIG_ISCSI_TCP=m CONFIG_ISCSI_BOOT_SYSFS=m CONFIG_MVME147_SCSI=y CONFIG_MD=y -CONFIG_MD_LINEAR=m CONFIG_BLK_DEV_DM=m CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m @@ -527,12 +526,10 @@ CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_ARC4=m -CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_HCTR2=m CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_LRW=m -CONFIG_CRYPTO_OFB=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m CONFIG_CRYPTO_AEGIS128=m diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig index 83bc029d1f33..afb5aa9c5012 100644 --- a/arch/m68k/configs/mvme16x_defconfig +++ b/arch/m68k/configs/mvme16x_defconfig @@ -314,7 +314,6 @@ CONFIG_ISCSI_TCP=m CONFIG_ISCSI_BOOT_SYSFS=m CONFIG_MVME16x_SCSI=y CONFIG_MD=y -CONFIG_MD_LINEAR=m CONFIG_BLK_DEV_DM=m CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m @@ -528,12 +527,10 @@ CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_ARC4=m -CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_HCTR2=m CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_LRW=m -CONFIG_CRYPTO_OFB=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m CONFIG_CRYPTO_AEGIS128=m diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig index 4f551dac2ed7..e40f7a308966 100644 --- a/arch/m68k/configs/q40_defconfig +++ b/arch/m68k/configs/q40_defconfig @@ -320,7 +320,6 @@ CONFIG_ATA=y # CONFIG_ATA_BMDMA is not set CONFIG_PATA_FALCON=y CONFIG_MD=y -CONFIG_MD_LINEAR=m CONFIG_BLK_DEV_DM=m CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m @@ -545,12 +544,10 @@ CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_ARC4=m -CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_HCTR2=m CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_LRW=m -CONFIG_CRYPTO_OFB=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m CONFIG_CRYPTO_AEGIS128=m diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig index b1bf01182bd3..4df397c0395f 100644 --- a/arch/m68k/configs/sun3_defconfig +++ b/arch/m68k/configs/sun3_defconfig @@ -310,7 +310,6 @@ CONFIG_ISCSI_TCP=m CONFIG_ISCSI_BOOT_SYSFS=m CONFIG_SUN3_SCSI=y CONFIG_MD=y -CONFIG_MD_LINEAR=m CONFIG_BLK_DEV_DM=m CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m @@ -526,12 +525,10 @@ CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_ARC4=m -CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_HCTR2=m CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_LRW=m -CONFIG_CRYPTO_OFB=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m CONFIG_CRYPTO_AEGIS128=m diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig index 5c9a3f71f036..aa7719b3947f 100644 --- a/arch/m68k/configs/sun3x_defconfig +++ b/arch/m68k/configs/sun3x_defconfig @@ -311,7 +311,6 @@ CONFIG_ISCSI_TCP=m CONFIG_ISCSI_BOOT_SYSFS=m CONFIG_SUN3X_ESP=y CONFIG_MD=y -CONFIG_MD_LINEAR=m CONFIG_BLK_DEV_DM=m CONFIG_DM_UNSTRIPED=m CONFIG_DM_CRYPT=m @@ -526,12 +525,10 @@ CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m CONFIG_CRYPTO_ADIANTUM=m CONFIG_CRYPTO_ARC4=m -CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_HCTR2=m CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_LRW=m -CONFIG_CRYPTO_OFB=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m CONFIG_CRYPTO_AEGIS128=m diff --git a/arch/openrisc/kernel/smp.c b/arch/openrisc/kernel/smp.c index 1c5a2d71d675..86da4bc5ee0b 100644 --- a/arch/openrisc/kernel/smp.c +++ b/arch/openrisc/kernel/smp.c @@ -57,10 +57,6 @@ static void boot_secondary(unsigned int cpu, struct task_struct *idle) spin_unlock(&boot_lock); } -void __init smp_prepare_boot_cpu(void) -{ -} - void __init smp_init_cpus(void) { struct device_node *cpu; diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 693334c20d07..a60e4139214b 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -984,7 +984,7 @@ static bool shared_caches __ro_after_init; /* cpumask of CPUs with asymmetric SMT dependency */ static int powerpc_smt_flags(void) { - int flags = SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES; + int flags = SD_SHARE_CPUCAPACITY | SD_SHARE_LLC; if (cpu_has_feature(CPU_FTR_ASYM_SMT)) { printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n"); @@ -1010,9 +1010,9 @@ static __ro_after_init DEFINE_STATIC_KEY_FALSE(splpar_asym_pack); static int powerpc_shared_cache_flags(void) { if (static_branch_unlikely(&splpar_asym_pack)) - return SD_SHARE_PKG_RESOURCES | SD_ASYM_PACKING; + return SD_SHARE_LLC | SD_ASYM_PACKING; - return SD_SHARE_PKG_RESOURCES; + return SD_SHARE_LLC; } static int powerpc_shared_proc_flags(void) diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c index 519b6bd946e5..c4ed7d977f57 100644 --- a/arch/riscv/kernel/smpboot.c +++ b/arch/riscv/kernel/smpboot.c @@ -42,10 +42,6 @@ static DECLARE_COMPLETION(cpu_running); -void __init smp_prepare_boot_cpu(void) -{ -} - void __init smp_prepare_cpus(unsigned int max_cpus) { int cpuid; diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index fe565f3a3a91..2dc722fb31b4 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -127,6 +127,7 @@ config S390 select ARCH_WANT_DEFAULT_BPF_JIT select ARCH_WANT_IPC_PARSE_VERSION select ARCH_WANT_KERNEL_PMD_MKWRITE + select ARCH_WANT_LD_ORPHAN_WARN select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP select BUILDTIME_TABLE_SORT select CLONE_BACKWARDS2 @@ -448,7 +449,7 @@ config COMPAT select COMPAT_OLD_SIGACTION select HAVE_UID16 depends on MULTIUSER - depends on !CC_IS_CLANG + depends on !CC_IS_CLANG && !LD_IS_LLD help Select this option if you want to enable your system kernel to handle system-calls from ELF binaries for 31 bit ESA. This option @@ -582,14 +583,23 @@ config RELOCATABLE help This builds a kernel image that retains relocation information so it can be loaded at an arbitrary address. - The kernel is linked as a position-independent executable (PIE) - and contains dynamic relocations which are processed early in the - bootup process. The relocations make the kernel image about 15% larger (compressed 10%), but are discarded at runtime. Note: this option exists only for documentation purposes, please do not remove it. +config PIE_BUILD + def_bool CC_IS_CLANG && !$(cc-option,-munaligned-symbols) + help + If the compiler is unable to generate code that can manage unaligned + symbols, the kernel is linked as a position-independent executable + (PIE) and includes dynamic relocations that are processed early + during bootup. + + For kpatch functionality, it is recommended to build the kernel + without the PIE_BUILD option. PIE_BUILD is only enabled when the + compiler lacks proper support for handling unaligned symbols. + config RANDOMIZE_BASE bool "Randomize the address of the kernel image (KASLR)" default y diff --git a/arch/s390/Makefile b/arch/s390/Makefile index 73873e451686..2a58e1864931 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -14,8 +14,14 @@ KBUILD_AFLAGS_MODULE += -fPIC KBUILD_CFLAGS_MODULE += -fPIC KBUILD_AFLAGS += -m64 KBUILD_CFLAGS += -m64 +ifdef CONFIG_PIE_BUILD KBUILD_CFLAGS += -fPIE -LDFLAGS_vmlinux := -pie +LDFLAGS_vmlinux := -pie -z notext +else +KBUILD_CFLAGS += $(call cc-option,-munaligned-symbols,) +LDFLAGS_vmlinux := --emit-relocs --discard-none +extra_tools := relocs +endif aflags_dwarf := -Wa,-gdwarf-2 KBUILD_AFLAGS_DECOMPRESSOR := $(CLANG_FLAGS) -m64 -D__ASSEMBLY__ ifndef CONFIG_AS_IS_LLVM @@ -143,7 +149,7 @@ archheaders: archprepare: $(Q)$(MAKE) $(build)=$(syscalls) kapi - $(Q)$(MAKE) $(build)=$(tools) kapi + $(Q)$(MAKE) $(build)=$(tools) kapi $(extra_tools) ifeq ($(KBUILD_EXTMOD),) # We need to generate vdso-offsets.h before compiling certain files in kernel/. # In order to do that, we should use the archprepare target, but we can't since diff --git a/arch/s390/boot/.gitignore b/arch/s390/boot/.gitignore index f56591bc0897..f5ef099e2fd3 100644 --- a/arch/s390/boot/.gitignore +++ b/arch/s390/boot/.gitignore @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only image bzImage +relocs.S section_cmp.* vmlinux vmlinux.lds diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile index c7c81e5f9218..294f08a8811a 100644 --- a/arch/s390/boot/Makefile +++ b/arch/s390/boot/Makefile @@ -37,7 +37,8 @@ CFLAGS_sclp_early_core.o += -I$(srctree)/drivers/s390/char obj-y := head.o als.o startup.o physmem_info.o ipl_parm.o ipl_report.o vmem.o obj-y += string.o ebcdic.o sclp_early_core.o mem.o ipl_vmparm.o cmdline.o -obj-y += version.o pgm_check_info.o ctype.o ipl_data.o machine_kexec_reloc.o +obj-y += version.o pgm_check_info.o ctype.o ipl_data.o +obj-y += $(if $(CONFIG_PIE_BUILD),machine_kexec_reloc.o,relocs.o) obj-$(findstring y, $(CONFIG_PROTECTED_VIRTUALIZATION_GUEST) $(CONFIG_PGSTE)) += uv.o obj-$(CONFIG_RANDOMIZE_BASE) += kaslr.o obj-y += $(if $(CONFIG_KERNEL_UNCOMPRESSED),,decompressor.o) info.o @@ -48,6 +49,9 @@ targets := bzImage section_cmp.boot.data section_cmp.boot.preserved.data $(obj-y targets += vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 targets += vmlinux.bin.xz vmlinux.bin.lzma vmlinux.bin.lzo vmlinux.bin.lz4 targets += vmlinux.bin.zst info.bin syms.bin vmlinux.syms $(obj-all) +ifndef CONFIG_PIE_BUILD +targets += relocs.S +endif OBJECTS := $(addprefix $(obj)/,$(obj-y)) OBJECTS_ALL := $(addprefix $(obj)/,$(obj-all)) @@ -56,9 +60,9 @@ clean-files += vmlinux.map quiet_cmd_section_cmp = SECTCMP $* define cmd_section_cmp - s1=`$(OBJDUMP) -t -j "$*" "$<" | sort | \ + s1=`$(OBJDUMP) -t "$<" | grep "\s$*\s\+" | sort | \ sed -n "/0000000000000000/! s/.*\s$*\s\+//p" | sha256sum`; \ - s2=`$(OBJDUMP) -t -j "$*" "$(word 2,$^)" | sort | \ + s2=`$(OBJDUMP) -t "$(word 2,$^)" | grep "\s$*\s\+" | sort | \ sed -n "/0000000000000000/! s/.*\s$*\s\+//p" | sha256sum`; \ if [ "$$s1" != "$$s2" ]; then \ echo "error: section $* differs between $< and $(word 2,$^)" >&2; \ @@ -73,11 +77,12 @@ $(obj)/bzImage: $(obj)/vmlinux $(obj)/section_cmp.boot.data $(obj)/section_cmp.b $(obj)/section_cmp%: vmlinux $(obj)/vmlinux FORCE $(call if_changed,section_cmp) -LDFLAGS_vmlinux := --oformat $(LD_BFD) -e startup $(if $(CONFIG_VMLINUX_MAP),-Map=$(obj)/vmlinux.map) --build-id=sha1 -T +LDFLAGS_vmlinux-$(CONFIG_LD_ORPHAN_WARN) := --orphan-handling=$(CONFIG_LD_ORPHAN_WARN_LEVEL) +LDFLAGS_vmlinux := $(LDFLAGS_vmlinux-y) --oformat $(LD_BFD) -e startup $(if $(CONFIG_VMLINUX_MAP),-Map=$(obj)/vmlinux.map) --build-id=sha1 -T $(obj)/vmlinux: $(obj)/vmlinux.lds $(OBJECTS_ALL) FORCE $(call if_changed,ld) -LDFLAGS_vmlinux.syms := --oformat $(LD_BFD) -e startup -T +LDFLAGS_vmlinux.syms := $(LDFLAGS_vmlinux-y) --oformat $(LD_BFD) -e startup -T $(obj)/vmlinux.syms: $(obj)/vmlinux.lds $(OBJECTS) FORCE $(call if_changed,ld) @@ -93,7 +98,7 @@ OBJCOPYFLAGS_syms.o := -I binary -O elf64-s390 -B s390:64-bit --rename-section . $(obj)/syms.o: $(obj)/syms.bin FORCE $(call if_changed,objcopy) -OBJCOPYFLAGS_info.bin := -O binary --only-section=.vmlinux.info --set-section-flags .vmlinux.info=load +OBJCOPYFLAGS_info.bin := -O binary --only-section=.vmlinux.info --set-section-flags .vmlinux.info=alloc,load $(obj)/info.bin: vmlinux FORCE $(call if_changed,objcopy) @@ -105,6 +110,14 @@ OBJCOPYFLAGS_vmlinux.bin := -O binary --remove-section=.comment --remove-section $(obj)/vmlinux.bin: vmlinux FORCE $(call if_changed,objcopy) +ifndef CONFIG_PIE_BUILD +CMD_RELOCS=arch/s390/tools/relocs +quiet_cmd_relocs = RELOCS $@ + cmd_relocs = $(CMD_RELOCS) $< > $@ +$(obj)/relocs.S: vmlinux FORCE + $(call if_changed,relocs) +endif + suffix-$(CONFIG_KERNEL_GZIP) := .gz suffix-$(CONFIG_KERNEL_BZIP2) := .bz2 suffix-$(CONFIG_KERNEL_LZ4) := .lz4 diff --git a/arch/s390/boot/boot.h b/arch/s390/boot/boot.h index 222c6886acf6..567d60f78bbc 100644 --- a/arch/s390/boot/boot.h +++ b/arch/s390/boot/boot.h @@ -25,9 +25,14 @@ struct vmlinux_info { unsigned long bootdata_size; unsigned long bootdata_preserved_off; unsigned long bootdata_preserved_size; +#ifdef CONFIG_PIE_BUILD unsigned long dynsym_start; unsigned long rela_dyn_start; unsigned long rela_dyn_end; +#else + unsigned long got_start; + unsigned long got_end; +#endif unsigned long amode31_size; unsigned long init_mm_off; unsigned long swapper_pg_dir_off; @@ -83,6 +88,7 @@ extern unsigned long vmalloc_size; extern int vmalloc_size_set; extern char __boot_data_start[], __boot_data_end[]; extern char __boot_data_preserved_start[], __boot_data_preserved_end[]; +extern char __vmlinux_relocs_64_start[], __vmlinux_relocs_64_end[]; extern char _decompressor_syms_start[], _decompressor_syms_end[]; extern char _stack_start[], _stack_end[]; extern char _end[], _decompressor_end[]; diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index 9cc76e631759..6cf89314209a 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -141,7 +141,8 @@ static void copy_bootdata(void) memcpy((void *)vmlinux.bootdata_preserved_off, __boot_data_preserved_start, vmlinux.bootdata_preserved_size); } -static void handle_relocs(unsigned long offset) +#ifdef CONFIG_PIE_BUILD +static void kaslr_adjust_relocs(unsigned long min_addr, unsigned long max_addr, unsigned long offset) { Elf64_Rela *rela_start, *rela_end, *rela; int r_type, r_sym, rc; @@ -172,6 +173,54 @@ static void handle_relocs(unsigned long offset) } } +static void kaslr_adjust_got(unsigned long offset) {} +static void rescue_relocs(void) {} +static void free_relocs(void) {} +#else +static int *vmlinux_relocs_64_start; +static int *vmlinux_relocs_64_end; + +static void rescue_relocs(void) +{ + unsigned long size = __vmlinux_relocs_64_end - __vmlinux_relocs_64_start; + + vmlinux_relocs_64_start = (void *)physmem_alloc_top_down(RR_RELOC, size, 0); + vmlinux_relocs_64_end = (void *)vmlinux_relocs_64_start + size; + memmove(vmlinux_relocs_64_start, __vmlinux_relocs_64_start, size); +} + +static void free_relocs(void) +{ + physmem_free(RR_RELOC); +} + +static void kaslr_adjust_relocs(unsigned long min_addr, unsigned long max_addr, unsigned long offset) +{ + int *reloc; + long loc; + + /* Adjust R_390_64 relocations */ + for (reloc = vmlinux_relocs_64_start; reloc < vmlinux_relocs_64_end; reloc++) { + loc = (long)*reloc + offset; + if (loc < min_addr || loc > max_addr) + error("64-bit relocation outside of kernel!\n"); + *(u64 *)loc += offset; + } +} + +static void kaslr_adjust_got(unsigned long offset) +{ + u64 *entry; + + /* + * Even without -fPIE, Clang still uses a global offset table for some + * reason. Adjust the GOT entries. + */ + for (entry = (u64 *)vmlinux.got_start; entry < (u64 *)vmlinux.got_end; entry++) + *entry += offset; +} +#endif + /* * Merge information from several sources into a single ident_map_size value. * "ident_map_size" represents the upper limit of physical memory we may ever @@ -299,14 +348,19 @@ static void setup_vmalloc_size(void) vmalloc_size = max(size, vmalloc_size); } -static void offset_vmlinux_info(unsigned long offset) +static void kaslr_adjust_vmlinux_info(unsigned long offset) { *(unsigned long *)(&vmlinux.entry) += offset; vmlinux.bootdata_off += offset; vmlinux.bootdata_preserved_off += offset; +#ifdef CONFIG_PIE_BUILD vmlinux.rela_dyn_start += offset; vmlinux.rela_dyn_end += offset; vmlinux.dynsym_start += offset; +#else + vmlinux.got_start += offset; + vmlinux.got_end += offset; +#endif vmlinux.init_mm_off += offset; vmlinux.swapper_pg_dir_off += offset; vmlinux.invalid_pg_dir_off += offset; @@ -361,6 +415,7 @@ void startup_kernel(void) detect_physmem_online_ranges(max_physmem_end); save_ipl_cert_comp_list(); rescue_initrd(safe_addr, ident_map_size); + rescue_relocs(); if (kaslr_enabled()) { vmlinux_lma = randomize_within_range(vmlinux.image_size + vmlinux.bss_size, @@ -368,7 +423,7 @@ void startup_kernel(void) ident_map_size); if (vmlinux_lma) { __kaslr_offset = vmlinux_lma - vmlinux.default_lma; - offset_vmlinux_info(__kaslr_offset); + kaslr_adjust_vmlinux_info(__kaslr_offset); } } vmlinux_lma = vmlinux_lma ?: vmlinux.default_lma; @@ -393,18 +448,20 @@ void startup_kernel(void) /* * The order of the following operations is important: * - * - handle_relocs() must follow clear_bss_section() to establish static - * memory references to data in .bss to be used by setup_vmem() + * - kaslr_adjust_relocs() must follow clear_bss_section() to establish + * static memory references to data in .bss to be used by setup_vmem() * (i.e init_mm.pgd) * - * - setup_vmem() must follow handle_relocs() to be able using + * - setup_vmem() must follow kaslr_adjust_relocs() to be able using * static memory references to data in .bss (i.e init_mm.pgd) * - * - copy_bootdata() must follow setup_vmem() to propagate changes to - * bootdata made by setup_vmem() + * - copy_bootdata() must follow setup_vmem() to propagate changes + * to bootdata made by setup_vmem() */ clear_bss_section(vmlinux_lma); - handle_relocs(__kaslr_offset); + kaslr_adjust_relocs(vmlinux_lma, vmlinux_lma + vmlinux.image_size, __kaslr_offset); + kaslr_adjust_got(__kaslr_offset); + free_relocs(); setup_vmem(asce_limit); copy_bootdata(); diff --git a/arch/s390/boot/vmlinux.lds.S b/arch/s390/boot/vmlinux.lds.S index 389df0e0d9e5..3d7ea585ab99 100644 --- a/arch/s390/boot/vmlinux.lds.S +++ b/arch/s390/boot/vmlinux.lds.S @@ -31,6 +31,7 @@ SECTIONS _text = .; /* Text */ *(.text) *(.text.*) + INIT_TEXT _etext = . ; } .rodata : { @@ -39,6 +40,9 @@ SECTIONS *(.rodata.*) _erodata = . ; } + .got : { + *(.got) + } NOTES .data : { _data = . ; @@ -106,6 +110,24 @@ SECTIONS _compressed_end = .; } +#ifndef CONFIG_PIE_BUILD + /* + * When the kernel is built with CONFIG_KERNEL_UNCOMPRESSED, the entire + * uncompressed vmlinux.bin is positioned in the bzImage decompressor + * image at the default kernel LMA of 0x100000, enabling it to be + * executed in-place. However, the size of .vmlinux.relocs could be + * large enough to cause an overlap with the uncompressed kernel at the + * address 0x100000. To address this issue, .vmlinux.relocs is + * positioned after the .rodata.compressed. + */ + . = ALIGN(4); + .vmlinux.relocs : { + __vmlinux_relocs_64_start = .; + *(.vmlinux.relocs_64) + __vmlinux_relocs_64_end = .; + } +#endif + #define SB_TRAILER_SIZE 32 /* Trailer needed for Secure Boot */ . += SB_TRAILER_SIZE; /* make sure .sb.trailer does not overwrite the previous section */ @@ -118,8 +140,34 @@ SECTIONS } _end = .; + DWARF_DEBUG + ELF_DETAILS + + /* + * Make sure that the .got.plt is either completely empty or it + * contains only the three reserved double words. + */ + .got.plt : { + *(.got.plt) + } + ASSERT(SIZEOF(.got.plt) == 0 || SIZEOF(.got.plt) == 0x18, "Unexpected GOT/PLT entries detected!") + + /* + * Sections that should stay zero sized, which is safer to + * explicitly check instead of blindly discarding. + */ + .plt : { + *(.plt) *(.plt.*) *(.iplt) *(.igot .igot.plt) + } + ASSERT(SIZEOF(.plt) == 0, "Unexpected run-time procedure linkages detected!") + .rela.dyn : { + *(.rela.*) *(.rela_*) + } + ASSERT(SIZEOF(.rela.dyn) == 0, "Unexpected run-time relocations (.rela) detected!") + /* Sections to be discarded */ /DISCARD/ : { + COMMON_DISCARDS *(.eh_frame) *(__ex_table) *(*__ksymtab*) diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 06756bad5e30..4032e6e136ac 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -824,6 +824,8 @@ CONFIG_TEST_LOCKUP=m CONFIG_DEBUG_PREEMPT=y CONFIG_PROVE_LOCKING=y CONFIG_LOCK_STAT=y +CONFIG_LOCKDEP_BITS=16 +CONFIG_LOCKDEP_CHAINS_BITS=17 CONFIG_DEBUG_ATOMIC_SLEEP=y CONFIG_DEBUG_LOCKING_API_SELFTESTS=y CONFIG_DEBUG_IRQFLAGS=y diff --git a/arch/s390/crypto/chacha-glue.c b/arch/s390/crypto/chacha-glue.c index ed9959e6f714..f8b0c52e77a4 100644 --- a/arch/s390/crypto/chacha-glue.c +++ b/arch/s390/crypto/chacha-glue.c @@ -15,14 +15,14 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/sizes.h> -#include <asm/fpu/api.h> +#include <asm/fpu.h> #include "chacha-s390.h" static void chacha20_crypt_s390(u32 *state, u8 *dst, const u8 *src, unsigned int nbytes, const u32 *key, u32 *counter) { - struct kernel_fpu vxstate; + DECLARE_KERNEL_FPU_ONSTACK32(vxstate); kernel_fpu_begin(&vxstate, KERNEL_VXR); chacha20_vx(dst, src, nbytes, key, counter); diff --git a/arch/s390/crypto/chacha-s390.S b/arch/s390/crypto/chacha-s390.S index 37cb63f25b17..63f3102678c0 100644 --- a/arch/s390/crypto/chacha-s390.S +++ b/arch/s390/crypto/chacha-s390.S @@ -8,7 +8,7 @@ #include <linux/linkage.h> #include <asm/nospec-insn.h> -#include <asm/vx-insn.h> +#include <asm/fpu-insn.h> #define SP %r15 #define FRAME (16 * 8 + 4 * 8) diff --git a/arch/s390/crypto/crc32-vx.c b/arch/s390/crypto/crc32-vx.c index 017143e9cef7..74f17c905d12 100644 --- a/arch/s390/crypto/crc32-vx.c +++ b/arch/s390/crypto/crc32-vx.c @@ -13,8 +13,8 @@ #include <linux/cpufeature.h> #include <linux/crc32.h> #include <crypto/internal/hash.h> -#include <asm/fpu/api.h> - +#include <asm/fpu.h> +#include "crc32-vx.h" #define CRC32_BLOCK_SIZE 1 #define CRC32_DIGEST_SIZE 4 @@ -31,11 +31,6 @@ struct crc_desc_ctx { u32 crc; }; -/* Prototypes for functions in assembly files */ -u32 crc32_le_vgfm_16(u32 crc, unsigned char const *buf, size_t size); -u32 crc32_be_vgfm_16(u32 crc, unsigned char const *buf, size_t size); -u32 crc32c_le_vgfm_16(u32 crc, unsigned char const *buf, size_t size); - /* * DEFINE_CRC32_VX() - Define a CRC-32 function using the vector extension * @@ -49,8 +44,8 @@ u32 crc32c_le_vgfm_16(u32 crc, unsigned char const *buf, size_t size); static u32 __pure ___fname(u32 crc, \ unsigned char const *data, size_t datalen) \ { \ - struct kernel_fpu vxstate; \ unsigned long prealign, aligned, remaining; \ + DECLARE_KERNEL_FPU_ONSTACK16(vxstate); \ \ if (datalen < VX_MIN_LEN + VX_ALIGN_MASK) \ return ___crc32_sw(crc, data, datalen); \ diff --git a/arch/s390/crypto/crc32-vx.h b/arch/s390/crypto/crc32-vx.h new file mode 100644 index 000000000000..652c96e1a822 --- /dev/null +++ b/arch/s390/crypto/crc32-vx.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _CRC32_VX_S390_H +#define _CRC32_VX_S390_H + +#include <linux/types.h> + +u32 crc32_be_vgfm_16(u32 crc, unsigned char const *buf, size_t size); +u32 crc32_le_vgfm_16(u32 crc, unsigned char const *buf, size_t size); +u32 crc32c_le_vgfm_16(u32 crc, unsigned char const *buf, size_t size); + +#endif /* _CRC32_VX_S390_H */ diff --git a/arch/s390/crypto/crc32be-vx.S b/arch/s390/crypto/crc32be-vx.c index 34ee47926891..fed7c9c70d05 100644 --- a/arch/s390/crypto/crc32be-vx.S +++ b/arch/s390/crypto/crc32be-vx.c @@ -12,20 +12,17 @@ * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com> */ -#include <linux/linkage.h> -#include <asm/nospec-insn.h> -#include <asm/vx-insn.h> +#include <linux/types.h> +#include <asm/fpu.h> +#include "crc32-vx.h" /* Vector register range containing CRC-32 constants */ -#define CONST_R1R2 %v9 -#define CONST_R3R4 %v10 -#define CONST_R5 %v11 -#define CONST_R6 %v12 -#define CONST_RU_POLY %v13 -#define CONST_CRC_POLY %v14 - - .data - .balign 8 +#define CONST_R1R2 9 +#define CONST_R3R4 10 +#define CONST_R5 11 +#define CONST_R6 12 +#define CONST_RU_POLY 13 +#define CONST_CRC_POLY 14 /* * The CRC-32 constant block contains reduction constants to fold and @@ -58,105 +55,74 @@ * P'(x) = 0xEDB88320 */ -SYM_DATA_START_LOCAL(constants_CRC_32_BE) - .quad 0x08833794c, 0x0e6228b11 # R1, R2 - .quad 0x0c5b9cd4c, 0x0e8a45605 # R3, R4 - .quad 0x0f200aa66, 1 << 32 # R5, x32 - .quad 0x0490d678d, 1 # R6, 1 - .quad 0x104d101df, 0 # u - .quad 0x104C11DB7, 0 # P(x) -SYM_DATA_END(constants_CRC_32_BE) - - .previous - - GEN_BR_THUNK %r14 - - .text -/* - * The CRC-32 function(s) use these calling conventions: - * - * Parameters: - * - * %r2: Initial CRC value, typically ~0; and final CRC (return) value. - * %r3: Input buffer pointer, performance might be improved if the - * buffer is on a doubleword boundary. - * %r4: Length of the buffer, must be 64 bytes or greater. +static unsigned long constants_CRC_32_BE[] = { + 0x08833794c, 0x0e6228b11, /* R1, R2 */ + 0x0c5b9cd4c, 0x0e8a45605, /* R3, R4 */ + 0x0f200aa66, 1UL << 32, /* R5, x32 */ + 0x0490d678d, 1, /* R6, 1 */ + 0x104d101df, 0, /* u */ + 0x104C11DB7, 0, /* P(x) */ +}; + +/** + * crc32_be_vgfm_16 - Compute CRC-32 (BE variant) with vector registers + * @crc: Initial CRC value, typically ~0. + * @buf: Input buffer pointer, performance might be improved if the + * buffer is on a doubleword boundary. + * @size: Size of the buffer, must be 64 bytes or greater. * * Register usage: - * - * %r5: CRC-32 constant pool base pointer. * V0: Initial CRC value and intermediate constants and results. * V1..V4: Data for CRC computation. * V5..V8: Next data chunks that are fetched from the input buffer. - * * V9..V14: CRC-32 constants. */ -SYM_FUNC_START(crc32_be_vgfm_16) +u32 crc32_be_vgfm_16(u32 crc, unsigned char const *buf, size_t size) +{ /* Load CRC-32 constants */ - larl %r5,constants_CRC_32_BE - VLM CONST_R1R2,CONST_CRC_POLY,0,%r5 + fpu_vlm(CONST_R1R2, CONST_CRC_POLY, &constants_CRC_32_BE); + fpu_vzero(0); /* Load the initial CRC value into the leftmost word of V0. */ - VZERO %v0 - VLVGF %v0,%r2,0 + fpu_vlvgf(0, crc, 0); /* Load a 64-byte data chunk and XOR with CRC */ - VLM %v1,%v4,0,%r3 /* 64-bytes into V1..V4 */ - VX %v1,%v0,%v1 /* V1 ^= CRC */ - aghi %r3,64 /* BUF = BUF + 64 */ - aghi %r4,-64 /* LEN = LEN - 64 */ - - /* Check remaining buffer size and jump to proper folding method */ - cghi %r4,64 - jl .Lless_than_64bytes - -.Lfold_64bytes_loop: - /* Load the next 64-byte data chunk into V5 to V8 */ - VLM %v5,%v8,0,%r3 + fpu_vlm(1, 4, buf); + fpu_vx(1, 0, 1); + buf += 64; + size -= 64; + + while (size >= 64) { + /* Load the next 64-byte data chunk into V5 to V8 */ + fpu_vlm(5, 8, buf); + + /* + * Perform a GF(2) multiplication of the doublewords in V1 with + * the reduction constants in V0. The intermediate result is + * then folded (accumulated) with the next data chunk in V5 and + * stored in V1. Repeat this step for the register contents + * in V2, V3, and V4 respectively. + */ + fpu_vgfmag(1, CONST_R1R2, 1, 5); + fpu_vgfmag(2, CONST_R1R2, 2, 6); + fpu_vgfmag(3, CONST_R1R2, 3, 7); + fpu_vgfmag(4, CONST_R1R2, 4, 8); + buf += 64; + size -= 64; + } - /* - * Perform a GF(2) multiplication of the doublewords in V1 with - * the reduction constants in V0. The intermediate result is - * then folded (accumulated) with the next data chunk in V5 and - * stored in V1. Repeat this step for the register contents - * in V2, V3, and V4 respectively. - */ - VGFMAG %v1,CONST_R1R2,%v1,%v5 - VGFMAG %v2,CONST_R1R2,%v2,%v6 - VGFMAG %v3,CONST_R1R2,%v3,%v7 - VGFMAG %v4,CONST_R1R2,%v4,%v8 - - /* Adjust buffer pointer and length for next loop */ - aghi %r3,64 /* BUF = BUF + 64 */ - aghi %r4,-64 /* LEN = LEN - 64 */ - - cghi %r4,64 - jnl .Lfold_64bytes_loop - -.Lless_than_64bytes: /* Fold V1 to V4 into a single 128-bit value in V1 */ - VGFMAG %v1,CONST_R3R4,%v1,%v2 - VGFMAG %v1,CONST_R3R4,%v1,%v3 - VGFMAG %v1,CONST_R3R4,%v1,%v4 - - /* Check whether to continue with 64-bit folding */ - cghi %r4,16 - jl .Lfinal_fold + fpu_vgfmag(1, CONST_R3R4, 1, 2); + fpu_vgfmag(1, CONST_R3R4, 1, 3); + fpu_vgfmag(1, CONST_R3R4, 1, 4); -.Lfold_16bytes_loop: + while (size >= 16) { + fpu_vl(2, buf); + fpu_vgfmag(1, CONST_R3R4, 1, 2); + buf += 16; + size -= 16; + } - VL %v2,0,,%r3 /* Load next data chunk */ - VGFMAG %v1,CONST_R3R4,%v1,%v2 /* Fold next data chunk */ - - /* Adjust buffer pointer and size for folding next data chunk */ - aghi %r3,16 - aghi %r4,-16 - - /* Process remaining data chunks */ - cghi %r4,16 - jnl .Lfold_16bytes_loop - -.Lfinal_fold: /* * The R5 constant is used to fold a 128-bit value into an 96-bit value * that is XORed with the next 96-bit input data chunk. To use a single @@ -164,7 +130,7 @@ SYM_FUNC_START(crc32_be_vgfm_16) * form an intermediate 96-bit value (with appended zeros) which is then * XORed with the intermediate reduction result. */ - VGFMG %v1,CONST_R5,%v1 + fpu_vgfmg(1, CONST_R5, 1); /* * Further reduce the remaining 96-bit value to a 64-bit value using a @@ -173,7 +139,7 @@ SYM_FUNC_START(crc32_be_vgfm_16) * doubleword with R6. The result is a 64-bit value and is subject to * the Barret reduction. */ - VGFMG %v1,CONST_R6,%v1 + fpu_vgfmg(1, CONST_R6, 1); /* * The input values to the Barret reduction are the degree-63 polynomial @@ -194,20 +160,15 @@ SYM_FUNC_START(crc32_be_vgfm_16) */ /* T1(x) = floor( R(x) / x^32 ) GF2MUL u */ - VUPLLF %v2,%v1 - VGFMG %v2,CONST_RU_POLY,%v2 + fpu_vupllf(2, 1); + fpu_vgfmg(2, CONST_RU_POLY, 2); /* * Compute the GF(2) product of the CRC polynomial in VO with T1(x) in * V2 and XOR the intermediate result, T2(x), with the value in V1. * The final result is in the rightmost word of V2. */ - VUPLLF %v2,%v2 - VGFMAG %v2,CONST_CRC_POLY,%v2,%v1 - -.Ldone: - VLGVF %r2,%v2,3 - BR_EX %r14 -SYM_FUNC_END(crc32_be_vgfm_16) - -.previous + fpu_vupllf(2, 2); + fpu_vgfmag(2, CONST_CRC_POLY, 2, 1); + return fpu_vlgvf(2, 3); +} diff --git a/arch/s390/crypto/crc32le-vx.S b/arch/s390/crypto/crc32le-vx.c index 5a819ae09a0b..2f629f394df7 100644 --- a/arch/s390/crypto/crc32le-vx.S +++ b/arch/s390/crypto/crc32le-vx.c @@ -13,20 +13,17 @@ * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com> */ -#include <linux/linkage.h> -#include <asm/nospec-insn.h> -#include <asm/vx-insn.h> +#include <linux/types.h> +#include <asm/fpu.h> +#include "crc32-vx.h" /* Vector register range containing CRC-32 constants */ -#define CONST_PERM_LE2BE %v9 -#define CONST_R2R1 %v10 -#define CONST_R4R3 %v11 -#define CONST_R5 %v12 -#define CONST_RU_POLY %v13 -#define CONST_CRC_POLY %v14 - - .data - .balign 8 +#define CONST_PERM_LE2BE 9 +#define CONST_R2R1 10 +#define CONST_R4R3 11 +#define CONST_R5 12 +#define CONST_RU_POLY 13 +#define CONST_CRC_POLY 14 /* * The CRC-32 constant block contains reduction constants to fold and @@ -59,64 +56,43 @@ * P'(x) = 0x82F63B78 */ -SYM_DATA_START_LOCAL(constants_CRC_32_LE) - .octa 0x0F0E0D0C0B0A09080706050403020100 # BE->LE mask - .quad 0x1c6e41596, 0x154442bd4 # R2, R1 - .quad 0x0ccaa009e, 0x1751997d0 # R4, R3 - .octa 0x163cd6124 # R5 - .octa 0x1F7011641 # u' - .octa 0x1DB710641 # P'(x) << 1 -SYM_DATA_END(constants_CRC_32_LE) - -SYM_DATA_START_LOCAL(constants_CRC_32C_LE) - .octa 0x0F0E0D0C0B0A09080706050403020100 # BE->LE mask - .quad 0x09e4addf8, 0x740eef02 # R2, R1 - .quad 0x14cd00bd6, 0xf20c0dfe # R4, R3 - .octa 0x0dd45aab8 # R5 - .octa 0x0dea713f1 # u' - .octa 0x105ec76f0 # P'(x) << 1 -SYM_DATA_END(constants_CRC_32C_LE) - - .previous - - GEN_BR_THUNK %r14 - - .text - -/* - * The CRC-32 functions use these calling conventions: - * - * Parameters: - * - * %r2: Initial CRC value, typically ~0; and final CRC (return) value. - * %r3: Input buffer pointer, performance might be improved if the - * buffer is on a doubleword boundary. - * %r4: Length of the buffer, must be 64 bytes or greater. +static unsigned long constants_CRC_32_LE[] = { + 0x0f0e0d0c0b0a0908, 0x0706050403020100, /* BE->LE mask */ + 0x1c6e41596, 0x154442bd4, /* R2, R1 */ + 0x0ccaa009e, 0x1751997d0, /* R4, R3 */ + 0x0, 0x163cd6124, /* R5 */ + 0x0, 0x1f7011641, /* u' */ + 0x0, 0x1db710641 /* P'(x) << 1 */ +}; + +static unsigned long constants_CRC_32C_LE[] = { + 0x0f0e0d0c0b0a0908, 0x0706050403020100, /* BE->LE mask */ + 0x09e4addf8, 0x740eef02, /* R2, R1 */ + 0x14cd00bd6, 0xf20c0dfe, /* R4, R3 */ + 0x0, 0x0dd45aab8, /* R5 */ + 0x0, 0x0dea713f1, /* u' */ + 0x0, 0x105ec76f0 /* P'(x) << 1 */ +}; + +/** + * crc32_le_vgfm_generic - Compute CRC-32 (LE variant) with vector registers + * @crc: Initial CRC value, typically ~0. + * @buf: Input buffer pointer, performance might be improved if the + * buffer is on a doubleword boundary. + * @size: Size of the buffer, must be 64 bytes or greater. + * @constants: CRC-32 constant pool base pointer. * * Register usage: - * - * %r5: CRC-32 constant pool base pointer. - * V0: Initial CRC value and intermediate constants and results. - * V1..V4: Data for CRC computation. - * V5..V8: Next data chunks that are fetched from the input buffer. - * V9: Constant for BE->LE conversion and shift operations - * + * V0: Initial CRC value and intermediate constants and results. + * V1..V4: Data for CRC computation. + * V5..V8: Next data chunks that are fetched from the input buffer. + * V9: Constant for BE->LE conversion and shift operations * V10..V14: CRC-32 constants. */ - -SYM_FUNC_START(crc32_le_vgfm_16) - larl %r5,constants_CRC_32_LE - j crc32_le_vgfm_generic -SYM_FUNC_END(crc32_le_vgfm_16) - -SYM_FUNC_START(crc32c_le_vgfm_16) - larl %r5,constants_CRC_32C_LE - j crc32_le_vgfm_generic -SYM_FUNC_END(crc32c_le_vgfm_16) - -SYM_FUNC_START(crc32_le_vgfm_generic) +static u32 crc32_le_vgfm_generic(u32 crc, unsigned char const *buf, size_t size, unsigned long *constants) +{ /* Load CRC-32 constants */ - VLM CONST_PERM_LE2BE,CONST_CRC_POLY,0,%r5 + fpu_vlm(CONST_PERM_LE2BE, CONST_CRC_POLY, constants); /* * Load the initial CRC value. @@ -125,90 +101,73 @@ SYM_FUNC_START(crc32_le_vgfm_generic) * vector register and is later XORed with the LSB portion * of the loaded input data. */ - VZERO %v0 /* Clear V0 */ - VLVGF %v0,%r2,3 /* Load CRC into rightmost word */ + fpu_vzero(0); /* Clear V0 */ + fpu_vlvgf(0, crc, 3); /* Load CRC into rightmost word */ /* Load a 64-byte data chunk and XOR with CRC */ - VLM %v1,%v4,0,%r3 /* 64-bytes into V1..V4 */ - VPERM %v1,%v1,%v1,CONST_PERM_LE2BE - VPERM %v2,%v2,%v2,CONST_PERM_LE2BE - VPERM %v3,%v3,%v3,CONST_PERM_LE2BE - VPERM %v4,%v4,%v4,CONST_PERM_LE2BE + fpu_vlm(1, 4, buf); + fpu_vperm(1, 1, 1, CONST_PERM_LE2BE); + fpu_vperm(2, 2, 2, CONST_PERM_LE2BE); + fpu_vperm(3, 3, 3, CONST_PERM_LE2BE); + fpu_vperm(4, 4, 4, CONST_PERM_LE2BE); + + fpu_vx(1, 0, 1); /* V1 ^= CRC */ + buf += 64; + size -= 64; + + while (size >= 64) { + fpu_vlm(5, 8, buf); + fpu_vperm(5, 5, 5, CONST_PERM_LE2BE); + fpu_vperm(6, 6, 6, CONST_PERM_LE2BE); + fpu_vperm(7, 7, 7, CONST_PERM_LE2BE); + fpu_vperm(8, 8, 8, CONST_PERM_LE2BE); + /* + * Perform a GF(2) multiplication of the doublewords in V1 with + * the R1 and R2 reduction constants in V0. The intermediate + * result is then folded (accumulated) with the next data chunk + * in V5 and stored in V1. Repeat this step for the register + * contents in V2, V3, and V4 respectively. + */ + fpu_vgfmag(1, CONST_R2R1, 1, 5); + fpu_vgfmag(2, CONST_R2R1, 2, 6); + fpu_vgfmag(3, CONST_R2R1, 3, 7); + fpu_vgfmag(4, CONST_R2R1, 4, 8); + buf += 64; + size -= 64; + } - VX %v1,%v0,%v1 /* V1 ^= CRC */ - aghi %r3,64 /* BUF = BUF + 64 */ - aghi %r4,-64 /* LEN = LEN - 64 */ - - cghi %r4,64 - jl .Lless_than_64bytes - -.Lfold_64bytes_loop: - /* Load the next 64-byte data chunk into V5 to V8 */ - VLM %v5,%v8,0,%r3 - VPERM %v5,%v5,%v5,CONST_PERM_LE2BE - VPERM %v6,%v6,%v6,CONST_PERM_LE2BE - VPERM %v7,%v7,%v7,CONST_PERM_LE2BE - VPERM %v8,%v8,%v8,CONST_PERM_LE2BE - - /* - * Perform a GF(2) multiplication of the doublewords in V1 with - * the R1 and R2 reduction constants in V0. The intermediate result - * is then folded (accumulated) with the next data chunk in V5 and - * stored in V1. Repeat this step for the register contents - * in V2, V3, and V4 respectively. - */ - VGFMAG %v1,CONST_R2R1,%v1,%v5 - VGFMAG %v2,CONST_R2R1,%v2,%v6 - VGFMAG %v3,CONST_R2R1,%v3,%v7 - VGFMAG %v4,CONST_R2R1,%v4,%v8 - - aghi %r3,64 /* BUF = BUF + 64 */ - aghi %r4,-64 /* LEN = LEN - 64 */ - - cghi %r4,64 - jnl .Lfold_64bytes_loop - -.Lless_than_64bytes: /* * Fold V1 to V4 into a single 128-bit value in V1. Multiply V1 with R3 * and R4 and accumulating the next 128-bit chunk until a single 128-bit * value remains. */ - VGFMAG %v1,CONST_R4R3,%v1,%v2 - VGFMAG %v1,CONST_R4R3,%v1,%v3 - VGFMAG %v1,CONST_R4R3,%v1,%v4 - - cghi %r4,16 - jl .Lfinal_fold - -.Lfold_16bytes_loop: - - VL %v2,0,,%r3 /* Load next data chunk */ - VPERM %v2,%v2,%v2,CONST_PERM_LE2BE - VGFMAG %v1,CONST_R4R3,%v1,%v2 /* Fold next data chunk */ + fpu_vgfmag(1, CONST_R4R3, 1, 2); + fpu_vgfmag(1, CONST_R4R3, 1, 3); + fpu_vgfmag(1, CONST_R4R3, 1, 4); + + while (size >= 16) { + fpu_vl(2, buf); + fpu_vperm(2, 2, 2, CONST_PERM_LE2BE); + fpu_vgfmag(1, CONST_R4R3, 1, 2); + buf += 16; + size -= 16; + } - aghi %r3,16 - aghi %r4,-16 - - cghi %r4,16 - jnl .Lfold_16bytes_loop - -.Lfinal_fold: /* * Set up a vector register for byte shifts. The shift value must * be loaded in bits 1-4 in byte element 7 of a vector register. * Shift by 8 bytes: 0x40 * Shift by 4 bytes: 0x20 */ - VLEIB %v9,0x40,7 + fpu_vleib(9, 0x40, 7); /* * Prepare V0 for the next GF(2) multiplication: shift V0 by 8 bytes * to move R4 into the rightmost doubleword and set the leftmost * doubleword to 0x1. */ - VSRLB %v0,CONST_R4R3,%v9 - VLEIG %v0,1,0 + fpu_vsrlb(0, CONST_R4R3, 9); + fpu_vleig(0, 1, 0); /* * Compute GF(2) product of V1 and V0. The rightmost doubleword @@ -216,7 +175,7 @@ SYM_FUNC_START(crc32_le_vgfm_generic) * multiplied by 0x1 and is then XORed with rightmost product. * Implicitly, the intermediate leftmost product becomes padded */ - VGFMG %v1,%v0,%v1 + fpu_vgfmg(1, 0, 1); /* * Now do the final 32-bit fold by multiplying the rightmost word @@ -231,10 +190,10 @@ SYM_FUNC_START(crc32_le_vgfm_generic) * rightmost doubleword and the leftmost doubleword is zero to ignore * the leftmost product of V1. */ - VLEIB %v9,0x20,7 /* Shift by words */ - VSRLB %v2,%v1,%v9 /* Store remaining bits in V2 */ - VUPLLF %v1,%v1 /* Split rightmost doubleword */ - VGFMAG %v1,CONST_R5,%v1,%v2 /* V1 = (V1 * R5) XOR V2 */ + fpu_vleib(9, 0x20, 7); /* Shift by words */ + fpu_vsrlb(2, 1, 9); /* Store remaining bits in V2 */ + fpu_vupllf(1, 1); /* Split rightmost doubleword */ + fpu_vgfmag(1, CONST_R5, 1, 2); /* V1 = (V1 * R5) XOR V2 */ /* * Apply a Barret reduction to compute the final 32-bit CRC value. @@ -256,20 +215,26 @@ SYM_FUNC_START(crc32_le_vgfm_generic) */ /* T1(x) = floor( R(x) / x^32 ) GF2MUL u */ - VUPLLF %v2,%v1 - VGFMG %v2,CONST_RU_POLY,%v2 + fpu_vupllf(2, 1); + fpu_vgfmg(2, CONST_RU_POLY, 2); /* * Compute the GF(2) product of the CRC polynomial with T1(x) in * V2 and XOR the intermediate result, T2(x), with the value in V1. * The final result is stored in word element 2 of V2. */ - VUPLLF %v2,%v2 - VGFMAG %v2,CONST_CRC_POLY,%v2,%v1 + fpu_vupllf(2, 2); + fpu_vgfmag(2, CONST_CRC_POLY, 2, 1); + + return fpu_vlgvf(2, 2); +} -.Ldone: - VLGVF %r2,%v2,2 - BR_EX %r14 -SYM_FUNC_END(crc32_le_vgfm_generic) +u32 crc32_le_vgfm_16(u32 crc, unsigned char const *buf, size_t size) +{ + return crc32_le_vgfm_generic(crc, buf, size, &constants_CRC_32_LE[0]); +} -.previous +u32 crc32c_le_vgfm_16(u32 crc, unsigned char const *buf, size_t size) +{ + return crc32_le_vgfm_generic(crc, buf, size, &constants_CRC_32C_LE[0]); +} diff --git a/arch/s390/crypto/paes_s390.c b/arch/s390/crypto/paes_s390.c index 55ee5567a5ea..99f7e1f2b70a 100644 --- a/arch/s390/crypto/paes_s390.c +++ b/arch/s390/crypto/paes_s390.c @@ -125,20 +125,8 @@ struct s390_pxts_ctx { static inline int __paes_keyblob2pkey(struct key_blob *kb, struct pkey_protkey *pk) { - int i, ret; - - /* try three times in case of failure */ - for (i = 0; i < 3; i++) { - if (i > 0 && ret == -EAGAIN && in_task()) - if (msleep_interruptible(1000)) - return -EINTR; - ret = pkey_keyblob2pkey(kb->key, kb->keylen, - pk->protkey, &pk->len, &pk->type); - if (ret == 0) - break; - } - - return ret; + return pkey_keyblob2pkey(kb->key, kb->keylen, + pk->protkey, &pk->len, &pk->type); } static inline int __paes_convert_key(struct s390_paes_ctx *ctx) diff --git a/arch/s390/hypfs/hypfs_diag0c.c b/arch/s390/hypfs/hypfs_diag0c.c index 9a2786079e3a..4131f0daa5ea 100644 --- a/arch/s390/hypfs/hypfs_diag0c.c +++ b/arch/s390/hypfs/hypfs_diag0c.c @@ -20,8 +20,7 @@ */ static void diag0c_fn(void *data) { - diag_stat_inc(DIAG_STAT_X00C); - diag_amode31_ops.diag0c(((void **)data)[smp_processor_id()]); + diag0c(((void **)data)[smp_processor_id()]); } /* diff --git a/arch/s390/hypfs/hypfs_sprp.c b/arch/s390/hypfs/hypfs_sprp.c index f5f7e78ddc0c..9fc3f0dae8f0 100644 --- a/arch/s390/hypfs/hypfs_sprp.c +++ b/arch/s390/hypfs/hypfs_sprp.c @@ -25,7 +25,7 @@ static inline unsigned long __hypfs_sprp_diag304(void *data, unsigned long cmd) { - union register_pair r1 = { .even = (unsigned long)data, }; + union register_pair r1 = { .even = virt_to_phys(data), }; asm volatile("diag %[r1],%[r3],0x304\n" : [r1] "+&d" (r1.pair) @@ -74,7 +74,7 @@ static int __hypfs_sprp_ioctl(void __user *user_area) int rc; rc = -ENOMEM; - data = (void *) get_zeroed_page(GFP_KERNEL | GFP_DMA); + data = (void *)get_zeroed_page(GFP_KERNEL); diag304 = kzalloc(sizeof(*diag304), GFP_KERNEL); if (!data || !diag304) goto out; diff --git a/arch/s390/include/asm/access-regs.h b/arch/s390/include/asm/access-regs.h new file mode 100644 index 000000000000..1a6412d9f5ad --- /dev/null +++ b/arch/s390/include/asm/access-regs.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright IBM Corp. 1999, 2024 + */ + +#ifndef __ASM_S390_ACCESS_REGS_H +#define __ASM_S390_ACCESS_REGS_H + +#include <linux/instrumented.h> +#include <asm/sigcontext.h> + +struct access_regs { + unsigned int regs[NUM_ACRS]; +}; + +static inline void save_access_regs(unsigned int *acrs) +{ + struct access_regs *regs = (struct access_regs *)acrs; + + instrument_write(regs, sizeof(*regs)); + asm volatile("stamy 0,15,%[regs]" + : [regs] "=QS" (*regs) + : + : "memory"); +} + +static inline void restore_access_regs(unsigned int *acrs) +{ + struct access_regs *regs = (struct access_regs *)acrs; + + instrument_read(regs, sizeof(*regs)); + asm volatile("lamy 0,15,%[regs]" + : + : [regs] "QS" (*regs) + : "memory"); +} + +#endif /* __ASM_S390_ACCESS_REGS_H */ diff --git a/arch/s390/include/asm/appldata.h b/arch/s390/include/asm/appldata.h index f2240392c708..a92ebbc7aa7a 100644 --- a/arch/s390/include/asm/appldata.h +++ b/arch/s390/include/asm/appldata.h @@ -54,13 +54,13 @@ static inline int appldata_asm(struct appldata_parameter_list *parm_list, parm_list->function = fn; parm_list->parlist_length = sizeof(*parm_list); parm_list->buffer_length = length; - parm_list->product_id_addr = (unsigned long) id; + parm_list->product_id_addr = virt_to_phys(id); parm_list->buffer_addr = virt_to_phys(buffer); diag_stat_inc(DIAG_STAT_X0DC); asm volatile( " diag %1,%0,0xdc" : "=d" (ry) - : "d" (parm_list), "m" (*parm_list), "m" (*id) + : "d" (virt_to_phys(parm_list)), "m" (*parm_list), "m" (*id) : "cc"); return ry; } diff --git a/arch/s390/include/asm/asm-prototypes.h b/arch/s390/include/asm/asm-prototypes.h index a873e873e1ee..56096ae26f29 100644 --- a/arch/s390/include/asm/asm-prototypes.h +++ b/arch/s390/include/asm/asm-prototypes.h @@ -3,7 +3,7 @@ #include <linux/kvm_host.h> #include <linux/ftrace.h> -#include <asm/fpu/api.h> +#include <asm/fpu.h> #include <asm-generic/asm-prototypes.h> __int128_t __ashlti3(__int128_t a, int b); diff --git a/arch/s390/include/asm/bug.h b/arch/s390/include/asm/bug.h index aebe1e22c7be..c500d45fb465 100644 --- a/arch/s390/include/asm/bug.h +++ b/arch/s390/include/asm/bug.h @@ -14,7 +14,7 @@ ".section .rodata.str,\"aMS\",@progbits,1\n" \ "1: .asciz \""__FILE__"\"\n" \ ".previous\n" \ - ".section __bug_table,\"awM\",@progbits,%2\n" \ + ".section __bug_table,\"aw\"\n" \ "2: .long 0b-.\n" \ " .long 1b-.\n" \ " .short %0,%1\n" \ @@ -30,7 +30,7 @@ #define __EMIT_BUG(x) do { \ asm_inline volatile( \ "0: mc 0,0\n" \ - ".section __bug_table,\"awM\",@progbits,%1\n" \ + ".section __bug_table,\"aw\"\n" \ "1: .long 0b-.\n" \ " .short %0\n" \ " .org 1b+%1\n" \ diff --git a/arch/s390/include/asm/checksum.h b/arch/s390/include/asm/checksum.h index 69837eec2ff5..b89159591ca0 100644 --- a/arch/s390/include/asm/checksum.h +++ b/arch/s390/include/asm/checksum.h @@ -12,36 +12,29 @@ #ifndef _S390_CHECKSUM_H #define _S390_CHECKSUM_H -#include <linux/kasan-checks.h> +#include <linux/instrumented.h> #include <linux/in6.h> -/* - * Computes the checksum of a memory block at buff, length len, - * and adds in "sum" (32-bit). - * - * Returns a 32-bit number suitable for feeding into itself - * or csum_tcpudp_magic. - * - * This function must be called with even lengths, except - * for the last fragment, which may be odd. - * - * It's best to have buff aligned on a 32-bit boundary. - */ -static inline __wsum csum_partial(const void *buff, int len, __wsum sum) +static inline __wsum cksm(const void *buff, int len, __wsum sum) { union register_pair rp = { - .even = (unsigned long) buff, - .odd = (unsigned long) len, + .even = (unsigned long)buff, + .odd = (unsigned long)len, }; - kasan_check_read(buff, len); - asm volatile( + instrument_read(buff, len); + asm volatile("\n" "0: cksm %[sum],%[rp]\n" " jo 0b\n" : [sum] "+&d" (sum), [rp] "+&d" (rp.pair) : : "cc", "memory"); return sum; } +__wsum csum_partial(const void *buff, int len, __wsum sum); + +#define _HAVE_ARCH_CSUM_AND_COPY +__wsum csum_partial_copy_nocheck(const void *src, void *dst, int len); + /* * Fold a partial checksum without adding pseudo headers. */ diff --git a/arch/s390/include/asm/diag.h b/arch/s390/include/asm/diag.h index bed804137537..20b94220113b 100644 --- a/arch/s390/include/asm/diag.h +++ b/arch/s390/include/asm/diag.h @@ -44,6 +44,13 @@ enum diag_stat_enum { void diag_stat_inc(enum diag_stat_enum nr); void diag_stat_inc_norecursion(enum diag_stat_enum nr); +struct hypfs_diag0c_entry; + +/* + * Diagnose 0c: Pseudo Timer + */ +void diag0c(struct hypfs_diag0c_entry *data); + /* * Diagnose 10: Release page range */ @@ -331,10 +338,10 @@ struct hypfs_diag0c_entry; */ struct diag_ops { int (*diag210)(struct diag210 *addr); - int (*diag26c)(void *req, void *resp, enum diag26c_sc subcode); + int (*diag26c)(unsigned long rx, unsigned long rx1, enum diag26c_sc subcode); int (*diag14)(unsigned long rx, unsigned long ry1, unsigned long subcode); int (*diag8c)(struct diag8c *addr, struct ccw_dev_id *devno, size_t len); - void (*diag0c)(struct hypfs_diag0c_entry *entry); + void (*diag0c)(unsigned long rx); void (*diag308_reset)(void); }; @@ -342,9 +349,9 @@ extern struct diag_ops diag_amode31_ops; extern struct diag210 *__diag210_tmp_amode31; int _diag210_amode31(struct diag210 *addr); -int _diag26c_amode31(void *req, void *resp, enum diag26c_sc subcode); +int _diag26c_amode31(unsigned long rx, unsigned long rx1, enum diag26c_sc subcode); int _diag14_amode31(unsigned long rx, unsigned long ry1, unsigned long subcode); -void _diag0c_amode31(struct hypfs_diag0c_entry *entry); +void _diag0c_amode31(unsigned long rx); void _diag308_reset_amode31(void); int _diag8c_amode31(struct diag8c *addr, struct ccw_dev_id *devno, size_t len); diff --git a/arch/s390/include/asm/entry-common.h b/arch/s390/include/asm/entry-common.h index fdd319a622b0..7f5004065e8a 100644 --- a/arch/s390/include/asm/entry-common.h +++ b/arch/s390/include/asm/entry-common.h @@ -8,7 +8,7 @@ #include <linux/processor.h> #include <linux/uaccess.h> #include <asm/timex.h> -#include <asm/fpu/api.h> +#include <asm/fpu.h> #include <asm/pai.h> #define ARCH_EXIT_TO_USER_MODE_WORK (_TIF_GUARDED_STORAGE | _TIF_PER_TRAP) @@ -41,8 +41,7 @@ static __always_inline void arch_exit_to_user_mode_work(struct pt_regs *regs, static __always_inline void arch_exit_to_user_mode(void) { - if (test_cpu_flag(CIF_FPU)) - __load_fpu_regs(); + load_user_fpu_regs(); if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) debug_user_asce(1); diff --git a/arch/s390/include/asm/vx-insn-asm.h b/arch/s390/include/asm/fpu-insn-asm.h index 360f8b36d962..02ccfe46050a 100644 --- a/arch/s390/include/asm/vx-insn-asm.h +++ b/arch/s390/include/asm/fpu-insn-asm.h @@ -9,11 +9,11 @@ * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com> */ -#ifndef __ASM_S390_VX_INSN_INTERNAL_H -#define __ASM_S390_VX_INSN_INTERNAL_H +#ifndef __ASM_S390_FPU_INSN_ASM_H +#define __ASM_S390_FPU_INSN_ASM_H -#ifndef __ASM_S390_VX_INSN_H -#error only <asm/vx-insn.h> can be included directly +#ifndef __ASM_S390_FPU_INSN_H +#error only <asm/fpu-insn.h> can be included directly #endif #ifdef __ASSEMBLY__ @@ -195,10 +195,26 @@ /* RXB - Compute most significant bit used vector registers * * @rxb: Operand to store computed RXB value - * @v1: First vector register designated operand - * @v2: Second vector register designated operand - * @v3: Third vector register designated operand - * @v4: Fourth vector register designated operand + * @v1: Vector register designated operand whose MSB is stored in + * RXB bit 0 (instruction bit 36) and whose remaining bits + * are stored in instruction bits 8-11. + * @v2: Vector register designated operand whose MSB is stored in + * RXB bit 1 (instruction bit 37) and whose remaining bits + * are stored in instruction bits 12-15. + * @v3: Vector register designated operand whose MSB is stored in + * RXB bit 2 (instruction bit 38) and whose remaining bits + * are stored in instruction bits 16-19. + * @v4: Vector register designated operand whose MSB is stored in + * RXB bit 3 (instruction bit 39) and whose remaining bits + * are stored in instruction bits 32-35. + * + * Note: In most vector instruction formats [1] V1, V2, V3, and V4 directly + * correspond to @v1, @v2, @v3, and @v4. But there are exceptions, such as but + * not limited to the vector instruction formats VRR-g, VRR-h, VRS-a, VRS-d, + * and VSI. + * + * [1] IBM z/Architecture Principles of Operation, chapter "Program + * Execution, section "Instructions", subsection "Instruction Formats". */ .macro RXB rxb v1 v2=0 v3=0 v4=0 \rxb = 0 @@ -223,6 +239,9 @@ * @v2: Second vector register designated operand (for RXB) * @v3: Third vector register designated operand (for RXB) * @v4: Fourth vector register designated operand (for RXB) + * + * Note: For @v1, @v2, @v3, and @v4 also refer to the RXB macro + * description for further details. */ .macro MRXB m v1 v2=0 v3=0 v4=0 rxb = 0 @@ -238,6 +257,9 @@ * @v2: Second vector register designated operand (for RXB) * @v3: Third vector register designated operand (for RXB) * @v4: Fourth vector register designated operand (for RXB) + * + * Note: For @v1, @v2, @v3, and @v4 also refer to the RXB macro + * description for further details. */ .macro MRXBOPC m opc v1 v2=0 v3=0 v4=0 MRXB \m, \v1, \v2, \v3, \v4 @@ -350,7 +372,7 @@ VX_NUM v3, \vr .word 0xE700 | (r1 << 4) | (v3&15) .word (b2 << 12) | (\disp) - MRXBOPC \m, 0x21, v3 + MRXBOPC \m, 0x21, 0, v3 .endm .macro VLGVB gr, vr, disp, base="%r0" VLGV \gr, \vr, \disp, \base, 0 @@ -499,6 +521,25 @@ VMRL \vr1, \vr2, \vr3, 3 .endm +/* VECTOR LOAD WITH LENGTH */ +.macro VLL v, gr, disp, base + VX_NUM v1, \v + GR_NUM b2, \base + GR_NUM r3, \gr + .word 0xE700 | ((v1&15) << 4) | r3 + .word (b2 << 12) | (\disp) + MRXBOPC 0, 0x37, v1 +.endm + +/* VECTOR STORE WITH LENGTH */ +.macro VSTL v, gr, disp, base + VX_NUM v1, \v + GR_NUM b2, \base + GR_NUM r3, \gr + .word 0xE700 | ((v1&15) << 4) | r3 + .word (b2 << 12) | (\disp) + MRXBOPC 0, 0x3f, v1 +.endm /* Vector integer instructions */ @@ -512,6 +553,16 @@ MRXBOPC 0, 0x68, v1, v2, v3 .endm +/* VECTOR CHECKSUM */ +.macro VCKSM vr1, vr2, vr3 + VX_NUM v1, \vr1 + VX_NUM v2, \vr2 + VX_NUM v3, \vr3 + .word 0xE700 | ((v1&15) << 4) | (v2&15) + .word ((v3&15) << 12) + MRXBOPC 0, 0x66, v1, v2, v3 +.endm + /* VECTOR EXCLUSIVE OR */ .macro VX vr1, vr2, vr3 VX_NUM v1, \vr1 @@ -678,4 +729,4 @@ .endm #endif /* __ASSEMBLY__ */ -#endif /* __ASM_S390_VX_INSN_INTERNAL_H */ +#endif /* __ASM_S390_FPU_INSN_ASM_H */ diff --git a/arch/s390/include/asm/fpu-insn.h b/arch/s390/include/asm/fpu-insn.h new file mode 100644 index 000000000000..c1e2e521d9af --- /dev/null +++ b/arch/s390/include/asm/fpu-insn.h @@ -0,0 +1,486 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Support for Floating Point and Vector Instructions + * + */ + +#ifndef __ASM_S390_FPU_INSN_H +#define __ASM_S390_FPU_INSN_H + +#include <asm/fpu-insn-asm.h> + +#ifndef __ASSEMBLY__ + +#include <linux/instrumented.h> +#include <asm/asm-extable.h> + +asm(".include \"asm/fpu-insn-asm.h\"\n"); + +/* + * Various small helper functions, which can and should be used within + * kernel fpu code sections. Each function represents only one floating + * point or vector instruction (except for helper functions which require + * exception handling). + * + * This allows to use floating point and vector instructions like C + * functions, which has the advantage that all supporting code, like + * e.g. loops, can be written in easy to read C code. + * + * Each of the helper functions provides support for code instrumentation, + * like e.g. KASAN. Therefore instrumentation is also covered automatically + * when using these functions. + * + * In order to ensure that code generated with the helper functions stays + * within kernel fpu sections, which are guarded with kernel_fpu_begin() + * and kernel_fpu_end() calls, each function has a mandatory "memory" + * barrier. + */ + +static __always_inline void fpu_cefbr(u8 f1, s32 val) +{ + asm volatile("cefbr %[f1],%[val]\n" + : + : [f1] "I" (f1), [val] "d" (val) + : "memory"); +} + +static __always_inline unsigned long fpu_cgebr(u8 f2, u8 mode) +{ + unsigned long val; + + asm volatile("cgebr %[val],%[mode],%[f2]\n" + : [val] "=d" (val) + : [f2] "I" (f2), [mode] "I" (mode) + : "memory"); + return val; +} + +static __always_inline void fpu_debr(u8 f1, u8 f2) +{ + asm volatile("debr %[f1],%[f2]\n" + : + : [f1] "I" (f1), [f2] "I" (f2) + : "memory"); +} + +static __always_inline void fpu_ld(unsigned short fpr, freg_t *reg) +{ + instrument_read(reg, sizeof(*reg)); + asm volatile("ld %[fpr],%[reg]\n" + : + : [fpr] "I" (fpr), [reg] "Q" (reg->ui) + : "memory"); +} + +static __always_inline void fpu_ldgr(u8 f1, u32 val) +{ + asm volatile("ldgr %[f1],%[val]\n" + : + : [f1] "I" (f1), [val] "d" (val) + : "memory"); +} + +static __always_inline void fpu_lfpc(unsigned int *fpc) +{ + instrument_read(fpc, sizeof(*fpc)); + asm volatile("lfpc %[fpc]" + : + : [fpc] "Q" (*fpc) + : "memory"); +} + +/** + * fpu_lfpc_safe - Load floating point control register safely. + * @fpc: new value for floating point control register + * + * Load floating point control register. This may lead to an exception, + * since a saved value may have been modified by user space (ptrace, + * signal return, kvm registers) to an invalid value. In such a case + * set the floating point control register to zero. + */ +static inline void fpu_lfpc_safe(unsigned int *fpc) +{ + u32 tmp; + + instrument_read(fpc, sizeof(*fpc)); + asm volatile("\n" + "0: lfpc %[fpc]\n" + "1: nopr %%r7\n" + ".pushsection .fixup, \"ax\"\n" + "2: lghi %[tmp],0\n" + " sfpc %[tmp]\n" + " jg 1b\n" + ".popsection\n" + EX_TABLE(1b, 2b) + : [tmp] "=d" (tmp) + : [fpc] "Q" (*fpc) + : "memory"); +} + +static __always_inline void fpu_std(unsigned short fpr, freg_t *reg) +{ + instrument_write(reg, sizeof(*reg)); + asm volatile("std %[fpr],%[reg]\n" + : [reg] "=Q" (reg->ui) + : [fpr] "I" (fpr) + : "memory"); +} + +static __always_inline void fpu_sfpc(unsigned int fpc) +{ + asm volatile("sfpc %[fpc]" + : + : [fpc] "d" (fpc) + : "memory"); +} + +static __always_inline void fpu_stfpc(unsigned int *fpc) +{ + instrument_write(fpc, sizeof(*fpc)); + asm volatile("stfpc %[fpc]" + : [fpc] "=Q" (*fpc) + : + : "memory"); +} + +static __always_inline void fpu_vab(u8 v1, u8 v2, u8 v3) +{ + asm volatile("VAB %[v1],%[v2],%[v3]" + : + : [v1] "I" (v1), [v2] "I" (v2), [v3] "I" (v3) + : "memory"); +} + +static __always_inline void fpu_vcksm(u8 v1, u8 v2, u8 v3) +{ + asm volatile("VCKSM %[v1],%[v2],%[v3]" + : + : [v1] "I" (v1), [v2] "I" (v2), [v3] "I" (v3) + : "memory"); +} + +static __always_inline void fpu_vesravb(u8 v1, u8 v2, u8 v3) +{ + asm volatile("VESRAVB %[v1],%[v2],%[v3]" + : + : [v1] "I" (v1), [v2] "I" (v2), [v3] "I" (v3) + : "memory"); +} + +static __always_inline void fpu_vgfmag(u8 v1, u8 v2, u8 v3, u8 v4) +{ + asm volatile("VGFMAG %[v1],%[v2],%[v3],%[v4]" + : + : [v1] "I" (v1), [v2] "I" (v2), [v3] "I" (v3), [v4] "I" (v4) + : "memory"); +} + +static __always_inline void fpu_vgfmg(u8 v1, u8 v2, u8 v3) +{ + asm volatile("VGFMG %[v1],%[v2],%[v3]" + : + : [v1] "I" (v1), [v2] "I" (v2), [v3] "I" (v3) + : "memory"); +} + +#ifdef CONFIG_CC_IS_CLANG + +static __always_inline void fpu_vl(u8 v1, const void *vxr) +{ + instrument_read(vxr, sizeof(__vector128)); + asm volatile("\n" + " la 1,%[vxr]\n" + " VL %[v1],0,,1\n" + : + : [vxr] "R" (*(__vector128 *)vxr), + [v1] "I" (v1) + : "memory", "1"); +} + +#else /* CONFIG_CC_IS_CLANG */ + +static __always_inline void fpu_vl(u8 v1, const void *vxr) +{ + instrument_read(vxr, sizeof(__vector128)); + asm volatile("VL %[v1],%O[vxr],,%R[vxr]\n" + : + : [vxr] "Q" (*(__vector128 *)vxr), + [v1] "I" (v1) + : "memory"); +} + +#endif /* CONFIG_CC_IS_CLANG */ + +static __always_inline void fpu_vleib(u8 v, s16 val, u8 index) +{ + asm volatile("VLEIB %[v],%[val],%[index]" + : + : [v] "I" (v), [val] "K" (val), [index] "I" (index) + : "memory"); +} + +static __always_inline void fpu_vleig(u8 v, s16 val, u8 index) +{ + asm volatile("VLEIG %[v],%[val],%[index]" + : + : [v] "I" (v), [val] "K" (val), [index] "I" (index) + : "memory"); +} + +static __always_inline u64 fpu_vlgvf(u8 v, u16 index) +{ + u64 val; + + asm volatile("VLGVF %[val],%[v],%[index]" + : [val] "=d" (val) + : [v] "I" (v), [index] "L" (index) + : "memory"); + return val; +} + +#ifdef CONFIG_CC_IS_CLANG + +static __always_inline void fpu_vll(u8 v1, u32 index, const void *vxr) +{ + unsigned int size; + + size = min(index + 1, sizeof(__vector128)); + instrument_read(vxr, size); + asm volatile("\n" + " la 1,%[vxr]\n" + " VLL %[v1],%[index],0,1\n" + : + : [vxr] "R" (*(u8 *)vxr), + [index] "d" (index), + [v1] "I" (v1) + : "memory", "1"); +} + +#else /* CONFIG_CC_IS_CLANG */ + +static __always_inline void fpu_vll(u8 v1, u32 index, const void *vxr) +{ + unsigned int size; + + size = min(index + 1, sizeof(__vector128)); + instrument_read(vxr, size); + asm volatile("VLL %[v1],%[index],%O[vxr],%R[vxr]\n" + : + : [vxr] "Q" (*(u8 *)vxr), + [index] "d" (index), + [v1] "I" (v1) + : "memory"); +} + +#endif /* CONFIG_CC_IS_CLANG */ + +#ifdef CONFIG_CC_IS_CLANG + +#define fpu_vlm(_v1, _v3, _vxrs) \ +({ \ + unsigned int size = ((_v3) - (_v1) + 1) * sizeof(__vector128); \ + struct { \ + __vector128 _v[(_v3) - (_v1) + 1]; \ + } *_v = (void *)(_vxrs); \ + \ + instrument_read(_v, size); \ + asm volatile("\n" \ + " la 1,%[vxrs]\n" \ + " VLM %[v1],%[v3],0,1\n" \ + : \ + : [vxrs] "R" (*_v), \ + [v1] "I" (_v1), [v3] "I" (_v3) \ + : "memory", "1"); \ + (_v3) - (_v1) + 1; \ +}) + +#else /* CONFIG_CC_IS_CLANG */ + +#define fpu_vlm(_v1, _v3, _vxrs) \ +({ \ + unsigned int size = ((_v3) - (_v1) + 1) * sizeof(__vector128); \ + struct { \ + __vector128 _v[(_v3) - (_v1) + 1]; \ + } *_v = (void *)(_vxrs); \ + \ + instrument_read(_v, size); \ + asm volatile("VLM %[v1],%[v3],%O[vxrs],%R[vxrs]\n" \ + : \ + : [vxrs] "Q" (*_v), \ + [v1] "I" (_v1), [v3] "I" (_v3) \ + : "memory"); \ + (_v3) - (_v1) + 1; \ +}) + +#endif /* CONFIG_CC_IS_CLANG */ + +static __always_inline void fpu_vlr(u8 v1, u8 v2) +{ + asm volatile("VLR %[v1],%[v2]" + : + : [v1] "I" (v1), [v2] "I" (v2) + : "memory"); +} + +static __always_inline void fpu_vlvgf(u8 v, u32 val, u16 index) +{ + asm volatile("VLVGF %[v],%[val],%[index]" + : + : [v] "I" (v), [val] "d" (val), [index] "L" (index) + : "memory"); +} + +static __always_inline void fpu_vn(u8 v1, u8 v2, u8 v3) +{ + asm volatile("VN %[v1],%[v2],%[v3]" + : + : [v1] "I" (v1), [v2] "I" (v2), [v3] "I" (v3) + : "memory"); +} + +static __always_inline void fpu_vperm(u8 v1, u8 v2, u8 v3, u8 v4) +{ + asm volatile("VPERM %[v1],%[v2],%[v3],%[v4]" + : + : [v1] "I" (v1), [v2] "I" (v2), [v3] "I" (v3), [v4] "I" (v4) + : "memory"); +} + +static __always_inline void fpu_vrepib(u8 v1, s16 i2) +{ + asm volatile("VREPIB %[v1],%[i2]" + : + : [v1] "I" (v1), [i2] "K" (i2) + : "memory"); +} + +static __always_inline void fpu_vsrlb(u8 v1, u8 v2, u8 v3) +{ + asm volatile("VSRLB %[v1],%[v2],%[v3]" + : + : [v1] "I" (v1), [v2] "I" (v2), [v3] "I" (v3) + : "memory"); +} + +#ifdef CONFIG_CC_IS_CLANG + +static __always_inline void fpu_vst(u8 v1, const void *vxr) +{ + instrument_write(vxr, sizeof(__vector128)); + asm volatile("\n" + " la 1,%[vxr]\n" + " VST %[v1],0,,1\n" + : [vxr] "=R" (*(__vector128 *)vxr) + : [v1] "I" (v1) + : "memory", "1"); +} + +#else /* CONFIG_CC_IS_CLANG */ + +static __always_inline void fpu_vst(u8 v1, const void *vxr) +{ + instrument_write(vxr, sizeof(__vector128)); + asm volatile("VST %[v1],%O[vxr],,%R[vxr]\n" + : [vxr] "=Q" (*(__vector128 *)vxr) + : [v1] "I" (v1) + : "memory"); +} + +#endif /* CONFIG_CC_IS_CLANG */ + +#ifdef CONFIG_CC_IS_CLANG + +static __always_inline void fpu_vstl(u8 v1, u32 index, const void *vxr) +{ + unsigned int size; + + size = min(index + 1, sizeof(__vector128)); + instrument_write(vxr, size); + asm volatile("\n" + " la 1,%[vxr]\n" + " VSTL %[v1],%[index],0,1\n" + : [vxr] "=R" (*(u8 *)vxr) + : [index] "d" (index), [v1] "I" (v1) + : "memory", "1"); +} + +#else /* CONFIG_CC_IS_CLANG */ + +static __always_inline void fpu_vstl(u8 v1, u32 index, const void *vxr) +{ + unsigned int size; + + size = min(index + 1, sizeof(__vector128)); + instrument_write(vxr, size); + asm volatile("VSTL %[v1],%[index],%O[vxr],%R[vxr]\n" + : [vxr] "=Q" (*(u8 *)vxr) + : [index] "d" (index), [v1] "I" (v1) + : "memory"); +} + +#endif /* CONFIG_CC_IS_CLANG */ + +#ifdef CONFIG_CC_IS_CLANG + +#define fpu_vstm(_v1, _v3, _vxrs) \ +({ \ + unsigned int size = ((_v3) - (_v1) + 1) * sizeof(__vector128); \ + struct { \ + __vector128 _v[(_v3) - (_v1) + 1]; \ + } *_v = (void *)(_vxrs); \ + \ + instrument_write(_v, size); \ + asm volatile("\n" \ + " la 1,%[vxrs]\n" \ + " VSTM %[v1],%[v3],0,1\n" \ + : [vxrs] "=R" (*_v) \ + : [v1] "I" (_v1), [v3] "I" (_v3) \ + : "memory", "1"); \ + (_v3) - (_v1) + 1; \ +}) + +#else /* CONFIG_CC_IS_CLANG */ + +#define fpu_vstm(_v1, _v3, _vxrs) \ +({ \ + unsigned int size = ((_v3) - (_v1) + 1) * sizeof(__vector128); \ + struct { \ + __vector128 _v[(_v3) - (_v1) + 1]; \ + } *_v = (void *)(_vxrs); \ + \ + instrument_write(_v, size); \ + asm volatile("VSTM %[v1],%[v3],%O[vxrs],%R[vxrs]\n" \ + : [vxrs] "=Q" (*_v) \ + : [v1] "I" (_v1), [v3] "I" (_v3) \ + : "memory"); \ + (_v3) - (_v1) + 1; \ +}) + +#endif /* CONFIG_CC_IS_CLANG */ + +static __always_inline void fpu_vupllf(u8 v1, u8 v2) +{ + asm volatile("VUPLLF %[v1],%[v2]" + : + : [v1] "I" (v1), [v2] "I" (v2) + : "memory"); +} + +static __always_inline void fpu_vx(u8 v1, u8 v2, u8 v3) +{ + asm volatile("VX %[v1],%[v2],%[v3]" + : + : [v1] "I" (v1), [v2] "I" (v2), [v3] "I" (v3) + : "memory"); +} + +static __always_inline void fpu_vzero(u8 v) +{ + asm volatile("VZERO %[v]" + : + : [v] "I" (v) + : "memory"); +} + +#endif /* __ASSEMBLY__ */ +#endif /* __ASM_S390_FPU_INSN_H */ diff --git a/arch/s390/include/asm/fpu-types.h b/arch/s390/include/asm/fpu-types.h new file mode 100644 index 000000000000..8d58d5a95399 --- /dev/null +++ b/arch/s390/include/asm/fpu-types.h @@ -0,0 +1,51 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * FPU data structures + * + * Copyright IBM Corp. 2015 + * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com> + */ + +#ifndef _ASM_S390_FPU_TYPES_H +#define _ASM_S390_FPU_TYPES_H + +#include <asm/sigcontext.h> + +struct fpu { + u32 fpc; + __vector128 vxrs[__NUM_VXRS] __aligned(8); +}; + +struct kernel_fpu_hdr { + int mask; + u32 fpc; +}; + +struct kernel_fpu { + struct kernel_fpu_hdr hdr; + __vector128 vxrs[] __aligned(8); +}; + +#define KERNEL_FPU_STRUCT(vxr_size) \ +struct kernel_fpu_##vxr_size { \ + struct kernel_fpu_hdr hdr; \ + __vector128 vxrs[vxr_size] __aligned(8); \ +} + +KERNEL_FPU_STRUCT(8); +KERNEL_FPU_STRUCT(16); +KERNEL_FPU_STRUCT(32); + +#define DECLARE_KERNEL_FPU_ONSTACK(vxr_size, name) \ + struct kernel_fpu_##vxr_size name __uninitialized + +#define DECLARE_KERNEL_FPU_ONSTACK8(name) \ + DECLARE_KERNEL_FPU_ONSTACK(8, name) + +#define DECLARE_KERNEL_FPU_ONSTACK16(name) \ + DECLARE_KERNEL_FPU_ONSTACK(16, name) + +#define DECLARE_KERNEL_FPU_ONSTACK32(name) \ + DECLARE_KERNEL_FPU_ONSTACK(32, name) + +#endif /* _ASM_S390_FPU_TYPES_H */ diff --git a/arch/s390/include/asm/fpu.h b/arch/s390/include/asm/fpu.h new file mode 100644 index 000000000000..c84cb33913e2 --- /dev/null +++ b/arch/s390/include/asm/fpu.h @@ -0,0 +1,295 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * In-kernel FPU support functions + * + * + * Consider these guidelines before using in-kernel FPU functions: + * + * 1. Use kernel_fpu_begin() and kernel_fpu_end() to enclose all in-kernel + * use of floating-point or vector registers and instructions. + * + * 2. For kernel_fpu_begin(), specify the vector register range you want to + * use with the KERNEL_VXR_* constants. Consider these usage guidelines: + * + * a) If your function typically runs in process-context, use the lower + * half of the vector registers, for example, specify KERNEL_VXR_LOW. + * b) If your function typically runs in soft-irq or hard-irq context, + * prefer using the upper half of the vector registers, for example, + * specify KERNEL_VXR_HIGH. + * + * If you adhere to these guidelines, an interrupted process context + * does not require to save and restore vector registers because of + * disjoint register ranges. + * + * Also note that the __kernel_fpu_begin()/__kernel_fpu_end() functions + * includes logic to save and restore up to 16 vector registers at once. + * + * 3. You can nest kernel_fpu_begin()/kernel_fpu_end() by using different + * struct kernel_fpu states. Vector registers that are in use by outer + * levels are saved and restored. You can minimize the save and restore + * effort by choosing disjoint vector register ranges. + * + * 5. To use vector floating-point instructions, specify the KERNEL_FPC + * flag to save and restore floating-point controls in addition to any + * vector register range. + * + * 6. To use floating-point registers and instructions only, specify the + * KERNEL_FPR flag. This flag triggers a save and restore of vector + * registers V0 to V15 and floating-point controls. + * + * Copyright IBM Corp. 2015 + * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com> + */ + +#ifndef _ASM_S390_FPU_H +#define _ASM_S390_FPU_H + +#include <linux/processor.h> +#include <linux/preempt.h> +#include <linux/string.h> +#include <linux/sched.h> +#include <asm/sigcontext.h> +#include <asm/fpu-types.h> +#include <asm/fpu-insn.h> +#include <asm/facility.h> + +static inline bool cpu_has_vx(void) +{ + return likely(test_facility(129)); +} + +enum { + KERNEL_FPC_BIT = 0, + KERNEL_VXR_V0V7_BIT, + KERNEL_VXR_V8V15_BIT, + KERNEL_VXR_V16V23_BIT, + KERNEL_VXR_V24V31_BIT, +}; + +#define KERNEL_FPC BIT(KERNEL_FPC_BIT) +#define KERNEL_VXR_V0V7 BIT(KERNEL_VXR_V0V7_BIT) +#define KERNEL_VXR_V8V15 BIT(KERNEL_VXR_V8V15_BIT) +#define KERNEL_VXR_V16V23 BIT(KERNEL_VXR_V16V23_BIT) +#define KERNEL_VXR_V24V31 BIT(KERNEL_VXR_V24V31_BIT) + +#define KERNEL_VXR_LOW (KERNEL_VXR_V0V7 | KERNEL_VXR_V8V15) +#define KERNEL_VXR_MID (KERNEL_VXR_V8V15 | KERNEL_VXR_V16V23) +#define KERNEL_VXR_HIGH (KERNEL_VXR_V16V23 | KERNEL_VXR_V24V31) + +#define KERNEL_VXR (KERNEL_VXR_LOW | KERNEL_VXR_HIGH) +#define KERNEL_FPR (KERNEL_FPC | KERNEL_VXR_LOW) + +void load_fpu_state(struct fpu *state, int flags); +void save_fpu_state(struct fpu *state, int flags); +void __kernel_fpu_begin(struct kernel_fpu *state, int flags); +void __kernel_fpu_end(struct kernel_fpu *state, int flags); + +static __always_inline void save_vx_regs(__vector128 *vxrs) +{ + fpu_vstm(0, 15, &vxrs[0]); + fpu_vstm(16, 31, &vxrs[16]); +} + +static __always_inline void load_vx_regs(__vector128 *vxrs) +{ + fpu_vlm(0, 15, &vxrs[0]); + fpu_vlm(16, 31, &vxrs[16]); +} + +static __always_inline void __save_fp_regs(freg_t *fprs, unsigned int offset) +{ + fpu_std(0, &fprs[0 * offset]); + fpu_std(1, &fprs[1 * offset]); + fpu_std(2, &fprs[2 * offset]); + fpu_std(3, &fprs[3 * offset]); + fpu_std(4, &fprs[4 * offset]); + fpu_std(5, &fprs[5 * offset]); + fpu_std(6, &fprs[6 * offset]); + fpu_std(7, &fprs[7 * offset]); + fpu_std(8, &fprs[8 * offset]); + fpu_std(9, &fprs[9 * offset]); + fpu_std(10, &fprs[10 * offset]); + fpu_std(11, &fprs[11 * offset]); + fpu_std(12, &fprs[12 * offset]); + fpu_std(13, &fprs[13 * offset]); + fpu_std(14, &fprs[14 * offset]); + fpu_std(15, &fprs[15 * offset]); +} + +static __always_inline void __load_fp_regs(freg_t *fprs, unsigned int offset) +{ + fpu_ld(0, &fprs[0 * offset]); + fpu_ld(1, &fprs[1 * offset]); + fpu_ld(2, &fprs[2 * offset]); + fpu_ld(3, &fprs[3 * offset]); + fpu_ld(4, &fprs[4 * offset]); + fpu_ld(5, &fprs[5 * offset]); + fpu_ld(6, &fprs[6 * offset]); + fpu_ld(7, &fprs[7 * offset]); + fpu_ld(8, &fprs[8 * offset]); + fpu_ld(9, &fprs[9 * offset]); + fpu_ld(10, &fprs[10 * offset]); + fpu_ld(11, &fprs[11 * offset]); + fpu_ld(12, &fprs[12 * offset]); + fpu_ld(13, &fprs[13 * offset]); + fpu_ld(14, &fprs[14 * offset]); + fpu_ld(15, &fprs[15 * offset]); +} + +static __always_inline void save_fp_regs(freg_t *fprs) +{ + __save_fp_regs(fprs, sizeof(freg_t) / sizeof(freg_t)); +} + +static __always_inline void load_fp_regs(freg_t *fprs) +{ + __load_fp_regs(fprs, sizeof(freg_t) / sizeof(freg_t)); +} + +static __always_inline void save_fp_regs_vx(__vector128 *vxrs) +{ + freg_t *fprs = (freg_t *)&vxrs[0].high; + + __save_fp_regs(fprs, sizeof(__vector128) / sizeof(freg_t)); +} + +static __always_inline void load_fp_regs_vx(__vector128 *vxrs) +{ + freg_t *fprs = (freg_t *)&vxrs[0].high; + + __load_fp_regs(fprs, sizeof(__vector128) / sizeof(freg_t)); +} + +static inline void load_user_fpu_regs(void) +{ + struct thread_struct *thread = ¤t->thread; + + if (!thread->ufpu_flags) + return; + load_fpu_state(&thread->ufpu, thread->ufpu_flags); + thread->ufpu_flags = 0; +} + +static __always_inline void __save_user_fpu_regs(struct thread_struct *thread, int flags) +{ + save_fpu_state(&thread->ufpu, flags); + __atomic_or(flags, &thread->ufpu_flags); +} + +static inline void save_user_fpu_regs(void) +{ + struct thread_struct *thread = ¤t->thread; + int mask, flags; + + mask = __atomic_or(KERNEL_FPC | KERNEL_VXR, &thread->kfpu_flags); + flags = ~READ_ONCE(thread->ufpu_flags) & (KERNEL_FPC | KERNEL_VXR); + if (flags) + __save_user_fpu_regs(thread, flags); + barrier(); + WRITE_ONCE(thread->kfpu_flags, mask); +} + +static __always_inline void _kernel_fpu_begin(struct kernel_fpu *state, int flags) +{ + struct thread_struct *thread = ¤t->thread; + int mask, uflags; + + mask = __atomic_or(flags, &thread->kfpu_flags); + state->hdr.mask = mask; + uflags = READ_ONCE(thread->ufpu_flags); + if ((uflags & flags) != flags) + __save_user_fpu_regs(thread, ~uflags & flags); + if (mask & flags) + __kernel_fpu_begin(state, flags); +} + +static __always_inline void _kernel_fpu_end(struct kernel_fpu *state, int flags) +{ + int mask = state->hdr.mask; + + if (mask & flags) + __kernel_fpu_end(state, flags); + barrier(); + WRITE_ONCE(current->thread.kfpu_flags, mask); +} + +void __kernel_fpu_invalid_size(void); + +static __always_inline void kernel_fpu_check_size(int flags, unsigned int size) +{ + unsigned int cnt = 0; + + if (flags & KERNEL_VXR_V0V7) + cnt += 8; + if (flags & KERNEL_VXR_V8V15) + cnt += 8; + if (flags & KERNEL_VXR_V16V23) + cnt += 8; + if (flags & KERNEL_VXR_V24V31) + cnt += 8; + if (cnt != size) + __kernel_fpu_invalid_size(); +} + +#define kernel_fpu_begin(state, flags) \ +{ \ + typeof(state) s = (state); \ + int _flags = (flags); \ + \ + kernel_fpu_check_size(_flags, ARRAY_SIZE(s->vxrs)); \ + _kernel_fpu_begin((struct kernel_fpu *)s, _flags); \ +} + +#define kernel_fpu_end(state, flags) \ +{ \ + typeof(state) s = (state); \ + int _flags = (flags); \ + \ + kernel_fpu_check_size(_flags, ARRAY_SIZE(s->vxrs)); \ + _kernel_fpu_end((struct kernel_fpu *)s, _flags); \ +} + +static inline void save_kernel_fpu_regs(struct thread_struct *thread) +{ + if (!thread->kfpu_flags) + return; + save_fpu_state(&thread->kfpu, thread->kfpu_flags); +} + +static inline void restore_kernel_fpu_regs(struct thread_struct *thread) +{ + if (!thread->kfpu_flags) + return; + load_fpu_state(&thread->kfpu, thread->kfpu_flags); +} + +static inline void convert_vx_to_fp(freg_t *fprs, __vector128 *vxrs) +{ + int i; + + for (i = 0; i < __NUM_FPRS; i++) + fprs[i].ui = vxrs[i].high; +} + +static inline void convert_fp_to_vx(__vector128 *vxrs, freg_t *fprs) +{ + int i; + + for (i = 0; i < __NUM_FPRS; i++) + vxrs[i].high = fprs[i].ui; +} + +static inline void fpregs_store(_s390_fp_regs *fpregs, struct fpu *fpu) +{ + fpregs->pad = 0; + fpregs->fpc = fpu->fpc; + convert_vx_to_fp((freg_t *)&fpregs->fprs, fpu->vxrs); +} + +static inline void fpregs_load(_s390_fp_regs *fpregs, struct fpu *fpu) +{ + fpu->fpc = fpregs->fpc; + convert_fp_to_vx(fpu->vxrs, (freg_t *)&fpregs->fprs); +} + +#endif /* _ASM_S390_FPU_H */ diff --git a/arch/s390/include/asm/fpu/api.h b/arch/s390/include/asm/fpu/api.h deleted file mode 100644 index d6ca8bc6ca68..000000000000 --- a/arch/s390/include/asm/fpu/api.h +++ /dev/null @@ -1,126 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * In-kernel FPU support functions - * - * - * Consider these guidelines before using in-kernel FPU functions: - * - * 1. Use kernel_fpu_begin() and kernel_fpu_end() to enclose all in-kernel - * use of floating-point or vector registers and instructions. - * - * 2. For kernel_fpu_begin(), specify the vector register range you want to - * use with the KERNEL_VXR_* constants. Consider these usage guidelines: - * - * a) If your function typically runs in process-context, use the lower - * half of the vector registers, for example, specify KERNEL_VXR_LOW. - * b) If your function typically runs in soft-irq or hard-irq context, - * prefer using the upper half of the vector registers, for example, - * specify KERNEL_VXR_HIGH. - * - * If you adhere to these guidelines, an interrupted process context - * does not require to save and restore vector registers because of - * disjoint register ranges. - * - * Also note that the __kernel_fpu_begin()/__kernel_fpu_end() functions - * includes logic to save and restore up to 16 vector registers at once. - * - * 3. You can nest kernel_fpu_begin()/kernel_fpu_end() by using different - * struct kernel_fpu states. Vector registers that are in use by outer - * levels are saved and restored. You can minimize the save and restore - * effort by choosing disjoint vector register ranges. - * - * 5. To use vector floating-point instructions, specify the KERNEL_FPC - * flag to save and restore floating-point controls in addition to any - * vector register range. - * - * 6. To use floating-point registers and instructions only, specify the - * KERNEL_FPR flag. This flag triggers a save and restore of vector - * registers V0 to V15 and floating-point controls. - * - * Copyright IBM Corp. 2015 - * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com> - */ - -#ifndef _ASM_S390_FPU_API_H -#define _ASM_S390_FPU_API_H - -#include <linux/preempt.h> -#include <asm/asm-extable.h> -#include <asm/fpu/internal.h> - -void save_fpu_regs(void); -void load_fpu_regs(void); -void __load_fpu_regs(void); - -/** - * sfpc_safe - Set floating point control register safely. - * @fpc: new value for floating point control register - * - * Set floating point control register. This may lead to an exception, - * since a saved value may have been modified by user space (ptrace, - * signal return, kvm registers) to an invalid value. In such a case - * set the floating point control register to zero. - */ -static inline void sfpc_safe(u32 fpc) -{ - asm volatile("\n" - "0: sfpc %[fpc]\n" - "1: nopr %%r7\n" - ".pushsection .fixup, \"ax\"\n" - "2: lghi %[fpc],0\n" - " jg 0b\n" - ".popsection\n" - EX_TABLE(1b, 2b) - : [fpc] "+d" (fpc) - : : "memory"); -} - -#define KERNEL_FPC 1 -#define KERNEL_VXR_V0V7 2 -#define KERNEL_VXR_V8V15 4 -#define KERNEL_VXR_V16V23 8 -#define KERNEL_VXR_V24V31 16 - -#define KERNEL_VXR_LOW (KERNEL_VXR_V0V7|KERNEL_VXR_V8V15) -#define KERNEL_VXR_MID (KERNEL_VXR_V8V15|KERNEL_VXR_V16V23) -#define KERNEL_VXR_HIGH (KERNEL_VXR_V16V23|KERNEL_VXR_V24V31) - -#define KERNEL_VXR (KERNEL_VXR_LOW|KERNEL_VXR_HIGH) -#define KERNEL_FPR (KERNEL_FPC|KERNEL_VXR_LOW) - -struct kernel_fpu; - -/* - * Note the functions below must be called with preemption disabled. - * Do not enable preemption before calling __kernel_fpu_end() to prevent - * an corruption of an existing kernel FPU state. - * - * Prefer using the kernel_fpu_begin()/kernel_fpu_end() pair of functions. - */ -void __kernel_fpu_begin(struct kernel_fpu *state, u32 flags); -void __kernel_fpu_end(struct kernel_fpu *state, u32 flags); - - -static inline void kernel_fpu_begin(struct kernel_fpu *state, u32 flags) -{ - preempt_disable(); - state->mask = S390_lowcore.fpu_flags; - if (!test_cpu_flag(CIF_FPU)) - /* Save user space FPU state and register contents */ - save_fpu_regs(); - else if (state->mask & flags) - /* Save FPU/vector register in-use by the kernel */ - __kernel_fpu_begin(state, flags); - S390_lowcore.fpu_flags |= flags; -} - -static inline void kernel_fpu_end(struct kernel_fpu *state, u32 flags) -{ - S390_lowcore.fpu_flags = state->mask; - if (state->mask & flags) - /* Restore FPU/vector register in-use by the kernel */ - __kernel_fpu_end(state, flags); - preempt_enable(); -} - -#endif /* _ASM_S390_FPU_API_H */ diff --git a/arch/s390/include/asm/fpu/internal.h b/arch/s390/include/asm/fpu/internal.h deleted file mode 100644 index d511c4cf5afb..000000000000 --- a/arch/s390/include/asm/fpu/internal.h +++ /dev/null @@ -1,67 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * FPU state and register content conversion primitives - * - * Copyright IBM Corp. 2015 - * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com> - */ - -#ifndef _ASM_S390_FPU_INTERNAL_H -#define _ASM_S390_FPU_INTERNAL_H - -#include <linux/string.h> -#include <asm/facility.h> -#include <asm/fpu/types.h> - -static inline bool cpu_has_vx(void) -{ - return likely(test_facility(129)); -} - -static inline void save_vx_regs(__vector128 *vxrs) -{ - asm volatile( - " la 1,%0\n" - " .word 0xe70f,0x1000,0x003e\n" /* vstm 0,15,0(1) */ - " .word 0xe70f,0x1100,0x0c3e\n" /* vstm 16,31,256(1) */ - : "=Q" (*(struct vx_array *) vxrs) : : "1"); -} - -static inline void convert_vx_to_fp(freg_t *fprs, __vector128 *vxrs) -{ - int i; - - for (i = 0; i < __NUM_FPRS; i++) - fprs[i].ui = vxrs[i].high; -} - -static inline void convert_fp_to_vx(__vector128 *vxrs, freg_t *fprs) -{ - int i; - - for (i = 0; i < __NUM_FPRS; i++) - vxrs[i].high = fprs[i].ui; -} - -static inline void fpregs_store(_s390_fp_regs *fpregs, struct fpu *fpu) -{ - fpregs->pad = 0; - fpregs->fpc = fpu->fpc; - if (cpu_has_vx()) - convert_vx_to_fp((freg_t *)&fpregs->fprs, fpu->vxrs); - else - memcpy((freg_t *)&fpregs->fprs, fpu->fprs, - sizeof(fpregs->fprs)); -} - -static inline void fpregs_load(_s390_fp_regs *fpregs, struct fpu *fpu) -{ - fpu->fpc = fpregs->fpc; - if (cpu_has_vx()) - convert_fp_to_vx(fpu->vxrs, (freg_t *)&fpregs->fprs); - else - memcpy(fpu->fprs, (freg_t *)&fpregs->fprs, - sizeof(fpregs->fprs)); -} - -#endif /* _ASM_S390_FPU_INTERNAL_H */ diff --git a/arch/s390/include/asm/fpu/types.h b/arch/s390/include/asm/fpu/types.h deleted file mode 100644 index d889e9436865..000000000000 --- a/arch/s390/include/asm/fpu/types.h +++ /dev/null @@ -1,38 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * FPU data structures - * - * Copyright IBM Corp. 2015 - * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com> - */ - -#ifndef _ASM_S390_FPU_TYPES_H -#define _ASM_S390_FPU_TYPES_H - -#include <asm/sigcontext.h> - -struct fpu { - __u32 fpc; /* Floating-point control */ - void *regs; /* Pointer to the current save area */ - union { - /* Floating-point register save area */ - freg_t fprs[__NUM_FPRS]; - /* Vector register save area */ - __vector128 vxrs[__NUM_VXRS]; - }; -}; - -/* VX array structure for address operand constraints in inline assemblies */ -struct vx_array { __vector128 _[__NUM_VXRS]; }; - -/* In-kernel FPU state structure */ -struct kernel_fpu { - u32 mask; - u32 fpc; - union { - freg_t fprs[__NUM_FPRS]; - __vector128 vxrs[__NUM_VXRS]; - }; -}; - -#endif /* _ASM_S390_FPU_TYPES_H */ diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 52664105a473..95990461888f 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -23,7 +23,7 @@ #include <linux/mmu_notifier.h> #include <asm/debug.h> #include <asm/cpu.h> -#include <asm/fpu/api.h> +#include <asm/fpu.h> #include <asm/isc.h> #include <asm/guarded_storage.h> @@ -743,7 +743,6 @@ struct kvm_vcpu_arch { struct kvm_s390_sie_block *vsie_block; unsigned int host_acrs[NUM_ACRS]; struct gs_cb *host_gscb; - struct fpu host_fpregs; struct kvm_s390_local_interrupt local_int; struct hrtimer ckc_timer; struct kvm_s390_pgm_info pgm; @@ -765,6 +764,8 @@ struct kvm_vcpu_arch { __u64 cputm_start; bool gs_enabled; bool skey_enabled; + /* Indicator if the access registers have been loaded from guest */ + bool acrs_loaded; struct kvm_s390_pv_vcpu pv; union diag318_info diag318_info; }; diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h index 5dc1b6345006..8c5f16857539 100644 --- a/arch/s390/include/asm/lowcore.h +++ b/arch/s390/include/asm/lowcore.h @@ -157,7 +157,7 @@ struct lowcore { __s32 preempt_count; /* 0x03a8 */ __u32 spinlock_lockval; /* 0x03ac */ __u32 spinlock_index; /* 0x03b0 */ - __u32 fpu_flags; /* 0x03b4 */ + __u8 pad_0x03b4[0x03b8-0x03b4]; /* 0x03b4 */ __u64 percpu_offset; /* 0x03b8 */ __u8 pad_0x03c0[0x03c8-0x03c0]; /* 0x03c0 */ __u64 machine_flags; /* 0x03c8 */ diff --git a/arch/s390/include/asm/pai.h b/arch/s390/include/asm/pai.h index 7d1888e3dee6..3f609565734b 100644 --- a/arch/s390/include/asm/pai.h +++ b/arch/s390/include/asm/pai.h @@ -16,7 +16,7 @@ struct qpaci_info_block { u64 header; struct { u64 : 8; - u64 num_cc : 8; /* # of supported crypto counters */ + u64 num_cc : 8; /* # of supported crypto counters */ u64 : 9; u64 num_nnpa : 7; /* # of supported NNPA counters */ u64 : 32; @@ -81,4 +81,5 @@ enum paievt_mode { PAI_MODE_COUNTING, }; +#define PAI_SAVE_AREA(x) ((x)->hw.event_base) #endif diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index e91cd6bbc330..30820a649e6e 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -122,6 +122,7 @@ struct zpci_dev { struct rcu_head rcu; struct hotplug_slot hotplug_slot; + struct mutex state_lock; /* protect state changes */ enum zpci_state state; u32 fid; /* function ID, used by sclp */ u32 fh; /* function handle, used by insn's */ @@ -142,7 +143,6 @@ struct zpci_dev { u8 reserved : 2; unsigned int devfn; /* DEVFN part of the RID*/ - struct mutex lock; u8 pfip[CLP_PFIP_NR_SEGMENTS]; /* pci function internal path */ u32 uid; /* user defined id */ u8 util_str[CLP_UTIL_STR_LEN]; /* utility string */ @@ -170,6 +170,7 @@ struct zpci_dev { u64 dma_mask; /* DMA address space mask */ /* Function measurement block */ + struct mutex fmb_lock; struct zpci_fmb *fmb; u16 fmb_update; /* update interval */ u16 fmb_length; diff --git a/arch/s390/include/asm/physmem_info.h b/arch/s390/include/asm/physmem_info.h index 9e41a74fce9a..e747b067f8db 100644 --- a/arch/s390/include/asm/physmem_info.h +++ b/arch/s390/include/asm/physmem_info.h @@ -22,6 +22,7 @@ enum reserved_range_type { RR_DECOMPRESSOR, RR_INITRD, RR_VMLINUX, + RR_RELOC, RR_AMODE31, RR_IPLREPORT, RR_CERT_COMP_LIST, diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index c0b6e74d899a..7cf00cf8fb0b 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -15,13 +15,11 @@ #include <linux/bits.h> #define CIF_NOHZ_DELAY 2 /* delay HZ disable for a tick */ -#define CIF_FPU 3 /* restore FPU registers */ #define CIF_ENABLED_WAIT 5 /* in enabled wait state */ #define CIF_MCCK_GUEST 6 /* machine check happening in guest */ #define CIF_DEDICATED_CPU 7 /* this CPU is dedicated */ #define _CIF_NOHZ_DELAY BIT(CIF_NOHZ_DELAY) -#define _CIF_FPU BIT(CIF_FPU) #define _CIF_ENABLED_WAIT BIT(CIF_ENABLED_WAIT) #define _CIF_MCCK_GUEST BIT(CIF_MCCK_GUEST) #define _CIF_DEDICATED_CPU BIT(CIF_DEDICATED_CPU) @@ -33,13 +31,12 @@ #include <linux/cpumask.h> #include <linux/linkage.h> #include <linux/irqflags.h> +#include <asm/fpu-types.h> #include <asm/cpu.h> #include <asm/page.h> #include <asm/ptrace.h> #include <asm/setup.h> #include <asm/runtime_instr.h> -#include <asm/fpu/types.h> -#include <asm/fpu/internal.h> #include <asm/irqflags.h> typedef long (*sys_call_ptr_t)(struct pt_regs *regs); @@ -169,6 +166,8 @@ struct thread_struct { unsigned int gmap_write_flag; /* gmap fault write indication */ unsigned int gmap_int_code; /* int code of last gmap fault */ unsigned int gmap_pfault; /* signal of a pending guest pfault */ + int ufpu_flags; /* user fpu flags */ + int kfpu_flags; /* kernel fpu flags */ /* Per-thread information related to debugging */ struct per_regs per_user; /* User specified PER registers */ @@ -184,7 +183,8 @@ struct thread_struct { struct gs_cb *gs_cb; /* Current guarded storage cb */ struct gs_cb *gs_bc_cb; /* Broadcast guarded storage cb */ struct pgm_tdb trap_tdb; /* Transaction abort diagnose block */ - struct fpu fpu; /* FP and VX register save area */ + struct fpu ufpu; /* User FP and VX register save area */ + struct fpu kfpu; /* Kernel FP and VX register save area */ }; /* Flag to disable transactions. */ @@ -203,7 +203,6 @@ typedef struct thread_struct thread_struct; #define INIT_THREAD { \ .ksp = sizeof(init_stack) + (unsigned long) &init_stack, \ - .fpu.regs = (void *) init_task.thread.fpu.fprs, \ .last_break = 1, \ } diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h index d28bf8fb2799..788bc4467445 100644 --- a/arch/s390/include/asm/ptrace.h +++ b/arch/s390/include/asm/ptrace.h @@ -203,6 +203,10 @@ static inline int test_and_clear_pt_regs_flag(struct pt_regs *regs, int flag) return ret; } +struct task_struct; + +void update_cr_regs(struct task_struct *task); + /* * These are defined as per linux/ptrace.h, which see. */ diff --git a/arch/s390/include/asm/stacktrace.h b/arch/s390/include/asm/stacktrace.h index 31ec4f545e03..433fde85b14e 100644 --- a/arch/s390/include/asm/stacktrace.h +++ b/arch/s390/include/asm/stacktrace.h @@ -4,7 +4,6 @@ #include <linux/uaccess.h> #include <linux/ptrace.h> -#include <asm/switch_to.h> struct stack_frame_user { unsigned long back_chain; diff --git a/arch/s390/include/asm/switch_to.h b/arch/s390/include/asm/switch_to.h deleted file mode 100644 index c61b2cc1a8a8..000000000000 --- a/arch/s390/include/asm/switch_to.h +++ /dev/null @@ -1,49 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright IBM Corp. 1999, 2009 - * - * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com> - */ - -#ifndef __ASM_SWITCH_TO_H -#define __ASM_SWITCH_TO_H - -#include <linux/thread_info.h> -#include <asm/fpu/api.h> -#include <asm/ptrace.h> -#include <asm/guarded_storage.h> - -extern struct task_struct *__switch_to(void *, void *); -extern void update_cr_regs(struct task_struct *task); - -static inline void save_access_regs(unsigned int *acrs) -{ - typedef struct { int _[NUM_ACRS]; } acrstype; - - asm volatile("stam 0,15,%0" : "=Q" (*(acrstype *)acrs)); -} - -static inline void restore_access_regs(unsigned int *acrs) -{ - typedef struct { int _[NUM_ACRS]; } acrstype; - - asm volatile("lam 0,15,%0" : : "Q" (*(acrstype *)acrs)); -} - -#define switch_to(prev, next, last) do { \ - /* save_fpu_regs() sets the CIF_FPU flag, which enforces \ - * a restore of the floating point / vector registers as \ - * soon as the next task returns to user space \ - */ \ - save_fpu_regs(); \ - save_access_regs(&prev->thread.acrs[0]); \ - save_ri_cb(prev->thread.ri_cb); \ - save_gs_cb(prev->thread.gs_cb); \ - update_cr_regs(next); \ - restore_access_regs(&next->thread.acrs[0]); \ - restore_ri_cb(next->thread.ri_cb, prev->thread.ri_cb); \ - restore_gs_cb(next->thread.gs_cb); \ - prev = __switch_to(prev, next); \ -} while (0) - -#endif /* __ASM_SWITCH_TO_H */ diff --git a/arch/s390/include/asm/vx-insn.h b/arch/s390/include/asm/vx-insn.h deleted file mode 100644 index 8c188f1c6d27..000000000000 --- a/arch/s390/include/asm/vx-insn.h +++ /dev/null @@ -1,19 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Support for Vector Instructions - * - * This wrapper header file allows to use the vector instruction macros in - * both assembler files as well as in inline assemblies in C files. - */ - -#ifndef __ASM_S390_VX_INSN_H -#define __ASM_S390_VX_INSN_H - -#include <asm/vx-insn-asm.h> - -#ifndef __ASSEMBLY__ - -asm(".include \"asm/vx-insn-asm.h\"\n"); - -#endif /* __ASSEMBLY__ */ -#endif /* __ASM_S390_VX_INSN_H */ diff --git a/arch/s390/kernel/cache.c b/arch/s390/kernel/cache.c index 56254fa06f99..4f2669030220 100644 --- a/arch/s390/kernel/cache.c +++ b/arch/s390/kernel/cache.c @@ -166,5 +166,6 @@ int populate_cache_leaves(unsigned int cpu) ci_leaf_init(this_leaf++, pvt, ctype, level, cpu); } } + this_cpu_ci->cpu_map_populated = true; return 0; } diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c index f8fc6c25d051..1942e2a9f8db 100644 --- a/arch/s390/kernel/compat_signal.c +++ b/arch/s390/kernel/compat_signal.c @@ -24,12 +24,12 @@ #include <linux/tty.h> #include <linux/personality.h> #include <linux/binfmts.h> +#include <asm/access-regs.h> #include <asm/ucontext.h> #include <linux/uaccess.h> #include <asm/lowcore.h> -#include <asm/switch_to.h> #include <asm/vdso.h> -#include <asm/fpu/api.h> +#include <asm/fpu.h> #include "compat_linux.h" #include "compat_ptrace.h" #include "entry.h" @@ -56,7 +56,7 @@ typedef struct static void store_sigregs(void) { save_access_regs(current->thread.acrs); - save_fpu_regs(); + save_user_fpu_regs(); } /* Load registers after signal return */ @@ -79,7 +79,7 @@ static int save_sigregs32(struct pt_regs *regs, _sigregs32 __user *sregs) user_sregs.regs.gprs[i] = (__u32) regs->gprs[i]; memcpy(&user_sregs.regs.acrs, current->thread.acrs, sizeof(user_sregs.regs.acrs)); - fpregs_store((_s390_fp_regs *) &user_sregs.fpregs, ¤t->thread.fpu); + fpregs_store((_s390_fp_regs *) &user_sregs.fpregs, ¤t->thread.ufpu); if (__copy_to_user(sregs, &user_sregs, sizeof(_sigregs32))) return -EFAULT; return 0; @@ -113,7 +113,7 @@ static int restore_sigregs32(struct pt_regs *regs,_sigregs32 __user *sregs) regs->gprs[i] = (__u64) user_sregs.regs.gprs[i]; memcpy(¤t->thread.acrs, &user_sregs.regs.acrs, sizeof(current->thread.acrs)); - fpregs_load((_s390_fp_regs *) &user_sregs.fpregs, ¤t->thread.fpu); + fpregs_load((_s390_fp_regs *)&user_sregs.fpregs, ¤t->thread.ufpu); clear_pt_regs_flag(regs, PIF_SYSCALL); /* No longer in a system call */ return 0; @@ -136,11 +136,11 @@ static int save_sigregs_ext32(struct pt_regs *regs, /* Save vector registers to signal stack */ if (cpu_has_vx()) { for (i = 0; i < __NUM_VXRS_LOW; i++) - vxrs[i] = current->thread.fpu.vxrs[i].low; + vxrs[i] = current->thread.ufpu.vxrs[i].low; if (__copy_to_user(&sregs_ext->vxrs_low, vxrs, sizeof(sregs_ext->vxrs_low)) || __copy_to_user(&sregs_ext->vxrs_high, - current->thread.fpu.vxrs + __NUM_VXRS_LOW, + current->thread.ufpu.vxrs + __NUM_VXRS_LOW, sizeof(sregs_ext->vxrs_high))) return -EFAULT; } @@ -165,12 +165,12 @@ static int restore_sigregs_ext32(struct pt_regs *regs, if (cpu_has_vx()) { if (__copy_from_user(vxrs, &sregs_ext->vxrs_low, sizeof(sregs_ext->vxrs_low)) || - __copy_from_user(current->thread.fpu.vxrs + __NUM_VXRS_LOW, + __copy_from_user(current->thread.ufpu.vxrs + __NUM_VXRS_LOW, &sregs_ext->vxrs_high, sizeof(sregs_ext->vxrs_high))) return -EFAULT; for (i = 0; i < __NUM_VXRS_LOW; i++) - current->thread.fpu.vxrs[i].low = vxrs[i]; + current->thread.ufpu.vxrs[i].low = vxrs[i]; } return 0; } @@ -184,7 +184,7 @@ COMPAT_SYSCALL_DEFINE0(sigreturn) if (get_compat_sigset(&set, (compat_sigset_t __user *)frame->sc.oldmask)) goto badframe; set_current_blocked(&set); - save_fpu_regs(); + save_user_fpu_regs(); if (restore_sigregs32(regs, &frame->sregs)) goto badframe; if (restore_sigregs_ext32(regs, &frame->sregs_ext)) @@ -207,7 +207,7 @@ COMPAT_SYSCALL_DEFINE0(rt_sigreturn) set_current_blocked(&set); if (compat_restore_altstack(&frame->uc.uc_stack)) goto badframe; - save_fpu_regs(); + save_user_fpu_regs(); if (restore_sigregs32(regs, &frame->uc.uc_mcontext)) goto badframe; if (restore_sigregs_ext32(regs, &frame->uc.uc_mcontext_ext)) diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c index 5c46c2659305..d09ebb6f5262 100644 --- a/arch/s390/kernel/crash_dump.c +++ b/arch/s390/kernel/crash_dump.c @@ -22,7 +22,7 @@ #include <asm/ipl.h> #include <asm/sclp.h> #include <asm/maccess.h> -#include <asm/fpu/api.h> +#include <asm/fpu.h> #define PTR_ADD(x, y) (((char *) (x)) + ((unsigned long) (y))) #define PTR_SUB(x, y) (((char *) (x)) - ((unsigned long) (y))) diff --git a/arch/s390/kernel/diag.c b/arch/s390/kernel/diag.c index 92fdc35f028c..8dee9aa0ec95 100644 --- a/arch/s390/kernel/diag.c +++ b/arch/s390/kernel/diag.c @@ -147,11 +147,40 @@ void notrace diag_stat_inc_norecursion(enum diag_stat_enum nr) EXPORT_SYMBOL(diag_stat_inc_norecursion); /* + * Diagnose 0c: Pseudo Timer + */ +void diag0c(struct hypfs_diag0c_entry *data) +{ + diag_stat_inc(DIAG_STAT_X00C); + diag_amode31_ops.diag0c(virt_to_phys(data)); +} + +/* * Diagnose 14: Input spool file manipulation + * + * The subcode parameter determines the type of the first parameter rx. + * Currently used are the following 3 subcommands: + * 0x0: Read the Next Spool File Buffer (Data Record) + * 0x28: Position a Spool File to the Designated Record + * 0xfff: Retrieve Next File Descriptor + * + * For subcommands 0x0 and 0xfff, the value of the first parameter is + * a virtual address of a memory buffer and needs virtual to physical + * address translation. For other subcommands the rx parameter is not + * a virtual address. */ int diag14(unsigned long rx, unsigned long ry1, unsigned long subcode) { diag_stat_inc(DIAG_STAT_X014); + switch (subcode) { + case 0x0: + case 0xfff: + rx = virt_to_phys((void *)rx); + break; + default: + /* Do nothing */ + break; + } return diag_amode31_ops.diag14(rx, ry1, subcode); } EXPORT_SYMBOL(diag14); @@ -265,6 +294,6 @@ EXPORT_SYMBOL(diag224); int diag26c(void *req, void *resp, enum diag26c_sc subcode) { diag_stat_inc(DIAG_STAT_X26C); - return diag_amode31_ops.diag26c(req, resp, subcode); + return diag_amode31_ops.diag26c(virt_to_phys(req), virt_to_phys(resp), subcode); } EXPORT_SYMBOL(diag26c); diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index 2345ea332b97..c666271433fb 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -19,8 +19,10 @@ #include <linux/kernel.h> #include <asm/asm-extable.h> #include <linux/memblock.h> +#include <asm/access-regs.h> #include <asm/diag.h> #include <asm/ebcdic.h> +#include <asm/fpu.h> #include <asm/ipl.h> #include <asm/lowcore.h> #include <asm/processor.h> @@ -31,7 +33,6 @@ #include <asm/sclp.h> #include <asm/facility.h> #include <asm/boot_data.h> -#include <asm/switch_to.h> #include "entry.h" #define decompressor_handled_param(param) \ diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 49a11f6dd7ae..fc5277eab554 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -24,7 +24,7 @@ #include <asm/page.h> #include <asm/sigp.h> #include <asm/irq.h> -#include <asm/vx-insn.h> +#include <asm/fpu-insn.h> #include <asm/setup.h> #include <asm/nmi.h> #include <asm/nospec-insn.h> @@ -171,13 +171,13 @@ _LPP_OFFSET = __LC_LPP nop 0 /* - * Scheduler resume function, called by switch_to - * gpr2 = (task_struct *) prev - * gpr3 = (task_struct *) next + * Scheduler resume function, called by __switch_to + * gpr2 = (task_struct *)prev + * gpr3 = (task_struct *)next * Returns: * gpr2 = prev */ -SYM_FUNC_START(__switch_to) +SYM_FUNC_START(__switch_to_asm) stmg %r6,%r15,__SF_GPRS(%r15) # store gprs of prev task lghi %r4,__TASK_stack lghi %r1,__TASK_thread @@ -193,7 +193,7 @@ SYM_FUNC_START(__switch_to) lmg %r6,%r15,__SF_GPRS(%r15) # load gprs of next task ALTERNATIVE "nop", "lpp _LPP_OFFSET", 40 BR_EX %r14 -SYM_FUNC_END(__switch_to) +SYM_FUNC_END(__switch_to_asm) #if IS_ENABLED(CONFIG_KVM) /* @@ -220,8 +220,6 @@ SYM_FUNC_START(__sie64a) oi __SIE_PROG0C+3(%r14),1 # we are going into SIE now tm __SIE_PROG20+3(%r14),3 # last exit... jnz .Lsie_skip - TSTMSK __LC_CPU_FLAGS,_CIF_FPU - jo .Lsie_skip # exit if fp/vx regs changed lg %r14,__SF_SIE_CONTROL_PHYS(%r15) # get sie block phys addr BPEXIT __SF_SIE_FLAGS(%r15),_TIF_ISOLATE_BP_GUEST .Lsie_entry: @@ -489,16 +487,11 @@ SYM_FUNC_END(psw_idle) */ SYM_CODE_START(mcck_int_handler) BPOFF - la %r1,4095 # validate r1 - spt __LC_CPU_TIMER_SAVE_AREA-4095(%r1) # validate cpu timer - LBEAR __LC_LAST_BREAK_SAVE_AREA-4095(%r1) # validate bear - lmg %r0,%r15,__LC_GPREGS_SAVE_AREA # validate gprs lmg %r8,%r9,__LC_MCK_OLD_PSW TSTMSK __LC_MCCK_CODE,MCCK_CODE_SYSTEM_DAMAGE jo .Lmcck_panic # yes -> rest of mcck code invalid TSTMSK __LC_MCCK_CODE,MCCK_CODE_CR_VALID jno .Lmcck_panic # control registers invalid -> panic - lctlg %c0,%c15,__LC_CREGS_SAVE_AREA # validate ctl regs ptlb lghi %r14,__LC_CPU_TIMER_SAVE_AREA mvc __LC_MCCK_ENTER_TIMER(8),0(%r14) diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index 9f41853f36b9..21969520f947 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -19,6 +19,7 @@ void mcck_int_handler(void); void restart_int_handler(void); void early_pgm_check_handler(void); +struct task_struct *__switch_to_asm(struct task_struct *prev, struct task_struct *next); void __ret_from_fork(struct task_struct *prev, struct pt_regs *regs); void __do_pgm_check(struct pt_regs *regs); void __do_syscall(struct pt_regs *regs, int per_trap); diff --git a/arch/s390/kernel/fpu.c b/arch/s390/kernel/fpu.c index a4f3449cc814..fa90bbdc5ef9 100644 --- a/arch/s390/kernel/fpu.c +++ b/arch/s390/kernel/fpu.c @@ -8,256 +8,186 @@ #include <linux/kernel.h> #include <linux/cpu.h> #include <linux/sched.h> -#include <asm/fpu/types.h> -#include <asm/fpu/api.h> -#include <asm/vx-insn.h> +#include <asm/fpu.h> -void __kernel_fpu_begin(struct kernel_fpu *state, u32 flags) +void __kernel_fpu_begin(struct kernel_fpu *state, int flags) { + __vector128 *vxrs = state->vxrs; + int mask; + /* * Limit the save to the FPU/vector registers already - * in use by the previous context + * in use by the previous context. */ - flags &= state->mask; - + flags &= state->hdr.mask; if (flags & KERNEL_FPC) - /* Save floating point control */ - asm volatile("stfpc %0" : "=Q" (state->fpc)); - + fpu_stfpc(&state->hdr.fpc); if (!cpu_has_vx()) { - if (flags & KERNEL_VXR_V0V7) { - /* Save floating-point registers */ - asm volatile("std 0,%0" : "=Q" (state->fprs[0])); - asm volatile("std 1,%0" : "=Q" (state->fprs[1])); - asm volatile("std 2,%0" : "=Q" (state->fprs[2])); - asm volatile("std 3,%0" : "=Q" (state->fprs[3])); - asm volatile("std 4,%0" : "=Q" (state->fprs[4])); - asm volatile("std 5,%0" : "=Q" (state->fprs[5])); - asm volatile("std 6,%0" : "=Q" (state->fprs[6])); - asm volatile("std 7,%0" : "=Q" (state->fprs[7])); - asm volatile("std 8,%0" : "=Q" (state->fprs[8])); - asm volatile("std 9,%0" : "=Q" (state->fprs[9])); - asm volatile("std 10,%0" : "=Q" (state->fprs[10])); - asm volatile("std 11,%0" : "=Q" (state->fprs[11])); - asm volatile("std 12,%0" : "=Q" (state->fprs[12])); - asm volatile("std 13,%0" : "=Q" (state->fprs[13])); - asm volatile("std 14,%0" : "=Q" (state->fprs[14])); - asm volatile("std 15,%0" : "=Q" (state->fprs[15])); - } + if (flags & KERNEL_VXR_LOW) + save_fp_regs_vx(vxrs); return; } - - /* Test and save vector registers */ - asm volatile ( - /* - * Test if any vector register must be saved and, if so, - * test if all register can be saved. - */ - " la 1,%[vxrs]\n" /* load save area */ - " tmll %[m],30\n" /* KERNEL_VXR */ - " jz 7f\n" /* no work -> done */ - " jo 5f\n" /* -> save V0..V31 */ - /* - * Test for special case KERNEL_FPU_MID only. In this - * case a vstm V8..V23 is the best instruction - */ - " chi %[m],12\n" /* KERNEL_VXR_MID */ - " jne 0f\n" /* -> save V8..V23 */ - " VSTM 8,23,128,1\n" /* vstm %v8,%v23,128(%r1) */ - " j 7f\n" - /* Test and save the first half of 16 vector registers */ - "0: tmll %[m],6\n" /* KERNEL_VXR_LOW */ - " jz 3f\n" /* -> KERNEL_VXR_HIGH */ - " jo 2f\n" /* 11 -> save V0..V15 */ - " brc 2,1f\n" /* 10 -> save V8..V15 */ - " VSTM 0,7,0,1\n" /* vstm %v0,%v7,0(%r1) */ - " j 3f\n" - "1: VSTM 8,15,128,1\n" /* vstm %v8,%v15,128(%r1) */ - " j 3f\n" - "2: VSTM 0,15,0,1\n" /* vstm %v0,%v15,0(%r1) */ - /* Test and save the second half of 16 vector registers */ - "3: tmll %[m],24\n" /* KERNEL_VXR_HIGH */ - " jz 7f\n" - " jo 6f\n" /* 11 -> save V16..V31 */ - " brc 2,4f\n" /* 10 -> save V24..V31 */ - " VSTM 16,23,256,1\n" /* vstm %v16,%v23,256(%r1) */ - " j 7f\n" - "4: VSTM 24,31,384,1\n" /* vstm %v24,%v31,384(%r1) */ - " j 7f\n" - "5: VSTM 0,15,0,1\n" /* vstm %v0,%v15,0(%r1) */ - "6: VSTM 16,31,256,1\n" /* vstm %v16,%v31,256(%r1) */ - "7:" - : [vxrs] "=Q" (*(struct vx_array *) &state->vxrs) - : [m] "d" (flags) - : "1", "cc"); + mask = flags & KERNEL_VXR; + if (mask == KERNEL_VXR) { + vxrs += fpu_vstm(0, 15, vxrs); + vxrs += fpu_vstm(16, 31, vxrs); + return; + } + if (mask == KERNEL_VXR_MID) { + vxrs += fpu_vstm(8, 23, vxrs); + return; + } + mask = flags & KERNEL_VXR_LOW; + if (mask) { + if (mask == KERNEL_VXR_LOW) + vxrs += fpu_vstm(0, 15, vxrs); + else if (mask == KERNEL_VXR_V0V7) + vxrs += fpu_vstm(0, 7, vxrs); + else + vxrs += fpu_vstm(8, 15, vxrs); + } + mask = flags & KERNEL_VXR_HIGH; + if (mask) { + if (mask == KERNEL_VXR_HIGH) + vxrs += fpu_vstm(16, 31, vxrs); + else if (mask == KERNEL_VXR_V16V23) + vxrs += fpu_vstm(16, 23, vxrs); + else + vxrs += fpu_vstm(24, 31, vxrs); + } } EXPORT_SYMBOL(__kernel_fpu_begin); -void __kernel_fpu_end(struct kernel_fpu *state, u32 flags) +void __kernel_fpu_end(struct kernel_fpu *state, int flags) { + __vector128 *vxrs = state->vxrs; + int mask; + /* * Limit the restore to the FPU/vector registers of the - * previous context that have been overwritte by the - * current context + * previous context that have been overwritten by the + * current context. */ - flags &= state->mask; - + flags &= state->hdr.mask; if (flags & KERNEL_FPC) - /* Restore floating-point controls */ - asm volatile("lfpc %0" : : "Q" (state->fpc)); - + fpu_lfpc(&state->hdr.fpc); if (!cpu_has_vx()) { - if (flags & KERNEL_VXR_V0V7) { - /* Restore floating-point registers */ - asm volatile("ld 0,%0" : : "Q" (state->fprs[0])); - asm volatile("ld 1,%0" : : "Q" (state->fprs[1])); - asm volatile("ld 2,%0" : : "Q" (state->fprs[2])); - asm volatile("ld 3,%0" : : "Q" (state->fprs[3])); - asm volatile("ld 4,%0" : : "Q" (state->fprs[4])); - asm volatile("ld 5,%0" : : "Q" (state->fprs[5])); - asm volatile("ld 6,%0" : : "Q" (state->fprs[6])); - asm volatile("ld 7,%0" : : "Q" (state->fprs[7])); - asm volatile("ld 8,%0" : : "Q" (state->fprs[8])); - asm volatile("ld 9,%0" : : "Q" (state->fprs[9])); - asm volatile("ld 10,%0" : : "Q" (state->fprs[10])); - asm volatile("ld 11,%0" : : "Q" (state->fprs[11])); - asm volatile("ld 12,%0" : : "Q" (state->fprs[12])); - asm volatile("ld 13,%0" : : "Q" (state->fprs[13])); - asm volatile("ld 14,%0" : : "Q" (state->fprs[14])); - asm volatile("ld 15,%0" : : "Q" (state->fprs[15])); - } + if (flags & KERNEL_VXR_LOW) + load_fp_regs_vx(vxrs); return; } - - /* Test and restore (load) vector registers */ - asm volatile ( - /* - * Test if any vector register must be loaded and, if so, - * test if all registers can be loaded at once. - */ - " la 1,%[vxrs]\n" /* load restore area */ - " tmll %[m],30\n" /* KERNEL_VXR */ - " jz 7f\n" /* no work -> done */ - " jo 5f\n" /* -> restore V0..V31 */ - /* - * Test for special case KERNEL_FPU_MID only. In this - * case a vlm V8..V23 is the best instruction - */ - " chi %[m],12\n" /* KERNEL_VXR_MID */ - " jne 0f\n" /* -> restore V8..V23 */ - " VLM 8,23,128,1\n" /* vlm %v8,%v23,128(%r1) */ - " j 7f\n" - /* Test and restore the first half of 16 vector registers */ - "0: tmll %[m],6\n" /* KERNEL_VXR_LOW */ - " jz 3f\n" /* -> KERNEL_VXR_HIGH */ - " jo 2f\n" /* 11 -> restore V0..V15 */ - " brc 2,1f\n" /* 10 -> restore V8..V15 */ - " VLM 0,7,0,1\n" /* vlm %v0,%v7,0(%r1) */ - " j 3f\n" - "1: VLM 8,15,128,1\n" /* vlm %v8,%v15,128(%r1) */ - " j 3f\n" - "2: VLM 0,15,0,1\n" /* vlm %v0,%v15,0(%r1) */ - /* Test and restore the second half of 16 vector registers */ - "3: tmll %[m],24\n" /* KERNEL_VXR_HIGH */ - " jz 7f\n" - " jo 6f\n" /* 11 -> restore V16..V31 */ - " brc 2,4f\n" /* 10 -> restore V24..V31 */ - " VLM 16,23,256,1\n" /* vlm %v16,%v23,256(%r1) */ - " j 7f\n" - "4: VLM 24,31,384,1\n" /* vlm %v24,%v31,384(%r1) */ - " j 7f\n" - "5: VLM 0,15,0,1\n" /* vlm %v0,%v15,0(%r1) */ - "6: VLM 16,31,256,1\n" /* vlm %v16,%v31,256(%r1) */ - "7:" - : [vxrs] "=Q" (*(struct vx_array *) &state->vxrs) - : [m] "d" (flags) - : "1", "cc"); + mask = flags & KERNEL_VXR; + if (mask == KERNEL_VXR) { + vxrs += fpu_vlm(0, 15, vxrs); + vxrs += fpu_vlm(16, 31, vxrs); + return; + } + if (mask == KERNEL_VXR_MID) { + vxrs += fpu_vlm(8, 23, vxrs); + return; + } + mask = flags & KERNEL_VXR_LOW; + if (mask) { + if (mask == KERNEL_VXR_LOW) + vxrs += fpu_vlm(0, 15, vxrs); + else if (mask == KERNEL_VXR_V0V7) + vxrs += fpu_vlm(0, 7, vxrs); + else + vxrs += fpu_vlm(8, 15, vxrs); + } + mask = flags & KERNEL_VXR_HIGH; + if (mask) { + if (mask == KERNEL_VXR_HIGH) + vxrs += fpu_vlm(16, 31, vxrs); + else if (mask == KERNEL_VXR_V16V23) + vxrs += fpu_vlm(16, 23, vxrs); + else + vxrs += fpu_vlm(24, 31, vxrs); + } } EXPORT_SYMBOL(__kernel_fpu_end); -void __load_fpu_regs(void) +void load_fpu_state(struct fpu *state, int flags) { - unsigned long *regs = current->thread.fpu.regs; - struct fpu *state = ¤t->thread.fpu; + __vector128 *vxrs = &state->vxrs[0]; + int mask; - sfpc_safe(state->fpc); - if (likely(cpu_has_vx())) { - asm volatile("lgr 1,%0\n" - "VLM 0,15,0,1\n" - "VLM 16,31,256,1\n" - : - : "d" (regs) - : "1", "cc", "memory"); - } else { - asm volatile("ld 0,%0" : : "Q" (regs[0])); - asm volatile("ld 1,%0" : : "Q" (regs[1])); - asm volatile("ld 2,%0" : : "Q" (regs[2])); - asm volatile("ld 3,%0" : : "Q" (regs[3])); - asm volatile("ld 4,%0" : : "Q" (regs[4])); - asm volatile("ld 5,%0" : : "Q" (regs[5])); - asm volatile("ld 6,%0" : : "Q" (regs[6])); - asm volatile("ld 7,%0" : : "Q" (regs[7])); - asm volatile("ld 8,%0" : : "Q" (regs[8])); - asm volatile("ld 9,%0" : : "Q" (regs[9])); - asm volatile("ld 10,%0" : : "Q" (regs[10])); - asm volatile("ld 11,%0" : : "Q" (regs[11])); - asm volatile("ld 12,%0" : : "Q" (regs[12])); - asm volatile("ld 13,%0" : : "Q" (regs[13])); - asm volatile("ld 14,%0" : : "Q" (regs[14])); - asm volatile("ld 15,%0" : : "Q" (regs[15])); + if (flags & KERNEL_FPC) + fpu_lfpc(&state->fpc); + if (!cpu_has_vx()) { + if (flags & KERNEL_VXR_V0V7) + load_fp_regs_vx(state->vxrs); + return; + } + mask = flags & KERNEL_VXR; + if (mask == KERNEL_VXR) { + fpu_vlm(0, 15, &vxrs[0]); + fpu_vlm(16, 31, &vxrs[16]); + return; + } + if (mask == KERNEL_VXR_MID) { + fpu_vlm(8, 23, &vxrs[8]); + return; + } + mask = flags & KERNEL_VXR_LOW; + if (mask) { + if (mask == KERNEL_VXR_LOW) + fpu_vlm(0, 15, &vxrs[0]); + else if (mask == KERNEL_VXR_V0V7) + fpu_vlm(0, 7, &vxrs[0]); + else + fpu_vlm(8, 15, &vxrs[8]); + } + mask = flags & KERNEL_VXR_HIGH; + if (mask) { + if (mask == KERNEL_VXR_HIGH) + fpu_vlm(16, 31, &vxrs[16]); + else if (mask == KERNEL_VXR_V16V23) + fpu_vlm(16, 23, &vxrs[16]); + else + fpu_vlm(24, 31, &vxrs[24]); } - clear_cpu_flag(CIF_FPU); -} - -void load_fpu_regs(void) -{ - raw_local_irq_disable(); - __load_fpu_regs(); - raw_local_irq_enable(); } -EXPORT_SYMBOL(load_fpu_regs); -void save_fpu_regs(void) +void save_fpu_state(struct fpu *state, int flags) { - unsigned long flags, *regs; - struct fpu *state; - - local_irq_save(flags); + __vector128 *vxrs = &state->vxrs[0]; + int mask; - if (test_cpu_flag(CIF_FPU)) - goto out; - - state = ¤t->thread.fpu; - regs = current->thread.fpu.regs; - - asm volatile("stfpc %0" : "=Q" (state->fpc)); - if (likely(cpu_has_vx())) { - asm volatile("lgr 1,%0\n" - "VSTM 0,15,0,1\n" - "VSTM 16,31,256,1\n" - : - : "d" (regs) - : "1", "cc", "memory"); - } else { - asm volatile("std 0,%0" : "=Q" (regs[0])); - asm volatile("std 1,%0" : "=Q" (regs[1])); - asm volatile("std 2,%0" : "=Q" (regs[2])); - asm volatile("std 3,%0" : "=Q" (regs[3])); - asm volatile("std 4,%0" : "=Q" (regs[4])); - asm volatile("std 5,%0" : "=Q" (regs[5])); - asm volatile("std 6,%0" : "=Q" (regs[6])); - asm volatile("std 7,%0" : "=Q" (regs[7])); - asm volatile("std 8,%0" : "=Q" (regs[8])); - asm volatile("std 9,%0" : "=Q" (regs[9])); - asm volatile("std 10,%0" : "=Q" (regs[10])); - asm volatile("std 11,%0" : "=Q" (regs[11])); - asm volatile("std 12,%0" : "=Q" (regs[12])); - asm volatile("std 13,%0" : "=Q" (regs[13])); - asm volatile("std 14,%0" : "=Q" (regs[14])); - asm volatile("std 15,%0" : "=Q" (regs[15])); + if (flags & KERNEL_FPC) + fpu_stfpc(&state->fpc); + if (!cpu_has_vx()) { + if (flags & KERNEL_VXR_LOW) + save_fp_regs_vx(state->vxrs); + return; + } + mask = flags & KERNEL_VXR; + if (mask == KERNEL_VXR) { + fpu_vstm(0, 15, &vxrs[0]); + fpu_vstm(16, 31, &vxrs[16]); + return; + } + if (mask == KERNEL_VXR_MID) { + fpu_vstm(8, 23, &vxrs[8]); + return; + } + mask = flags & KERNEL_VXR_LOW; + if (mask) { + if (mask == KERNEL_VXR_LOW) + fpu_vstm(0, 15, &vxrs[0]); + else if (mask == KERNEL_VXR_V0V7) + fpu_vstm(0, 7, &vxrs[0]); + else + fpu_vstm(8, 15, &vxrs[8]); + } + mask = flags & KERNEL_VXR_HIGH; + if (mask) { + if (mask == KERNEL_VXR_HIGH) + fpu_vstm(16, 31, &vxrs[16]); + else if (mask == KERNEL_VXR_V16V23) + fpu_vstm(16, 23, &vxrs[16]); + else + fpu_vstm(24, 31, &vxrs[24]); } - set_cpu_flag(CIF_FPU); -out: - local_irq_restore(flags); } -EXPORT_SYMBOL(save_fpu_regs); +EXPORT_SYMBOL(save_fpu_state); diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index ba75f6bee774..1486350a4177 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -1941,8 +1941,7 @@ static void dump_reipl_run(struct shutdown_trigger *trigger) reipl_type == IPL_TYPE_UNKNOWN) os_info_flags |= OS_INFO_FLAG_REIPL_CLEAR; os_info_entry_add(OS_INFO_FLAGS_ENTRY, &os_info_flags, sizeof(os_info_flags)); - csum = (__force unsigned int) - csum_partial(reipl_block_actual, reipl_block_actual->hdr.len, 0); + csum = (__force unsigned int)cksm(reipl_block_actual, reipl_block_actual->hdr.len, 0); abs_lc = get_abs_lowcore(); abs_lc->ipib = __pa(reipl_block_actual); abs_lc->ipib_checksum = csum; diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c index aa22ffc16bcd..c5d0c1cf984b 100644 --- a/arch/s390/kernel/machine_kexec.c +++ b/arch/s390/kernel/machine_kexec.c @@ -13,8 +13,10 @@ #include <linux/reboot.h> #include <linux/ftrace.h> #include <linux/debug_locks.h> +#include <asm/guarded_storage.h> #include <asm/pfault.h> #include <asm/cio.h> +#include <asm/fpu.h> #include <asm/setup.h> #include <asm/smp.h> #include <asm/ipl.h> @@ -26,7 +28,6 @@ #include <asm/os_info.h> #include <asm/set_memory.h> #include <asm/stacktrace.h> -#include <asm/switch_to.h> #include <asm/nmi.h> #include <asm/sclp.h> diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c index 9ad44c26d1a2..c77382a67325 100644 --- a/arch/s390/kernel/nmi.c +++ b/arch/s390/kernel/nmi.c @@ -23,16 +23,14 @@ #include <linux/export.h> #include <asm/lowcore.h> #include <asm/ctlreg.h> +#include <asm/fpu.h> #include <asm/smp.h> #include <asm/stp.h> #include <asm/cputime.h> #include <asm/nmi.h> #include <asm/crw.h> -#include <asm/switch_to.h> #include <asm/asm-offsets.h> #include <asm/pai.h> -#include <asm/vx-insn.h> -#include <asm/fpu/api.h> struct mcck_struct { unsigned int kill_task : 1; @@ -204,133 +202,63 @@ void s390_handle_mcck(void) } } -/* - * returns 0 if register contents could be validated - * returns 1 otherwise +/** + * nmi_registers_valid - verify if registers are valid + * @mci: machine check interruption code + * + * Inspect a machine check interruption code and verify if all required + * registers are valid. For some registers the corresponding validity bit is + * ignored and the registers are set to the expected value. + * Returns true if all registers are valid, otherwise false. */ -static int notrace s390_validate_registers(union mci mci) +static bool notrace nmi_registers_valid(union mci mci) { - struct mcesa *mcesa; - void *fpt_save_area; union ctlreg2 cr2; - int kill_task; - u64 zero; - - kill_task = 0; - zero = 0; - - if (!mci.gr || !mci.fp) - kill_task = 1; - fpt_save_area = &S390_lowcore.floating_pt_save_area; - if (!mci.fc) { - kill_task = 1; - asm volatile( - " lfpc %0\n" - : - : "Q" (zero)); - } else { - asm volatile( - " lfpc %0\n" - : - : "Q" (S390_lowcore.fpt_creg_save_area)); - } - mcesa = __va(S390_lowcore.mcesad & MCESA_ORIGIN_MASK); - if (!cpu_has_vx()) { - /* Validate floating point registers */ - asm volatile( - " ld 0,0(%0)\n" - " ld 1,8(%0)\n" - " ld 2,16(%0)\n" - " ld 3,24(%0)\n" - " ld 4,32(%0)\n" - " ld 5,40(%0)\n" - " ld 6,48(%0)\n" - " ld 7,56(%0)\n" - " ld 8,64(%0)\n" - " ld 9,72(%0)\n" - " ld 10,80(%0)\n" - " ld 11,88(%0)\n" - " ld 12,96(%0)\n" - " ld 13,104(%0)\n" - " ld 14,112(%0)\n" - " ld 15,120(%0)\n" - : - : "a" (fpt_save_area) - : "memory"); - } else { - /* Validate vector registers */ - union ctlreg0 cr0; - - /* - * The vector validity must only be checked if not running a - * KVM guest. For KVM guests the machine check is forwarded by - * KVM and it is the responsibility of the guest to take - * appropriate actions. The host vector or FPU values have been - * saved by KVM and will be restored by KVM. - */ - if (!mci.vr && !test_cpu_flag(CIF_MCCK_GUEST)) - kill_task = 1; - cr0.reg = S390_lowcore.cregs_save_area[0]; - cr0.afp = cr0.vx = 1; - local_ctl_load(0, &cr0.reg); - asm volatile( - " la 1,%0\n" - " VLM 0,15,0,1\n" - " VLM 16,31,256,1\n" - : - : "Q" (*(struct vx_array *)mcesa->vector_save_area) - : "1"); - local_ctl_load(0, &S390_lowcore.cregs_save_area[0]); - } - /* Validate access registers */ - asm volatile( - " lam 0,15,0(%0)\n" - : - : "a" (&S390_lowcore.access_regs_save_area) - : "memory"); - if (!mci.ar) - kill_task = 1; - /* Validate guarded storage registers */ - cr2.reg = S390_lowcore.cregs_save_area[2]; - if (cr2.gse) { - if (!mci.gs) { - /* - * 2 cases: - * - machine check in kernel or userspace - * - machine check while running SIE (KVM guest) - * For kernel or userspace the userspace values of - * guarded storage control can not be recreated, the - * process must be terminated. - * For SIE the guest values of guarded storage can not - * be recreated. This is either due to a bug or due to - * GS being disabled in the guest. The guest will be - * notified by KVM code and the guests machine check - * handling must take care of this. The host values - * are saved by KVM and are not affected. - */ - if (!test_cpu_flag(CIF_MCCK_GUEST)) - kill_task = 1; - } else { - load_gs_cb((struct gs_cb *)mcesa->guarded_storage_save_area); - } - } /* - * The getcpu vdso syscall reads CPU number from the programmable + * The getcpu vdso syscall reads the CPU number from the programmable * field of the TOD clock. Disregard the TOD programmable register - * validity bit and load the CPU number into the TOD programmable - * field unconditionally. + * validity bit and load the CPU number into the TOD programmable field + * unconditionally. */ set_tod_programmable_field(raw_smp_processor_id()); - /* Validate clock comparator register */ + /* + * Set the clock comparator register to the next expected value. + */ set_clock_comparator(S390_lowcore.clock_comparator); - + if (!mci.gr || !mci.fp || !mci.fc) + return false; + /* + * The vector validity must only be checked if not running a + * KVM guest. For KVM guests the machine check is forwarded by + * KVM and it is the responsibility of the guest to take + * appropriate actions. The host vector or FPU values have been + * saved by KVM and will be restored by KVM. + */ + if (!mci.vr && !test_cpu_flag(CIF_MCCK_GUEST)) + return false; + if (!mci.ar) + return false; + /* + * Two cases for guarded storage registers: + * - machine check in kernel or userspace + * - machine check while running SIE (KVM guest) + * For kernel or userspace the userspace values of guarded storage + * control can not be recreated, the process must be terminated. + * For SIE the guest values of guarded storage can not be recreated. + * This is either due to a bug or due to GS being disabled in the + * guest. The guest will be notified by KVM code and the guests machine + * check handling must take care of this. The host values are saved by + * KVM and are not affected. + */ + cr2.reg = S390_lowcore.cregs_save_area[2]; + if (cr2.gse && !mci.gs && !test_cpu_flag(CIF_MCCK_GUEST)) + return false; if (!mci.ms || !mci.pm || !mci.ia) - kill_task = 1; - - return kill_task; + return false; + return true; } -NOKPROBE_SYMBOL(s390_validate_registers); +NOKPROBE_SYMBOL(nmi_registers_valid); /* * Backup the guest's machine check info to its description block @@ -428,7 +356,7 @@ void notrace s390_do_machine_check(struct pt_regs *regs) s390_handle_damage(); } } - if (s390_validate_registers(mci)) { + if (!nmi_registers_valid(mci)) { if (!user_mode(regs)) s390_handle_damage(); /* diff --git a/arch/s390/kernel/os_info.c b/arch/s390/kernel/os_info.c index 6e1824141b29..a801e6bd5341 100644 --- a/arch/s390/kernel/os_info.c +++ b/arch/s390/kernel/os_info.c @@ -29,7 +29,7 @@ static struct os_info os_info __page_aligned_data; u32 os_info_csum(struct os_info *os_info) { int size = sizeof(*os_info) - offsetof(struct os_info, version_major); - return (__force u32)csum_partial(&os_info->version_major, size, 0); + return (__force u32)cksm(&os_info->version_major, size, 0); } /* @@ -49,7 +49,7 @@ void os_info_entry_add(int nr, void *ptr, u64 size) { os_info.entry[nr].addr = __pa(ptr); os_info.entry[nr].size = size; - os_info.entry[nr].csum = (__force u32)csum_partial(ptr, size, 0); + os_info.entry[nr].csum = (__force u32)cksm(ptr, size, 0); os_info.csum = os_info_csum(&os_info); } @@ -98,7 +98,7 @@ static void os_info_old_alloc(int nr, int align) msg = "copy failed"; goto fail_free; } - csum = (__force u32)csum_partial(buf_align, size, 0); + csum = (__force u32)cksm(buf_align, size, 0); if (csum != os_info_old->entry[nr].csum) { msg = "checksum failed"; goto fail_free; diff --git a/arch/s390/kernel/perf_pai_crypto.c b/arch/s390/kernel/perf_pai_crypto.c index bf8a672b15a4..823d652e3917 100644 --- a/arch/s390/kernel/perf_pai_crypto.c +++ b/arch/s390/kernel/perf_pai_crypto.c @@ -98,6 +98,7 @@ static void paicrypt_event_destroy(struct perf_event *event) event->attr.config, event->cpu, cpump->active_events, cpump->mode, refcount_read(&cpump->refcnt)); + free_page(PAI_SAVE_AREA(event)); if (refcount_dec_and_test(&cpump->refcnt)) { debug_sprintf_event(cfm_dbg, 4, "%s page %#lx save %p\n", __func__, (unsigned long)cpump->page, @@ -260,6 +261,7 @@ static int paicrypt_event_init(struct perf_event *event) { struct perf_event_attr *a = &event->attr; struct paicrypt_map *cpump; + int rc = 0; /* PAI crypto PMU registered as PERF_TYPE_RAW, check event type */ if (a->type != PERF_TYPE_RAW && event->pmu->type != a->type) @@ -274,10 +276,21 @@ static int paicrypt_event_init(struct perf_event *event) /* Allow only CRYPTO_ALL for sampling. */ if (a->sample_period && a->config != PAI_CRYPTO_BASE) return -EINVAL; + /* Get a page to store last counter values for sampling */ + if (a->sample_period) { + PAI_SAVE_AREA(event) = get_zeroed_page(GFP_KERNEL); + if (!PAI_SAVE_AREA(event)) { + rc = -ENOMEM; + goto out; + } + } cpump = paicrypt_busy(event); - if (IS_ERR(cpump)) - return PTR_ERR(cpump); + if (IS_ERR(cpump)) { + free_page(PAI_SAVE_AREA(event)); + rc = PTR_ERR(cpump); + goto out; + } event->destroy = paicrypt_event_destroy; @@ -293,7 +306,8 @@ static int paicrypt_event_init(struct perf_event *event) } static_branch_inc(&pai_key); - return 0; +out: + return rc; } static void paicrypt_read(struct perf_event *event) @@ -310,20 +324,15 @@ static void paicrypt_read(struct perf_event *event) static void paicrypt_start(struct perf_event *event, int flags) { + struct paicrypt_mapptr *mp = this_cpu_ptr(paicrypt_root.mapptr); + struct paicrypt_map *cpump = mp->mapptr; u64 sum; - /* Event initialization sets last_tag to 0. When later on the events - * are deleted and re-added, do not reset the event count value to zero. - * Events are added, deleted and re-added when 2 or more events - * are active at the same time. - */ if (!event->attr.sample_period) { /* Counting */ - if (!event->hw.last_tag) { - event->hw.last_tag = 1; - sum = paicrypt_getall(event); /* Get current value */ - local64_set(&event->hw.prev_count, sum); - } + sum = paicrypt_getall(event); /* Get current value */ + local64_set(&event->hw.prev_count, sum); } else { /* Sampling */ + cpump->event = event; perf_sched_cb_inc(event->pmu); } } @@ -339,7 +348,6 @@ static int paicrypt_add(struct perf_event *event, int flags) WRITE_ONCE(S390_lowcore.ccd, ccd); local_ctl_set_bit(0, CR0_CRYPTOGRAPHY_COUNTER_BIT); } - cpump->event = event; if (flags & PERF_EF_START) paicrypt_start(event, PERF_EF_RELOAD); event->hw.state = 0; @@ -367,23 +375,34 @@ static void paicrypt_del(struct perf_event *event, int flags) } } -/* Create raw data and save it in buffer. Returns number of bytes copied. - * Saves only positive counter entries of the form +/* Create raw data and save it in buffer. Calculate the delta for each + * counter between this invocation and the last invocation. + * Returns number of bytes copied. + * Saves only entries with positive counter difference of the form * 2 bytes: Number of counter * 8 bytes: Value of counter */ static size_t paicrypt_copy(struct pai_userdata *userdata, unsigned long *page, - bool exclude_user, bool exclude_kernel) + unsigned long *page_old, bool exclude_user, + bool exclude_kernel) { int i, outidx = 0; for (i = 1; i <= paicrypt_cnt; i++) { - u64 val = 0; + u64 val = 0, val_old = 0; - if (!exclude_kernel) + if (!exclude_kernel) { val += paicrypt_getctr(page, i, true); - if (!exclude_user) + val_old += paicrypt_getctr(page_old, i, true); + } + if (!exclude_user) { val += paicrypt_getctr(page, i, false); + val_old += paicrypt_getctr(page_old, i, false); + } + if (val >= val_old) + val -= val_old; + else + val = (~0ULL - val_old) + val + 1; if (val) { userdata[outidx].num = i; userdata[outidx].value = val; @@ -426,8 +445,8 @@ static int paicrypt_push_sample(size_t rawsize, struct paicrypt_map *cpump, overflow = perf_event_overflow(event, &data, ®s); perf_event_update_userpage(event); - /* Clear lowcore page after read */ - memset(cpump->page, 0, PAGE_SIZE); + /* Save crypto counter lowcore page after reading event data. */ + memcpy((void *)PAI_SAVE_AREA(event), cpump->page, PAGE_SIZE); return overflow; } @@ -443,6 +462,7 @@ static int paicrypt_have_sample(void) if (!event) /* No event active */ return 0; rawsize = paicrypt_copy(cpump->save, cpump->page, + (unsigned long *)PAI_SAVE_AREA(event), cpump->event->attr.exclude_user, cpump->event->attr.exclude_kernel); if (rawsize) /* No incremented counters */ @@ -694,6 +714,12 @@ static int __init attr_event_init_one(struct attribute **attrs, int num) { struct perf_pmu_events_attr *pa; + /* Index larger than array_size, no counter name available */ + if (num >= ARRAY_SIZE(paicrypt_ctrnames)) { + attrs[num] = NULL; + return 0; + } + pa = kzalloc(sizeof(*pa), GFP_KERNEL); if (!pa) return -ENOMEM; @@ -714,14 +740,13 @@ static int __init attr_event_init(void) struct attribute **attrs; int ret, i; - attrs = kmalloc_array(ARRAY_SIZE(paicrypt_ctrnames) + 1, sizeof(*attrs), - GFP_KERNEL); + attrs = kmalloc_array(paicrypt_cnt + 2, sizeof(*attrs), GFP_KERNEL); if (!attrs) return -ENOMEM; - for (i = 0; i < ARRAY_SIZE(paicrypt_ctrnames); i++) { + for (i = 0; i <= paicrypt_cnt; i++) { ret = attr_event_init_one(attrs, i); if (ret) { - attr_event_free(attrs, i - 1); + attr_event_free(attrs, i); return ret; } } @@ -742,8 +767,10 @@ static int __init paicrypt_init(void) paicrypt_cnt = ib.num_cc; if (paicrypt_cnt == 0) return 0; - if (paicrypt_cnt >= PAI_CRYPTO_MAXCTR) - paicrypt_cnt = PAI_CRYPTO_MAXCTR - 1; + if (paicrypt_cnt >= PAI_CRYPTO_MAXCTR) { + pr_err("Too many PMU pai_crypto counters %d\n", paicrypt_cnt); + return -E2BIG; + } rc = attr_event_init(); /* Export known PAI crypto events */ if (rc) { diff --git a/arch/s390/kernel/perf_pai_ext.c b/arch/s390/kernel/perf_pai_ext.c index af7f2b538c8f..616a25606cd6 100644 --- a/arch/s390/kernel/perf_pai_ext.c +++ b/arch/s390/kernel/perf_pai_ext.c @@ -120,6 +120,7 @@ static void paiext_event_destroy(struct perf_event *event) struct paiext_mapptr *mp = per_cpu_ptr(paiext_root.mapptr, event->cpu); struct paiext_map *cpump = mp->mapptr; + free_page(PAI_SAVE_AREA(event)); mutex_lock(&paiext_reserve_mutex); cpump->event = NULL; if (refcount_dec_and_test(&cpump->refcnt)) /* Last reference gone */ @@ -202,7 +203,6 @@ static int paiext_alloc(struct perf_event_attr *a, struct perf_event *event) } rc = 0; - cpump->event = event; undo: if (rc) { @@ -256,10 +256,18 @@ static int paiext_event_init(struct perf_event *event) /* Prohibit exclude_user event selection */ if (a->exclude_user) return -EINVAL; + /* Get a page to store last counter values for sampling */ + if (a->sample_period) { + PAI_SAVE_AREA(event) = get_zeroed_page(GFP_KERNEL); + if (!PAI_SAVE_AREA(event)) + return -ENOMEM; + } rc = paiext_alloc(a, event); - if (rc) + if (rc) { + free_page(PAI_SAVE_AREA(event)); return rc; + } event->destroy = paiext_event_destroy; if (a->sample_period) { @@ -319,15 +327,15 @@ static void paiext_read(struct perf_event *event) static void paiext_start(struct perf_event *event, int flags) { + struct paiext_mapptr *mp = this_cpu_ptr(paiext_root.mapptr); + struct paiext_map *cpump = mp->mapptr; u64 sum; if (!event->attr.sample_period) { /* Counting */ - if (!event->hw.last_tag) { - event->hw.last_tag = 1; - sum = paiext_getall(event); /* Get current value */ - local64_set(&event->hw.prev_count, sum); - } + sum = paiext_getall(event); /* Get current value */ + local64_set(&event->hw.prev_count, sum); } else { /* Sampling */ + cpump->event = event; perf_sched_cb_inc(event->pmu); } } @@ -346,7 +354,6 @@ static int paiext_add(struct perf_event *event, int flags) debug_sprintf_event(paiext_dbg, 4, "%s 1508 %llx acc %llx\n", __func__, S390_lowcore.aicd, pcb->acc); } - cpump->event = event; if (flags & PERF_EF_START) paiext_start(event, PERF_EF_RELOAD); event->hw.state = 0; @@ -384,13 +391,19 @@ static void paiext_del(struct perf_event *event, int flags) * 2 bytes: Number of counter * 8 bytes: Value of counter */ -static size_t paiext_copy(struct pai_userdata *userdata, unsigned long *area) +static size_t paiext_copy(struct pai_userdata *userdata, unsigned long *area, + unsigned long *area_old) { int i, outidx = 0; for (i = 1; i <= paiext_cnt; i++) { u64 val = paiext_getctr(area, i); + u64 val_old = paiext_getctr(area_old, i); + if (val >= val_old) + val -= val_old; + else + val = (~0ULL - val_old) + val + 1; if (val) { userdata[outidx].num = i; userdata[outidx].value = val; @@ -446,8 +459,9 @@ static int paiext_push_sample(size_t rawsize, struct paiext_map *cpump, overflow = perf_event_overflow(event, &data, ®s); perf_event_update_userpage(event); - /* Clear lowcore area after read */ - memset(cpump->area, 0, PAIE1_CTRBLOCK_SZ); + /* Save NNPA lowcore area after read in event */ + memcpy((void *)PAI_SAVE_AREA(event), cpump->area, + PAIE1_CTRBLOCK_SZ); return overflow; } @@ -462,7 +476,8 @@ static int paiext_have_sample(void) if (!event) return 0; - rawsize = paiext_copy(cpump->save, cpump->area); + rawsize = paiext_copy(cpump->save, cpump->area, + (unsigned long *)PAI_SAVE_AREA(event)); if (rawsize) /* Incremented counters */ rc = paiext_push_sample(rawsize, cpump, event); return rc; @@ -584,6 +599,12 @@ static int __init attr_event_init_one(struct attribute **attrs, int num) { struct perf_pmu_events_attr *pa; + /* Index larger than array_size, no counter name available */ + if (num >= ARRAY_SIZE(paiext_ctrnames)) { + attrs[num] = NULL; + return 0; + } + pa = kzalloc(sizeof(*pa), GFP_KERNEL); if (!pa) return -ENOMEM; @@ -604,14 +625,13 @@ static int __init attr_event_init(void) struct attribute **attrs; int ret, i; - attrs = kmalloc_array(ARRAY_SIZE(paiext_ctrnames) + 1, sizeof(*attrs), - GFP_KERNEL); + attrs = kmalloc_array(paiext_cnt + 2, sizeof(*attrs), GFP_KERNEL); if (!attrs) return -ENOMEM; - for (i = 0; i < ARRAY_SIZE(paiext_ctrnames); i++) { + for (i = 0; i <= paiext_cnt; i++) { ret = attr_event_init_one(attrs, i); if (ret) { - attr_event_free(attrs, i - 1); + attr_event_free(attrs, i); return ret; } } diff --git a/arch/s390/kernel/perf_regs.c b/arch/s390/kernel/perf_regs.c index 3d93656bd948..a6b058ee4a36 100644 --- a/arch/s390/kernel/perf_regs.c +++ b/arch/s390/kernel/perf_regs.c @@ -5,8 +5,7 @@ #include <linux/errno.h> #include <linux/bug.h> #include <asm/ptrace.h> -#include <asm/fpu/api.h> -#include <asm/fpu/types.h> +#include <asm/fpu.h> u64 perf_reg_value(struct pt_regs *regs, int idx) { @@ -20,10 +19,7 @@ u64 perf_reg_value(struct pt_regs *regs, int idx) return 0; idx -= PERF_REG_S390_FP0; - if (cpu_has_vx()) - fp = *(freg_t *)(current->thread.fpu.vxrs + idx); - else - fp = current->thread.fpu.fprs[idx]; + fp = *(freg_t *)(current->thread.ufpu.vxrs + idx); return fp.ui; } @@ -65,6 +61,6 @@ void perf_get_regs_user(struct perf_regs *regs_user, */ regs_user->regs = task_pt_regs(current); if (user_mode(regs_user->regs)) - save_fpu_regs(); + save_user_fpu_regs(); regs_user->abi = perf_reg_abi(current); } diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index 4e3b366589fb..dd456b475861 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -31,15 +31,19 @@ #include <linux/init_task.h> #include <linux/entry-common.h> #include <linux/io.h> +#include <asm/guarded_storage.h> +#include <asm/access-regs.h> +#include <asm/switch_to.h> #include <asm/cpu_mf.h> #include <asm/processor.h> +#include <asm/ptrace.h> #include <asm/vtimer.h> #include <asm/exec.h> +#include <asm/fpu.h> #include <asm/irq.h> #include <asm/nmi.h> #include <asm/smp.h> #include <asm/stacktrace.h> -#include <asm/switch_to.h> #include <asm/runtime_instr.h> #include <asm/unwind.h> #include "entry.h" @@ -84,13 +88,13 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { /* * Save the floating-point or vector register state of the current - * task and set the CIF_FPU flag to lazy restore the FPU register + * task and set the TIF_FPU flag to lazy restore the FPU register * state when returning to user space. */ - save_fpu_regs(); + save_user_fpu_regs(); *dst = *src; - dst->thread.fpu.regs = dst->thread.fpu.fprs; + dst->thread.kfpu_flags = 0; /* * Don't transfer over the runtime instrumentation or the guarded @@ -186,8 +190,23 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) void execve_tail(void) { - current->thread.fpu.fpc = 0; - asm volatile("sfpc %0" : : "d" (0)); + current->thread.ufpu.fpc = 0; + fpu_sfpc(0); +} + +struct task_struct *__switch_to(struct task_struct *prev, struct task_struct *next) +{ + save_user_fpu_regs(); + save_kernel_fpu_regs(&prev->thread); + save_access_regs(&prev->thread.acrs[0]); + save_ri_cb(prev->thread.ri_cb); + save_gs_cb(prev->thread.gs_cb); + update_cr_regs(next); + restore_kernel_fpu_regs(&next->thread); + restore_access_regs(&next->thread.acrs[0]); + restore_ri_cb(next->thread.ri_cb, prev->thread.ri_cb); + restore_gs_cb(next->thread.gs_cb); + return __switch_to_asm(prev, next); } unsigned long __get_wchan(struct task_struct *p) diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index f1897a8bb221..1cfed8b710b8 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -24,13 +24,14 @@ #include <linux/seccomp.h> #include <linux/compat.h> #include <trace/syscall.h> +#include <asm/guarded_storage.h> +#include <asm/access-regs.h> #include <asm/page.h> #include <linux/uaccess.h> #include <asm/unistd.h> -#include <asm/switch_to.h> #include <asm/runtime_instr.h> #include <asm/facility.h> -#include <asm/fpu/api.h> +#include <asm/fpu.h> #include "entry.h" @@ -246,22 +247,15 @@ static unsigned long __peek_user(struct task_struct *child, addr_t addr) /* * floating point control reg. is in the thread structure */ - tmp = child->thread.fpu.fpc; + tmp = child->thread.ufpu.fpc; tmp <<= BITS_PER_LONG - 32; } else if (addr < offsetof(struct user, regs.fp_regs) + sizeof(s390_fp_regs)) { /* - * floating point regs. are either in child->thread.fpu - * or the child->thread.fpu.vxrs array + * floating point regs. are in the child->thread.ufpu.vxrs array */ offset = addr - offsetof(struct user, regs.fp_regs.fprs); - if (cpu_has_vx()) - tmp = *(addr_t *) - ((addr_t) child->thread.fpu.vxrs + 2*offset); - else - tmp = *(addr_t *) - ((addr_t) child->thread.fpu.fprs + offset); - + tmp = *(addr_t *)((addr_t)child->thread.ufpu.vxrs + 2 * offset); } else if (addr < offsetof(struct user, regs.per_info) + sizeof(per_struct)) { /* * Handle access to the per_info structure. @@ -395,21 +389,14 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data) */ if ((unsigned int)data != 0) return -EINVAL; - child->thread.fpu.fpc = data >> (BITS_PER_LONG - 32); + child->thread.ufpu.fpc = data >> (BITS_PER_LONG - 32); } else if (addr < offsetof(struct user, regs.fp_regs) + sizeof(s390_fp_regs)) { /* - * floating point regs. are either in child->thread.fpu - * or the child->thread.fpu.vxrs array + * floating point regs. are in the child->thread.ufpu.vxrs array */ offset = addr - offsetof(struct user, regs.fp_regs.fprs); - if (cpu_has_vx()) - *(addr_t *)((addr_t) - child->thread.fpu.vxrs + 2*offset) = data; - else - *(addr_t *)((addr_t) - child->thread.fpu.fprs + offset) = data; - + *(addr_t *)((addr_t)child->thread.ufpu.vxrs + 2 * offset) = data; } else if (addr < offsetof(struct user, regs.per_info) + sizeof(per_struct)) { /* * Handle access to the per_info structure. @@ -622,21 +609,14 @@ static u32 __peek_user_compat(struct task_struct *child, addr_t addr) /* * floating point control reg. is in the thread structure */ - tmp = child->thread.fpu.fpc; + tmp = child->thread.ufpu.fpc; } else if (addr < offsetof(struct compat_user, regs.fp_regs) + sizeof(s390_fp_regs)) { /* - * floating point regs. are either in child->thread.fpu - * or the child->thread.fpu.vxrs array + * floating point regs. are in the child->thread.ufpu.vxrs array */ offset = addr - offsetof(struct compat_user, regs.fp_regs.fprs); - if (cpu_has_vx()) - tmp = *(__u32 *) - ((addr_t) child->thread.fpu.vxrs + 2*offset); - else - tmp = *(__u32 *) - ((addr_t) child->thread.fpu.fprs + offset); - + tmp = *(__u32 *)((addr_t)child->thread.ufpu.vxrs + 2 * offset); } else if (addr < offsetof(struct compat_user, regs.per_info) + sizeof(struct compat_per_struct_kernel)) { /* * Handle access to the per_info structure. @@ -748,21 +728,14 @@ static int __poke_user_compat(struct task_struct *child, /* * floating point control reg. is in the thread structure */ - child->thread.fpu.fpc = data; + child->thread.ufpu.fpc = data; } else if (addr < offsetof(struct compat_user, regs.fp_regs) + sizeof(s390_fp_regs)) { /* - * floating point regs. are either in child->thread.fpu - * or the child->thread.fpu.vxrs array + * floating point regs. are in the child->thread.ufpu.vxrs array */ offset = addr - offsetof(struct compat_user, regs.fp_regs.fprs); - if (cpu_has_vx()) - *(__u32 *)((addr_t) - child->thread.fpu.vxrs + 2*offset) = tmp; - else - *(__u32 *)((addr_t) - child->thread.fpu.fprs + offset) = tmp; - + *(__u32 *)((addr_t)child->thread.ufpu.vxrs + 2 * offset) = tmp; } else if (addr < offsetof(struct compat_user, regs.per_info) + sizeof(struct compat_per_struct_kernel)) { /* * Handle access to the per_info structure. @@ -893,10 +866,10 @@ static int s390_fpregs_get(struct task_struct *target, _s390_fp_regs fp_regs; if (target == current) - save_fpu_regs(); + save_user_fpu_regs(); - fp_regs.fpc = target->thread.fpu.fpc; - fpregs_store(&fp_regs, &target->thread.fpu); + fp_regs.fpc = target->thread.ufpu.fpc; + fpregs_store(&fp_regs, &target->thread.ufpu); return membuf_write(&to, &fp_regs, sizeof(fp_regs)); } @@ -910,22 +883,17 @@ static int s390_fpregs_set(struct task_struct *target, freg_t fprs[__NUM_FPRS]; if (target == current) - save_fpu_regs(); - - if (cpu_has_vx()) - convert_vx_to_fp(fprs, target->thread.fpu.vxrs); - else - memcpy(&fprs, target->thread.fpu.fprs, sizeof(fprs)); - + save_user_fpu_regs(); + convert_vx_to_fp(fprs, target->thread.ufpu.vxrs); if (count > 0 && pos < offsetof(s390_fp_regs, fprs)) { - u32 ufpc[2] = { target->thread.fpu.fpc, 0 }; + u32 ufpc[2] = { target->thread.ufpu.fpc, 0 }; rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ufpc, 0, offsetof(s390_fp_regs, fprs)); if (rc) return rc; if (ufpc[1] != 0) return -EINVAL; - target->thread.fpu.fpc = ufpc[0]; + target->thread.ufpu.fpc = ufpc[0]; } if (rc == 0 && count > 0) @@ -933,12 +901,7 @@ static int s390_fpregs_set(struct task_struct *target, fprs, offsetof(s390_fp_regs, fprs), -1); if (rc) return rc; - - if (cpu_has_vx()) - convert_fp_to_vx(target->thread.fpu.vxrs, fprs); - else - memcpy(target->thread.fpu.fprs, &fprs, sizeof(fprs)); - + convert_fp_to_vx(target->thread.ufpu.vxrs, fprs); return rc; } @@ -988,9 +951,9 @@ static int s390_vxrs_low_get(struct task_struct *target, if (!cpu_has_vx()) return -ENODEV; if (target == current) - save_fpu_regs(); + save_user_fpu_regs(); for (i = 0; i < __NUM_VXRS_LOW; i++) - vxrs[i] = target->thread.fpu.vxrs[i].low; + vxrs[i] = target->thread.ufpu.vxrs[i].low; return membuf_write(&to, vxrs, sizeof(vxrs)); } @@ -1005,15 +968,15 @@ static int s390_vxrs_low_set(struct task_struct *target, if (!cpu_has_vx()) return -ENODEV; if (target == current) - save_fpu_regs(); + save_user_fpu_regs(); for (i = 0; i < __NUM_VXRS_LOW; i++) - vxrs[i] = target->thread.fpu.vxrs[i].low; + vxrs[i] = target->thread.ufpu.vxrs[i].low; rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf, vxrs, 0, -1); if (rc == 0) for (i = 0; i < __NUM_VXRS_LOW; i++) - target->thread.fpu.vxrs[i].low = vxrs[i]; + target->thread.ufpu.vxrs[i].low = vxrs[i]; return rc; } @@ -1025,8 +988,8 @@ static int s390_vxrs_high_get(struct task_struct *target, if (!cpu_has_vx()) return -ENODEV; if (target == current) - save_fpu_regs(); - return membuf_write(&to, target->thread.fpu.vxrs + __NUM_VXRS_LOW, + save_user_fpu_regs(); + return membuf_write(&to, target->thread.ufpu.vxrs + __NUM_VXRS_LOW, __NUM_VXRS_HIGH * sizeof(__vector128)); } @@ -1040,10 +1003,10 @@ static int s390_vxrs_high_set(struct task_struct *target, if (!cpu_has_vx()) return -ENODEV; if (target == current) - save_fpu_regs(); + save_user_fpu_regs(); rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - target->thread.fpu.vxrs + __NUM_VXRS_LOW, 0, -1); + target->thread.ufpu.vxrs + __NUM_VXRS_LOW, 0, -1); return rc; } diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index d1f3b56e7afc..24ed33f044ec 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -504,12 +504,12 @@ static void __init setup_resources(void) int j; u64 i; - code_resource.start = (unsigned long) _text; - code_resource.end = (unsigned long) _etext - 1; - data_resource.start = (unsigned long) _etext; - data_resource.end = (unsigned long) _edata - 1; - bss_resource.start = (unsigned long) __bss_start; - bss_resource.end = (unsigned long) __bss_stop - 1; + code_resource.start = __pa_symbol(_text); + code_resource.end = __pa_symbol(_etext) - 1; + data_resource.start = __pa_symbol(_etext); + data_resource.end = __pa_symbol(_edata) - 1; + bss_resource.start = __pa_symbol(__bss_start); + bss_resource.end = __pa_symbol(__bss_stop) - 1; for_each_mem_range(i, &start, &end) { res = memblock_alloc(sizeof(*res), 8); diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c index 43e9661cd715..6c2cb345402f 100644 --- a/arch/s390/kernel/signal.c +++ b/arch/s390/kernel/signal.c @@ -30,8 +30,8 @@ #include <linux/compat.h> #include <asm/ucontext.h> #include <linux/uaccess.h> +#include <asm/access-regs.h> #include <asm/lowcore.h> -#include <asm/switch_to.h> #include <asm/vdso.h> #include "entry.h" @@ -109,7 +109,7 @@ struct rt_sigframe static void store_sigregs(void) { save_access_regs(current->thread.acrs); - save_fpu_regs(); + save_user_fpu_regs(); } /* Load registers after signal return */ @@ -131,7 +131,7 @@ static int save_sigregs(struct pt_regs *regs, _sigregs __user *sregs) memcpy(&user_sregs.regs.gprs, ®s->gprs, sizeof(sregs->regs.gprs)); memcpy(&user_sregs.regs.acrs, current->thread.acrs, sizeof(user_sregs.regs.acrs)); - fpregs_store(&user_sregs.fpregs, ¤t->thread.fpu); + fpregs_store(&user_sregs.fpregs, ¤t->thread.ufpu); if (__copy_to_user(sregs, &user_sregs, sizeof(_sigregs))) return -EFAULT; return 0; @@ -165,7 +165,7 @@ static int restore_sigregs(struct pt_regs *regs, _sigregs __user *sregs) memcpy(¤t->thread.acrs, &user_sregs.regs.acrs, sizeof(current->thread.acrs)); - fpregs_load(&user_sregs.fpregs, ¤t->thread.fpu); + fpregs_load(&user_sregs.fpregs, ¤t->thread.ufpu); clear_pt_regs_flag(regs, PIF_SYSCALL); /* No longer in a system call */ return 0; @@ -181,11 +181,11 @@ static int save_sigregs_ext(struct pt_regs *regs, /* Save vector registers to signal stack */ if (cpu_has_vx()) { for (i = 0; i < __NUM_VXRS_LOW; i++) - vxrs[i] = current->thread.fpu.vxrs[i].low; + vxrs[i] = current->thread.ufpu.vxrs[i].low; if (__copy_to_user(&sregs_ext->vxrs_low, vxrs, sizeof(sregs_ext->vxrs_low)) || __copy_to_user(&sregs_ext->vxrs_high, - current->thread.fpu.vxrs + __NUM_VXRS_LOW, + current->thread.ufpu.vxrs + __NUM_VXRS_LOW, sizeof(sregs_ext->vxrs_high))) return -EFAULT; } @@ -202,12 +202,12 @@ static int restore_sigregs_ext(struct pt_regs *regs, if (cpu_has_vx()) { if (__copy_from_user(vxrs, &sregs_ext->vxrs_low, sizeof(sregs_ext->vxrs_low)) || - __copy_from_user(current->thread.fpu.vxrs + __NUM_VXRS_LOW, + __copy_from_user(current->thread.ufpu.vxrs + __NUM_VXRS_LOW, &sregs_ext->vxrs_high, sizeof(sregs_ext->vxrs_high))) return -EFAULT; for (i = 0; i < __NUM_VXRS_LOW; i++) - current->thread.fpu.vxrs[i].low = vxrs[i]; + current->thread.ufpu.vxrs[i].low = vxrs[i]; } return 0; } @@ -222,7 +222,7 @@ SYSCALL_DEFINE0(sigreturn) if (__copy_from_user(&set.sig, &frame->sc.oldmask, _SIGMASK_COPY_SIZE)) goto badframe; set_current_blocked(&set); - save_fpu_regs(); + save_user_fpu_regs(); if (restore_sigregs(regs, &frame->sregs)) goto badframe; if (restore_sigregs_ext(regs, &frame->sregs_ext)) @@ -246,7 +246,7 @@ SYSCALL_DEFINE0(rt_sigreturn) set_current_blocked(&set); if (restore_altstack(&frame->uc.uc_stack)) goto badframe; - save_fpu_regs(); + save_user_fpu_regs(); if (restore_sigregs(regs, &frame->uc.uc_mcontext)) goto badframe; if (restore_sigregs_ext(regs, &frame->uc.uc_mcontext_ext)) diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index c39d9f0d4b1c..0324649aae0a 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -36,12 +36,13 @@ #include <linux/sched/task_stack.h> #include <linux/crash_dump.h> #include <linux/kprobes.h> +#include <asm/access-regs.h> #include <asm/asm-offsets.h> #include <asm/ctlreg.h> #include <asm/pfault.h> #include <asm/diag.h> -#include <asm/switch_to.h> #include <asm/facility.h> +#include <asm/fpu.h> #include <asm/ipl.h> #include <asm/setup.h> #include <asm/irq.h> diff --git a/arch/s390/kernel/sysinfo.c b/arch/s390/kernel/sysinfo.c index f6f8f498c9be..1b1be3110cfc 100644 --- a/arch/s390/kernel/sysinfo.c +++ b/arch/s390/kernel/sysinfo.c @@ -20,7 +20,7 @@ #include <asm/sysinfo.h> #include <asm/cpcmd.h> #include <asm/topology.h> -#include <asm/fpu/api.h> +#include <asm/fpu.h> int topology_max_mnest; @@ -426,9 +426,9 @@ subsys_initcall(create_proc_service_level); */ void s390_adjust_jiffies(void) { + DECLARE_KERNEL_FPU_ONSTACK16(fpu); struct sysinfo_1_2_2 *info; unsigned long capability; - struct kernel_fpu fpu; info = (void *) get_zeroed_page(GFP_KERNEL); if (!info) @@ -447,21 +447,14 @@ void s390_adjust_jiffies(void) * point division .. */ kernel_fpu_begin(&fpu, KERNEL_FPR); - asm volatile( - " sfpc %3\n" - " l %0,%1\n" - " tmlh %0,0xff80\n" - " jnz 0f\n" - " cefbr %%f2,%0\n" - " j 1f\n" - "0: le %%f2,%1\n" - "1: cefbr %%f0,%2\n" - " debr %%f0,%%f2\n" - " cgebr %0,5,%%f0\n" - : "=&d" (capability) - : "Q" (info->capability), "d" (10000000), "d" (0) - : "cc" - ); + fpu_sfpc(0); + if (info->capability & 0xff800000) + fpu_ldgr(2, info->capability); + else + fpu_cefbr(2, info->capability); + fpu_cefbr(0, 10000000); + fpu_debr(0, 2); + capability = fpu_cgebr(0, 5); kernel_fpu_end(&fpu, KERNEL_FPR); } else /* diff --git a/arch/s390/kernel/text_amode31.S b/arch/s390/kernel/text_amode31.S index 14c6d25c035f..c0a70efa2426 100644 --- a/arch/s390/kernel/text_amode31.S +++ b/arch/s390/kernel/text_amode31.S @@ -90,7 +90,7 @@ SYM_FUNC_START(_diag26c_amode31) SYM_FUNC_END(_diag26c_amode31) /* - * void _diag0c_amode31(struct hypfs_diag0c_entry *entry) + * void _diag0c_amode31(unsigned long rx) */ SYM_FUNC_START(_diag0c_amode31) sam31 diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index 14abad953c02..fb9f31f36628 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -251,8 +251,8 @@ static struct clocksource clocksource_tod = { .rating = 400, .read = read_tod_clock, .mask = CLOCKSOURCE_MASK(64), - .mult = 1000, - .shift = 12, + .mult = 4096000, + .shift = 24, .flags = CLOCK_SOURCE_IS_CONTINUOUS, .vdso_clock_mode = VDSO_CLOCKMODE_TOD, }; @@ -716,7 +716,7 @@ out_unlock: /* * STP subsys sysfs interface functions */ -static struct bus_type stp_subsys = { +static const struct bus_type stp_subsys = { .name = "stp", .dev_name = "stp", }; diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c index 46dac4540ca8..52578b5cecbd 100644 --- a/arch/s390/kernel/traps.c +++ b/arch/s390/kernel/traps.c @@ -28,8 +28,8 @@ #include <linux/cpu.h> #include <linux/entry-common.h> #include <asm/asm-extable.h> -#include <asm/fpu/api.h> #include <asm/vtime.h> +#include <asm/fpu.h> #include "entry.h" static inline void __user *get_trap_ip(struct pt_regs *regs) @@ -201,8 +201,8 @@ static void vector_exception(struct pt_regs *regs) } /* get vector interrupt code from fpc */ - save_fpu_regs(); - vic = (current->thread.fpu.fpc & 0xf00) >> 8; + save_user_fpu_regs(); + vic = (current->thread.ufpu.fpc & 0xf00) >> 8; switch (vic) { case 1: /* invalid vector operation */ si_code = FPE_FLTINV; @@ -227,9 +227,9 @@ static void vector_exception(struct pt_regs *regs) static void data_exception(struct pt_regs *regs) { - save_fpu_regs(); - if (current->thread.fpu.fpc & FPC_DXC_MASK) - do_fp_trap(regs, current->thread.fpu.fpc); + save_user_fpu_regs(); + if (current->thread.ufpu.fpc & FPC_DXC_MASK) + do_fp_trap(regs, current->thread.ufpu.fpc); else do_trap(regs, SIGILL, ILL_ILLOPN, "data exception"); } diff --git a/arch/s390/kernel/uprobes.c b/arch/s390/kernel/uprobes.c index b88345ef8bd9..5b0633ea8d93 100644 --- a/arch/s390/kernel/uprobes.c +++ b/arch/s390/kernel/uprobes.c @@ -12,7 +12,6 @@ #include <linux/kdebug.h> #include <linux/sched/task_stack.h> -#include <asm/switch_to.h> #include <asm/facility.h> #include <asm/kprobes.h> #include <asm/dis.h> diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile index caec7db6f966..b12a274cbb47 100644 --- a/arch/s390/kernel/vdso32/Makefile +++ b/arch/s390/kernel/vdso32/Makefile @@ -22,7 +22,7 @@ KBUILD_CFLAGS_32 := $(filter-out -m64,$(KBUILD_CFLAGS)) KBUILD_CFLAGS_32 := $(filter-out -mno-pic-data-is-text-relative,$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 += -m31 -fPIC -shared -fno-common -fno-builtin -LDFLAGS_vdso32.so.dbg += -fPIC -shared -soname=linux-vdso32.so.1 \ +LDFLAGS_vdso32.so.dbg += -shared -soname=linux-vdso32.so.1 \ --hash-style=both --build-id=sha1 -melf_s390 -T $(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_32) diff --git a/arch/s390/kernel/vdso32/vdso32.lds.S b/arch/s390/kernel/vdso32/vdso32.lds.S index edf5ff1debe1..65b9513a5a0e 100644 --- a/arch/s390/kernel/vdso32/vdso32.lds.S +++ b/arch/s390/kernel/vdso32/vdso32.lds.S @@ -9,7 +9,6 @@ OUTPUT_FORMAT("elf32-s390", "elf32-s390", "elf32-s390") OUTPUT_ARCH(s390:31-bit) -ENTRY(_start) SECTIONS { diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile index e3c9085f8fa7..ef9832726097 100644 --- a/arch/s390/kernel/vdso64/Makefile +++ b/arch/s390/kernel/vdso64/Makefile @@ -25,8 +25,9 @@ KBUILD_AFLAGS_64 += -m64 KBUILD_CFLAGS_64 := $(filter-out -m64,$(KBUILD_CFLAGS)) KBUILD_CFLAGS_64 := $(filter-out -mno-pic-data-is-text-relative,$(KBUILD_CFLAGS_64)) +KBUILD_CFLAGS_64 := $(filter-out -munaligned-symbols,$(KBUILD_CFLAGS_64)) KBUILD_CFLAGS_64 += -m64 -fPIC -fno-common -fno-builtin -ldflags-y := -fPIC -shared -soname=linux-vdso64.so.1 \ +ldflags-y := -shared -soname=linux-vdso64.so.1 \ --hash-style=both --build-id=sha1 -T $(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_64) diff --git a/arch/s390/kernel/vdso64/vdso64.lds.S b/arch/s390/kernel/vdso64/vdso64.lds.S index 4461ea151e49..37e2a505e81d 100644 --- a/arch/s390/kernel/vdso64/vdso64.lds.S +++ b/arch/s390/kernel/vdso64/vdso64.lds.S @@ -9,7 +9,6 @@ OUTPUT_FORMAT("elf64-s390", "elf64-s390", "elf64-s390") OUTPUT_ARCH(s390:64-bit) -ENTRY(_start) SECTIONS { diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index e32ef446f451..48de296e8905 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -59,6 +59,14 @@ SECTIONS } :text = 0x0700 RO_DATA(PAGE_SIZE) + .data.rel.ro : { + *(.data.rel.ro .data.rel.ro.*) + } + .got : { + __got_start = .; + *(.got) + __got_end = .; + } . = ALIGN(PAGE_SIZE); _sdata = .; /* Start of data section */ @@ -73,6 +81,9 @@ SECTIONS __end_ro_after_init = .; RW_DATA(0x100, PAGE_SIZE, THREAD_SIZE) + .data.rel : { + *(.data.rel*) + } BOOT_DATA_PRESERVED . = ALIGN(8); @@ -181,6 +192,7 @@ SECTIONS PERCPU_SECTION(0x100) +#ifdef CONFIG_PIE_BUILD .dynsym ALIGN(8) : { __dynsym_start = .; *(.dynsym) @@ -191,6 +203,19 @@ SECTIONS *(.rela*) __rela_dyn_end = .; } + .dynamic ALIGN(8) : { + *(.dynamic) + } + .dynstr ALIGN(8) : { + *(.dynstr) + } +#endif + .hash ALIGN(8) : { + *(.hash) + } + .gnu.hash ALIGN(8) : { + *(.gnu.hash) + } . = ALIGN(PAGE_SIZE); __init_end = .; /* freed after init ends here */ @@ -214,9 +239,14 @@ SECTIONS QUAD(__boot_data_preserved_start) /* bootdata_preserved_off */ QUAD(__boot_data_preserved_end - __boot_data_preserved_start) /* bootdata_preserved_size */ +#ifdef CONFIG_PIE_BUILD QUAD(__dynsym_start) /* dynsym_start */ QUAD(__rela_dyn_start) /* rela_dyn_start */ QUAD(__rela_dyn_end) /* rela_dyn_end */ +#else + QUAD(__got_start) /* got_start */ + QUAD(__got_end) /* got_end */ +#endif QUAD(_eamode31 - _samode31) /* amode31_size */ QUAD(init_mm) QUAD(swapper_pg_dir) @@ -235,6 +265,30 @@ SECTIONS DWARF_DEBUG ELF_DETAILS + /* + * Make sure that the .got.plt is either completely empty or it + * contains only the three reserved double words. + */ + .got.plt : { + *(.got.plt) + } + ASSERT(SIZEOF(.got.plt) == 0 || SIZEOF(.got.plt) == 0x18, "Unexpected GOT/PLT entries detected!") + + /* + * Sections that should stay zero sized, which is safer to + * explicitly check instead of blindly discarding. + */ + .plt : { + *(.plt) *(.plt.*) *(.iplt) *(.igot .igot.plt) + } + ASSERT(SIZEOF(.plt) == 0, "Unexpected run-time procedure linkages detected!") +#ifndef CONFIG_PIE_BUILD + .rela.dyn : { + *(.rela.*) *(.rela_*) + } + ASSERT(SIZEOF(.rela.dyn) == 0, "Unexpected run-time relocations (.rela) detected!") +#endif + /* Sections to be discarded */ DISCARDS /DISCARD/ : { diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c index 5bfcc50c1a68..ee863566910b 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -11,11 +11,11 @@ #include <linux/err.h> #include <linux/pgtable.h> #include <linux/bitfield.h> +#include <asm/access-regs.h> #include <asm/fault.h> #include <asm/gmap.h> #include "kvm-s390.h" #include "gaccess.h" -#include <asm/switch_to.h> union asce { unsigned long val; @@ -391,7 +391,8 @@ static int ar_translation(struct kvm_vcpu *vcpu, union asce *asce, u8 ar, if (ar >= NUM_ACRS) return -EINVAL; - save_access_regs(vcpu->run->s.regs.acrs); + if (vcpu->arch.acrs_loaded) + save_access_regs(vcpu->run->s.regs.acrs); alet.val = vcpu->run->s.regs.acrs[ar]; if (ar == 0 || alet.val == 0) { diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index fc4007cc067a..dc721d50a942 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -19,13 +19,13 @@ #include <linux/slab.h> #include <linux/bitmap.h> #include <linux/vmalloc.h> +#include <asm/access-regs.h> #include <asm/asm-offsets.h> #include <asm/dis.h> #include <linux/uaccess.h> #include <asm/sclp.h> #include <asm/isc.h> #include <asm/gmap.h> -#include <asm/switch_to.h> #include <asm/nmi.h> #include <asm/airq.h> #include <asm/tpi.h> @@ -584,7 +584,7 @@ static int __write_machine_check(struct kvm_vcpu *vcpu, mci.val = mchk->mcic; /* take care of lazy register loading */ - save_fpu_regs(); + kvm_s390_fpu_store(vcpu->run); save_access_regs(vcpu->run->s.regs.acrs); if (MACHINE_HAS_GS && vcpu->arch.gs_enabled) save_gs_cb(current->thread.gs_cb); @@ -648,7 +648,7 @@ static int __write_machine_check(struct kvm_vcpu *vcpu, } rc |= write_guest_lc(vcpu, __LC_GPREGS_SAVE_AREA, vcpu->run->s.regs.gprs, 128); - rc |= put_guest_lc(vcpu, current->thread.fpu.fpc, + rc |= put_guest_lc(vcpu, vcpu->run->s.regs.fpc, (u32 __user *) __LC_FP_CREG_SAVE_AREA); rc |= put_guest_lc(vcpu, vcpu->arch.sie_block->todpr, (u32 __user *) __LC_TOD_PROGREG_SAVE_AREA); diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index ea63ac769889..b11bb8e780a1 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -33,19 +33,19 @@ #include <linux/pgtable.h> #include <linux/mmu_notifier.h> +#include <asm/access-regs.h> #include <asm/asm-offsets.h> #include <asm/lowcore.h> #include <asm/stp.h> #include <asm/gmap.h> #include <asm/nmi.h> -#include <asm/switch_to.h> #include <asm/isc.h> #include <asm/sclp.h> #include <asm/cpacf.h> #include <asm/timex.h> +#include <asm/fpu.h> #include <asm/ap.h> #include <asm/uv.h> -#include <asm/fpu/api.h> #include "kvm-s390.h" #include "gaccess.h" #include "pci.h" @@ -3951,6 +3951,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) KVM_SYNC_ARCH0 | KVM_SYNC_PFAULT | KVM_SYNC_DIAG318; + vcpu->arch.acrs_loaded = false; kvm_s390_set_prefix(vcpu, 0); if (test_kvm_facility(vcpu->kvm, 64)) vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB; @@ -4829,8 +4830,6 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) vcpu->run->s.regs.gprs, sizeof(sie_page->pv_grregs)); } - if (test_cpu_flag(CIF_FPU)) - load_fpu_regs(); exit_reason = sie64a(vcpu->arch.sie_block, vcpu->run->s.regs.gprs); if (kvm_s390_pv_cpu_is_protected(vcpu)) { @@ -4951,16 +4950,8 @@ static void sync_regs(struct kvm_vcpu *vcpu) } save_access_regs(vcpu->arch.host_acrs); restore_access_regs(vcpu->run->s.regs.acrs); - /* save host (userspace) fprs/vrs */ - save_fpu_regs(); - vcpu->arch.host_fpregs.fpc = current->thread.fpu.fpc; - vcpu->arch.host_fpregs.regs = current->thread.fpu.regs; - if (cpu_has_vx()) - current->thread.fpu.regs = vcpu->run->s.regs.vrs; - else - current->thread.fpu.regs = vcpu->run->s.regs.fprs; - current->thread.fpu.fpc = vcpu->run->s.regs.fpc; - + vcpu->arch.acrs_loaded = true; + kvm_s390_fpu_load(vcpu->run); /* Sync fmt2 only data */ if (likely(!kvm_s390_pv_cpu_is_protected(vcpu))) { sync_regs_fmt2(vcpu); @@ -5021,12 +5012,8 @@ static void store_regs(struct kvm_vcpu *vcpu) kvm_run->s.regs.pfc = vcpu->arch.pfault_compare; save_access_regs(vcpu->run->s.regs.acrs); restore_access_regs(vcpu->arch.host_acrs); - /* Save guest register state */ - save_fpu_regs(); - vcpu->run->s.regs.fpc = current->thread.fpu.fpc; - /* Restore will be done lazily at return */ - current->thread.fpu.fpc = vcpu->arch.host_fpregs.fpc; - current->thread.fpu.regs = vcpu->arch.host_fpregs.regs; + vcpu->arch.acrs_loaded = false; + kvm_s390_fpu_store(vcpu->run); if (likely(!kvm_s390_pv_cpu_is_protected(vcpu))) store_regs_fmt2(vcpu); } @@ -5034,6 +5021,7 @@ static void store_regs(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) { struct kvm_run *kvm_run = vcpu->run; + DECLARE_KERNEL_FPU_ONSTACK32(fpu); int rc; /* @@ -5075,6 +5063,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) goto out; } + kernel_fpu_begin(&fpu, KERNEL_FPC | KERNEL_VXR); sync_regs(vcpu); enable_cpu_timer_accounting(vcpu); @@ -5098,6 +5087,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) disable_cpu_timer_accounting(vcpu); store_regs(vcpu); + kernel_fpu_end(&fpu, KERNEL_FPC | KERNEL_VXR); kvm_sigset_deactivate(vcpu); @@ -5172,8 +5162,7 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr) * switch in the run ioctl. Let's update our copies before we save * it into the save area */ - save_fpu_regs(); - vcpu->run->s.regs.fpc = current->thread.fpu.fpc; + kvm_s390_fpu_store(vcpu->run); save_access_regs(vcpu->run->s.regs.acrs); return kvm_s390_store_status_unloaded(vcpu, addr); diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index a7ea80cfa445..111eb5c74784 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -20,6 +20,24 @@ #include <asm/processor.h> #include <asm/sclp.h> +static inline void kvm_s390_fpu_store(struct kvm_run *run) +{ + fpu_stfpc(&run->s.regs.fpc); + if (cpu_has_vx()) + save_vx_regs((__vector128 *)&run->s.regs.vrs); + else + save_fp_regs((freg_t *)&run->s.regs.fprs); +} + +static inline void kvm_s390_fpu_load(struct kvm_run *run) +{ + fpu_lfpc_safe(&run->s.regs.fpc); + if (cpu_has_vx()) + load_vx_regs((__vector128 *)&run->s.regs.vrs); + else + load_fp_regs((freg_t *)&run->s.regs.fprs); +} + /* Transactional Memory Execution related macros */ #define IS_TE_ENABLED(vcpu) ((vcpu->arch.sie_block->ecb & ECB_TE)) #define TDB_FORMAT1 1 diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index 3af3bd20ac7b..b2c9f010f0fe 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -18,7 +18,6 @@ #include <asm/sclp.h> #include <asm/nmi.h> #include <asm/dis.h> -#include <asm/fpu/api.h> #include <asm/facility.h> #include "kvm-s390.h" #include "gaccess.h" @@ -1149,8 +1148,6 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) */ vcpu->arch.sie_block->prog0c |= PROG_IN_SIE; barrier(); - if (test_cpu_flag(CIF_FPU)) - load_fpu_regs(); if (!kvm_s390_vcpu_sie_inhibited(vcpu)) rc = sie64a(scb_s, vcpu->run->s.regs.gprs); barrier(); diff --git a/arch/s390/lib/Makefile b/arch/s390/lib/Makefile index 7c50eca85ca4..90eac15ea62a 100644 --- a/arch/s390/lib/Makefile +++ b/arch/s390/lib/Makefile @@ -4,6 +4,7 @@ # lib-y += delay.o string.o uaccess.o find.o spinlock.o tishift.o +lib-y += csum-partial.o obj-y += mem.o xor.o lib-$(CONFIG_KPROBES) += probes.o lib-$(CONFIG_UPROBES) += probes.o diff --git a/arch/s390/lib/csum-partial.c b/arch/s390/lib/csum-partial.c new file mode 100644 index 000000000000..458abd9bac70 --- /dev/null +++ b/arch/s390/lib/csum-partial.c @@ -0,0 +1,91 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/export.h> +#include <asm/checksum.h> +#include <asm/fpu.h> + +/* + * Computes the checksum of a memory block at src, length len, + * and adds in "sum" (32-bit). If copy is true copies to dst. + * + * Returns a 32-bit number suitable for feeding into itself + * or csum_tcpudp_magic. + * + * This function must be called with even lengths, except + * for the last fragment, which may be odd. + * + * It's best to have src and dst aligned on a 64-bit boundary. + */ +static __always_inline __wsum csum_copy(void *dst, const void *src, int len, __wsum sum, bool copy) +{ + DECLARE_KERNEL_FPU_ONSTACK8(vxstate); + + if (!cpu_has_vx()) { + if (copy) + memcpy(dst, src, len); + return cksm(dst, len, sum); + } + kernel_fpu_begin(&vxstate, KERNEL_VXR_V16V23); + fpu_vlvgf(16, (__force u32)sum, 1); + fpu_vzero(17); + fpu_vzero(18); + fpu_vzero(19); + while (len >= 64) { + fpu_vlm(20, 23, src); + if (copy) { + fpu_vstm(20, 23, dst); + dst += 64; + } + fpu_vcksm(16, 20, 16); + fpu_vcksm(17, 21, 17); + fpu_vcksm(18, 22, 18); + fpu_vcksm(19, 23, 19); + src += 64; + len -= 64; + } + while (len >= 32) { + fpu_vlm(20, 21, src); + if (copy) { + fpu_vstm(20, 21, dst); + dst += 32; + } + fpu_vcksm(16, 20, 16); + fpu_vcksm(17, 21, 17); + src += 32; + len -= 32; + } + while (len >= 16) { + fpu_vl(20, src); + if (copy) { + fpu_vst(20, dst); + dst += 16; + } + fpu_vcksm(16, 20, 16); + src += 16; + len -= 16; + } + if (len) { + fpu_vll(20, len - 1, src); + if (copy) + fpu_vstl(20, len - 1, dst); + fpu_vcksm(16, 20, 16); + } + fpu_vcksm(18, 19, 18); + fpu_vcksm(16, 17, 16); + fpu_vcksm(16, 18, 16); + sum = (__force __wsum)fpu_vlgvf(16, 1); + kernel_fpu_end(&vxstate, KERNEL_VXR_V16V23); + return sum; +} + +__wsum csum_partial(const void *buff, int len, __wsum sum) +{ + return csum_copy(NULL, buff, len, sum, false); +} +EXPORT_SYMBOL(csum_partial); + +__wsum csum_partial_copy_nocheck(const void *src, void *dst, int len) +{ + return csum_copy(dst, src, len, 0, true); +} +EXPORT_SYMBOL(csum_partial_copy_nocheck); diff --git a/arch/s390/mm/extmem.c b/arch/s390/mm/extmem.c index e41869f5cc95..282fefe107a2 100644 --- a/arch/s390/mm/extmem.c +++ b/arch/s390/mm/extmem.c @@ -136,7 +136,7 @@ dcss_diag(int *func, void *parameter, unsigned long rx, ry; int rc; - rx = (unsigned long) parameter; + rx = virt_to_phys(parameter); ry = (unsigned long) *func; diag_stat_inc(DIAG_STAT_X064); @@ -178,7 +178,7 @@ query_segment_type (struct dcss_segment *seg) /* initialize diag input parameters */ qin->qopcode = DCSS_FINDSEGA; - qin->qoutptr = (unsigned long) qout; + qin->qoutptr = virt_to_phys(qout); qin->qoutlen = sizeof(struct qout64); memcpy (qin->qname, seg->dcss_name, 8); diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index fc9a7dc26c5e..b14fc0887654 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -71,6 +71,15 @@ static inline unsigned long mmap_base(unsigned long rnd, return PAGE_ALIGN(STACK_TOP - gap - rnd); } +static int get_align_mask(struct file *filp, unsigned long flags) +{ + if (!(current->flags & PF_RANDOMIZE)) + return 0; + if (filp || (flags & MAP_SHARED)) + return MMAP_ALIGN_MASK << PAGE_SHIFT; + return 0; +} + unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) @@ -97,10 +106,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, info.length = len; info.low_limit = mm->mmap_base; info.high_limit = TASK_SIZE; - if (filp || (flags & MAP_SHARED)) - info.align_mask = MMAP_ALIGN_MASK << PAGE_SHIFT; - else - info.align_mask = 0; + info.align_mask = get_align_mask(filp, flags); info.align_offset = pgoff << PAGE_SHIFT; addr = vm_unmapped_area(&info); if (offset_in_page(addr)) @@ -138,10 +144,7 @@ unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long ad info.length = len; info.low_limit = PAGE_SIZE; info.high_limit = mm->mmap_base; - if (filp || (flags & MAP_SHARED)) - info.align_mask = MMAP_ALIGN_MASK << PAGE_SHIFT; - else - info.align_mask = 0; + info.align_mask = get_align_mask(filp, flags); info.align_offset = pgoff << PAGE_SHIFT; addr = vm_unmapped_area(&info); diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 52a44e353796..26afde0d1ed3 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -28,6 +28,7 @@ #include <linux/jump_label.h> #include <linux/pci.h> #include <linux/printk.h> +#include <linux/lockdep.h> #include <asm/isc.h> #include <asm/airq.h> @@ -730,12 +731,12 @@ EXPORT_SYMBOL_GPL(zpci_disable_device); * equivalent to its state during boot when first probing a driver. * Consequently after reset the PCI function requires re-initialization via the * common PCI code including re-enabling IRQs via pci_alloc_irq_vectors() - * and enabling the function via e.g.pci_enablde_device_flags().The caller + * and enabling the function via e.g. pci_enable_device_flags(). The caller * must guard against concurrent reset attempts. * * In most cases this function should not be called directly but through * pci_reset_function() or pci_reset_bus() which handle the save/restore and - * locking. + * locking - asserted by lockdep. * * Return: 0 on success and an error value otherwise */ @@ -744,6 +745,7 @@ int zpci_hot_reset_device(struct zpci_dev *zdev) u8 status; int rc; + lockdep_assert_held(&zdev->state_lock); zpci_dbg(3, "rst fid:%x, fh:%x\n", zdev->fid, zdev->fh); if (zdev_enabled(zdev)) { /* Disables device access, DMAs and IRQs (reset state) */ @@ -806,7 +808,8 @@ struct zpci_dev *zpci_create_device(u32 fid, u32 fh, enum zpci_state state) zdev->state = state; kref_init(&zdev->kref); - mutex_init(&zdev->lock); + mutex_init(&zdev->state_lock); + mutex_init(&zdev->fmb_lock); mutex_init(&zdev->kzdev_lock); rc = zpci_init_iommu(zdev); @@ -870,6 +873,10 @@ int zpci_deconfigure_device(struct zpci_dev *zdev) { int rc; + lockdep_assert_held(&zdev->state_lock); + if (zdev->state != ZPCI_FN_STATE_CONFIGURED) + return 0; + if (zdev->zbus->bus) zpci_bus_remove_device(zdev, false); @@ -889,7 +896,7 @@ int zpci_deconfigure_device(struct zpci_dev *zdev) } /** - * zpci_device_reserved() - Mark device as resverved + * zpci_device_reserved() - Mark device as reserved * @zdev: the zpci_dev that was reserved * * Handle the case that a given zPCI function was reserved by another system. @@ -899,8 +906,6 @@ int zpci_deconfigure_device(struct zpci_dev *zdev) */ void zpci_device_reserved(struct zpci_dev *zdev) { - if (zdev->has_hp_slot) - zpci_exit_slot(zdev); /* * Remove device from zpci_list as it is going away. This also * makes sure we ignore subsequent zPCI events for this device. @@ -918,6 +923,9 @@ void zpci_release_device(struct kref *kref) struct zpci_dev *zdev = container_of(kref, struct zpci_dev, kref); int ret; + if (zdev->has_hp_slot) + zpci_exit_slot(zdev); + if (zdev->zbus->bus) zpci_bus_remove_device(zdev, false); diff --git a/arch/s390/pci/pci_debug.c b/arch/s390/pci/pci_debug.c index 6dde2263c79d..2cb5043a997d 100644 --- a/arch/s390/pci/pci_debug.c +++ b/arch/s390/pci/pci_debug.c @@ -91,9 +91,9 @@ static int pci_perf_show(struct seq_file *m, void *v) if (!zdev) return 0; - mutex_lock(&zdev->lock); + mutex_lock(&zdev->fmb_lock); if (!zdev->fmb) { - mutex_unlock(&zdev->lock); + mutex_unlock(&zdev->fmb_lock); seq_puts(m, "FMB statistics disabled\n"); return 0; } @@ -130,7 +130,7 @@ static int pci_perf_show(struct seq_file *m, void *v) } pci_sw_counter_show(m); - mutex_unlock(&zdev->lock); + mutex_unlock(&zdev->fmb_lock); return 0; } @@ -148,7 +148,7 @@ static ssize_t pci_perf_seq_write(struct file *file, const char __user *ubuf, if (rc) return rc; - mutex_lock(&zdev->lock); + mutex_lock(&zdev->fmb_lock); switch (val) { case 0: rc = zpci_fmb_disable_device(zdev); @@ -157,7 +157,7 @@ static ssize_t pci_perf_seq_write(struct file *file, const char __user *ubuf, rc = zpci_fmb_enable_device(zdev); break; } - mutex_unlock(&zdev->lock); + mutex_unlock(&zdev->fmb_lock); return rc ? rc : count; } diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index 4d9773ef9e0a..dbe95ec5917e 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -267,6 +267,7 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf) zpci_err_hex(ccdf, sizeof(*ccdf)); if (zdev) { + mutex_lock(&zdev->state_lock); zpci_update_fh(zdev, ccdf->fh); if (zdev->zbus->bus) pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn); @@ -294,6 +295,8 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf) } pci_dev_put(pdev); no_pdev: + if (zdev) + mutex_unlock(&zdev->state_lock); zpci_zdev_put(zdev); } @@ -326,6 +329,10 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) zpci_dbg(3, "avl fid:%x, fh:%x, pec:%x\n", ccdf->fid, ccdf->fh, ccdf->pec); + + if (existing_zdev) + mutex_lock(&zdev->state_lock); + switch (ccdf->pec) { case 0x0301: /* Reserved|Standby -> Configured */ if (!zdev) { @@ -348,7 +355,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) break; case 0x0303: /* Deconfiguration requested */ if (zdev) { - /* The event may have been queued before we confirgured + /* The event may have been queued before we configured * the device. */ if (zdev->state != ZPCI_FN_STATE_CONFIGURED) @@ -359,7 +366,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) break; case 0x0304: /* Configured -> Standby|Reserved */ if (zdev) { - /* The event may have been queued before we confirgured + /* The event may have been queued before we configured * the device.: */ if (zdev->state == ZPCI_FN_STATE_CONFIGURED) @@ -383,8 +390,10 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) default: break; } - if (existing_zdev) + if (existing_zdev) { + mutex_unlock(&zdev->state_lock); zpci_zdev_put(zdev); + } } void zpci_event_availability(void *data) diff --git a/arch/s390/pci/pci_sysfs.c b/arch/s390/pci/pci_sysfs.c index 8a7abac51816..a0b872b74fe3 100644 --- a/arch/s390/pci/pci_sysfs.c +++ b/arch/s390/pci/pci_sysfs.c @@ -49,6 +49,39 @@ static ssize_t mio_enabled_show(struct device *dev, } static DEVICE_ATTR_RO(mio_enabled); +static int _do_recover(struct pci_dev *pdev, struct zpci_dev *zdev) +{ + u8 status; + int ret; + + pci_stop_and_remove_bus_device(pdev); + if (zdev_enabled(zdev)) { + ret = zpci_disable_device(zdev); + /* + * Due to a z/VM vs LPAR inconsistency in the error + * state the FH may indicate an enabled device but + * disable says the device is already disabled don't + * treat it as an error here. + */ + if (ret == -EINVAL) + ret = 0; + if (ret) + return ret; + } + + ret = zpci_enable_device(zdev); + if (ret) + return ret; + + if (zdev->dma_table) { + ret = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma, + virt_to_phys(zdev->dma_table), &status); + if (ret) + zpci_disable_device(zdev); + } + return ret; +} + static ssize_t recover_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { @@ -56,7 +89,6 @@ static ssize_t recover_store(struct device *dev, struct device_attribute *attr, struct pci_dev *pdev = to_pci_dev(dev); struct zpci_dev *zdev = to_zpci(pdev); int ret = 0; - u8 status; /* Can't use device_remove_self() here as that would lead us to lock * the pci_rescan_remove_lock while holding the device' kernfs lock. @@ -70,6 +102,12 @@ static ssize_t recover_store(struct device *dev, struct device_attribute *attr, */ kn = sysfs_break_active_protection(&dev->kobj, &attr->attr); WARN_ON_ONCE(!kn); + + /* Device needs to be configured and state must not change */ + mutex_lock(&zdev->state_lock); + if (zdev->state != ZPCI_FN_STATE_CONFIGURED) + goto out; + /* device_remove_file() serializes concurrent calls ignoring all but * the first */ @@ -82,35 +120,13 @@ static ssize_t recover_store(struct device *dev, struct device_attribute *attr, */ pci_lock_rescan_remove(); if (pci_dev_is_added(pdev)) { - pci_stop_and_remove_bus_device(pdev); - if (zdev_enabled(zdev)) { - ret = zpci_disable_device(zdev); - /* - * Due to a z/VM vs LPAR inconsistency in the error - * state the FH may indicate an enabled device but - * disable says the device is already disabled don't - * treat it as an error here. - */ - if (ret == -EINVAL) - ret = 0; - if (ret) - goto out; - } - - ret = zpci_enable_device(zdev); - if (ret) - goto out; - - if (zdev->dma_table) { - ret = zpci_register_ioat(zdev, 0, zdev->start_dma, zdev->end_dma, - virt_to_phys(zdev->dma_table), &status); - if (ret) - zpci_disable_device(zdev); - } + ret = _do_recover(pdev, zdev); } -out: pci_rescan_bus(zdev->zbus->bus); pci_unlock_rescan_remove(); + +out: + mutex_unlock(&zdev->state_lock); if (kn) sysfs_unbreak_active_protection(kn); return ret ? ret : count; diff --git a/arch/s390/tools/.gitignore b/arch/s390/tools/.gitignore index ea62f37b79ef..e6af51d9d183 100644 --- a/arch/s390/tools/.gitignore +++ b/arch/s390/tools/.gitignore @@ -1,3 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only gen_facilities gen_opcode_table +relocs diff --git a/arch/s390/tools/Makefile b/arch/s390/tools/Makefile index f9dd47ff9ac4..f2862364fb42 100644 --- a/arch/s390/tools/Makefile +++ b/arch/s390/tools/Makefile @@ -25,3 +25,8 @@ $(kapi)/facility-defs.h: $(obj)/gen_facilities FORCE $(kapi)/dis-defs.h: $(obj)/gen_opcode_table FORCE $(call filechk,dis-defs.h) + +hostprogs += relocs +PHONY += relocs +relocs: $(obj)/relocs + @: diff --git a/arch/s390/tools/relocs.c b/arch/s390/tools/relocs.c new file mode 100644 index 000000000000..30a732c808f3 --- /dev/null +++ b/arch/s390/tools/relocs.c @@ -0,0 +1,387 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <stdio.h> +#include <stdarg.h> +#include <stdlib.h> +#include <stdint.h> +#include <inttypes.h> +#include <string.h> +#include <errno.h> +#include <unistd.h> +#include <elf.h> +#include <byteswap.h> +#define USE_BSD +#include <endian.h> + +#define ELF_BITS 64 + +#define ELF_MACHINE EM_S390 +#define ELF_MACHINE_NAME "IBM S/390" +#define SHT_REL_TYPE SHT_RELA +#define Elf_Rel Elf64_Rela + +#define ELF_CLASS ELFCLASS64 +#define ELF_ENDIAN ELFDATA2MSB +#define ELF_R_SYM(val) ELF64_R_SYM(val) +#define ELF_R_TYPE(val) ELF64_R_TYPE(val) +#define ELF_ST_TYPE(o) ELF64_ST_TYPE(o) +#define ELF_ST_BIND(o) ELF64_ST_BIND(o) +#define ELF_ST_VISIBILITY(o) ELF64_ST_VISIBILITY(o) + +#define ElfW(type) _ElfW(ELF_BITS, type) +#define _ElfW(bits, type) __ElfW(bits, type) +#define __ElfW(bits, type) Elf##bits##_##type + +#define Elf_Addr ElfW(Addr) +#define Elf_Ehdr ElfW(Ehdr) +#define Elf_Phdr ElfW(Phdr) +#define Elf_Shdr ElfW(Shdr) +#define Elf_Sym ElfW(Sym) + +static Elf_Ehdr ehdr; +static unsigned long shnum; +static unsigned int shstrndx; + +struct relocs { + uint32_t *offset; + unsigned long count; + unsigned long size; +}; + +static struct relocs relocs64; +#define FMT PRIu64 + +struct section { + Elf_Shdr shdr; + struct section *link; + Elf_Rel *reltab; +}; + +static struct section *secs; + +#if BYTE_ORDER == LITTLE_ENDIAN +#define le16_to_cpu(val) (val) +#define le32_to_cpu(val) (val) +#define le64_to_cpu(val) (val) +#define be16_to_cpu(val) bswap_16(val) +#define be32_to_cpu(val) bswap_32(val) +#define be64_to_cpu(val) bswap_64(val) +#endif + +#if BYTE_ORDER == BIG_ENDIAN +#define le16_to_cpu(val) bswap_16(val) +#define le32_to_cpu(val) bswap_32(val) +#define le64_to_cpu(val) bswap_64(val) +#define be16_to_cpu(val) (val) +#define be32_to_cpu(val) (val) +#define be64_to_cpu(val) (val) +#endif + +static uint16_t elf16_to_cpu(uint16_t val) +{ + if (ehdr.e_ident[EI_DATA] == ELFDATA2LSB) + return le16_to_cpu(val); + else + return be16_to_cpu(val); +} + +static uint32_t elf32_to_cpu(uint32_t val) +{ + if (ehdr.e_ident[EI_DATA] == ELFDATA2LSB) + return le32_to_cpu(val); + else + return be32_to_cpu(val); +} + +#define elf_half_to_cpu(x) elf16_to_cpu(x) +#define elf_word_to_cpu(x) elf32_to_cpu(x) + +static uint64_t elf64_to_cpu(uint64_t val) +{ + return be64_to_cpu(val); +} + +#define elf_addr_to_cpu(x) elf64_to_cpu(x) +#define elf_off_to_cpu(x) elf64_to_cpu(x) +#define elf_xword_to_cpu(x) elf64_to_cpu(x) + +static void die(char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + vfprintf(stderr, fmt, ap); + va_end(ap); + exit(1); +} + +static void read_ehdr(FILE *fp) +{ + if (fread(&ehdr, sizeof(ehdr), 1, fp) != 1) + die("Cannot read ELF header: %s\n", strerror(errno)); + if (memcmp(ehdr.e_ident, ELFMAG, SELFMAG) != 0) + die("No ELF magic\n"); + if (ehdr.e_ident[EI_CLASS] != ELF_CLASS) + die("Not a %d bit executable\n", ELF_BITS); + if (ehdr.e_ident[EI_DATA] != ELF_ENDIAN) + die("ELF endian mismatch\n"); + if (ehdr.e_ident[EI_VERSION] != EV_CURRENT) + die("Unknown ELF version\n"); + + /* Convert the fields to native endian */ + ehdr.e_type = elf_half_to_cpu(ehdr.e_type); + ehdr.e_machine = elf_half_to_cpu(ehdr.e_machine); + ehdr.e_version = elf_word_to_cpu(ehdr.e_version); + ehdr.e_entry = elf_addr_to_cpu(ehdr.e_entry); + ehdr.e_phoff = elf_off_to_cpu(ehdr.e_phoff); + ehdr.e_shoff = elf_off_to_cpu(ehdr.e_shoff); + ehdr.e_flags = elf_word_to_cpu(ehdr.e_flags); + ehdr.e_ehsize = elf_half_to_cpu(ehdr.e_ehsize); + ehdr.e_phentsize = elf_half_to_cpu(ehdr.e_phentsize); + ehdr.e_phnum = elf_half_to_cpu(ehdr.e_phnum); + ehdr.e_shentsize = elf_half_to_cpu(ehdr.e_shentsize); + ehdr.e_shnum = elf_half_to_cpu(ehdr.e_shnum); + ehdr.e_shstrndx = elf_half_to_cpu(ehdr.e_shstrndx); + + shnum = ehdr.e_shnum; + shstrndx = ehdr.e_shstrndx; + + if ((ehdr.e_type != ET_EXEC) && (ehdr.e_type != ET_DYN)) + die("Unsupported ELF header type\n"); + if (ehdr.e_machine != ELF_MACHINE) + die("Not for %s\n", ELF_MACHINE_NAME); + if (ehdr.e_version != EV_CURRENT) + die("Unknown ELF version\n"); + if (ehdr.e_ehsize != sizeof(Elf_Ehdr)) + die("Bad Elf header size\n"); + if (ehdr.e_phentsize != sizeof(Elf_Phdr)) + die("Bad program header entry\n"); + if (ehdr.e_shentsize != sizeof(Elf_Shdr)) + die("Bad section header entry\n"); + + if (shnum == SHN_UNDEF || shstrndx == SHN_XINDEX) { + Elf_Shdr shdr; + + if (fseek(fp, ehdr.e_shoff, SEEK_SET) < 0) + die("Seek to %" FMT " failed: %s\n", ehdr.e_shoff, strerror(errno)); + + if (fread(&shdr, sizeof(shdr), 1, fp) != 1) + die("Cannot read initial ELF section header: %s\n", strerror(errno)); + + if (shnum == SHN_UNDEF) + shnum = elf_xword_to_cpu(shdr.sh_size); + + if (shstrndx == SHN_XINDEX) + shstrndx = elf_word_to_cpu(shdr.sh_link); + } + + if (shstrndx >= shnum) + die("String table index out of bounds\n"); +} + +static void read_shdrs(FILE *fp) +{ + Elf_Shdr shdr; + int i; + + secs = calloc(shnum, sizeof(struct section)); + if (!secs) + die("Unable to allocate %ld section headers\n", shnum); + + if (fseek(fp, ehdr.e_shoff, SEEK_SET) < 0) + die("Seek to %" FMT " failed: %s\n", ehdr.e_shoff, strerror(errno)); + + for (i = 0; i < shnum; i++) { + struct section *sec = &secs[i]; + + if (fread(&shdr, sizeof(shdr), 1, fp) != 1) { + die("Cannot read ELF section headers %d/%ld: %s\n", + i, shnum, strerror(errno)); + } + + sec->shdr.sh_name = elf_word_to_cpu(shdr.sh_name); + sec->shdr.sh_type = elf_word_to_cpu(shdr.sh_type); + sec->shdr.sh_flags = elf_xword_to_cpu(shdr.sh_flags); + sec->shdr.sh_addr = elf_addr_to_cpu(shdr.sh_addr); + sec->shdr.sh_offset = elf_off_to_cpu(shdr.sh_offset); + sec->shdr.sh_size = elf_xword_to_cpu(shdr.sh_size); + sec->shdr.sh_link = elf_word_to_cpu(shdr.sh_link); + sec->shdr.sh_info = elf_word_to_cpu(shdr.sh_info); + sec->shdr.sh_addralign = elf_xword_to_cpu(shdr.sh_addralign); + sec->shdr.sh_entsize = elf_xword_to_cpu(shdr.sh_entsize); + + if (sec->shdr.sh_link < shnum) + sec->link = &secs[sec->shdr.sh_link]; + } + +} + +static void read_relocs(FILE *fp) +{ + int i, j; + + for (i = 0; i < shnum; i++) { + struct section *sec = &secs[i]; + + if (sec->shdr.sh_type != SHT_REL_TYPE) + continue; + + sec->reltab = malloc(sec->shdr.sh_size); + if (!sec->reltab) + die("malloc of %" FMT " bytes for relocs failed\n", sec->shdr.sh_size); + + if (fseek(fp, sec->shdr.sh_offset, SEEK_SET) < 0) + die("Seek to %" FMT " failed: %s\n", sec->shdr.sh_offset, strerror(errno)); + + if (fread(sec->reltab, 1, sec->shdr.sh_size, fp) != sec->shdr.sh_size) + die("Cannot read symbol table: %s\n", strerror(errno)); + + for (j = 0; j < sec->shdr.sh_size / sizeof(Elf_Rel); j++) { + Elf_Rel *rel = &sec->reltab[j]; + + rel->r_offset = elf_addr_to_cpu(rel->r_offset); + rel->r_info = elf_xword_to_cpu(rel->r_info); +#if (SHT_REL_TYPE == SHT_RELA) + rel->r_addend = elf_xword_to_cpu(rel->r_addend); +#endif + } + } +} + +static void add_reloc(struct relocs *r, uint32_t offset) +{ + if (r->count == r->size) { + unsigned long newsize = r->size + 50000; + void *mem = realloc(r->offset, newsize * sizeof(r->offset[0])); + + if (!mem) + die("realloc of %ld entries for relocs failed\n", newsize); + + r->offset = mem; + r->size = newsize; + } + r->offset[r->count++] = offset; +} + +static int do_reloc(struct section *sec, Elf_Rel *rel) +{ + unsigned int r_type = ELF64_R_TYPE(rel->r_info); + ElfW(Addr) offset = rel->r_offset; + + switch (r_type) { + case R_390_NONE: + case R_390_PC32: + case R_390_PC64: + case R_390_PC16DBL: + case R_390_PC32DBL: + case R_390_PLT32DBL: + case R_390_GOTENT: + case R_390_GOTPCDBL: + case R_390_GOTOFF64: + break; + case R_390_64: + add_reloc(&relocs64, offset); + break; + default: + die("Unsupported relocation type: %d\n", r_type); + break; + } + + return 0; +} + +static void walk_relocs(void) +{ + int i; + + /* Walk through the relocations */ + for (i = 0; i < shnum; i++) { + struct section *sec_applies; + int j; + struct section *sec = &secs[i]; + + if (sec->shdr.sh_type != SHT_REL_TYPE) + continue; + + sec_applies = &secs[sec->shdr.sh_info]; + if (!(sec_applies->shdr.sh_flags & SHF_ALLOC)) + continue; + + for (j = 0; j < sec->shdr.sh_size / sizeof(Elf_Rel); j++) { + Elf_Rel *rel = &sec->reltab[j]; + + do_reloc(sec, rel); + } + } +} + +static int cmp_relocs(const void *va, const void *vb) +{ + const uint32_t *a, *b; + + a = va; b = vb; + return (*a == *b) ? 0 : (*a > *b) ? 1 : -1; +} + +static void sort_relocs(struct relocs *r) +{ + qsort(r->offset, r->count, sizeof(r->offset[0]), cmp_relocs); +} + +static int print_reloc(uint32_t v) +{ + return fprintf(stdout, "\t.long 0x%08"PRIx32"\n", v) > 0 ? 0 : -1; +} + +static void emit_relocs(void) +{ + int i; + + walk_relocs(); + sort_relocs(&relocs64); + + printf(".section \".vmlinux.relocs_64\",\"a\"\n"); + for (i = 0; i < relocs64.count; i++) + print_reloc(relocs64.offset[i]); +} + +static void process(FILE *fp) +{ + read_ehdr(fp); + read_shdrs(fp); + read_relocs(fp); + emit_relocs(); +} + +static void usage(void) +{ + die("relocs vmlinux\n"); +} + +int main(int argc, char **argv) +{ + unsigned char e_ident[EI_NIDENT]; + const char *fname; + FILE *fp; + + fname = NULL; + + if (argc != 2) + usage(); + + fname = argv[1]; + + fp = fopen(fname, "r"); + if (!fp) + die("Cannot open %s: %s\n", fname, strerror(errno)); + + if (fread(&e_ident, 1, EI_NIDENT, fp) != EI_NIDENT) + die("Cannot read %s: %s", fname, strerror(errno)); + + rewind(fp); + + process(fp); + + fclose(fp); + return 0; +} diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index f3969a3600db..a0cc9bb41a92 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -1206,10 +1206,6 @@ void __init smp_prepare_cpus(unsigned int max_cpus) { } -void smp_prepare_boot_cpu(void) -{ -} - void __init smp_setup_processor_id(void) { if (tlb_type == spitfire) diff --git a/arch/x86/Kbuild b/arch/x86/Kbuild index 5a83da703e87..6a1f36df6a18 100644 --- a/arch/x86/Kbuild +++ b/arch/x86/Kbuild @@ -28,5 +28,7 @@ obj-y += net/ obj-$(CONFIG_KEXEC_FILE) += purgatory/ +obj-y += virt/svm/ + # for cleaning subdir- += boot tools diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 854ab38a359a..e88f6f7b6b41 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -147,6 +147,7 @@ config X86 select EDAC_ATOMIC_SCRUB select EDAC_SUPPORT select GENERIC_CLOCKEVENTS_BROADCAST if X86_64 || (X86_32 && X86_LOCAL_APIC) + select GENERIC_CLOCKEVENTS_BROADCAST_IDLE if GENERIC_CLOCKEVENTS_BROADCAST select GENERIC_CLOCKEVENTS_MIN_ADJUST select GENERIC_CMOS_UPDATE select GENERIC_CPU_AUTOPROBE @@ -1548,19 +1549,6 @@ config AMD_MEM_ENCRYPT This requires an AMD processor that supports Secure Memory Encryption (SME). -config AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT - bool "Activate AMD Secure Memory Encryption (SME) by default" - depends on AMD_MEM_ENCRYPT - help - Say yes to have system memory encrypted by default if running on - an AMD processor that supports Secure Memory Encryption (SME). - - If set to Y, then the encryption of system memory can be - deactivated with the mem_encrypt=off command line option. - - If set to N, then the encryption of system memory can be - activated with the mem_encrypt=on command line option. - # Common NUMA Features config NUMA bool "NUMA Memory Allocation and Scheduler Support" @@ -2123,11 +2111,11 @@ config PHYSICAL_START help This gives the physical address where the kernel is loaded. - If kernel is a not relocatable (CONFIG_RELOCATABLE=n) then - bzImage will decompress itself to above physical address and - run from there. Otherwise, bzImage will run from the address where - it has been loaded by the boot loader and will ignore above physical - address. + If the kernel is not relocatable (CONFIG_RELOCATABLE=n) then bzImage + will decompress itself to above physical address and run from there. + Otherwise, bzImage will run from the address where it has been loaded + by the boot loader. The only exception is if it is loaded below the + above physical address, in which case it will relocate itself there. In normal kdump cases one does not have to set/change this option as now bzImage can be compiled as a completely relocatable image @@ -2443,6 +2431,18 @@ source "kernel/livepatch/Kconfig" endmenu +config CC_HAS_NAMED_AS + def_bool CC_IS_GCC && GCC_VERSION >= 120100 + +config USE_X86_SEG_SUPPORT + def_bool y + depends on CC_HAS_NAMED_AS + # + # -fsanitize=kernel-address (KASAN) is at the moment incompatible + # with named address spaces - see GCC PR sanitizer/111736. + # + depends on !KASAN + config CC_HAS_SLS def_bool $(cc-option,-mharden-sls=all) @@ -2474,12 +2474,12 @@ config CALL_PADDING config FINEIBT def_bool y - depends on X86_KERNEL_IBT && CFI_CLANG && RETPOLINE + depends on X86_KERNEL_IBT && CFI_CLANG && MITIGATION_RETPOLINE select CALL_PADDING config HAVE_CALL_THUNKS def_bool y - depends on CC_HAS_ENTRY_PADDING && RETHUNK && OBJTOOL + depends on CC_HAS_ENTRY_PADDING && MITIGATION_RETHUNK && OBJTOOL config CALL_THUNKS def_bool n @@ -2501,7 +2501,7 @@ menuconfig SPECULATION_MITIGATIONS if SPECULATION_MITIGATIONS -config PAGE_TABLE_ISOLATION +config MITIGATION_PAGE_TABLE_ISOLATION bool "Remove the kernel mapping in user mode" default y depends on (X86_64 || X86_PAE) @@ -2512,7 +2512,7 @@ config PAGE_TABLE_ISOLATION See Documentation/arch/x86/pti.rst for more details. -config RETPOLINE +config MITIGATION_RETPOLINE bool "Avoid speculative indirect branches in kernel" select OBJTOOL if HAVE_OBJTOOL default y @@ -2522,9 +2522,9 @@ config RETPOLINE branches. Requires a compiler with -mindirect-branch=thunk-extern support for full protection. The kernel may run slower. -config RETHUNK +config MITIGATION_RETHUNK bool "Enable return-thunks" - depends on RETPOLINE && CC_HAS_RETURN_THUNK + depends on MITIGATION_RETPOLINE && CC_HAS_RETURN_THUNK select OBJTOOL if HAVE_OBJTOOL default y if X86_64 help @@ -2533,14 +2533,14 @@ config RETHUNK Requires a compiler with -mfunction-return=thunk-extern support for full protection. The kernel may run slower. -config CPU_UNRET_ENTRY +config MITIGATION_UNRET_ENTRY bool "Enable UNRET on kernel entry" - depends on CPU_SUP_AMD && RETHUNK && X86_64 + depends on CPU_SUP_AMD && MITIGATION_RETHUNK && X86_64 default y help Compile the kernel with support for the retbleed=unret mitigation. -config CALL_DEPTH_TRACKING +config MITIGATION_CALL_DEPTH_TRACKING bool "Mitigate RSB underflow with call depth tracking" depends on CPU_SUP_INTEL && HAVE_CALL_THUNKS select HAVE_DYNAMIC_FTRACE_NO_PATCHABLE @@ -2560,7 +2560,7 @@ config CALL_DEPTH_TRACKING config CALL_THUNKS_DEBUG bool "Enable call thunks and call depth tracking debugging" - depends on CALL_DEPTH_TRACKING + depends on MITIGATION_CALL_DEPTH_TRACKING select FUNCTION_ALIGNMENT_32B default n help @@ -2571,14 +2571,14 @@ config CALL_THUNKS_DEBUG Only enable this when you are debugging call thunks as this creates a noticeable runtime overhead. If unsure say N. -config CPU_IBPB_ENTRY +config MITIGATION_IBPB_ENTRY bool "Enable IBPB on kernel entry" depends on CPU_SUP_AMD && X86_64 default y help Compile the kernel with support for the retbleed=ibpb mitigation. -config CPU_IBRS_ENTRY +config MITIGATION_IBRS_ENTRY bool "Enable IBRS on kernel entry" depends on CPU_SUP_INTEL && X86_64 default y @@ -2587,14 +2587,14 @@ config CPU_IBRS_ENTRY This mitigates both spectre_v2 and retbleed at great cost to performance. -config CPU_SRSO +config MITIGATION_SRSO bool "Mitigate speculative RAS overflow on AMD" - depends on CPU_SUP_AMD && X86_64 && RETHUNK + depends on CPU_SUP_AMD && X86_64 && MITIGATION_RETHUNK default y help Enable the SRSO mitigation needed on AMD Zen1-4 machines. -config SLS +config MITIGATION_SLS bool "Mitigate Straight-Line-Speculation" depends on CC_HAS_SLS && X86_64 select OBJTOOL if HAVE_OBJTOOL @@ -2604,7 +2604,7 @@ config SLS against straight line speculation. The kernel image might be slightly larger. -config GDS_FORCE_MITIGATION +config MITIGATION_GDS_FORCE bool "Force GDS Mitigation" depends on CPU_SUP_INTEL default n @@ -2623,6 +2623,17 @@ config GDS_FORCE_MITIGATION If in doubt, say N. +config MITIGATION_RFDS + bool "RFDS Mitigation" + depends on CPU_SUP_INTEL + default y + help + Enable mitigation for Register File Data Sampling (RFDS) by default. + RFDS is a hardware vulnerability which affects Intel Atom CPUs. It + allows unprivileged speculative access to stale data previously + stored in floating point, vector and integer registers. + See also <file:Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst> + endif config ARCH_HAS_ADD_PAGES diff --git a/arch/x86/Makefile b/arch/x86/Makefile index b221dd87c034..ba6c59c18f5e 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -22,7 +22,7 @@ RETPOLINE_VDSO_CFLAGS := -mretpoline endif RETPOLINE_CFLAGS += $(call cc-option,-mindirect-branch-cs-prefix) -ifdef CONFIG_RETHUNK +ifdef CONFIG_MITIGATION_RETHUNK RETHUNK_CFLAGS := -mfunction-return=thunk-extern RETPOLINE_CFLAGS += $(RETHUNK_CFLAGS) endif @@ -53,6 +53,9 @@ REALMODE_CFLAGS += -fno-stack-protector REALMODE_CFLAGS += -Wno-address-of-packed-member REALMODE_CFLAGS += $(cc_stack_align4) REALMODE_CFLAGS += $(CLANG_FLAGS) +ifdef CONFIG_CC_IS_CLANG +REALMODE_CFLAGS += -Wno-gnu +endif export REALMODE_CFLAGS # BITS is used as extension for files which are available in a 32 bit @@ -192,7 +195,7 @@ KBUILD_CFLAGS += -Wno-sign-compare KBUILD_CFLAGS += -fno-asynchronous-unwind-tables # Avoid indirect branches in kernel to deal with Spectre -ifdef CONFIG_RETPOLINE +ifdef CONFIG_MITIGATION_RETPOLINE KBUILD_CFLAGS += $(RETPOLINE_CFLAGS) # Additionally, avoid generating expensive indirect jumps which # are subject to retpolines for small number of switch cases. @@ -205,7 +208,7 @@ ifdef CONFIG_RETPOLINE endif endif -ifdef CONFIG_SLS +ifdef CONFIG_MITIGATION_SLS KBUILD_CFLAGS += -mharden-sls=all endif @@ -299,12 +302,11 @@ install: vdso-install-$(CONFIG_X86_64) += arch/x86/entry/vdso/vdso64.so.dbg vdso-install-$(CONFIG_X86_X32_ABI) += arch/x86/entry/vdso/vdsox32.so.dbg -vdso-install-$(CONFIG_X86_32) += arch/x86/entry/vdso/vdso32.so.dbg -vdso-install-$(CONFIG_IA32_EMULATION) += arch/x86/entry/vdso/vdso32.so.dbg +vdso-install-$(CONFIG_COMPAT_32) += arch/x86/entry/vdso/vdso32.so.dbg archprepare: checkbin checkbin: -ifdef CONFIG_RETPOLINE +ifdef CONFIG_MITIGATION_RETPOLINE ifeq ($(RETPOLINE_CFLAGS),) @echo "You are building kernel with non-retpoline compiler." >&2 @echo "Please update your compiler." >&2 diff --git a/arch/x86/boot/compressed/acpi.c b/arch/x86/boot/compressed/acpi.c index 18d15d1ce87d..f196b1d1ddf8 100644 --- a/arch/x86/boot/compressed/acpi.c +++ b/arch/x86/boot/compressed/acpi.c @@ -5,6 +5,8 @@ #include "../string.h" #include "efi.h" +#include <asm/bootparam.h> + #include <linux/numa.h> /* diff --git a/arch/x86/boot/compressed/cmdline.c b/arch/x86/boot/compressed/cmdline.c index c1bb180973ea..e162d7f59cc5 100644 --- a/arch/x86/boot/compressed/cmdline.c +++ b/arch/x86/boot/compressed/cmdline.c @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 #include "misc.h" +#include <asm/bootparam.h> + static unsigned long fs; static inline void set_fs(unsigned long seg) { diff --git a/arch/x86/boot/compressed/efi.c b/arch/x86/boot/compressed/efi.c index 6edd034b0b30..f2e50f9758e6 100644 --- a/arch/x86/boot/compressed/efi.c +++ b/arch/x86/boot/compressed/efi.c @@ -7,6 +7,8 @@ #include "misc.h" +#include <asm/bootparam.h> + /** * efi_get_type - Given a pointer to boot_params, determine the type of EFI environment. * diff --git a/arch/x86/boot/compressed/efi.h b/arch/x86/boot/compressed/efi.h index 866c0af8b5b9..b22300970f97 100644 --- a/arch/x86/boot/compressed/efi.h +++ b/arch/x86/boot/compressed/efi.h @@ -97,15 +97,6 @@ typedef struct { u32 tables; } efi_system_table_32_t; -/* kexec external ABI */ -struct efi_setup_data { - u64 fw_vendor; - u64 __unused; - u64 tables; - u64 smbios; - u64 reserved[8]; -}; - struct efi_unaccepted_memory { u32 version; u32 unit_size; diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index d040080d7edb..909f2a35b60c 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -8,8 +8,8 @@ * Copyright (C) 2016 Kees Cook */ -/* No PAGE_TABLE_ISOLATION support needed either: */ -#undef CONFIG_PAGE_TABLE_ISOLATION +/* No MITIGATION_PAGE_TABLE_ISOLATION support needed either: */ +#undef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION #include "error.h" #include "misc.h" @@ -389,5 +389,5 @@ void do_boot_page_fault(struct pt_regs *regs, unsigned long error_code) void do_boot_nmi_trap(struct pt_regs *regs, unsigned long error_code) { - /* Empty handler to ignore NMI during early boot */ + spurious_nmi_count++; } diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index b99e08e6815b..408507e305be 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -52,6 +52,7 @@ struct port_io_ops pio_ops; memptr free_mem_ptr; memptr free_mem_end_ptr; +int spurious_nmi_count; static char *vidmem; static int vidport; @@ -164,21 +165,34 @@ void __putstr(const char *s) outb(0xff & (pos >> 1), vidport+1); } -void __puthex(unsigned long value) +static noinline void __putnum(unsigned long value, unsigned int base, + int mindig) { - char alpha[2] = "0"; - int bits; + char buf[8*sizeof(value)+1]; + char *p; - for (bits = sizeof(value) * 8 - 4; bits >= 0; bits -= 4) { - unsigned long digit = (value >> bits) & 0xf; + p = buf + sizeof(buf); + *--p = '\0'; - if (digit < 0xA) - alpha[0] = '0' + digit; - else - alpha[0] = 'a' + (digit - 0xA); + while (mindig-- > 0 || value) { + unsigned char digit = value % base; + digit += (digit >= 10) ? ('a'-10) : '0'; + *--p = digit; - __putstr(alpha); + value /= base; } + + __putstr(p); +} + +void __puthex(unsigned long value) +{ + __putnum(value, 16, sizeof(value)*2); +} + +void __putdec(unsigned long value) +{ + __putnum(value, 10, 1); } #ifdef CONFIG_X86_NEED_RELOCS @@ -358,6 +372,19 @@ unsigned long decompress_kernel(unsigned char *outbuf, unsigned long virt_addr, } /* + * Set the memory encryption xloadflag based on the mem_encrypt= command line + * parameter, if provided. + */ +static void parse_mem_encrypt(struct setup_header *hdr) +{ + int on = cmdline_find_option_bool("mem_encrypt=on"); + int off = cmdline_find_option_bool("mem_encrypt=off"); + + if (on > off) + hdr->xloadflags |= XLF_MEM_ENCRYPTION; +} + +/* * The compressed kernel image (ZO), has been moved so that its position * is against the end of the buffer used to hold the uncompressed kernel * image (VO) and the execution environment (.bss, .brk), which makes sure @@ -387,6 +414,8 @@ asmlinkage __visible void *extract_kernel(void *rmode, unsigned char *output) /* Clear flags intended for solely in-kernel use. */ boot_params_ptr->hdr.loadflags &= ~KASLR_FLAG; + parse_mem_encrypt(&boot_params_ptr->hdr); + sanitize_boot_params(boot_params_ptr); if (boot_params_ptr->screen_info.orig_video_mode == 7) { @@ -493,6 +522,12 @@ asmlinkage __visible void *extract_kernel(void *rmode, unsigned char *output) /* Disable exception handling before booting the kernel */ cleanup_exception_handling(); + if (spurious_nmi_count) { + error_putstr("Spurious early NMIs ignored: "); + error_putdec(spurious_nmi_count); + error_putstr("\n"); + } + return output + entry_offset; } diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index bc2f0f17fb90..b353a7be380c 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -59,12 +59,15 @@ extern char _head[], _end[]; /* misc.c */ extern memptr free_mem_ptr; extern memptr free_mem_end_ptr; +extern int spurious_nmi_count; void *malloc(int size); void free(void *where); void __putstr(const char *s); void __puthex(unsigned long value); +void __putdec(unsigned long value); #define error_putstr(__x) __putstr(__x) #define error_puthex(__x) __puthex(__x) +#define error_putdec(__x) __putdec(__x) #ifdef CONFIG_X86_VERBOSE_BOOTUP diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c index 51f957b24ba7..c882e1f67af0 100644 --- a/arch/x86/boot/compressed/pgtable_64.c +++ b/arch/x86/boot/compressed/pgtable_64.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include "misc.h" +#include <asm/bootparam.h> #include <asm/e820/types.h> #include <asm/processor.h> #include "pgtable.h" diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c index 454acd7a2daf..ec71846d28c9 100644 --- a/arch/x86/boot/compressed/sev.c +++ b/arch/x86/boot/compressed/sev.c @@ -12,6 +12,7 @@ */ #include "misc.h" +#include <asm/bootparam.h> #include <asm/pgtable_types.h> #include <asm/sev.h> #include <asm/trapnr.h> @@ -116,6 +117,9 @@ static bool fault_in_kernel_space(unsigned long address) #undef __init #define __init +#undef __head +#define __head + #define __BOOT_COMPRESSED /* Basic instruction decoding support needed */ @@ -304,6 +308,10 @@ void do_boot_stage2_vc(struct pt_regs *regs, unsigned long exit_code) if (result != ES_OK) goto finish; + result = vc_check_opcode_bytes(&ctxt, exit_code); + if (result != ES_OK) + goto finish; + switch (exit_code) { case SVM_EXIT_RDTSC: case SVM_EXIT_RDTSCP: @@ -365,7 +373,7 @@ static void enforce_vmpl0(void) MSR_AMD64_SNP_VMPL_SSS | \ MSR_AMD64_SNP_SECURE_TSC | \ MSR_AMD64_SNP_VMGEXIT_PARAM | \ - MSR_AMD64_SNP_VMSA_REG_PROTECTION | \ + MSR_AMD64_SNP_VMSA_REG_PROT | \ MSR_AMD64_SNP_RESERVED_BIT13 | \ MSR_AMD64_SNP_RESERVED_BIT15 | \ MSR_AMD64_SNP_RESERVED_MASK) diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index a1bbedd989e4..b5c79f43359b 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -111,11 +111,7 @@ extra_header_fields: .long salign # SizeOfHeaders .long 0 # CheckSum .word IMAGE_SUBSYSTEM_EFI_APPLICATION # Subsystem (EFI application) -#ifdef CONFIG_EFI_DXE_MEM_ATTRIBUTES .word IMAGE_DLL_CHARACTERISTICS_NX_COMPAT # DllCharacteristics -#else - .word 0 # DllCharacteristics -#endif #ifdef CONFIG_X86_32 .long 0 # SizeOfStackReserve .long 0 # SizeOfStackCommit diff --git a/arch/x86/coco/core.c b/arch/x86/coco/core.c index eeec9986570e..d07be9d05cd0 100644 --- a/arch/x86/coco/core.c +++ b/arch/x86/coco/core.c @@ -14,7 +14,7 @@ #include <asm/processor.h> enum cc_vendor cc_vendor __ro_after_init = CC_VENDOR_NONE; -static u64 cc_mask __ro_after_init; +u64 cc_mask __ro_after_init; static bool noinstr intel_cc_platform_has(enum cc_attr attr) { @@ -148,8 +148,3 @@ u64 cc_mkdec(u64 val) } } EXPORT_SYMBOL_GPL(cc_mkdec); - -__init void cc_set_mask(u64 mask) -{ - cc_mask = mask; -} diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index 73abbbdd26f8..91801138b10b 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -42,7 +42,7 @@ CONFIG_EFI_STUB=y CONFIG_HZ_1000=y CONFIG_KEXEC=y CONFIG_CRASH_DUMP=y -# CONFIG_RETHUNK is not set +# CONFIG_MITIGATION_RETHUNK is not set CONFIG_HIBERNATION=y CONFIG_PM_DEBUG=y CONFIG_PM_TRACE_RTC=y diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 3ff925b17b7e..ea81770629ee 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -147,10 +147,10 @@ For 32-bit we have the following conventions - kernel is built with .endif .endm -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION /* - * PAGE_TABLE_ISOLATION PGDs are 8k. Flip bit 12 to switch between the two + * MITIGATION_PAGE_TABLE_ISOLATION PGDs are 8k. Flip bit 12 to switch between the two * halves: */ #define PTI_USER_PGTABLE_BIT PAGE_SHIFT @@ -165,7 +165,7 @@ For 32-bit we have the following conventions - kernel is built with .macro ADJUST_KERNEL_CR3 reg:req ALTERNATIVE "", "SET_NOFLUSH_BIT \reg", X86_FEATURE_PCID - /* Clear PCID and "PAGE_TABLE_ISOLATION bit", point CR3 at kernel pagetables: */ + /* Clear PCID and "MITIGATION_PAGE_TABLE_ISOLATION bit", point CR3 at kernel pagetables: */ andq $(~PTI_USER_PGTABLE_AND_PCID_MASK), \reg .endm @@ -178,7 +178,7 @@ For 32-bit we have the following conventions - kernel is built with .endm #define THIS_CPU_user_pcid_flush_mask \ - PER_CPU_VAR(cpu_tlbstate) + TLB_STATE_user_pcid_flush_mask + PER_CPU_VAR(cpu_tlbstate + TLB_STATE_user_pcid_flush_mask) .macro SWITCH_TO_USER_CR3 scratch_reg:req scratch_reg2:req mov %cr3, \scratch_reg @@ -244,17 +244,19 @@ For 32-bit we have the following conventions - kernel is built with .Ldone_\@: .endm -.macro RESTORE_CR3 scratch_reg:req save_reg:req +/* Restore CR3 from a kernel context. May restore a user CR3 value. */ +.macro PARANOID_RESTORE_CR3 scratch_reg:req save_reg:req ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI - ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID - /* - * KERNEL pages can always resume with NOFLUSH as we do - * explicit flushes. + * If CR3 contained the kernel page tables at the paranoid exception + * entry, then there is nothing to restore as CR3 is not modified while + * handling the exception. */ bt $PTI_USER_PGTABLE_BIT, \save_reg - jnc .Lnoflush_\@ + jnc .Lend_\@ + + ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID /* * Check if there's a pending flush for the user ASID we're @@ -262,25 +264,17 @@ For 32-bit we have the following conventions - kernel is built with */ movq \save_reg, \scratch_reg andq $(0x7FF), \scratch_reg - bt \scratch_reg, THIS_CPU_user_pcid_flush_mask - jnc .Lnoflush_\@ - btr \scratch_reg, THIS_CPU_user_pcid_flush_mask - jmp .Lwrcr3_\@ + jc .Lwrcr3_\@ -.Lnoflush_\@: SET_NOFLUSH_BIT \save_reg .Lwrcr3_\@: - /* - * The CR3 write could be avoided when not changing its value, - * but would require a CR3 read *and* a scratch register. - */ movq \save_reg, %cr3 .Lend_\@: .endm -#else /* CONFIG_PAGE_TABLE_ISOLATION=n: */ +#else /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION=n: */ .macro SWITCH_TO_KERNEL_CR3 scratch_reg:req .endm @@ -290,7 +284,7 @@ For 32-bit we have the following conventions - kernel is built with .endm .macro SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg:req save_reg:req .endm -.macro RESTORE_CR3 scratch_reg:req save_reg:req +.macro PARANOID_RESTORE_CR3 scratch_reg:req save_reg:req .endm #endif @@ -308,7 +302,7 @@ For 32-bit we have the following conventions - kernel is built with * Assumes x86_spec_ctrl_{base,current} to have SPEC_CTRL_IBRS set. */ .macro IBRS_ENTER save_reg -#ifdef CONFIG_CPU_IBRS_ENTRY +#ifdef CONFIG_MITIGATION_IBRS_ENTRY ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_KERNEL_IBRS movl $MSR_IA32_SPEC_CTRL, %ecx @@ -337,7 +331,7 @@ For 32-bit we have the following conventions - kernel is built with * regs. Must be called after the last RET. */ .macro IBRS_EXIT save_reg -#ifdef CONFIG_CPU_IBRS_ENTRY +#ifdef CONFIG_MITIGATION_IBRS_ENTRY ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_KERNEL_IBRS movl $MSR_IA32_SPEC_CTRL, %ecx @@ -431,3 +425,63 @@ For 32-bit we have the following conventions - kernel is built with .endm #endif /* CONFIG_SMP */ + +#ifdef CONFIG_X86_64 + +/* rdi: arg1 ... normal C conventions. rax is saved/restored. */ +.macro THUNK name, func +SYM_FUNC_START(\name) + pushq %rbp + movq %rsp, %rbp + + pushq %rdi + pushq %rsi + pushq %rdx + pushq %rcx + pushq %rax + pushq %r8 + pushq %r9 + pushq %r10 + pushq %r11 + + call \func + + popq %r11 + popq %r10 + popq %r9 + popq %r8 + popq %rax + popq %rcx + popq %rdx + popq %rsi + popq %rdi + popq %rbp + RET +SYM_FUNC_END(\name) + _ASM_NOKPROBE(\name) +.endm + +#else /* CONFIG_X86_32 */ + +/* put return address in eax (arg1) */ +.macro THUNK name, func, put_ret_addr_in_eax=0 +SYM_CODE_START_NOALIGN(\name) + pushl %eax + pushl %ecx + pushl %edx + + .if \put_ret_addr_in_eax + /* Place EIP in the arg1 */ + movl 3*4(%esp), %eax + .endif + + call \func + popl %edx + popl %ecx + popl %eax + RET + _ASM_NOKPROBE(\name) +SYM_CODE_END(\name) + .endm + +#endif diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S index 003379049924..d9feadffa972 100644 --- a/arch/x86/entry/entry.S +++ b/arch/x86/entry/entry.S @@ -10,6 +10,8 @@ #include <asm/segment.h> #include <asm/cache.h> +#include "calling.h" + .pushsection .noinstr.text, "ax" SYM_FUNC_START(entry_ibpb) @@ -43,3 +45,4 @@ EXPORT_SYMBOL_GPL(mds_verw_sel); .popsection +THUNK warn_thunk_thunk, __warn_thunk diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index b8be0164385c..d3a814efbff6 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -305,7 +305,7 @@ .macro CHECK_AND_APPLY_ESPFIX #ifdef CONFIG_X86_ESPFIX32 #define GDT_ESPFIX_OFFSET (GDT_ENTRY_ESPFIX_SS * 8) -#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + GDT_ESPFIX_OFFSET +#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page + GDT_ESPFIX_OFFSET) ALTERNATIVE "jmp .Lend_\@", "", X86_BUG_ESPFIX diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 23c90813e877..8af2a26b24f6 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -191,7 +191,7 @@ SYM_FUNC_START(__switch_to_asm) #ifdef CONFIG_STACKPROTECTOR movq TASK_stack_canary(%rsi), %rbx - movq %rbx, PER_CPU_VAR(fixed_percpu_data) + FIXED_stack_canary + movq %rbx, PER_CPU_VAR(fixed_percpu_data + FIXED_stack_canary) #endif /* @@ -561,7 +561,7 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL) #ifdef CONFIG_XEN_PV ALTERNATIVE "", "jmp xenpv_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV #endif -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION ALTERNATIVE "", "jmp .Lpti_restore_regs_and_return_to_usermode", X86_FEATURE_PTI #endif @@ -578,7 +578,7 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL) jnz .Lnative_iret ud2 -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION .Lpti_restore_regs_and_return_to_usermode: POP_REGS pop_rdi=0 @@ -970,14 +970,14 @@ SYM_CODE_START_LOCAL(paranoid_exit) IBRS_EXIT save_reg=%r15 /* - * The order of operations is important. RESTORE_CR3 requires + * The order of operations is important. PARANOID_RESTORE_CR3 requires * kernel GSBASE. * * NB to anyone to try to optimize this code: this code does * not execute at all for exceptions from user mode. Those * exceptions go through error_return instead. */ - RESTORE_CR3 scratch_reg=%rax save_reg=%r14 + PARANOID_RESTORE_CR3 scratch_reg=%rax save_reg=%r14 /* Handle the three GSBASE cases */ ALTERNATIVE "jmp .Lparanoid_exit_checkgs", "", X86_FEATURE_FSGSBASE @@ -1098,7 +1098,7 @@ SYM_CODE_END(error_return) * * Registers: * %r14: Used to save/restore the CR3 of the interrupted context - * when PAGE_TABLE_ISOLATION is in use. Do not clobber. + * when MITIGATION_PAGE_TABLE_ISOLATION is in use. Do not clobber. */ SYM_CODE_START(asm_exc_nmi) UNWIND_HINT_IRET_ENTRY @@ -1406,8 +1406,7 @@ end_repeat_nmi: /* Always restore stashed SPEC_CTRL value (see paranoid_entry) */ IBRS_EXIT save_reg=%r15 - /* Always restore stashed CR3 value (see paranoid_entry) */ - RESTORE_CR3 scratch_reg=%r15 save_reg=%r14 + PARANOID_RESTORE_CR3 scratch_reg=%r15 save_reg=%r14 /* * The above invocation of paranoid_entry stored the GSBASE diff --git a/arch/x86/entry/thunk_32.S b/arch/x86/entry/thunk_32.S index 0103e103a657..da37f42f4549 100644 --- a/arch/x86/entry/thunk_32.S +++ b/arch/x86/entry/thunk_32.S @@ -4,33 +4,15 @@ * Copyright 2008 by Steven Rostedt, Red Hat, Inc * (inspired by Andi Kleen's thunk_64.S) */ - #include <linux/export.h> - #include <linux/linkage.h> - #include <asm/asm.h> - /* put return address in eax (arg1) */ - .macro THUNK name, func, put_ret_addr_in_eax=0 -SYM_CODE_START_NOALIGN(\name) - pushl %eax - pushl %ecx - pushl %edx +#include <linux/export.h> +#include <linux/linkage.h> +#include <asm/asm.h> - .if \put_ret_addr_in_eax - /* Place EIP in the arg1 */ - movl 3*4(%esp), %eax - .endif +#include "calling.h" - call \func - popl %edx - popl %ecx - popl %eax - RET - _ASM_NOKPROBE(\name) -SYM_CODE_END(\name) - .endm - - THUNK preempt_schedule_thunk, preempt_schedule - THUNK preempt_schedule_notrace_thunk, preempt_schedule_notrace - EXPORT_SYMBOL(preempt_schedule_thunk) - EXPORT_SYMBOL(preempt_schedule_notrace_thunk) +THUNK preempt_schedule_thunk, preempt_schedule +THUNK preempt_schedule_notrace_thunk, preempt_schedule_notrace +EXPORT_SYMBOL(preempt_schedule_thunk) +EXPORT_SYMBOL(preempt_schedule_notrace_thunk) diff --git a/arch/x86/entry/thunk_64.S b/arch/x86/entry/thunk_64.S index 416b400f39db..119ebdc3d362 100644 --- a/arch/x86/entry/thunk_64.S +++ b/arch/x86/entry/thunk_64.S @@ -9,39 +9,6 @@ #include "calling.h" #include <asm/asm.h> - /* rdi: arg1 ... normal C conventions. rax is saved/restored. */ - .macro THUNK name, func -SYM_FUNC_START(\name) - pushq %rbp - movq %rsp, %rbp - - pushq %rdi - pushq %rsi - pushq %rdx - pushq %rcx - pushq %rax - pushq %r8 - pushq %r9 - pushq %r10 - pushq %r11 - - call \func - - popq %r11 - popq %r10 - popq %r9 - popq %r8 - popq %rax - popq %rcx - popq %rdx - popq %rsi - popq %rdi - popq %rbp - RET -SYM_FUNC_END(\name) - _ASM_NOKPROBE(\name) - .endm - THUNK preempt_schedule_thunk, preempt_schedule THUNK preempt_schedule_notrace_thunk, preempt_schedule_notrace EXPORT_SYMBOL(preempt_schedule_thunk) diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index b1b8dd1608f7..620f6257bbe9 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -3,7 +3,7 @@ # Building vDSO images for x86. # -# Include the generic Makefile to check the built vdso. +# Include the generic Makefile to check the built vDSO: include $(srctree)/lib/vdso/Makefile # Sanitizer runtimes are unavailable and cannot be linked here. @@ -18,48 +18,39 @@ OBJECT_FILES_NON_STANDARD := y # Prevents link failures: __sanitizer_cov_trace_pc() is not linked in. KCOV_INSTRUMENT := n -VDSO64-$(CONFIG_X86_64) := y -VDSOX32-$(CONFIG_X86_X32_ABI) := y -VDSO32-$(CONFIG_X86_32) := y -VDSO32-$(CONFIG_IA32_EMULATION) := y - -# files to link into the vdso +# Files to link into the vDSO: vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o vobjs32-y := vdso32/note.o vdso32/system_call.o vdso32/sigreturn.o vobjs32-y += vdso32/vclock_gettime.o vdso32/vgetcpu.o vobjs-$(CONFIG_X86_SGX) += vsgx.o -# files to link into kernel -obj-y += vma.o extable.o -KASAN_SANITIZE_vma.o := y -UBSAN_SANITIZE_vma.o := y -KCSAN_SANITIZE_vma.o := y -OBJECT_FILES_NON_STANDARD_vma.o := n -OBJECT_FILES_NON_STANDARD_extable.o := n +# Files to link into the kernel: +obj-y += vma.o extable.o +KASAN_SANITIZE_vma.o := y +UBSAN_SANITIZE_vma.o := y +KCSAN_SANITIZE_vma.o := y + +OBJECT_FILES_NON_STANDARD_vma.o := n +OBJECT_FILES_NON_STANDARD_extable.o := n -# vDSO images to build -vdso_img-$(VDSO64-y) += 64 -vdso_img-$(VDSOX32-y) += x32 -vdso_img-$(VDSO32-y) += 32 +# vDSO images to build: +obj-$(CONFIG_X86_64) += vdso-image-64.o +obj-$(CONFIG_X86_X32_ABI) += vdso-image-x32.o +obj-$(CONFIG_COMPAT_32) += vdso-image-32.o vdso32-setup.o -obj-$(VDSO32-y) += vdso32-setup.o -OBJECT_FILES_NON_STANDARD_vdso32-setup.o := n +OBJECT_FILES_NON_STANDARD_vdso-image-32.o := n +OBJECT_FILES_NON_STANDARD_vdso-image-64.o := n +OBJECT_FILES_NON_STANDARD_vdso32-setup.o := n -vobjs := $(foreach F,$(vobjs-y),$(obj)/$F) -vobjs32 := $(foreach F,$(vobjs32-y),$(obj)/$F) +vobjs := $(addprefix $(obj)/, $(vobjs-y)) +vobjs32 := $(addprefix $(obj)/, $(vobjs32-y)) $(obj)/vdso.o: $(obj)/vdso.so targets += vdso.lds $(vobjs-y) targets += vdso32/vdso32.lds $(vobjs32-y) -# Build the vDSO image C files and link them in. -vdso_img_objs := $(vdso_img-y:%=vdso-image-%.o) -vdso_img_cfiles := $(vdso_img-y:%=vdso-image-%.c) -vdso_img_sodbg := $(vdso_img-y:%=vdso%.so.dbg) -obj-y += $(vdso_img_objs) -targets += $(vdso_img_cfiles) -targets += $(vdso_img_sodbg) $(vdso_img-y:%=vdso%.so) +targets += $(foreach x, 64 x32 32, vdso-image-$(x).c vdso$(x).so vdso$(x).so.dbg) CPPFLAGS_vdso.lds += -P -C @@ -87,7 +78,7 @@ CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \ -fno-omit-frame-pointer -foptimize-sibling-calls \ -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO -ifdef CONFIG_RETPOLINE +ifdef CONFIG_MITIGATION_RETPOLINE ifneq ($(RETPOLINE_VDSO_CFLAGS),) CFL += $(RETPOLINE_VDSO_CFLAGS) endif @@ -123,7 +114,7 @@ VDSO_LDFLAGS_vdsox32.lds = -m elf32_x86_64 -soname linux-vdso.so.1 \ vobjx32s-y := $(vobjs-y:.o=-x32.o) # same thing, but in the output directory -vobjx32s := $(foreach F,$(vobjx32s-y),$(obj)/$F) +vobjx32s := $(addprefix $(obj)/, $(vobjx32s-y)) # Convert 64bit object file to x32 for x32 vDSO. quiet_cmd_x32 = X32 $@ @@ -164,7 +155,7 @@ KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls) KBUILD_CFLAGS_32 += -fno-omit-frame-pointer KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING -ifdef CONFIG_RETPOLINE +ifdef CONFIG_MITIGATION_RETPOLINE ifneq ($(RETPOLINE_VDSO_CFLAGS),) KBUILD_CFLAGS_32 += $(RETPOLINE_VDSO_CFLAGS) endif @@ -190,5 +181,3 @@ GCOV_PROFILE := n quiet_cmd_vdso_and_check = VDSO $@ cmd_vdso_and_check = $(cmd_vdso); $(cmd_vdso_check) - -clean-files := vdso32.so vdso32.so.dbg vdso64* vdso-image-*.c vdsox32.so* diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index 7645730dc228..6d83ceb7f1ba 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -274,59 +274,6 @@ up_fail: return ret; } -#ifdef CONFIG_X86_64 -/* - * Put the vdso above the (randomized) stack with another randomized - * offset. This way there is no hole in the middle of address space. - * To save memory make sure it is still in the same PTE as the stack - * top. This doesn't give that many random bits. - * - * Note that this algorithm is imperfect: the distribution of the vdso - * start address within a PMD is biased toward the end. - * - * Only used for the 64-bit and x32 vdsos. - */ -static unsigned long vdso_addr(unsigned long start, unsigned len) -{ - unsigned long addr, end; - unsigned offset; - - /* - * Round up the start address. It can start out unaligned as a result - * of stack start randomization. - */ - start = PAGE_ALIGN(start); - - /* Round the lowest possible end address up to a PMD boundary. */ - end = (start + len + PMD_SIZE - 1) & PMD_MASK; - if (end >= DEFAULT_MAP_WINDOW) - end = DEFAULT_MAP_WINDOW; - end -= len; - - if (end > start) { - offset = get_random_u32_below(((end - start) >> PAGE_SHIFT) + 1); - addr = start + (offset << PAGE_SHIFT); - } else { - addr = start; - } - - /* - * Forcibly align the final address in case we have a hardware - * issue that requires alignment for performance reasons. - */ - addr = align_vdso_addr(addr); - - return addr; -} - -static int map_vdso_randomized(const struct vdso_image *image) -{ - unsigned long addr = vdso_addr(current->mm->start_stack, image->size-image->sym_vvar_start); - - return map_vdso(image, addr); -} -#endif - int map_vdso_once(const struct vdso_image *image, unsigned long addr) { struct mm_struct *mm = current->mm; @@ -369,7 +316,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) if (!vdso64_enabled) return 0; - return map_vdso_randomized(&vdso_image_64); + return map_vdso(&vdso_image_64, 0); } #ifdef CONFIG_COMPAT @@ -380,7 +327,7 @@ int compat_arch_setup_additional_pages(struct linux_binprm *bprm, if (x32) { if (!vdso64_enabled) return 0; - return map_vdso_randomized(&vdso_image_x32); + return map_vdso(&vdso_image_x32, 0); } #endif #ifdef CONFIG_IA32_EMULATION diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c index 5bf03c575812..4ccb8fa483e6 100644 --- a/arch/x86/events/amd/uncore.c +++ b/arch/x86/events/amd/uncore.c @@ -71,7 +71,7 @@ union amd_uncore_info { }; struct amd_uncore { - union amd_uncore_info * __percpu info; + union amd_uncore_info __percpu *info; struct amd_uncore_pmu *pmus; unsigned int num_pmus; bool init_done; diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 3804f21ab049..768d1414897f 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -17,6 +17,7 @@ #include <linux/kvm_host.h> #include <asm/cpufeature.h> +#include <asm/debugreg.h> #include <asm/hardirq.h> #include <asm/intel-family.h> #include <asm/intel_pt.h> diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index d49d661ec0a7..2641ba620f12 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -5,6 +5,7 @@ #include <linux/sched/clock.h> #include <asm/cpu_entry_area.h> +#include <asm/debugreg.h> #include <asm/perf_event.h> #include <asm/tlbflush.h> #include <asm/insn.h> diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index fbcfec4dc4cc..ca8eed1d496a 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -113,6 +113,20 @@ #endif +#ifndef __ASSEMBLY__ +#ifndef __pic__ +static __always_inline __pure void *rip_rel_ptr(void *p) +{ + asm("leaq %c1(%%rip), %0" : "=r"(p) : "i"(p)); + + return p; +} +#define RIP_REL_REF(var) (*(typeof(&(var)))rip_rel_ptr(&(var))) +#else +#define RIP_REL_REF(var) (var) +#endif +#endif + /* * Macros to generate condition code outputs from inline assembly, * The output operand must be type "bool". diff --git a/arch/x86/include/asm/coco.h b/arch/x86/include/asm/coco.h index 76c310b19b11..fb7388bbc212 100644 --- a/arch/x86/include/asm/coco.h +++ b/arch/x86/include/asm/coco.h @@ -2,6 +2,7 @@ #ifndef _ASM_X86_COCO_H #define _ASM_X86_COCO_H +#include <asm/asm.h> #include <asm/types.h> enum cc_vendor { @@ -12,7 +13,13 @@ enum cc_vendor { #ifdef CONFIG_ARCH_HAS_CC_PLATFORM extern enum cc_vendor cc_vendor; -void cc_set_mask(u64 mask); +extern u64 cc_mask; + +static inline void cc_set_mask(u64 mask) +{ + RIP_REL_REF(cc_mask) = mask; +} + u64 cc_mkenc(u64 val); u64 cc_mkdec(u64 val); #else diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 8e371c6cc5f9..f0337f7bcf16 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -442,6 +442,7 @@ #define X86_FEATURE_SEV (19*32+ 1) /* AMD Secure Encrypted Virtualization */ #define X86_FEATURE_VM_PAGE_FLUSH (19*32+ 2) /* "" VM Page Flush MSR is supported */ #define X86_FEATURE_SEV_ES (19*32+ 3) /* AMD Secure Encrypted Virtualization - Encrypted State */ +#define X86_FEATURE_SEV_SNP (19*32+ 4) /* AMD Secure Encrypted Virtualization - Secure Nested Paging */ #define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* "" Virtual TSC_AUX */ #define X86_FEATURE_SME_COHERENT (19*32+10) /* "" AMD hardware-enforced cache coherency */ #define X86_FEATURE_DEBUG_SWAP (19*32+14) /* AMD SEV-ES full debug state swap support */ @@ -505,4 +506,5 @@ /* BUG word 2 */ #define X86_BUG_SRSO X86_BUG(1*32 + 0) /* AMD SRSO bug */ #define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* AMD DIV0 speculation bug */ +#define X86_BUG_RFDS X86_BUG(1*32 + 2) /* CPU is vulnerable to Register File Data Sampling */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/current.h b/arch/x86/include/asm/current.h index dd4b67101bb7..bf5953883ec3 100644 --- a/arch/x86/include/asm/current.h +++ b/arch/x86/include/asm/current.h @@ -18,7 +18,7 @@ struct pcpu_hot { struct task_struct *current_task; int preempt_count; int cpu_number; -#ifdef CONFIG_CALL_DEPTH_TRACKING +#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING u64 call_depth; #endif unsigned long top_of_stack; @@ -37,8 +37,15 @@ static_assert(sizeof(struct pcpu_hot) == 64); DECLARE_PER_CPU_ALIGNED(struct pcpu_hot, pcpu_hot); +/* const-qualified alias to pcpu_hot, aliased by linker. */ +DECLARE_PER_CPU_ALIGNED(const struct pcpu_hot __percpu_seg_override, + const_pcpu_hot); + static __always_inline struct task_struct *get_current(void) { + if (IS_ENABLED(CONFIG_USE_X86_SEG_SUPPORT)) + return this_cpu_read_const(const_pcpu_hot.current_task); + return this_cpu_read_stable(pcpu_hot.current_task); } diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h index 0cec92c430cc..fdbbbfec745a 100644 --- a/arch/x86/include/asm/debugreg.h +++ b/arch/x86/include/asm/debugreg.h @@ -5,7 +5,9 @@ #include <linux/bug.h> #include <linux/percpu.h> #include <uapi/asm/debugreg.h> + #include <asm/cpufeature.h> +#include <asm/msr.h> DECLARE_PER_CPU(unsigned long, cpu_dr7); @@ -159,4 +161,26 @@ static inline unsigned long amd_get_dr_addr_mask(unsigned int dr) } #endif +static inline unsigned long get_debugctlmsr(void) +{ + unsigned long debugctlmsr = 0; + +#ifndef CONFIG_X86_DEBUGCTLMSR + if (boot_cpu_data.x86 < 6) + return 0; +#endif + rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr); + + return debugctlmsr; +} + +static inline void update_debugctlmsr(unsigned long debugctlmsr) +{ +#ifndef CONFIG_X86_DEBUGCTLMSR + if (boot_cpu_data.x86 < 6) + return; +#endif + wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr); +} + #endif /* _ASM_X86_DEBUGREG_H */ diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index ec95fe44fa3a..62dc9f59ea76 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -46,6 +46,7 @@ struct gdt_page { } __attribute__((aligned(PAGE_SIZE))); DECLARE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page); +DECLARE_INIT_PER_CPU(gdt_page); /* Provide the original GDT */ static inline struct desc_struct *get_cpu_gdt_rw(unsigned int cpu) diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index f40b29d3abad..da4054fbf533 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -44,32 +44,32 @@ # define DISABLE_LA57 (1<<(X86_FEATURE_LA57 & 31)) #endif -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION # define DISABLE_PTI 0 #else # define DISABLE_PTI (1 << (X86_FEATURE_PTI & 31)) #endif -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE # define DISABLE_RETPOLINE 0 #else # define DISABLE_RETPOLINE ((1 << (X86_FEATURE_RETPOLINE & 31)) | \ (1 << (X86_FEATURE_RETPOLINE_LFENCE & 31))) #endif -#ifdef CONFIG_RETHUNK +#ifdef CONFIG_MITIGATION_RETHUNK # define DISABLE_RETHUNK 0 #else # define DISABLE_RETHUNK (1 << (X86_FEATURE_RETHUNK & 31)) #endif -#ifdef CONFIG_CPU_UNRET_ENTRY +#ifdef CONFIG_MITIGATION_UNRET_ENTRY # define DISABLE_UNRET 0 #else # define DISABLE_UNRET (1 << (X86_FEATURE_UNRET & 31)) #endif -#ifdef CONFIG_CALL_DEPTH_TRACKING +#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING # define DISABLE_CALL_DEPTH_TRACKING 0 #else # define DISABLE_CALL_DEPTH_TRACKING (1 << (X86_FEATURE_CALL_DEPTH & 31)) @@ -123,6 +123,12 @@ # define DISABLE_FRED (1 << (X86_FEATURE_FRED & 31)) #endif +#ifdef CONFIG_KVM_AMD_SEV +#define DISABLE_SEV_SNP 0 +#else +#define DISABLE_SEV_SNP (1 << (X86_FEATURE_SEV_SNP & 31)) +#endif + /* * Make sure to add features to the correct mask */ @@ -147,7 +153,7 @@ DISABLE_ENQCMD) #define DISABLED_MASK17 0 #define DISABLED_MASK18 (DISABLE_IBT) -#define DISABLED_MASK19 0 +#define DISABLED_MASK19 (DISABLE_SEV_SNP) #define DISABLED_MASK20 0 #define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21) diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index c4555b269a1b..1dc600fa3ba5 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -143,15 +143,6 @@ extern void efi_free_boot_services(void); void arch_efi_call_virt_setup(void); void arch_efi_call_virt_teardown(void); -/* kexec external ABI */ -struct efi_setup_data { - u64 fw_vendor; - u64 __unused; - u64 tables; - u64 smbios; - u64 reserved[8]; -}; - extern u64 efi_setup; #ifdef CONFIG_EFI @@ -418,8 +409,9 @@ extern int __init efi_memmap_split_count(efi_memory_desc_t *md, extern void __init efi_memmap_insert(struct efi_memory_map *old_memmap, void *buf, struct efi_mem_range *mem); -#define arch_ima_efi_boot_mode \ - ({ extern struct boot_params boot_params; boot_params.secure_boot; }) +extern enum efi_secureboot_mode __x86_ima_efi_boot_mode(void); + +#define arch_ima_efi_boot_mode __x86_ima_efi_boot_mode() #ifdef CONFIG_EFI_RUNTIME_MAP int efi_get_runtime_map_size(void); diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 1e16bd5ac781..1fb83d47711f 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -392,5 +392,4 @@ struct va_alignment { } ____cacheline_aligned; extern struct va_alignment va_align; -extern unsigned long align_vdso_addr(unsigned long); #endif /* _ASM_X86_ELF_H */ diff --git a/arch/x86/include/asm/fpu/sched.h b/arch/x86/include/asm/fpu/sched.h index ca6e5e5f16b2..c485f1944c5f 100644 --- a/arch/x86/include/asm/fpu/sched.h +++ b/arch/x86/include/asm/fpu/sched.h @@ -37,10 +37,12 @@ extern void fpu_flush_thread(void); * The FPU context is only stored/restored for a user task and * PF_KTHREAD is used to distinguish between kernel and user threads. */ -static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu) +static inline void switch_fpu_prepare(struct task_struct *old, int cpu) { if (cpu_feature_enabled(X86_FEATURE_FPU) && - !(current->flags & (PF_KTHREAD | PF_USER_WORKER))) { + !(old->flags & (PF_KTHREAD | PF_USER_WORKER))) { + struct fpu *old_fpu = &old->thread.fpu; + save_fpregs_to_fpstate(old_fpu); /* * The save operation preserved register state, so the @@ -60,10 +62,10 @@ static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu) * Delay loading of the complete FPU state until the return to userland. * PKRU is handled separately. */ -static inline void switch_fpu_finish(void) +static inline void switch_fpu_finish(struct task_struct *new) { if (cpu_feature_enabled(X86_FEATURE_FPU)) - set_thread_flag(TIF_NEED_FPU_LOAD); + set_tsk_thread_flag(new, TIF_NEED_FPU_LOAD); } #endif /* _ASM_X86_FPU_SCHED_H */ diff --git a/arch/x86/include/asm/fsgsbase.h b/arch/x86/include/asm/fsgsbase.h index 35cff5f2becf..9e7e8ca8e299 100644 --- a/arch/x86/include/asm/fsgsbase.h +++ b/arch/x86/include/asm/fsgsbase.h @@ -6,7 +6,7 @@ #ifdef CONFIG_X86_64 -#include <asm/msr-index.h> +#include <asm/msr.h> /* * Read/write a task's FSBASE or GSBASE. This returns the value that diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index 3814a9263d64..294cd2a40818 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -379,7 +379,7 @@ static inline void iosubmit_cmds512(void __iomem *dst, const void *src, const u8 *end = from + count * 64; while (from < end) { - movdir64b(dst, from); + movdir64b_io(dst, from); from += 64; } } diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h index 2fd52b65deac..3be2451e7bc8 100644 --- a/arch/x86/include/asm/iommu.h +++ b/arch/x86/include/asm/iommu.h @@ -10,6 +10,7 @@ extern int force_iommu, no_iommu; extern int iommu_detected; extern int iommu_merge; extern int panic_on_overflow; +extern bool amd_iommu_snp_en; #ifdef CONFIG_SWIOTLB extern bool x86_swiotlb_enable; diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h index c9f6a6c5de3c..91ca9a9ee3a2 100644 --- a/arch/x86/include/asm/kexec.h +++ b/arch/x86/include/asm/kexec.h @@ -25,7 +25,6 @@ #include <asm/page.h> #include <asm/ptrace.h> -#include <asm/bootparam.h> struct kimage; diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 378ed944b849..ab24ce207988 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -138,6 +138,7 @@ KVM_X86_OP(complete_emulated_msr) KVM_X86_OP(vcpu_deliver_sipi_vector) KVM_X86_OP_OPTIONAL_RET0(vcpu_get_apicv_inhibit_reasons); KVM_X86_OP_OPTIONAL(get_untagged_addr) +KVM_X86_OP_OPTIONAL(alloc_apic_backing_page) #undef KVM_X86_OP #undef KVM_X86_OP_OPTIONAL diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index d271ba20a0b2..18cbde14cf81 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1796,6 +1796,7 @@ struct kvm_x86_ops { unsigned long (*vcpu_get_apicv_inhibit_reasons)(struct kvm_vcpu *vcpu); gva_t (*get_untagged_addr)(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags); + void *(*alloc_apic_backing_page)(struct kvm_vcpu *vcpu); }; struct kvm_x86_nested_ops { diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h index 571fe4d2d232..dc31b13b87a0 100644 --- a/arch/x86/include/asm/linkage.h +++ b/arch/x86/include/asm/linkage.h @@ -40,27 +40,27 @@ #ifdef __ASSEMBLY__ -#if defined(CONFIG_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO) +#if defined(CONFIG_MITIGATION_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO) #define RET jmp __x86_return_thunk -#else /* CONFIG_RETPOLINE */ -#ifdef CONFIG_SLS +#else /* CONFIG_MITIGATION_RETPOLINE */ +#ifdef CONFIG_MITIGATION_SLS #define RET ret; int3 #else #define RET ret #endif -#endif /* CONFIG_RETPOLINE */ +#endif /* CONFIG_MITIGATION_RETPOLINE */ #else /* __ASSEMBLY__ */ -#if defined(CONFIG_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO) +#if defined(CONFIG_MITIGATION_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO) #define ASM_RET "jmp __x86_return_thunk\n\t" -#else /* CONFIG_RETPOLINE */ -#ifdef CONFIG_SLS +#else /* CONFIG_MITIGATION_RETPOLINE */ +#ifdef CONFIG_MITIGATION_SLS #define ASM_RET "ret; int3\n\t" #else #define ASM_RET "ret\n\t" #endif -#endif /* CONFIG_RETPOLINE */ +#endif /* CONFIG_MITIGATION_RETPOLINE */ #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h index 73dba8b94443..59aa966dc212 100644 --- a/arch/x86/include/asm/local.h +++ b/arch/x86/include/asm/local.h @@ -131,8 +131,20 @@ static inline bool local_try_cmpxchg(local_t *l, long *old, long new) (typeof(l->a.counter) *) old, new); } -/* Always has a lock prefix */ -#define local_xchg(l, n) (xchg(&((l)->a.counter), (n))) +/* + * Implement local_xchg using CMPXCHG instruction without the LOCK prefix. + * XCHG is expensive due to the implied LOCK prefix. The processor + * cannot prefetch cachelines if XCHG is used. + */ +static __always_inline long +local_xchg(local_t *l, long n) +{ + long c = local_read(l); + + do { } while (!local_try_cmpxchg(l, &c, n)); + + return c; +} /** * local_add_unless - add unless the number is already a given value diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index 359ada486fa9..f922b682b9b4 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -15,7 +15,8 @@ #include <linux/init.h> #include <linux/cc_platform.h> -#include <asm/bootparam.h> +#include <asm/asm.h> +struct boot_params; #ifdef CONFIG_X86_MEM_ENCRYPT void __init mem_encrypt_init(void); @@ -46,8 +47,8 @@ void __init sme_unmap_bootdata(char *real_mode_data); void __init sme_early_init(void); -void __init sme_encrypt_kernel(struct boot_params *bp); -void __init sme_enable(struct boot_params *bp); +void sme_encrypt_kernel(struct boot_params *bp); +void sme_enable(struct boot_params *bp); int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size); int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size); @@ -58,6 +59,11 @@ void __init mem_encrypt_free_decrypted_mem(void); void __init sev_es_init_vc_handling(void); +static inline u64 sme_get_me_mask(void) +{ + return RIP_REL_REF(sme_me_mask); +} + #define __bss_decrypted __section(".bss..decrypted") #else /* !CONFIG_AMD_MEM_ENCRYPT */ @@ -75,8 +81,8 @@ static inline void __init sme_unmap_bootdata(char *real_mode_data) { } static inline void __init sme_early_init(void) { } -static inline void __init sme_encrypt_kernel(struct boot_params *bp) { } -static inline void __init sme_enable(struct boot_params *bp) { } +static inline void sme_encrypt_kernel(struct boot_params *bp) { } +static inline void sme_enable(struct boot_params *bp) { } static inline void sev_es_init_vc_handling(void) { } @@ -89,6 +95,8 @@ early_set_mem_enc_dec_hypercall(unsigned long vaddr, unsigned long size, bool en static inline void mem_encrypt_free_decrypted_mem(void) { } +static inline u64 sme_get_me_mask(void) { return 0; } + #define __bss_decrypted #endif /* CONFIG_AMD_MEM_ENCRYPT */ @@ -106,11 +114,6 @@ void add_encrypt_protection_map(void); extern char __start_bss_decrypted[], __end_bss_decrypted[], __start_bss_decrypted_unused[]; -static inline u64 sme_get_me_mask(void) -{ - return sme_me_mask; -} - #endif /* __ASSEMBLY__ */ #endif /* __X86_MEM_ENCRYPT_H__ */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 1f9dc9bd13eb..05956bd8bacf 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -176,6 +176,14 @@ * CPU is not vulnerable to Gather * Data Sampling (GDS). */ +#define ARCH_CAP_RFDS_NO BIT(27) /* + * Not susceptible to Register + * File Data Sampling. + */ +#define ARCH_CAP_RFDS_CLEAR BIT(28) /* + * VERW clears CPU Register + * File. + */ #define ARCH_CAP_XAPIC_DISABLE BIT(21) /* * IA32_XAPIC_DISABLE_STATUS MSR @@ -605,34 +613,47 @@ #define MSR_AMD64_SEV_ES_GHCB 0xc0010130 #define MSR_AMD64_SEV 0xc0010131 #define MSR_AMD64_SEV_ENABLED_BIT 0 -#define MSR_AMD64_SEV_ES_ENABLED_BIT 1 -#define MSR_AMD64_SEV_SNP_ENABLED_BIT 2 #define MSR_AMD64_SEV_ENABLED BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT) +#define MSR_AMD64_SEV_ES_ENABLED_BIT 1 #define MSR_AMD64_SEV_ES_ENABLED BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT) +#define MSR_AMD64_SEV_SNP_ENABLED_BIT 2 #define MSR_AMD64_SEV_SNP_ENABLED BIT_ULL(MSR_AMD64_SEV_SNP_ENABLED_BIT) - -/* SNP feature bits enabled by the hypervisor */ -#define MSR_AMD64_SNP_VTOM BIT_ULL(3) -#define MSR_AMD64_SNP_REFLECT_VC BIT_ULL(4) -#define MSR_AMD64_SNP_RESTRICTED_INJ BIT_ULL(5) -#define MSR_AMD64_SNP_ALT_INJ BIT_ULL(6) -#define MSR_AMD64_SNP_DEBUG_SWAP BIT_ULL(7) -#define MSR_AMD64_SNP_PREVENT_HOST_IBS BIT_ULL(8) -#define MSR_AMD64_SNP_BTB_ISOLATION BIT_ULL(9) -#define MSR_AMD64_SNP_VMPL_SSS BIT_ULL(10) -#define MSR_AMD64_SNP_SECURE_TSC BIT_ULL(11) -#define MSR_AMD64_SNP_VMGEXIT_PARAM BIT_ULL(12) -#define MSR_AMD64_SNP_IBS_VIRT BIT_ULL(14) -#define MSR_AMD64_SNP_VMSA_REG_PROTECTION BIT_ULL(16) -#define MSR_AMD64_SNP_SMT_PROTECTION BIT_ULL(17) - -/* SNP feature bits reserved for future use. */ -#define MSR_AMD64_SNP_RESERVED_BIT13 BIT_ULL(13) -#define MSR_AMD64_SNP_RESERVED_BIT15 BIT_ULL(15) -#define MSR_AMD64_SNP_RESERVED_MASK GENMASK_ULL(63, 18) +#define MSR_AMD64_SNP_VTOM_BIT 3 +#define MSR_AMD64_SNP_VTOM BIT_ULL(MSR_AMD64_SNP_VTOM_BIT) +#define MSR_AMD64_SNP_REFLECT_VC_BIT 4 +#define MSR_AMD64_SNP_REFLECT_VC BIT_ULL(MSR_AMD64_SNP_REFLECT_VC_BIT) +#define MSR_AMD64_SNP_RESTRICTED_INJ_BIT 5 +#define MSR_AMD64_SNP_RESTRICTED_INJ BIT_ULL(MSR_AMD64_SNP_RESTRICTED_INJ_BIT) +#define MSR_AMD64_SNP_ALT_INJ_BIT 6 +#define MSR_AMD64_SNP_ALT_INJ BIT_ULL(MSR_AMD64_SNP_ALT_INJ_BIT) +#define MSR_AMD64_SNP_DEBUG_SWAP_BIT 7 +#define MSR_AMD64_SNP_DEBUG_SWAP BIT_ULL(MSR_AMD64_SNP_DEBUG_SWAP_BIT) +#define MSR_AMD64_SNP_PREVENT_HOST_IBS_BIT 8 +#define MSR_AMD64_SNP_PREVENT_HOST_IBS BIT_ULL(MSR_AMD64_SNP_PREVENT_HOST_IBS_BIT) +#define MSR_AMD64_SNP_BTB_ISOLATION_BIT 9 +#define MSR_AMD64_SNP_BTB_ISOLATION BIT_ULL(MSR_AMD64_SNP_BTB_ISOLATION_BIT) +#define MSR_AMD64_SNP_VMPL_SSS_BIT 10 +#define MSR_AMD64_SNP_VMPL_SSS BIT_ULL(MSR_AMD64_SNP_VMPL_SSS_BIT) +#define MSR_AMD64_SNP_SECURE_TSC_BIT 11 +#define MSR_AMD64_SNP_SECURE_TSC BIT_ULL(MSR_AMD64_SNP_SECURE_TSC_BIT) +#define MSR_AMD64_SNP_VMGEXIT_PARAM_BIT 12 +#define MSR_AMD64_SNP_VMGEXIT_PARAM BIT_ULL(MSR_AMD64_SNP_VMGEXIT_PARAM_BIT) +#define MSR_AMD64_SNP_RESERVED_BIT13 BIT_ULL(13) +#define MSR_AMD64_SNP_IBS_VIRT_BIT 14 +#define MSR_AMD64_SNP_IBS_VIRT BIT_ULL(MSR_AMD64_SNP_IBS_VIRT_BIT) +#define MSR_AMD64_SNP_RESERVED_BIT15 BIT_ULL(15) +#define MSR_AMD64_SNP_VMSA_REG_PROT_BIT 16 +#define MSR_AMD64_SNP_VMSA_REG_PROT BIT_ULL(MSR_AMD64_SNP_VMSA_REG_PROT_BIT) +#define MSR_AMD64_SNP_SMT_PROT_BIT 17 +#define MSR_AMD64_SNP_SMT_PROT BIT_ULL(MSR_AMD64_SNP_SMT_PROT_BIT) +#define MSR_AMD64_SNP_RESV_BIT 18 +#define MSR_AMD64_SNP_RESERVED_MASK GENMASK_ULL(63, MSR_AMD64_SNP_RESV_BIT) #define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f +#define MSR_AMD64_RMP_BASE 0xc0010132 +#define MSR_AMD64_RMP_END 0xc0010133 + /* AMD Collaborative Processor Performance Control MSRs */ #define MSR_AMD_CPPC_CAP1 0xc00102b0 #define MSR_AMD_CPPC_ENABLE 0xc00102b1 @@ -719,8 +740,15 @@ #define MSR_K8_TOP_MEM1 0xc001001a #define MSR_K8_TOP_MEM2 0xc001001d #define MSR_AMD64_SYSCFG 0xc0010010 -#define MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT 23 +#define MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT 23 #define MSR_AMD64_SYSCFG_MEM_ENCRYPT BIT_ULL(MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT) +#define MSR_AMD64_SYSCFG_SNP_EN_BIT 24 +#define MSR_AMD64_SYSCFG_SNP_EN BIT_ULL(MSR_AMD64_SYSCFG_SNP_EN_BIT) +#define MSR_AMD64_SYSCFG_SNP_VMPL_EN_BIT 25 +#define MSR_AMD64_SYSCFG_SNP_VMPL_EN BIT_ULL(MSR_AMD64_SYSCFG_SNP_VMPL_EN_BIT) +#define MSR_AMD64_SYSCFG_MFDM_BIT 19 +#define MSR_AMD64_SYSCFG_MFDM BIT_ULL(MSR_AMD64_SYSCFG_MFDM_BIT) + #define MSR_K8_INT_PENDING_MSG 0xc0010055 /* C1E active bits in int pending message */ #define K8_INTP_C1E_ACTIVE_MASK 0x18000000 diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index c284ff9ebe67..d642037f9ed5 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -12,11 +12,13 @@ #include <uapi/asm/msr.h> #include <asm/shared/msr.h> +#include <linux/percpu.h> + struct msr_info { - u32 msr_no; - struct msr reg; - struct msr *msrs; - int err; + u32 msr_no; + struct msr reg; + struct msr __percpu *msrs; + int err; }; struct msr_regs_info { @@ -323,8 +325,8 @@ static inline int wrmsrl_safe(u32 msr, u64 val) return wrmsr_safe(msr, (u32)val, (u32)(val >> 32)); } -struct msr *msrs_alloc(void); -void msrs_free(struct msr *msrs); +struct msr __percpu *msrs_alloc(void); +void msrs_free(struct msr __percpu *msrs); int msr_set_bit(u32 msr, u8 bit); int msr_clear_bit(u32 msr, u8 bit); @@ -333,8 +335,8 @@ int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h); int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h); int rdmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 *q); int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q); -void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs); -void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs); +void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr __percpu *msrs); +void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr __percpu *msrs); int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h); int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h); int rdmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q); @@ -363,14 +365,14 @@ static inline int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q) return 0; } static inline void rdmsr_on_cpus(const struct cpumask *m, u32 msr_no, - struct msr *msrs) + struct msr __percpu *msrs) { - rdmsr_on_cpu(0, msr_no, &(msrs[0].l), &(msrs[0].h)); + rdmsr_on_cpu(0, msr_no, raw_cpu_ptr(&msrs->l), raw_cpu_ptr(&msrs->h)); } static inline void wrmsr_on_cpus(const struct cpumask *m, u32 msr_no, - struct msr *msrs) + struct msr __percpu *msrs) { - wrmsr_on_cpu(0, msr_no, msrs[0].l, msrs[0].h); + wrmsr_on_cpu(0, msr_no, raw_cpu_read(msrs->l), raw_cpu_read(msrs->h)); } static inline int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h) diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h index 5c5f1e56c404..41a0ebb699ec 100644 --- a/arch/x86/include/asm/nmi.h +++ b/arch/x86/include/asm/nmi.h @@ -14,9 +14,6 @@ extern void release_perfctr_nmi(unsigned int); extern int reserve_evntsel_nmi(unsigned int); extern void release_evntsel_nmi(unsigned int); -struct ctl_table; -extern int proc_nmi_enabled(struct ctl_table *, int , - void __user *, size_t *, loff_t *); extern int unknown_nmi_panic; #endif /* CONFIG_X86_LOCAL_APIC */ diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index ab19c7f1167b..fc3a8a3c7ffe 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -59,13 +59,13 @@ #ifdef CONFIG_CALL_THUNKS_DEBUG # define CALL_THUNKS_DEBUG_INC_CALLS \ - incq %gs:__x86_call_count; + incq PER_CPU_VAR(__x86_call_count); # define CALL_THUNKS_DEBUG_INC_RETS \ - incq %gs:__x86_ret_count; + incq PER_CPU_VAR(__x86_ret_count); # define CALL_THUNKS_DEBUG_INC_STUFFS \ - incq %gs:__x86_stuffs_count; + incq PER_CPU_VAR(__x86_stuffs_count); # define CALL_THUNKS_DEBUG_INC_CTXSW \ - incq %gs:__x86_ctxsw_count; + incq PER_CPU_VAR(__x86_ctxsw_count); #else # define CALL_THUNKS_DEBUG_INC_CALLS # define CALL_THUNKS_DEBUG_INC_RETS @@ -73,16 +73,13 @@ # define CALL_THUNKS_DEBUG_INC_CTXSW #endif -#if defined(CONFIG_CALL_DEPTH_TRACKING) && !defined(COMPILE_OFFSETS) +#if defined(CONFIG_MITIGATION_CALL_DEPTH_TRACKING) && !defined(COMPILE_OFFSETS) #include <asm/asm-offsets.h> #define CREDIT_CALL_DEPTH \ movq $-1, PER_CPU_VAR(pcpu_hot + X86_call_depth); -#define ASM_CREDIT_CALL_DEPTH \ - movq $-1, PER_CPU_VAR(pcpu_hot + X86_call_depth); - #define RESET_CALL_DEPTH \ xor %eax, %eax; \ bts $63, %rax; \ @@ -95,20 +92,14 @@ CALL_THUNKS_DEBUG_INC_CALLS #define INCREMENT_CALL_DEPTH \ - sarq $5, %gs:pcpu_hot + X86_call_depth; \ - CALL_THUNKS_DEBUG_INC_CALLS - -#define ASM_INCREMENT_CALL_DEPTH \ sarq $5, PER_CPU_VAR(pcpu_hot + X86_call_depth); \ CALL_THUNKS_DEBUG_INC_CALLS #else #define CREDIT_CALL_DEPTH -#define ASM_CREDIT_CALL_DEPTH #define RESET_CALL_DEPTH -#define INCREMENT_CALL_DEPTH -#define ASM_INCREMENT_CALL_DEPTH #define RESET_CALL_DEPTH_FROM_CALL +#define INCREMENT_CALL_DEPTH #endif /* @@ -158,7 +149,7 @@ jnz 771b; \ /* barrier for jnz misprediction */ \ lfence; \ - ASM_CREDIT_CALL_DEPTH \ + CREDIT_CALL_DEPTH \ CALL_THUNKS_DEBUG_INC_CTXSW #else /* @@ -212,7 +203,7 @@ */ .macro VALIDATE_UNRET_END #if defined(CONFIG_NOINSTR_VALIDATION) && \ - (defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO)) + (defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO)) ANNOTATE_RETPOLINE_SAFE nop #endif @@ -241,7 +232,7 @@ * instruction irrespective of kCFI. */ .macro JMP_NOSPEC reg:req -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE __CS_PREFIX \reg jmp __x86_indirect_thunk_\reg #else @@ -251,7 +242,7 @@ .endm .macro CALL_NOSPEC reg:req -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE __CS_PREFIX \reg call __x86_indirect_thunk_\reg #else @@ -271,7 +262,7 @@ .Lskip_rsb_\@: .endm -#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO) +#if defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO) #define CALL_UNTRAIN_RET "call entry_untrain_ret" #else #define CALL_UNTRAIN_RET "" @@ -289,7 +280,7 @@ * where we have a stack but before any RET instruction. */ .macro __UNTRAIN_RET ibpb_feature, call_depth_insns -#if defined(CONFIG_RETHUNK) || defined(CONFIG_CPU_IBPB_ENTRY) +#if defined(CONFIG_MITIGATION_RETHUNK) || defined(CONFIG_MITIGATION_IBPB_ENTRY) VALIDATE_UNRET_END ALTERNATIVE_3 "", \ CALL_UNTRAIN_RET, X86_FEATURE_UNRET, \ @@ -309,9 +300,9 @@ .macro CALL_DEPTH_ACCOUNT -#ifdef CONFIG_CALL_DEPTH_TRACKING +#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING ALTERNATIVE "", \ - __stringify(ASM_INCREMENT_CALL_DEPTH), X86_FEATURE_CALL_DEPTH + __stringify(INCREMENT_CALL_DEPTH), X86_FEATURE_CALL_DEPTH #endif .endm @@ -323,7 +314,7 @@ * Note: Only the memory operand variant of VERW clears the CPU buffers. */ .macro CLEAR_CPU_BUFFERS - ALTERNATIVE "", __stringify(verw mds_verw_sel), X86_FEATURE_CLEAR_CPU_BUF + ALTERNATIVE "", __stringify(verw _ASM_RIP(mds_verw_sel)), X86_FEATURE_CLEAR_CPU_BUF .endm #else /* __ASSEMBLY__ */ @@ -339,19 +330,19 @@ extern retpoline_thunk_t __x86_indirect_thunk_array[]; extern retpoline_thunk_t __x86_indirect_call_thunk_array[]; extern retpoline_thunk_t __x86_indirect_jump_thunk_array[]; -#ifdef CONFIG_RETHUNK +#ifdef CONFIG_MITIGATION_RETHUNK extern void __x86_return_thunk(void); #else static inline void __x86_return_thunk(void) {} #endif -#ifdef CONFIG_CPU_UNRET_ENTRY +#ifdef CONFIG_MITIGATION_UNRET_ENTRY extern void retbleed_return_thunk(void); #else static inline void retbleed_return_thunk(void) {} #endif -#ifdef CONFIG_CPU_SRSO +#ifdef CONFIG_MITIGATION_SRSO extern void srso_return_thunk(void); extern void srso_alias_return_thunk(void); #else @@ -368,7 +359,9 @@ extern void entry_ibpb(void); extern void (*x86_return_thunk)(void); -#ifdef CONFIG_CALL_DEPTH_TRACKING +extern void __warn_thunk(void); + +#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING extern void call_depth_return_thunk(void); #define CALL_DEPTH_ACCOUNT \ @@ -382,14 +375,14 @@ DECLARE_PER_CPU(u64, __x86_ret_count); DECLARE_PER_CPU(u64, __x86_stuffs_count); DECLARE_PER_CPU(u64, __x86_ctxsw_count); #endif -#else /* !CONFIG_CALL_DEPTH_TRACKING */ +#else /* !CONFIG_MITIGATION_CALL_DEPTH_TRACKING */ static inline void call_depth_return_thunk(void) {} #define CALL_DEPTH_ACCOUNT "" -#endif /* CONFIG_CALL_DEPTH_TRACKING */ +#endif /* CONFIG_MITIGATION_CALL_DEPTH_TRACKING */ -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE #define GEN(reg) \ extern retpoline_thunk_t __x86_indirect_thunk_ ## reg; @@ -410,7 +403,7 @@ static inline void call_depth_return_thunk(void) {} /* * Inline asm uses the %V modifier which is only in newer GCC - * which is ensured when CONFIG_RETPOLINE is defined. + * which is ensured when CONFIG_MITIGATION_RETPOLINE is defined. */ # define CALL_NOSPEC \ ALTERNATIVE_2( \ diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h index d18e5c332cb9..1b93ff80b43b 100644 --- a/arch/x86/include/asm/page.h +++ b/arch/x86/include/asm/page.h @@ -66,10 +66,14 @@ static inline void copy_user_page(void *to, void *from, unsigned long vaddr, * virt_addr_valid(kaddr) returns true. */ #define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT) -#define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT) extern bool __virt_addr_valid(unsigned long kaddr); #define virt_addr_valid(kaddr) __virt_addr_valid((unsigned long) (kaddr)) +static __always_inline void *pfn_to_kaddr(unsigned long pfn) +{ + return __va(pfn << PAGE_SHIFT); +} + static __always_inline u64 __canonical_address(u64 vaddr, u8 vaddr_bits) { return ((s64)vaddr << (64 - vaddr_bits)) >> (64 - vaddr_bits); diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index b40c462b4af3..b3ab80a03365 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -10,7 +10,6 @@ #include <linux/numa.h> #include <asm/io.h> #include <asm/memtype.h> -#include <asm/x86_init.h> struct pci_sysdata { int domain; /* PCI domain */ @@ -124,16 +123,4 @@ cpumask_of_pcibus(const struct pci_bus *bus) } #endif -struct pci_setup_rom { - struct setup_data data; - uint16_t vendor; - uint16_t devid; - uint64_t pcilen; - unsigned long segment; - unsigned long bus; - unsigned long device; - unsigned long function; - uint8_t romdata[]; -}; - #endif /* _ASM_X86_PCI_H */ diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index 5e01883eb51e..44958ebaf626 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -4,17 +4,21 @@ #ifdef CONFIG_X86_64 #define __percpu_seg gs +#define __percpu_rel (%rip) #else #define __percpu_seg fs +#define __percpu_rel #endif #ifdef __ASSEMBLY__ #ifdef CONFIG_SMP -#define PER_CPU_VAR(var) %__percpu_seg:var -#else /* ! SMP */ -#define PER_CPU_VAR(var) var -#endif /* SMP */ +#define __percpu %__percpu_seg: +#else +#define __percpu +#endif + +#define PER_CPU_VAR(var) __percpu(var)__percpu_rel #ifdef CONFIG_X86_64_SMP #define INIT_PER_CPU_VAR(var) init_per_cpu__##var @@ -24,30 +28,84 @@ #else /* ...!ASSEMBLY */ +#include <linux/build_bug.h> #include <linux/stringify.h> #include <asm/asm.h> #ifdef CONFIG_SMP + +#ifdef CONFIG_CC_HAS_NAMED_AS + +#ifdef __CHECKER__ +#define __seg_gs __attribute__((address_space(__seg_gs))) +#define __seg_fs __attribute__((address_space(__seg_fs))) +#endif + +#ifdef CONFIG_X86_64 +#define __percpu_seg_override __seg_gs +#else +#define __percpu_seg_override __seg_fs +#endif + +#define __percpu_prefix "" + +#else /* CONFIG_CC_HAS_NAMED_AS */ + +#define __percpu_seg_override #define __percpu_prefix "%%"__stringify(__percpu_seg)":" + +#endif /* CONFIG_CC_HAS_NAMED_AS */ + +#define __force_percpu_prefix "%%"__stringify(__percpu_seg)":" #define __my_cpu_offset this_cpu_read(this_cpu_off) +#ifdef CONFIG_USE_X86_SEG_SUPPORT +/* + * Efficient implementation for cases in which the compiler supports + * named address spaces. Allows the compiler to perform additional + * optimizations that can save more instructions. + */ +#define arch_raw_cpu_ptr(ptr) \ +({ \ + unsigned long tcp_ptr__; \ + tcp_ptr__ = __raw_cpu_read(, this_cpu_off); \ + \ + tcp_ptr__ += (unsigned long)(ptr); \ + (typeof(*(ptr)) __kernel __force *)tcp_ptr__; \ +}) +#else /* CONFIG_USE_X86_SEG_SUPPORT */ /* * Compared to the generic __my_cpu_offset version, the following * saves one instruction and avoids clobbering a temp register. */ -#define arch_raw_cpu_ptr(ptr) \ -({ \ - unsigned long tcp_ptr__; \ - asm ("add " __percpu_arg(1) ", %0" \ - : "=r" (tcp_ptr__) \ - : "m" (this_cpu_off), "0" (ptr)); \ - (typeof(*(ptr)) __kernel __force *)tcp_ptr__; \ +#define arch_raw_cpu_ptr(ptr) \ +({ \ + unsigned long tcp_ptr__; \ + asm ("mov " __percpu_arg(1) ", %0" \ + : "=r" (tcp_ptr__) \ + : "m" (__my_cpu_var(this_cpu_off))); \ + \ + tcp_ptr__ += (unsigned long)(ptr); \ + (typeof(*(ptr)) __kernel __force *)tcp_ptr__; \ }) -#else +#endif /* CONFIG_USE_X86_SEG_SUPPORT */ + +#define PER_CPU_VAR(var) %__percpu_seg:(var)__percpu_rel + +#else /* CONFIG_SMP */ +#define __percpu_seg_override #define __percpu_prefix "" -#endif +#define __force_percpu_prefix "" + +#define PER_CPU_VAR(var) (var)__percpu_rel +#endif /* CONFIG_SMP */ + +#define __my_cpu_type(var) typeof(var) __percpu_seg_override +#define __my_cpu_ptr(ptr) (__my_cpu_type(*ptr) *)(uintptr_t)(ptr) +#define __my_cpu_var(var) (*__my_cpu_ptr(&var)) #define __percpu_arg(x) __percpu_prefix "%" #x +#define __force_percpu_arg(x) __force_percpu_prefix "%" #x /* * Initialized pointers to per-cpu variables needed for the boot @@ -107,14 +165,14 @@ do { \ (void)pto_tmp__; \ } \ asm qual(__pcpu_op2_##size(op, "%[val]", __percpu_arg([var])) \ - : [var] "+m" (_var) \ + : [var] "+m" (__my_cpu_var(_var)) \ : [val] __pcpu_reg_imm_##size(pto_val__)); \ } while (0) #define percpu_unary_op(size, qual, op, _var) \ ({ \ asm qual (__pcpu_op1_##size(op, __percpu_arg([var])) \ - : [var] "+m" (_var)); \ + : [var] "+m" (__my_cpu_var(_var))); \ }) /* @@ -144,16 +202,16 @@ do { \ __pcpu_type_##size pfo_val__; \ asm qual (__pcpu_op2_##size(op, __percpu_arg([var]), "%[val]") \ : [val] __pcpu_reg_##size("=", pfo_val__) \ - : [var] "m" (_var)); \ + : [var] "m" (__my_cpu_var(_var))); \ (typeof(_var))(unsigned long) pfo_val__; \ }) #define percpu_stable_op(size, op, _var) \ ({ \ __pcpu_type_##size pfo_val__; \ - asm(__pcpu_op2_##size(op, __percpu_arg(P[var]), "%[val]") \ + asm(__pcpu_op2_##size(op, __force_percpu_arg(a[var]), "%[val]") \ : [val] __pcpu_reg_##size("=", pfo_val__) \ - : [var] "p" (&(_var))); \ + : [var] "i" (&(_var))); \ (typeof(_var))(unsigned long) pfo_val__; \ }) @@ -166,7 +224,7 @@ do { \ asm qual (__pcpu_op2_##size("xadd", "%[tmp]", \ __percpu_arg([var])) \ : [tmp] __pcpu_reg_##size("+", paro_tmp__), \ - [var] "+m" (_var) \ + [var] "+m" (__my_cpu_var(_var)) \ : : "memory"); \ (typeof(_var))(unsigned long) (paro_tmp__ + _val); \ }) @@ -187,7 +245,7 @@ do { \ __percpu_arg([var])) \ "\n\tjnz 1b" \ : [oval] "=&a" (pxo_old__), \ - [var] "+m" (_var) \ + [var] "+m" (__my_cpu_var(_var)) \ : [nval] __pcpu_reg_##size(, pxo_new__) \ : "memory"); \ (typeof(_var))(unsigned long) pxo_old__; \ @@ -204,7 +262,7 @@ do { \ asm qual (__pcpu_op2_##size("cmpxchg", "%[nval]", \ __percpu_arg([var])) \ : [oval] "+a" (pco_old__), \ - [var] "+m" (_var) \ + [var] "+m" (__my_cpu_var(_var)) \ : [nval] __pcpu_reg_##size(, pco_new__) \ : "memory"); \ (typeof(_var))(unsigned long) pco_old__; \ @@ -221,7 +279,7 @@ do { \ CC_SET(z) \ : CC_OUT(z) (success), \ [oval] "+a" (pco_old__), \ - [var] "+m" (_var) \ + [var] "+m" (__my_cpu_var(_var)) \ : [nval] __pcpu_reg_##size(, pco_new__) \ : "memory"); \ if (unlikely(!success)) \ @@ -244,7 +302,7 @@ do { \ \ asm qual (ALTERNATIVE("call this_cpu_cmpxchg8b_emu", \ "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \ - : [var] "+m" (_var), \ + : [var] "+m" (__my_cpu_var(_var)), \ "+a" (old__.low), \ "+d" (old__.high) \ : "b" (new__.low), \ @@ -276,7 +334,7 @@ do { \ "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \ CC_SET(z) \ : CC_OUT(z) (success), \ - [var] "+m" (_var), \ + [var] "+m" (__my_cpu_var(_var)), \ "+a" (old__.low), \ "+d" (old__.high) \ : "b" (new__.low), \ @@ -313,7 +371,7 @@ do { \ \ asm qual (ALTERNATIVE("call this_cpu_cmpxchg16b_emu", \ "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \ - : [var] "+m" (_var), \ + : [var] "+m" (__my_cpu_var(_var)), \ "+a" (old__.low), \ "+d" (old__.high) \ : "b" (new__.low), \ @@ -345,7 +403,7 @@ do { \ "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \ CC_SET(z) \ : CC_OUT(z) (success), \ - [var] "+m" (_var), \ + [var] "+m" (__my_cpu_var(_var)), \ "+a" (old__.low), \ "+d" (old__.high) \ : "b" (new__.low), \ @@ -366,9 +424,9 @@ do { \ * accessed while this_cpu_read_stable() allows the value to be cached. * this_cpu_read_stable() is more efficient and can be used if its value * is guaranteed to be valid across cpus. The current users include - * get_current() and get_thread_info() both of which are actually - * per-thread variables implemented as per-cpu variables and thus - * stable for the duration of the respective task. + * pcpu_hot.current_task and pcpu_hot.top_of_stack, both of which are + * actually per-thread variables implemented as per-CPU variables and + * thus stable for the duration of the respective task. */ #define this_cpu_read_stable_1(pcp) percpu_stable_op(1, "mov", pcp) #define this_cpu_read_stable_2(pcp) percpu_stable_op(2, "mov", pcp) @@ -376,13 +434,72 @@ do { \ #define this_cpu_read_stable_8(pcp) percpu_stable_op(8, "mov", pcp) #define this_cpu_read_stable(pcp) __pcpu_size_call_return(this_cpu_read_stable_, pcp) +#ifdef CONFIG_USE_X86_SEG_SUPPORT + +#define __raw_cpu_read(qual, pcp) \ +({ \ + *(qual __my_cpu_type(pcp) *)__my_cpu_ptr(&(pcp)); \ +}) + +#define __raw_cpu_write(qual, pcp, val) \ +do { \ + *(qual __my_cpu_type(pcp) *)__my_cpu_ptr(&(pcp)) = (val); \ +} while (0) + +#define raw_cpu_read_1(pcp) __raw_cpu_read(, pcp) +#define raw_cpu_read_2(pcp) __raw_cpu_read(, pcp) +#define raw_cpu_read_4(pcp) __raw_cpu_read(, pcp) +#define raw_cpu_write_1(pcp, val) __raw_cpu_write(, pcp, val) +#define raw_cpu_write_2(pcp, val) __raw_cpu_write(, pcp, val) +#define raw_cpu_write_4(pcp, val) __raw_cpu_write(, pcp, val) + +#define this_cpu_read_1(pcp) __raw_cpu_read(volatile, pcp) +#define this_cpu_read_2(pcp) __raw_cpu_read(volatile, pcp) +#define this_cpu_read_4(pcp) __raw_cpu_read(volatile, pcp) +#define this_cpu_write_1(pcp, val) __raw_cpu_write(volatile, pcp, val) +#define this_cpu_write_2(pcp, val) __raw_cpu_write(volatile, pcp, val) +#define this_cpu_write_4(pcp, val) __raw_cpu_write(volatile, pcp, val) + +#ifdef CONFIG_X86_64 +#define raw_cpu_read_8(pcp) __raw_cpu_read(, pcp) +#define raw_cpu_write_8(pcp, val) __raw_cpu_write(, pcp, val) + +#define this_cpu_read_8(pcp) __raw_cpu_read(volatile, pcp) +#define this_cpu_write_8(pcp, val) __raw_cpu_write(volatile, pcp, val) +#endif + +#define this_cpu_read_const(pcp) __raw_cpu_read(, pcp) +#else /* CONFIG_USE_X86_SEG_SUPPORT */ + #define raw_cpu_read_1(pcp) percpu_from_op(1, , "mov", pcp) #define raw_cpu_read_2(pcp) percpu_from_op(2, , "mov", pcp) #define raw_cpu_read_4(pcp) percpu_from_op(4, , "mov", pcp) - #define raw_cpu_write_1(pcp, val) percpu_to_op(1, , "mov", (pcp), val) #define raw_cpu_write_2(pcp, val) percpu_to_op(2, , "mov", (pcp), val) #define raw_cpu_write_4(pcp, val) percpu_to_op(4, , "mov", (pcp), val) + +#define this_cpu_read_1(pcp) percpu_from_op(1, volatile, "mov", pcp) +#define this_cpu_read_2(pcp) percpu_from_op(2, volatile, "mov", pcp) +#define this_cpu_read_4(pcp) percpu_from_op(4, volatile, "mov", pcp) +#define this_cpu_write_1(pcp, val) percpu_to_op(1, volatile, "mov", (pcp), val) +#define this_cpu_write_2(pcp, val) percpu_to_op(2, volatile, "mov", (pcp), val) +#define this_cpu_write_4(pcp, val) percpu_to_op(4, volatile, "mov", (pcp), val) + +#ifdef CONFIG_X86_64 +#define raw_cpu_read_8(pcp) percpu_from_op(8, , "mov", pcp) +#define raw_cpu_write_8(pcp, val) percpu_to_op(8, , "mov", (pcp), val) + +#define this_cpu_read_8(pcp) percpu_from_op(8, volatile, "mov", pcp) +#define this_cpu_write_8(pcp, val) percpu_to_op(8, volatile, "mov", (pcp), val) +#endif + +/* + * The generic per-cpu infrastrucutre is not suitable for + * reading const-qualified variables. + */ +#define this_cpu_read_const(pcp) ({ BUILD_BUG(); (typeof(pcp))0; }) +#endif /* CONFIG_USE_X86_SEG_SUPPORT */ + #define raw_cpu_add_1(pcp, val) percpu_add_op(1, , (pcp), val) #define raw_cpu_add_2(pcp, val) percpu_add_op(2, , (pcp), val) #define raw_cpu_add_4(pcp, val) percpu_add_op(4, , (pcp), val) @@ -408,12 +525,6 @@ do { \ #define raw_cpu_xchg_2(pcp, val) raw_percpu_xchg_op(pcp, val) #define raw_cpu_xchg_4(pcp, val) raw_percpu_xchg_op(pcp, val) -#define this_cpu_read_1(pcp) percpu_from_op(1, volatile, "mov", pcp) -#define this_cpu_read_2(pcp) percpu_from_op(2, volatile, "mov", pcp) -#define this_cpu_read_4(pcp) percpu_from_op(4, volatile, "mov", pcp) -#define this_cpu_write_1(pcp, val) percpu_to_op(1, volatile, "mov", (pcp), val) -#define this_cpu_write_2(pcp, val) percpu_to_op(2, volatile, "mov", (pcp), val) -#define this_cpu_write_4(pcp, val) percpu_to_op(4, volatile, "mov", (pcp), val) #define this_cpu_add_1(pcp, val) percpu_add_op(1, volatile, (pcp), val) #define this_cpu_add_2(pcp, val) percpu_add_op(2, volatile, (pcp), val) #define this_cpu_add_4(pcp, val) percpu_add_op(4, volatile, (pcp), val) @@ -452,8 +563,6 @@ do { \ * 32 bit must fall back to generic operations. */ #ifdef CONFIG_X86_64 -#define raw_cpu_read_8(pcp) percpu_from_op(8, , "mov", pcp) -#define raw_cpu_write_8(pcp, val) percpu_to_op(8, , "mov", (pcp), val) #define raw_cpu_add_8(pcp, val) percpu_add_op(8, , (pcp), val) #define raw_cpu_and_8(pcp, val) percpu_to_op(8, , "and", (pcp), val) #define raw_cpu_or_8(pcp, val) percpu_to_op(8, , "or", (pcp), val) @@ -462,8 +571,6 @@ do { \ #define raw_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(8, , pcp, oval, nval) #define raw_cpu_try_cmpxchg_8(pcp, ovalp, nval) percpu_try_cmpxchg_op(8, , pcp, ovalp, nval) -#define this_cpu_read_8(pcp) percpu_from_op(8, volatile, "mov", pcp) -#define this_cpu_write_8(pcp, val) percpu_to_op(8, volatile, "mov", (pcp), val) #define this_cpu_add_8(pcp, val) percpu_add_op(8, volatile, (pcp), val) #define this_cpu_and_8(pcp, val) percpu_to_op(8, volatile, "and", (pcp), val) #define this_cpu_or_8(pcp, val) percpu_to_op(8, volatile, "or", (pcp), val) @@ -494,7 +601,7 @@ static inline bool x86_this_cpu_variable_test_bit(int nr, asm volatile("btl "__percpu_arg(2)",%1" CC_SET(c) : CC_OUT(c) (oldbit) - : "m" (*(unsigned long __percpu *)addr), "Ir" (nr)); + : "m" (*__my_cpu_ptr((unsigned long __percpu *)(addr))), "Ir" (nr)); return oldbit; } diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h index c7ec5bb88334..dcd836b59beb 100644 --- a/arch/x86/include/asm/pgalloc.h +++ b/arch/x86/include/asm/pgalloc.h @@ -34,7 +34,7 @@ static inline void paravirt_release_p4d(unsigned long pfn) {} */ extern gfp_t __userpte_alloc_gfp; -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION /* * Instead of one PGD, we acquire two PGDs. Being order-1, it is * both 8k in size and 8k-aligned. That lets us just flip bit 12 diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h index 9e7c0b719c3c..dabafba957ea 100644 --- a/arch/x86/include/asm/pgtable-3level.h +++ b/arch/x86/include/asm/pgtable-3level.h @@ -52,7 +52,7 @@ static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd) static inline void native_set_pud(pud_t *pudp, pud_t pud) { -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION pud.p4d.pgd = pti_set_user_pgtbl(&pudp->p4d.pgd, pud.p4d.pgd); #endif pxx_xchg64(pud, pudp, native_pud_val(pud)); diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 9d077bca6a10..df0f7d4a96f3 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -909,7 +909,7 @@ static inline int is_new_memtype_allowed(u64 paddr, unsigned long size, pmd_t *populate_extra_pmd(unsigned long vaddr); pte_t *populate_extra_pte(unsigned long vaddr); -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd); /* @@ -923,12 +923,12 @@ static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd) return pgd; return __pti_set_user_pgtbl(pgdp, pgd); } -#else /* CONFIG_PAGE_TABLE_ISOLATION */ +#else /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */ static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd) { return pgd; } -#endif /* CONFIG_PAGE_TABLE_ISOLATION */ +#endif /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */ #endif /* __ASSEMBLY__ */ @@ -1131,7 +1131,7 @@ static inline int p4d_bad(p4d_t p4d) { unsigned long ignore_flags = _KERNPG_TABLE | _PAGE_USER; - if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) + if (IS_ENABLED(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION)) ignore_flags |= _PAGE_NX; return (p4d_flags(p4d) & ~ignore_flags) != 0; @@ -1177,7 +1177,7 @@ static inline int pgd_bad(pgd_t pgd) if (!pgtable_l5_enabled()) return 0; - if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) + if (IS_ENABLED(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION)) ignore_flags |= _PAGE_NX; return (pgd_flags(pgd) & ~ignore_flags) != _KERNPG_TABLE; @@ -1422,9 +1422,9 @@ static inline bool pgdp_maps_userspace(void *__ptr) #define pgd_leaf pgd_large static inline int pgd_large(pgd_t pgd) { return 0; } -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION /* - * All top-level PAGE_TABLE_ISOLATION page tables are order-1 pages + * All top-level MITIGATION_PAGE_TABLE_ISOLATION page tables are order-1 pages * (8k-aligned and 8k in size). The kernel one is at the beginning 4k and * the user one is in the last 4k. To switch between them, you * just need to flip the 12th bit in their addresses. @@ -1469,7 +1469,7 @@ static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp) { return ptr_clear_bit(p4dp, PTI_PGTABLE_SWITCH_BIT); } -#endif /* CONFIG_PAGE_TABLE_ISOLATION */ +#endif /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */ /* * clone_pgd_range(pgd_t *dst, pgd_t *src, int count); @@ -1484,7 +1484,7 @@ static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp) static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count) { memcpy(dst, src, count * sizeof(pgd_t)); -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION if (!static_cpu_has(X86_FEATURE_PTI)) return; /* Clone the user space pgd as well */ diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 24af25b1551a..7e9db77231ac 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -143,7 +143,8 @@ static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d) { pgd_t pgd; - if (pgtable_l5_enabled() || !IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) { + if (pgtable_l5_enabled() || + !IS_ENABLED(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION)) { WRITE_ONCE(*p4dp, p4d); return; } diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index 38b54b992f32..9053dfe9fa03 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -21,9 +21,9 @@ typedef unsigned long pgprotval_t; typedef struct { pteval_t pte; } pte_t; typedef struct { pmdval_t pmd; } pmd_t; -#ifdef CONFIG_X86_5LEVEL extern unsigned int __pgtable_l5_enabled; +#ifdef CONFIG_X86_5LEVEL #ifdef USE_EARLY_PGTABLE_L5 /* * cpu_feature_enabled() is not available in early boot code. diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h index af77235fded6..919909d8cb77 100644 --- a/arch/x86/include/asm/preempt.h +++ b/arch/x86/include/asm/preempt.h @@ -91,7 +91,7 @@ static __always_inline void __preempt_count_sub(int val) */ static __always_inline bool __preempt_count_dec_and_test(void) { - return GEN_UNARY_RMWcc("decl", pcpu_hot.preempt_count, e, + return GEN_UNARY_RMWcc("decl", __my_cpu_var(pcpu_hot.preempt_count), e, __percpu_arg([var])); } diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h index d8cccadc83a6..e5f204b9b33d 100644 --- a/arch/x86/include/asm/processor-flags.h +++ b/arch/x86/include/asm/processor-flags.h @@ -51,7 +51,7 @@ #define CR3_NOFLUSH 0 #endif -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION # define X86_CR3_PTI_PCID_USER_BIT 11 #endif diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 89cf39dbd306..811548f131f4 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -20,7 +20,6 @@ struct vm86; #include <asm/page.h> #include <asm/pgtable_types.h> #include <asm/percpu.h> -#include <asm/msr.h> #include <asm/desc_defs.h> #include <asm/nops.h> #include <asm/special_insns.h> @@ -185,13 +184,8 @@ extern struct cpuinfo_x86 new_cpu_data; extern __u32 cpu_caps_cleared[NCAPINTS + NBUGINTS]; extern __u32 cpu_caps_set[NCAPINTS + NBUGINTS]; -#ifdef CONFIG_SMP DECLARE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info); #define cpu_data(cpu) per_cpu(cpu_info, cpu) -#else -#define cpu_info boot_cpu_data -#define cpu_data(cpu) boot_cpu_data -#endif extern const struct seq_operations cpuinfo_op; @@ -532,6 +526,9 @@ static __always_inline unsigned long current_top_of_stack(void) * and around vm86 mode and sp0 on x86_64 is special because of the * entry trampoline. */ + if (IS_ENABLED(CONFIG_USE_X86_SEG_SUPPORT)) + return this_cpu_read_const(const_pcpu_hot.top_of_stack); + return this_cpu_read_stable(pcpu_hot.top_of_stack); } @@ -554,7 +551,7 @@ static inline void load_sp0(unsigned long sp0) unsigned long __get_wchan(struct task_struct *p); -extern void select_idle_routine(const struct cpuinfo_x86 *c); +extern void select_idle_routine(void); extern void amd_e400_c1e_apic_setup(void); extern unsigned long boot_option_idle_override; @@ -575,28 +572,6 @@ extern void cpu_init(void); extern void cpu_init_exception_handling(void); extern void cr4_init(void); -static inline unsigned long get_debugctlmsr(void) -{ - unsigned long debugctlmsr = 0; - -#ifndef CONFIG_X86_DEBUGCTLMSR - if (boot_cpu_data.x86 < 6) - return 0; -#endif - rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr); - - return debugctlmsr; -} - -static inline void update_debugctlmsr(unsigned long debugctlmsr) -{ -#ifndef CONFIG_X86_DEBUGCTLMSR - if (boot_cpu_data.x86 < 6) - return; -#endif - wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr); -} - extern void set_task_blockstep(struct task_struct *task, bool on); /* Boot loader type from the setup header: */ diff --git a/arch/x86/include/asm/pti.h b/arch/x86/include/asm/pti.h index 07375b476c4f..ab167c96b9ab 100644 --- a/arch/x86/include/asm/pti.h +++ b/arch/x86/include/asm/pti.h @@ -3,7 +3,7 @@ #define _ASM_X86_PTI_H #ifndef __ASSEMBLY__ -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION extern void pti_init(void); extern void pti_check_boottime_disable(void); extern void pti_finalize(void); diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h index 255a78d9d906..12dbd2588ca7 100644 --- a/arch/x86/include/asm/resctrl.h +++ b/arch/x86/include/asm/resctrl.h @@ -7,6 +7,13 @@ #include <linux/sched.h> #include <linux/jump_label.h> +/* + * This value can never be a valid CLOSID, and is used when mapping a + * (closid, rmid) pair to an index and back. On x86 only the RMID is + * needed. The index is a software defined value. + */ +#define X86_RESCTRL_EMPTY_CLOSID ((u32)~0) + /** * struct resctrl_pqr_state - State cache for the PQR MSR * @cur_rmid: The cached Resource Monitoring ID @@ -31,10 +38,47 @@ struct resctrl_pqr_state { DECLARE_PER_CPU(struct resctrl_pqr_state, pqr_state); +extern bool rdt_alloc_capable; +extern bool rdt_mon_capable; + DECLARE_STATIC_KEY_FALSE(rdt_enable_key); DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key); DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key); +static inline bool resctrl_arch_alloc_capable(void) +{ + return rdt_alloc_capable; +} + +static inline void resctrl_arch_enable_alloc(void) +{ + static_branch_enable_cpuslocked(&rdt_alloc_enable_key); + static_branch_inc_cpuslocked(&rdt_enable_key); +} + +static inline void resctrl_arch_disable_alloc(void) +{ + static_branch_disable_cpuslocked(&rdt_alloc_enable_key); + static_branch_dec_cpuslocked(&rdt_enable_key); +} + +static inline bool resctrl_arch_mon_capable(void) +{ + return rdt_mon_capable; +} + +static inline void resctrl_arch_enable_mon(void) +{ + static_branch_enable_cpuslocked(&rdt_mon_enable_key); + static_branch_inc_cpuslocked(&rdt_enable_key); +} + +static inline void resctrl_arch_disable_mon(void) +{ + static_branch_disable_cpuslocked(&rdt_mon_enable_key); + static_branch_dec_cpuslocked(&rdt_enable_key); +} + /* * __resctrl_sched_in() - Writes the task's CLOSid/RMID to IA32_PQR_MSR * @@ -88,12 +132,58 @@ static inline unsigned int resctrl_arch_round_mon_val(unsigned int val) return val * scale; } +static inline void resctrl_arch_set_closid_rmid(struct task_struct *tsk, + u32 closid, u32 rmid) +{ + WRITE_ONCE(tsk->closid, closid); + WRITE_ONCE(tsk->rmid, rmid); +} + +static inline bool resctrl_arch_match_closid(struct task_struct *tsk, u32 closid) +{ + return READ_ONCE(tsk->closid) == closid; +} + +static inline bool resctrl_arch_match_rmid(struct task_struct *tsk, u32 ignored, + u32 rmid) +{ + return READ_ONCE(tsk->rmid) == rmid; +} + static inline void resctrl_sched_in(struct task_struct *tsk) { if (static_branch_likely(&rdt_enable_key)) __resctrl_sched_in(tsk); } +static inline u32 resctrl_arch_system_num_rmid_idx(void) +{ + /* RMID are independent numbers for x86. num_rmid_idx == num_rmid */ + return boot_cpu_data.x86_cache_max_rmid + 1; +} + +static inline void resctrl_arch_rmid_idx_decode(u32 idx, u32 *closid, u32 *rmid) +{ + *rmid = idx; + *closid = X86_RESCTRL_EMPTY_CLOSID; +} + +static inline u32 resctrl_arch_rmid_idx_encode(u32 ignored, u32 rmid) +{ + return rmid; +} + +/* x86 can always read an rmid, nothing needs allocating */ +struct rdt_resource; +static inline void *resctrl_arch_mon_ctx_alloc(struct rdt_resource *r, int evtid) +{ + might_sleep(); + return NULL; +}; + +static inline void resctrl_arch_mon_ctx_free(struct rdt_resource *r, int evtid, + void *ctx) { }; + void resctrl_cpu_detect(struct cpuinfo_x86 *c); #else diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 5c83729c8e71..e61e68d71cba 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -48,7 +48,7 @@ extern unsigned long saved_video_mode; extern void reserve_standard_io_resources(void); extern void i386_reserve_resources(void); extern unsigned long __startup_64(unsigned long physaddr, struct boot_params *bp); -extern void startup_64_setup_env(unsigned long physbase); +extern void startup_64_setup_gdt_idt(void); extern void early_setup_idt(void); extern void __init do_early_exception(struct pt_regs *regs, int trapnr); diff --git a/arch/x86/include/asm/setup_data.h b/arch/x86/include/asm/setup_data.h new file mode 100644 index 000000000000..77c51111a893 --- /dev/null +++ b/arch/x86/include/asm/setup_data.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SETUP_DATA_H +#define _ASM_X86_SETUP_DATA_H + +#include <uapi/asm/setup_data.h> + +#ifndef __ASSEMBLY__ + +struct pci_setup_rom { + struct setup_data data; + uint16_t vendor; + uint16_t devid; + uint64_t pcilen; + unsigned long segment; + unsigned long bus; + unsigned long device; + unsigned long function; + uint8_t romdata[]; +}; + +/* kexec external ABI */ +struct efi_setup_data { + u64 fw_vendor; + u64 __unused; + u64 tables; + u64 smbios; + u64 reserved[8]; +}; + +#endif /* __ASSEMBLY__ */ + +#endif /* _ASM_X86_SETUP_DATA_H */ diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index 5b4a1ce3d368..9477b4053bce 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -13,7 +13,6 @@ #include <asm/insn.h> #include <asm/sev-common.h> -#include <asm/bootparam.h> #include <asm/coco.h> #define GHCB_PROTOCOL_MIN 1ULL @@ -22,6 +21,8 @@ #define VMGEXIT() { asm volatile("rep; vmmcall\n\r"); } +struct boot_params; + enum es_result { ES_OK, /* All good */ ES_UNSUPPORTED, /* Requested operation not supported */ @@ -87,9 +88,23 @@ extern bool handle_vc_boot_ghcb(struct pt_regs *regs); /* Software defined (when rFlags.CF = 1) */ #define PVALIDATE_FAIL_NOUPDATE 255 +/* RMUPDATE detected 4K page and 2MB page overlap. */ +#define RMPUPDATE_FAIL_OVERLAP 4 + /* RMP page size */ #define RMP_PG_SIZE_4K 0 #define RMP_PG_SIZE_2M 1 +#define RMP_TO_PG_LEVEL(level) (((level) == RMP_PG_SIZE_4K) ? PG_LEVEL_4K : PG_LEVEL_2M) +#define PG_LEVEL_TO_RMP(level) (((level) == PG_LEVEL_4K) ? RMP_PG_SIZE_4K : RMP_PG_SIZE_2M) + +struct rmp_state { + u64 gpa; + u8 assigned; + u8 pagesize; + u8 immutable; + u8 rsvd; + u32 asid; +} __packed; #define RMPADJUST_VMSA_PAGE_BIT BIT(16) @@ -199,20 +214,22 @@ static inline int pvalidate(unsigned long vaddr, bool rmp_psize, bool validate) struct snp_guest_request_ioctl; void setup_ghcb(void); -void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, - unsigned long npages); -void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr, - unsigned long npages); +void early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, + unsigned long npages); +void early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr, + unsigned long npages); void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op); void snp_set_memory_shared(unsigned long vaddr, unsigned long npages); void snp_set_memory_private(unsigned long vaddr, unsigned long npages); void snp_set_wakeup_secondary_cpu(void); bool snp_init(struct boot_params *bp); -void __init __noreturn snp_abort(void); +void __noreturn snp_abort(void); int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct snp_guest_request_ioctl *rio); void snp_accept_memory(phys_addr_t start, phys_addr_t end); u64 snp_get_unsupported_features(u64 status); u64 sev_get_status(void); +void kdump_sev_callback(void); +void sev_show_status(void); #else static inline void sev_es_ist_enter(struct pt_regs *regs) { } static inline void sev_es_ist_exit(void) { } @@ -241,6 +258,30 @@ static inline int snp_issue_guest_request(u64 exit_code, struct snp_req_data *in static inline void snp_accept_memory(phys_addr_t start, phys_addr_t end) { } static inline u64 snp_get_unsupported_features(u64 status) { return 0; } static inline u64 sev_get_status(void) { return 0; } +static inline void kdump_sev_callback(void) { } +static inline void sev_show_status(void) { } +#endif + +#ifdef CONFIG_KVM_AMD_SEV +bool snp_probe_rmptable_info(void); +int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level); +void snp_dump_hva_rmpentry(unsigned long address); +int psmash(u64 pfn); +int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, u32 asid, bool immutable); +int rmp_make_shared(u64 pfn, enum pg_level level); +void snp_leak_pages(u64 pfn, unsigned int npages); +#else +static inline bool snp_probe_rmptable_info(void) { return false; } +static inline int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level) { return -ENODEV; } +static inline void snp_dump_hva_rmpentry(unsigned long address) {} +static inline int psmash(u64 pfn) { return -ENODEV; } +static inline int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, u32 asid, + bool immutable) +{ + return -ENODEV; +} +static inline int rmp_make_shared(u64 pfn, enum pg_level level) { return -ENODEV; } +static inline void snp_leak_pages(u64 pfn, unsigned int npages) {} #endif #endif diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 54d6d71e0eca..a35936b512fe 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -56,11 +56,6 @@ static inline void stop_other_cpus(void) smp_ops.stop_other_cpus(1); } -static inline void smp_prepare_boot_cpu(void) -{ - smp_ops.smp_prepare_boot_cpu(); -} - static inline void smp_prepare_cpus(unsigned int max_cpus) { smp_ops.smp_prepare_cpus(max_cpus); diff --git a/arch/x86/include/asm/spec-ctrl.h b/arch/x86/include/asm/spec-ctrl.h index c648502e4535..658b690b2ccb 100644 --- a/arch/x86/include/asm/spec-ctrl.h +++ b/arch/x86/include/asm/spec-ctrl.h @@ -96,4 +96,6 @@ static inline void speculative_store_bypass_ht_init(void) { } extern void speculation_ctrl_update(unsigned long tif); extern void speculation_ctrl_update_current(void); +extern bool itlb_multihit_kvm_mitigation; + #endif diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index 48f8dd47cf68..2e9fc5c400cd 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -2,11 +2,11 @@ #ifndef _ASM_X86_SPECIAL_INSNS_H #define _ASM_X86_SPECIAL_INSNS_H - #ifdef __KERNEL__ - #include <asm/nops.h> #include <asm/processor-flags.h> + +#include <linux/errno.h> #include <linux/irqflags.h> #include <linux/jump_label.h> @@ -224,10 +224,10 @@ static inline void serialize(void) } /* The dst parameter must be 64-bytes aligned */ -static inline void movdir64b(void __iomem *dst, const void *src) +static inline void movdir64b(void *dst, const void *src) { const struct { char _[64]; } *__src = src; - struct { char _[64]; } __iomem *__dst = dst; + struct { char _[64]; } *__dst = dst; /* * MOVDIR64B %(rdx), rax. @@ -245,6 +245,11 @@ static inline void movdir64b(void __iomem *dst, const void *src) : "m" (*__src), "a" (__dst), "d" (__src)); } +static inline void movdir64b_io(void __iomem *dst, const void *src) +{ + movdir64b((void __force *)dst, src); +} + /** * enqcmds - Enqueue a command in supervisor (CPL0) mode * @dst: destination, in MMIO space (must be 512-bit aligned) diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h index 343b722ccaf2..125c407e2abe 100644 --- a/arch/x86/include/asm/static_call.h +++ b/arch/x86/include/asm/static_call.h @@ -46,7 +46,7 @@ #define ARCH_DEFINE_STATIC_CALL_TRAMP(name, func) \ __ARCH_DEFINE_STATIC_CALL_TRAMP(name, ".byte 0xe9; .long " #func " - (. + 4)") -#ifdef CONFIG_RETHUNK +#ifdef CONFIG_MITIGATION_RETHUNK #define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) \ __ARCH_DEFINE_STATIC_CALL_TRAMP(name, "jmp __x86_return_thunk") #else diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h index 0b70653a98c1..345aafbc1964 100644 --- a/arch/x86/include/asm/text-patching.h +++ b/arch/x86/include/asm/text-patching.h @@ -15,6 +15,8 @@ extern void text_poke_early(void *addr, const void *opcode, size_t len); +extern void apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len); + /* * Clear and restore the kernel write-protection flag on the local CPU. * Allows the kernel to edit read-only pages. diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 76b1d87f1531..abe3a8f22cbd 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -224,7 +224,7 @@ static inline bool topology_is_primary_thread(unsigned int cpu) static inline int topology_phys_to_logical_pkg(unsigned int pkg) { return 0; } static inline int topology_max_smt_threads(void) { return 1; } static inline bool topology_is_primary_thread(unsigned int cpu) { return true; } -static inline unsigned int topology_amd_nodes_per_pkg(void) { return 0; }; +static inline unsigned int topology_amd_nodes_per_pkg(void) { return 1; } #endif /* !CONFIG_SMP */ static inline void arch_fix_phys_package_id(int num, u32 slot) diff --git a/arch/x86/include/asm/trap_pf.h b/arch/x86/include/asm/trap_pf.h index afa524325e55..a23a7b707b64 100644 --- a/arch/x86/include/asm/trap_pf.h +++ b/arch/x86/include/asm/trap_pf.h @@ -2,6 +2,8 @@ #ifndef _ASM_X86_TRAP_PF_H #define _ASM_X86_TRAP_PF_H +#include <linux/bits.h> + /* * Page fault error code bits: * @@ -13,16 +15,18 @@ * bit 5 == 1: protection keys block access * bit 6 == 1: shadow stack access fault * bit 15 == 1: SGX MMU page-fault + * bit 31 == 1: fault was due to RMP violation */ enum x86_pf_error_code { - X86_PF_PROT = 1 << 0, - X86_PF_WRITE = 1 << 1, - X86_PF_USER = 1 << 2, - X86_PF_RSVD = 1 << 3, - X86_PF_INSTR = 1 << 4, - X86_PF_PK = 1 << 5, - X86_PF_SHSTK = 1 << 6, - X86_PF_SGX = 1 << 15, + X86_PF_PROT = BIT(0), + X86_PF_WRITE = BIT(1), + X86_PF_USER = BIT(2), + X86_PF_RSVD = BIT(3), + X86_PF_INSTR = BIT(4), + X86_PF_PK = BIT(5), + X86_PF_SHSTK = BIT(6), + X86_PF_SGX = BIT(15), + X86_PF_RMP = BIT(31), }; #endif /* _ASM_X86_TRAP_PF_H */ diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h index 594fce0ca744..405efb3e4996 100644 --- a/arch/x86/include/asm/tsc.h +++ b/arch/x86/include/asm/tsc.h @@ -5,8 +5,9 @@ #ifndef _ASM_X86_TSC_H #define _ASM_X86_TSC_H -#include <asm/processor.h> #include <asm/cpufeature.h> +#include <asm/processor.h> +#include <asm/msr.h> /* * Standard way to access the cycle counter. diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index f2c02e4469cc..04789f45ab2b 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -11,6 +11,7 @@ #include <asm/alternative.h> #include <asm/cpufeatures.h> #include <asm/page.h> +#include <asm/percpu.h> #ifdef CONFIG_ADDRESS_MASKING /* @@ -18,14 +19,10 @@ */ static inline unsigned long __untagged_addr(unsigned long addr) { - /* - * Refer tlbstate_untag_mask directly to avoid RIP-relative relocation - * in alternative instructions. The relocation gets wrong when gets - * copied to the target place. - */ asm (ALTERNATIVE("", - "and %%gs:tlbstate_untag_mask, %[addr]\n\t", X86_FEATURE_LAM) - : [addr] "+r" (addr) : "m" (tlbstate_untag_mask)); + "and " __percpu_arg([mask]) ", %[addr]", X86_FEATURE_LAM) + : [addr] "+r" (addr) + : [mask] "m" (__my_cpu_var(tlbstate_untag_mask))); return addr; } @@ -54,7 +51,7 @@ static inline unsigned long __untagged_addr_remote(struct mm_struct *mm, * half and a user half. When cast to a signed type, user pointers * are positive and kernel pointers are negative. */ -#define valid_user_address(x) ((long)(x) >= 0) +#define valid_user_address(x) ((__force long)(x) >= 0) /* * User pointers can have tag bits on x86-64. This scheme tolerates @@ -87,8 +84,9 @@ static inline bool __access_ok(const void __user *ptr, unsigned long size) if (__builtin_constant_p(size <= PAGE_SIZE) && size <= PAGE_SIZE) { return valid_user_address(ptr); } else { - unsigned long sum = size + (unsigned long)ptr; - return valid_user_address(sum) && sum >= (unsigned long)ptr; + unsigned long sum = size + (__force unsigned long)ptr; + + return valid_user_address(sum) && sum >= (__force unsigned long)ptr; } } #define __access_ok __access_ok diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 9ca624749176..b89b40f250e6 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -2,8 +2,6 @@ #ifndef _ASM_X86_PLATFORM_H #define _ASM_X86_PLATFORM_H -#include <asm/bootparam.h> - struct ghcb; struct mpc_bus; struct mpc_cpu; diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index 01d19fc22346..9b82eebd7add 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -2,21 +2,7 @@ #ifndef _ASM_X86_BOOTPARAM_H #define _ASM_X86_BOOTPARAM_H -/* setup_data/setup_indirect types */ -#define SETUP_NONE 0 -#define SETUP_E820_EXT 1 -#define SETUP_DTB 2 -#define SETUP_PCI 3 -#define SETUP_EFI 4 -#define SETUP_APPLE_PROPERTIES 5 -#define SETUP_JAILHOUSE 6 -#define SETUP_CC_BLOB 7 -#define SETUP_IMA 8 -#define SETUP_RNG_SEED 9 -#define SETUP_ENUM_MAX SETUP_RNG_SEED - -#define SETUP_INDIRECT (1<<31) -#define SETUP_TYPE_MAX (SETUP_ENUM_MAX | SETUP_INDIRECT) +#include <asm/setup_data.h> /* ram_size flags */ #define RAMDISK_IMAGE_START_MASK 0x07FF @@ -38,6 +24,7 @@ #define XLF_EFI_KEXEC (1<<4) #define XLF_5LEVEL (1<<5) #define XLF_5LEVEL_ENABLED (1<<6) +#define XLF_MEM_ENCRYPTION (1<<7) #ifndef __ASSEMBLY__ @@ -48,22 +35,6 @@ #include <asm/ist.h> #include <video/edid.h> -/* extensible setup data list node */ -struct setup_data { - __u64 next; - __u32 type; - __u32 len; - __u8 data[]; -}; - -/* extensible setup indirect data node */ -struct setup_indirect { - __u32 type; - __u32 reserved; /* Reserved, must be set to zero. */ - __u64 len; - __u64 addr; -}; - struct setup_header { __u8 setup_sects; __u16 root_flags; @@ -137,50 +108,10 @@ struct efi_info { #define E820_MAX_ENTRIES_ZEROPAGE 128 /* - * The E820 memory region entry of the boot protocol ABI: - */ -struct boot_e820_entry { - __u64 addr; - __u64 size; - __u32 type; -} __attribute__((packed)); - -/* * Smallest compatible version of jailhouse_setup_data required by this kernel. */ #define JAILHOUSE_SETUP_REQUIRED_VERSION 1 -/* - * The boot loader is passing platform information via this Jailhouse-specific - * setup data structure. - */ -struct jailhouse_setup_data { - struct { - __u16 version; - __u16 compatible_version; - } __attribute__((packed)) hdr; - struct { - __u16 pm_timer_address; - __u16 num_cpus; - __u64 pci_mmconfig_base; - __u32 tsc_khz; - __u32 apic_khz; - __u8 standard_ioapic; - __u8 cpu_ids[255]; - } __attribute__((packed)) v1; - struct { - __u32 flags; - } __attribute__((packed)) v2; -} __attribute__((packed)); - -/* - * IMA buffer setup data information from the previous kernel during kexec - */ -struct ima_setup_data { - __u64 addr; - __u64 size; -} __attribute__((packed)); - /* The so-called "zeropage" */ struct boot_params { struct screen_info screen_info; /* 0x000 */ diff --git a/arch/x86/include/uapi/asm/setup_data.h b/arch/x86/include/uapi/asm/setup_data.h new file mode 100644 index 000000000000..b111b0c18544 --- /dev/null +++ b/arch/x86/include/uapi/asm/setup_data.h @@ -0,0 +1,83 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_ASM_X86_SETUP_DATA_H +#define _UAPI_ASM_X86_SETUP_DATA_H + +/* setup_data/setup_indirect types */ +#define SETUP_NONE 0 +#define SETUP_E820_EXT 1 +#define SETUP_DTB 2 +#define SETUP_PCI 3 +#define SETUP_EFI 4 +#define SETUP_APPLE_PROPERTIES 5 +#define SETUP_JAILHOUSE 6 +#define SETUP_CC_BLOB 7 +#define SETUP_IMA 8 +#define SETUP_RNG_SEED 9 +#define SETUP_ENUM_MAX SETUP_RNG_SEED + +#define SETUP_INDIRECT (1<<31) +#define SETUP_TYPE_MAX (SETUP_ENUM_MAX | SETUP_INDIRECT) + +#ifndef __ASSEMBLY__ + +#include <linux/types.h> + +/* extensible setup data list node */ +struct setup_data { + __u64 next; + __u32 type; + __u32 len; + __u8 data[]; +}; + +/* extensible setup indirect data node */ +struct setup_indirect { + __u32 type; + __u32 reserved; /* Reserved, must be set to zero. */ + __u64 len; + __u64 addr; +}; + +/* + * The E820 memory region entry of the boot protocol ABI: + */ +struct boot_e820_entry { + __u64 addr; + __u64 size; + __u32 type; +} __attribute__((packed)); + +/* + * The boot loader is passing platform information via this Jailhouse-specific + * setup data structure. + */ +struct jailhouse_setup_data { + struct { + __u16 version; + __u16 compatible_version; + } __attribute__((packed)) hdr; + struct { + __u16 pm_timer_address; + __u16 num_cpus; + __u64 pci_mmconfig_base; + __u32 tsc_khz; + __u32 apic_khz; + __u8 standard_ioapic; + __u8 cpu_ids[255]; + } __attribute__((packed)) v1; + struct { + __u32 flags; + } __attribute__((packed)) v2; +} __attribute__((packed)); + +/* + * IMA buffer setup data information from the previous kernel during kexec + */ +struct ima_setup_data { + __u64 addr; + __u64 size; +} __attribute__((packed)); + +#endif /* __ASSEMBLY__ */ + +#endif /* _UAPI_ASM_X86_SETUP_DATA_H */ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 0dcbfc1a4c41..d0c744cb2a0e 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -33,6 +33,7 @@ KASAN_SANITIZE_sev.o := n KCSAN_SANITIZE := n KMSAN_SANITIZE_head$(BITS).o := n KMSAN_SANITIZE_nmi.o := n +KMSAN_SANITIZE_sev.o := n # If instrumentation of the following files is enabled, boot hangs during # first second. diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S index d5d8a352eafa..94ff83f3d3fe 100644 --- a/arch/x86/kernel/acpi/wakeup_64.S +++ b/arch/x86/kernel/acpi/wakeup_64.S @@ -17,7 +17,7 @@ * Hooray, we are in Long 64-bit mode (but still running in low memory) */ SYM_FUNC_START(wakeup_long64) - movq saved_magic, %rax + movq saved_magic(%rip), %rax movq $0x123456789abcdef0, %rdx cmpq %rdx, %rax je 2f @@ -33,14 +33,14 @@ SYM_FUNC_START(wakeup_long64) movw %ax, %es movw %ax, %fs movw %ax, %gs - movq saved_rsp, %rsp + movq saved_rsp(%rip), %rsp - movq saved_rbx, %rbx - movq saved_rdi, %rdi - movq saved_rsi, %rsi - movq saved_rbp, %rbp + movq saved_rbx(%rip), %rbx + movq saved_rdi(%rip), %rdi + movq saved_rsi(%rip), %rsi + movq saved_rbp(%rip), %rbp - movq saved_rip, %rax + movq saved_rip(%rip), %rax ANNOTATE_RETPOLINE_SAFE jmp *%rax SYM_FUNC_END(wakeup_long64) @@ -72,11 +72,11 @@ SYM_FUNC_START(do_suspend_lowlevel) movq $.Lresume_point, saved_rip(%rip) - movq %rsp, saved_rsp - movq %rbp, saved_rbp - movq %rbx, saved_rbx - movq %rdi, saved_rdi - movq %rsi, saved_rsi + movq %rsp, saved_rsp(%rip) + movq %rbp, saved_rbp(%rip) + movq %rbx, saved_rbx(%rip) + movq %rdi, saved_rdi(%rip) + movq %rsi, saved_rsi(%rip) addq $8, %rsp movl $3, %edi diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 1d85cb7071cb..ff6e32ec8259 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -45,7 +45,7 @@ EXPORT_SYMBOL_GPL(alternatives_patched); #define DA_ENDBR 0x08 #define DA_SMP 0x10 -static unsigned int __initdata_or_module debug_alternative; +static unsigned int debug_alternative; static int __init debug_alt(char *str) { @@ -133,7 +133,7 @@ const unsigned char * const x86_nops[ASM_NOP_MAX+1] = * each single-byte NOPs). If @len to fill out is > ASM_NOP_MAX, pad with INT3 and * *jump* over instead of executing long and daft NOPs. */ -static void __init_or_module add_nop(u8 *instr, unsigned int len) +static void add_nop(u8 *instr, unsigned int len) { u8 *target = instr + len; @@ -206,7 +206,7 @@ static int skip_nops(u8 *instr, int offset, int len) * Optimize a sequence of NOPs, possibly preceded by an unconditional jump * to the end of the NOP sequence into a single NOP. */ -static bool __init_or_module +static bool __optimize_nops(u8 *instr, size_t len, struct insn *insn, int *next, int *prev, int *target) { int i = *next - insn->length; @@ -335,8 +335,7 @@ bool need_reloc(unsigned long offset, u8 *src, size_t src_len) return (target < src || target > src + src_len); } -static void __init_or_module noinline -apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len) +void apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len) { int prev, target = 0; @@ -545,7 +544,7 @@ static inline bool is_jcc32(struct insn *insn) return insn->opcode.bytes[0] == 0x0f && (insn->opcode.bytes[1] & 0xf0) == 0x80; } -#if defined(CONFIG_RETPOLINE) && defined(CONFIG_OBJTOOL) +#if defined(CONFIG_MITIGATION_RETPOLINE) && defined(CONFIG_OBJTOOL) /* * CALL/JMP *%\reg @@ -709,8 +708,8 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes) /* * The compiler is supposed to EMIT an INT3 after every unconditional * JMP instruction due to AMD BTC. However, if the compiler is too old - * or SLS isn't enabled, we still need an INT3 after indirect JMPs - * even on Intel. + * or MITIGATION_SLS isn't enabled, we still need an INT3 after + * indirect JMPs even on Intel. */ if (op == JMP32_INSN_OPCODE && i < insn->length) bytes[i++] = INT3_INSN_OPCODE; @@ -770,7 +769,7 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) } } -#ifdef CONFIG_RETHUNK +#ifdef CONFIG_MITIGATION_RETHUNK /* * Rewrite the compiler generated return thunk tail-calls. @@ -843,14 +842,14 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end) } #else void __init_or_module noinline apply_returns(s32 *start, s32 *end) { } -#endif /* CONFIG_RETHUNK */ +#endif /* CONFIG_MITIGATION_RETHUNK */ -#else /* !CONFIG_RETPOLINE || !CONFIG_OBJTOOL */ +#else /* !CONFIG_MITIGATION_RETPOLINE || !CONFIG_OBJTOOL */ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) { } void __init_or_module noinline apply_returns(s32 *start, s32 *end) { } -#endif /* CONFIG_RETPOLINE && CONFIG_OBJTOOL */ +#endif /* CONFIG_MITIGATION_RETPOLINE && CONFIG_OBJTOOL */ #ifdef CONFIG_X86_KERNEL_IBT diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 76a5ced278c2..b37ab1095707 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -1055,35 +1055,6 @@ static int apm_get_power_status(u_short *status, u_short *bat, u_short *life) return APM_SUCCESS; } -#if 0 -static int apm_get_battery_status(u_short which, u_short *status, - u_short *bat, u_short *life, u_short *nbat) -{ - u32 eax; - u32 ebx; - u32 ecx; - u32 edx; - u32 esi; - - if (apm_info.connection_version < 0x0102) { - /* pretend we only have one battery. */ - if (which != 1) - return APM_BAD_DEVICE; - *nbat = 1; - return apm_get_power_status(status, bat, life); - } - - if (apm_bios_call(APM_FUNC_GET_STATUS, (0x8000 | (which)), 0, &eax, - &ebx, &ecx, &edx, &esi)) - return (eax >> 8) & 0xff; - *status = ebx; - *bat = ecx; - *life = edx; - *nbat = esi; - return APM_SUCCESS; -} -#endif - /** * apm_engage_power_management - enable PM on a device * @device: identity of device diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 6913b372ccf7..a98020bf31bb 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -109,7 +109,7 @@ static void __used common(void) OFFSET(TSS_sp2, tss_struct, x86_tss.sp2); OFFSET(X86_top_of_stack, pcpu_hot, top_of_stack); OFFSET(X86_current_task, pcpu_hot, current_task); -#ifdef CONFIG_CALL_DEPTH_TRACKING +#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING OFFSET(X86_call_depth, pcpu_hot, call_depth); #endif #if IS_ENABLED(CONFIG_CRYPTO_ARIA_AESNI_AVX_X86_64) diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c index 64ad2ddea121..30335182b6b0 100644 --- a/arch/x86/kernel/callthunks.c +++ b/arch/x86/kernel/callthunks.c @@ -24,6 +24,8 @@ static int __initdata_or_module debug_callthunks; +#define MAX_PATCH_LEN (255-1) + #define prdbg(fmt, args...) \ do { \ if (debug_callthunks) \ @@ -42,8 +44,8 @@ DEFINE_PER_CPU(u64, __x86_call_count); DEFINE_PER_CPU(u64, __x86_ret_count); DEFINE_PER_CPU(u64, __x86_stuffs_count); DEFINE_PER_CPU(u64, __x86_ctxsw_count); -EXPORT_SYMBOL_GPL(__x86_ctxsw_count); -EXPORT_SYMBOL_GPL(__x86_call_count); +EXPORT_PER_CPU_SYMBOL_GPL(__x86_ctxsw_count); +EXPORT_PER_CPU_SYMBOL_GPL(__x86_call_count); #endif extern s32 __call_sites[], __call_sites_end[]; @@ -179,10 +181,15 @@ static const u8 nops[] = { static void *patch_dest(void *dest, bool direct) { unsigned int tsize = SKL_TMPL_SIZE; + u8 insn_buff[MAX_PATCH_LEN]; u8 *pad = dest - tsize; + memcpy(insn_buff, skl_call_thunk_template, tsize); + apply_relocation(insn_buff, tsize, pad, + skl_call_thunk_template, tsize); + /* Already patched? */ - if (!bcmp(pad, skl_call_thunk_template, tsize)) + if (!bcmp(pad, insn_buff, tsize)) return pad; /* Ensure there are nops */ @@ -192,9 +199,9 @@ static void *patch_dest(void *dest, bool direct) } if (direct) - memcpy(pad, skl_call_thunk_template, tsize); + memcpy(pad, insn_buff, tsize); else - text_poke_copy_locked(pad, skl_call_thunk_template, tsize, true); + text_poke_copy_locked(pad, insn_buff, tsize, true); return pad; } @@ -290,20 +297,27 @@ void *callthunks_translate_call_dest(void *dest) static bool is_callthunk(void *addr) { unsigned int tmpl_size = SKL_TMPL_SIZE; - void *tmpl = skl_call_thunk_template; + u8 insn_buff[MAX_PATCH_LEN]; unsigned long dest; + u8 *pad; dest = roundup((unsigned long)addr, CONFIG_FUNCTION_ALIGNMENT); if (!thunks_initialized || skip_addr((void *)dest)) return false; - return !bcmp((void *)(dest - tmpl_size), tmpl, tmpl_size); + pad = (void *)(dest - tmpl_size); + + memcpy(insn_buff, skl_call_thunk_template, tmpl_size); + apply_relocation(insn_buff, tmpl_size, pad, + skl_call_thunk_template, tmpl_size); + + return !bcmp(pad, insn_buff, tmpl_size); } int x86_call_depth_emit_accounting(u8 **pprog, void *func) { unsigned int tmpl_size = SKL_TMPL_SIZE; - void *tmpl = skl_call_thunk_template; + u8 insn_buff[MAX_PATCH_LEN]; if (!thunks_initialized) return 0; @@ -312,7 +326,11 @@ int x86_call_depth_emit_accounting(u8 **pprog, void *func) if (func && is_callthunk(func)) return 0; - memcpy(*pprog, tmpl, tmpl_size); + memcpy(insn_buff, skl_call_thunk_template, tmpl_size); + apply_relocation(insn_buff, tmpl_size, *pprog, + skl_call_thunk_template, tmpl_size); + + memcpy(*pprog, insn_buff, tmpl_size); *pprog += tmpl_size; return tmpl_size; } diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index c82069e5f341..3282a747b645 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -20,6 +20,7 @@ #include <asm/delay.h> #include <asm/debugreg.h> #include <asm/resctrl.h> +#include <asm/sev.h> #ifdef CONFIG_X86_64 # include <asm/mmconfig.h> @@ -451,6 +452,21 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) break; } + if (cpu_has(c, X86_FEATURE_SEV_SNP)) { + /* + * RMP table entry format is not architectural and it can vary by processor + * and is defined by the per-processor PPR. Restrict SNP support on the + * known CPU model and family for which the RMP table entry format is + * currently defined for. + */ + if (!boot_cpu_has(X86_FEATURE_ZEN3) && + !boot_cpu_has(X86_FEATURE_ZEN4) && + !boot_cpu_has(X86_FEATURE_ZEN5)) + setup_clear_cpu_cap(X86_FEATURE_SEV_SNP); + else if (!snp_probe_rmptable_info()) + setup_clear_cpu_cap(X86_FEATURE_SEV_SNP); + } + return; warn: @@ -469,8 +485,8 @@ static void early_detect_mem_encrypt(struct cpuinfo_x86 *c) * SME feature (set in scattered.c). * If the kernel has not enabled SME via any means then * don't advertise the SME feature. - * For SEV: If BIOS has not enabled SEV then don't advertise the - * SEV and SEV_ES feature (set in scattered.c). + * For SEV: If BIOS has not enabled SEV then don't advertise SEV and + * any additional functionality based on it. * * In all cases, since support for SME and SEV requires long mode, * don't advertise the feature under CONFIG_X86_32. @@ -505,6 +521,7 @@ clear_all: clear_sev: setup_clear_cpu_cap(X86_FEATURE_SEV); setup_clear_cpu_cap(X86_FEATURE_SEV_ES); + setup_clear_cpu_cap(X86_FEATURE_SEV_SNP); } } @@ -800,7 +817,7 @@ static void fix_erratum_1386(struct cpuinfo_x86 *c) void init_spectral_chicken(struct cpuinfo_x86 *c) { -#ifdef CONFIG_CPU_UNRET_ENTRY +#ifdef CONFIG_MITIGATION_UNRET_ENTRY u64 value; /* @@ -828,7 +845,6 @@ static void init_amd_zen_common(void) static void init_amd_zen1(struct cpuinfo_x86 *c) { - init_amd_zen_common(); fix_erratum_1386(c); /* Fix up CPUID bits, but only if not virtualised. */ @@ -882,7 +898,6 @@ static void zen2_zenbleed_check(struct cpuinfo_x86 *c) static void init_amd_zen2(struct cpuinfo_x86 *c) { - init_amd_zen_common(); init_spectral_chicken(c); fix_erratum_1386(c); zen2_zenbleed_check(c); @@ -890,8 +905,6 @@ static void init_amd_zen2(struct cpuinfo_x86 *c) static void init_amd_zen3(struct cpuinfo_x86 *c) { - init_amd_zen_common(); - if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) { /* * Zen3 (Fam19 model < 0x10) parts are not susceptible to @@ -905,15 +918,12 @@ static void init_amd_zen3(struct cpuinfo_x86 *c) static void init_amd_zen4(struct cpuinfo_x86 *c) { - init_amd_zen_common(); - if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT); } static void init_amd_zen5(struct cpuinfo_x86 *c) { - init_amd_zen_common(); } static void init_amd(struct cpuinfo_x86 *c) @@ -950,6 +960,13 @@ static void init_amd(struct cpuinfo_x86 *c) case 0x16: init_amd_jg(c); break; } + /* + * Save up on some future enablement work and do common Zen + * settings. + */ + if (c->x86 >= 0x17) + init_amd_zen_common(); + if (boot_cpu_has(X86_FEATURE_ZEN1)) init_amd_zen1(c); else if (boot_cpu_has(X86_FEATURE_ZEN2)) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 48d049cd74e7..e7ba936d798b 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -56,7 +56,7 @@ EXPORT_SYMBOL_GPL(x86_spec_ctrl_base); /* The current value of the SPEC_CTRL MSR with task-specific bits set */ DEFINE_PER_CPU(u64, x86_spec_ctrl_current); -EXPORT_SYMBOL_GPL(x86_spec_ctrl_current); +EXPORT_PER_CPU_SYMBOL_GPL(x86_spec_ctrl_current); u64 x86_pred_cmd __ro_after_init = PRED_CMD_IBPB; EXPORT_SYMBOL_GPL(x86_pred_cmd); @@ -422,6 +422,13 @@ static void __init mmio_select_mitigation(void) if (boot_cpu_has_bug(X86_BUG_MDS) || (boot_cpu_has_bug(X86_BUG_TAA) && boot_cpu_has(X86_FEATURE_RTM))) setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); + + /* + * X86_FEATURE_CLEAR_CPU_BUF could be enabled by other VERW based + * mitigations, disable KVM-only mitigation in that case. + */ + if (boot_cpu_has(X86_FEATURE_CLEAR_CPU_BUF)) + static_branch_disable(&mmio_stale_data_clear); else static_branch_enable(&mmio_stale_data_clear); @@ -474,6 +481,57 @@ static int __init mmio_stale_data_parse_cmdline(char *str) early_param("mmio_stale_data", mmio_stale_data_parse_cmdline); #undef pr_fmt +#define pr_fmt(fmt) "Register File Data Sampling: " fmt + +enum rfds_mitigations { + RFDS_MITIGATION_OFF, + RFDS_MITIGATION_VERW, + RFDS_MITIGATION_UCODE_NEEDED, +}; + +/* Default mitigation for Register File Data Sampling */ +static enum rfds_mitigations rfds_mitigation __ro_after_init = + IS_ENABLED(CONFIG_MITIGATION_RFDS) ? RFDS_MITIGATION_VERW : RFDS_MITIGATION_OFF; + +static const char * const rfds_strings[] = { + [RFDS_MITIGATION_OFF] = "Vulnerable", + [RFDS_MITIGATION_VERW] = "Mitigation: Clear Register File", + [RFDS_MITIGATION_UCODE_NEEDED] = "Vulnerable: No microcode", +}; + +static void __init rfds_select_mitigation(void) +{ + if (!boot_cpu_has_bug(X86_BUG_RFDS) || cpu_mitigations_off()) { + rfds_mitigation = RFDS_MITIGATION_OFF; + return; + } + if (rfds_mitigation == RFDS_MITIGATION_OFF) + return; + + if (x86_read_arch_cap_msr() & ARCH_CAP_RFDS_CLEAR) + setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); + else + rfds_mitigation = RFDS_MITIGATION_UCODE_NEEDED; +} + +static __init int rfds_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!boot_cpu_has_bug(X86_BUG_RFDS)) + return 0; + + if (!strcmp(str, "off")) + rfds_mitigation = RFDS_MITIGATION_OFF; + else if (!strcmp(str, "on")) + rfds_mitigation = RFDS_MITIGATION_VERW; + + return 0; +} +early_param("reg_file_data_sampling", rfds_parse_cmdline); + +#undef pr_fmt #define pr_fmt(fmt) "" fmt static void __init md_clear_update_mitigation(void) @@ -498,11 +556,19 @@ static void __init md_clear_update_mitigation(void) taa_mitigation = TAA_MITIGATION_VERW; taa_select_mitigation(); } - if (mmio_mitigation == MMIO_MITIGATION_OFF && - boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) { + /* + * MMIO_MITIGATION_OFF is not checked here so that mmio_stale_data_clear + * gets updated correctly as per X86_FEATURE_CLEAR_CPU_BUF state. + */ + if (boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) { mmio_mitigation = MMIO_MITIGATION_VERW; mmio_select_mitigation(); } + if (rfds_mitigation == RFDS_MITIGATION_OFF && + boot_cpu_has_bug(X86_BUG_RFDS)) { + rfds_mitigation = RFDS_MITIGATION_VERW; + rfds_select_mitigation(); + } out: if (boot_cpu_has_bug(X86_BUG_MDS)) pr_info("MDS: %s\n", mds_strings[mds_mitigation]); @@ -512,6 +578,8 @@ out: pr_info("MMIO Stale Data: %s\n", mmio_strings[mmio_mitigation]); else if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN)) pr_info("MMIO Stale Data: Unknown: No mitigations\n"); + if (boot_cpu_has_bug(X86_BUG_RFDS)) + pr_info("Register File Data Sampling: %s\n", rfds_strings[rfds_mitigation]); } static void __init md_clear_select_mitigation(void) @@ -519,11 +587,12 @@ static void __init md_clear_select_mitigation(void) mds_select_mitigation(); taa_select_mitigation(); mmio_select_mitigation(); + rfds_select_mitigation(); /* - * As MDS, TAA and MMIO Stale Data mitigations are inter-related, update - * and print their mitigation after MDS, TAA and MMIO Stale Data - * mitigation selection is done. + * As these mitigations are inter-related and rely on VERW instruction + * to clear the microarchitural buffers, update and print their status + * after mitigation selection is done for each of these vulnerabilities. */ md_clear_update_mitigation(); } @@ -668,7 +737,7 @@ enum gds_mitigations { GDS_MITIGATION_HYPERVISOR, }; -#if IS_ENABLED(CONFIG_GDS_FORCE_MITIGATION) +#if IS_ENABLED(CONFIG_MITIGATION_GDS_FORCE) static enum gds_mitigations gds_mitigation __ro_after_init = GDS_MITIGATION_FORCE; #else static enum gds_mitigations gds_mitigation __ro_after_init = GDS_MITIGATION_FULL; @@ -979,10 +1048,10 @@ static void __init retbleed_select_mitigation(void) return; case RETBLEED_CMD_UNRET: - if (IS_ENABLED(CONFIG_CPU_UNRET_ENTRY)) { + if (IS_ENABLED(CONFIG_MITIGATION_UNRET_ENTRY)) { retbleed_mitigation = RETBLEED_MITIGATION_UNRET; } else { - pr_err("WARNING: kernel not compiled with CPU_UNRET_ENTRY.\n"); + pr_err("WARNING: kernel not compiled with MITIGATION_UNRET_ENTRY.\n"); goto do_cmd_auto; } break; @@ -991,24 +1060,24 @@ static void __init retbleed_select_mitigation(void) if (!boot_cpu_has(X86_FEATURE_IBPB)) { pr_err("WARNING: CPU does not support IBPB.\n"); goto do_cmd_auto; - } else if (IS_ENABLED(CONFIG_CPU_IBPB_ENTRY)) { + } else if (IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY)) { retbleed_mitigation = RETBLEED_MITIGATION_IBPB; } else { - pr_err("WARNING: kernel not compiled with CPU_IBPB_ENTRY.\n"); + pr_err("WARNING: kernel not compiled with MITIGATION_IBPB_ENTRY.\n"); goto do_cmd_auto; } break; case RETBLEED_CMD_STUFF: - if (IS_ENABLED(CONFIG_CALL_DEPTH_TRACKING) && + if (IS_ENABLED(CONFIG_MITIGATION_CALL_DEPTH_TRACKING) && spectre_v2_enabled == SPECTRE_V2_RETPOLINE) { retbleed_mitigation = RETBLEED_MITIGATION_STUFF; } else { - if (IS_ENABLED(CONFIG_CALL_DEPTH_TRACKING)) + if (IS_ENABLED(CONFIG_MITIGATION_CALL_DEPTH_TRACKING)) pr_err("WARNING: retbleed=stuff depends on spectre_v2=retpoline\n"); else - pr_err("WARNING: kernel not compiled with CALL_DEPTH_TRACKING.\n"); + pr_err("WARNING: kernel not compiled with MITIGATION_CALL_DEPTH_TRACKING.\n"); goto do_cmd_auto; } @@ -1018,9 +1087,10 @@ do_cmd_auto: case RETBLEED_CMD_AUTO: if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) { - if (IS_ENABLED(CONFIG_CPU_UNRET_ENTRY)) + if (IS_ENABLED(CONFIG_MITIGATION_UNRET_ENTRY)) retbleed_mitigation = RETBLEED_MITIGATION_UNRET; - else if (IS_ENABLED(CONFIG_CPU_IBPB_ENTRY) && boot_cpu_has(X86_FEATURE_IBPB)) + else if (IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY) && + boot_cpu_has(X86_FEATURE_IBPB)) retbleed_mitigation = RETBLEED_MITIGATION_IBPB; } @@ -1099,7 +1169,7 @@ static enum spectre_v2_user_mitigation spectre_v2_user_stibp __ro_after_init = static enum spectre_v2_user_mitigation spectre_v2_user_ibpb __ro_after_init = SPECTRE_V2_USER_NONE; -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE static bool spectre_v2_bad_module; bool retpoline_module_ok(bool has_retpoline) @@ -1412,7 +1482,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) cmd == SPECTRE_V2_CMD_RETPOLINE_GENERIC || cmd == SPECTRE_V2_CMD_EIBRS_LFENCE || cmd == SPECTRE_V2_CMD_EIBRS_RETPOLINE) && - !IS_ENABLED(CONFIG_RETPOLINE)) { + !IS_ENABLED(CONFIG_MITIGATION_RETPOLINE)) { pr_err("%s selected but not compiled in. Switching to AUTO select\n", mitigation_options[i].option); return SPECTRE_V2_CMD_AUTO; @@ -1435,7 +1505,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) return SPECTRE_V2_CMD_AUTO; } - if (cmd == SPECTRE_V2_CMD_IBRS && !IS_ENABLED(CONFIG_CPU_IBRS_ENTRY)) { + if (cmd == SPECTRE_V2_CMD_IBRS && !IS_ENABLED(CONFIG_MITIGATION_IBRS_ENTRY)) { pr_err("%s selected but not compiled in. Switching to AUTO select\n", mitigation_options[i].option); return SPECTRE_V2_CMD_AUTO; @@ -1466,7 +1536,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) static enum spectre_v2_mitigation __init spectre_v2_select_retpoline(void) { - if (!IS_ENABLED(CONFIG_RETPOLINE)) { + if (!IS_ENABLED(CONFIG_MITIGATION_RETPOLINE)) { pr_err("Kernel not compiled with retpoline; no mitigation available!"); return SPECTRE_V2_NONE; } @@ -1561,7 +1631,7 @@ static void __init spectre_v2_select_mitigation(void) break; } - if (IS_ENABLED(CONFIG_CPU_IBRS_ENTRY) && + if (IS_ENABLED(CONFIG_MITIGATION_IBRS_ENTRY) && boot_cpu_has_bug(X86_BUG_RETBLEED) && retbleed_cmd != RETBLEED_CMD_OFF && retbleed_cmd != RETBLEED_CMD_STUFF && @@ -2454,7 +2524,7 @@ static void __init srso_select_mitigation(void) break; case SRSO_CMD_SAFE_RET: - if (IS_ENABLED(CONFIG_CPU_SRSO)) { + if (IS_ENABLED(CONFIG_MITIGATION_SRSO)) { /* * Enable the return thunk for generated code * like ftrace, static_call, etc. @@ -2474,29 +2544,29 @@ static void __init srso_select_mitigation(void) else srso_mitigation = SRSO_MITIGATION_SAFE_RET_UCODE_NEEDED; } else { - pr_err("WARNING: kernel not compiled with CPU_SRSO.\n"); + pr_err("WARNING: kernel not compiled with MITIGATION_SRSO.\n"); } break; case SRSO_CMD_IBPB: - if (IS_ENABLED(CONFIG_CPU_IBPB_ENTRY)) { + if (IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY)) { if (has_microcode) { setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB); srso_mitigation = SRSO_MITIGATION_IBPB; } } else { - pr_err("WARNING: kernel not compiled with CPU_IBPB_ENTRY.\n"); + pr_err("WARNING: kernel not compiled with MITIGATION_IBPB_ENTRY.\n"); } break; case SRSO_CMD_IBPB_ON_VMEXIT: - if (IS_ENABLED(CONFIG_CPU_SRSO)) { + if (IS_ENABLED(CONFIG_MITIGATION_SRSO)) { if (!boot_cpu_has(X86_FEATURE_ENTRY_IBPB) && has_microcode) { setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT); srso_mitigation = SRSO_MITIGATION_IBPB_ON_VMEXIT; } } else { - pr_err("WARNING: kernel not compiled with CPU_SRSO.\n"); + pr_err("WARNING: kernel not compiled with MITIGATION_SRSO.\n"); } break; } @@ -2612,6 +2682,11 @@ static ssize_t mmio_stale_data_show_state(char *buf) sched_smt_active() ? "vulnerable" : "disabled"); } +static ssize_t rfds_show_state(char *buf) +{ + return sysfs_emit(buf, "%s\n", rfds_strings[rfds_mitigation]); +} + static char *stibp_state(void) { if (spectre_v2_in_eibrs_mode(spectre_v2_enabled) && @@ -2771,6 +2846,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_GDS: return gds_show_state(buf); + case X86_BUG_RFDS: + return rfds_show_state(buf); + default: break; } @@ -2845,4 +2923,14 @@ ssize_t cpu_show_gds(struct device *dev, struct device_attribute *attr, char *bu { return cpu_show_common(dev, attr, buf, X86_BUG_GDS); } + +ssize_t cpu_show_reg_file_data_sampling(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_RFDS); +} #endif + +void __warn_thunk(void) +{ + WARN_ONCE(1, "Unpatched return thunk in use. This should not happen!\n"); +} diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c index f2241e7e96fd..392d09c936d6 100644 --- a/arch/x86/kernel/cpu/cacheinfo.c +++ b/arch/x86/kernel/cpu/cacheinfo.c @@ -1118,15 +1118,16 @@ static void cache_cpu_init(void) unsigned long flags; local_irq_save(flags); - cache_disable(); - if (memory_caching_control & CACHE_MTRR) + if (memory_caching_control & CACHE_MTRR) { + cache_disable(); mtrr_generic_set_state(); + cache_enable(); + } if (memory_caching_control & CACHE_PAT) pat_cpu_init(); - cache_enable(); local_irq_restore(flags); } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index c44e6f0c8972..ba8cf5e9ce56 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -71,6 +71,9 @@ #include "cpu.h" +DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info); +EXPORT_PER_CPU_SYMBOL(cpu_info); + u32 elf_hwcap2 __read_mostly; /* Number of siblings per CPU package */ @@ -1221,6 +1224,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { #define SRSO BIT(5) /* CPU is affected by GDS */ #define GDS BIT(6) +/* CPU is affected by Register File Data Sampling */ +#define RFDS BIT(7) static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(IVYBRIDGE, X86_STEPPING_ANY, SRBDS), @@ -1248,9 +1253,18 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(TIGERLAKE, X86_STEPPING_ANY, GDS), VULNBL_INTEL_STEPPINGS(LAKEFIELD, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), VULNBL_INTEL_STEPPINGS(ROCKETLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS), - VULNBL_INTEL_STEPPINGS(ATOM_TREMONT, X86_STEPPING_ANY, MMIO | MMIO_SBDS), - VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO), - VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS), + VULNBL_INTEL_STEPPINGS(ALDERLAKE, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ALDERLAKE_L, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(RAPTORLAKE, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(RAPTORLAKE_P, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(RAPTORLAKE_S, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_GRACEMONT, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_TREMONT, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO | RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT_D, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPPINGS(ATOM_GOLDMONT_PLUS, X86_STEPPING_ANY, RFDS), VULNBL_AMD(0x15, RETBLEED), VULNBL_AMD(0x16, RETBLEED), @@ -1284,6 +1298,24 @@ static bool arch_cap_mmio_immune(u64 ia32_cap) ia32_cap & ARCH_CAP_SBDR_SSDP_NO); } +static bool __init vulnerable_to_rfds(u64 ia32_cap) +{ + /* The "immunity" bit trumps everything else: */ + if (ia32_cap & ARCH_CAP_RFDS_NO) + return false; + + /* + * VMMs set ARCH_CAP_RFDS_CLEAR for processors not in the blacklist to + * indicate that mitigation is needed because guest is running on a + * vulnerable hardware or may migrate to such hardware: + */ + if (ia32_cap & ARCH_CAP_RFDS_CLEAR) + return true; + + /* Only consult the blacklist when there is no enumeration: */ + return cpu_matches(cpu_vuln_blacklist, RFDS); +} + static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) { u64 ia32_cap = x86_read_arch_cap_msr(); @@ -1309,8 +1341,13 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) /* * AMD's AutoIBRS is equivalent to Intel's eIBRS - use the Intel feature * flag and protect from vendor-specific bugs via the whitelist. + * + * Don't use AutoIBRS when SNP is enabled because it degrades host + * userspace indirect branch performance. */ - if ((ia32_cap & ARCH_CAP_IBRS_ALL) || cpu_has(c, X86_FEATURE_AUTOIBRS)) { + if ((ia32_cap & ARCH_CAP_IBRS_ALL) || + (cpu_has(c, X86_FEATURE_AUTOIBRS) && + !cpu_feature_enabled(X86_FEATURE_SEV_SNP))) { setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED); if (!cpu_matches(cpu_vuln_whitelist, NO_EIBRS_PBRSB) && !(ia32_cap & ARCH_CAP_PBRSB_NO)) @@ -1395,6 +1432,9 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) boot_cpu_has(X86_FEATURE_AVX)) setup_force_cpu_bug(X86_BUG_GDS); + if (vulnerable_to_rfds(ia32_cap)) + setup_force_cpu_bug(X86_BUG_RFDS); + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; @@ -1848,8 +1888,6 @@ static void identify_cpu(struct cpuinfo_x86 *c) /* Init Machine Check Exception if available. */ mcheck_cpu_init(c); - select_idle_routine(c); - #ifdef CONFIG_NUMA numa_add_cpu(smp_processor_id()); #endif @@ -1959,6 +1997,7 @@ DEFINE_PER_CPU_ALIGNED(struct pcpu_hot, pcpu_hot) = { .top_of_stack = TOP_OF_INIT_STACK, }; EXPORT_PER_CPU_SYMBOL(pcpu_hot); +EXPORT_PER_CPU_SYMBOL(const_pcpu_hot); #ifdef CONFIG_X86_64 DEFINE_PER_CPU_FIRST(struct fixed_percpu_data, @@ -2270,6 +2309,8 @@ void __init arch_cpu_finalize_init(void) { identify_boot_cpu(); + select_idle_routine(); + /* * identify_boot_cpu() initialized SMT support information, let the * core code know. diff --git a/arch/x86/kernel/cpu/intel_pconfig.c b/arch/x86/kernel/cpu/intel_pconfig.c index 0771a905b286..5be2b1790282 100644 --- a/arch/x86/kernel/cpu/intel_pconfig.c +++ b/arch/x86/kernel/cpu/intel_pconfig.c @@ -7,6 +7,8 @@ * Author: * Kirill A. Shutemov <kirill.shutemov@linux.intel.com> */ +#include <linux/bug.h> +#include <linux/limits.h> #include <asm/cpufeature.h> #include <asm/intel_pconfig.h> diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 04acdc3534c8..b5cc557cfc37 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -2457,7 +2457,7 @@ static void mce_enable_ce(void *all) __mcheck_cpu_init_timer(); } -static struct bus_type mce_subsys = { +static const struct bus_type mce_subsys = { .name = "machinecheck", .dev_name = "machinecheck", }; diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index d3524778a545..422a4ddc2ab7 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -108,6 +108,9 @@ static inline void k8_check_syscfg_dram_mod_en(void) (boot_cpu_data.x86 >= 0x0f))) return; + if (cpu_feature_enabled(X86_FEATURE_SEV_SNP)) + return; + rdmsr(MSR_AMD64_SYSCFG, lo, hi); if (lo & K8_MTRRFIXRANGE_DRAM_MODIFY) { pr_err(FW_WARN "MTRR: CPU %u: SYSCFG[MtrrFixDramModEn]" diff --git a/arch/x86/kernel/cpu/rdrand.c b/arch/x86/kernel/cpu/rdrand.c index 26a427fa84ea..eeac00d20926 100644 --- a/arch/x86/kernel/cpu/rdrand.c +++ b/arch/x86/kernel/cpu/rdrand.c @@ -6,6 +6,7 @@ * Authors: Fenghua Yu <fenghua.yu@intel.com>, * H. Peter Anvin <hpa@linux.intel.com> */ +#include <linux/printk.h> #include <asm/processor.h> #include <asm/archrandom.h> diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 19e0681f0435..83e40341583e 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -16,6 +16,7 @@ #define pr_fmt(fmt) "resctrl: " fmt +#include <linux/cpu.h> #include <linux/slab.h> #include <linux/err.h> #include <linux/cacheinfo.h> @@ -25,8 +26,15 @@ #include <asm/resctrl.h> #include "internal.h" -/* Mutex to protect rdtgroup access. */ -DEFINE_MUTEX(rdtgroup_mutex); +/* + * rdt_domain structures are kfree()d when their last CPU goes offline, + * and allocated when the first CPU in a new domain comes online. + * The rdt_resource's domain list is updated when this happens. Readers of + * the domain list must either take cpus_read_lock(), or rely on an RCU + * read-side critical section, to avoid observing concurrent modification. + * All writers take this mutex: + */ +static DEFINE_MUTEX(domain_list_lock); /* * The cached resctrl_pqr_state is strictly per CPU and can never be @@ -136,15 +144,15 @@ static inline void cache_alloc_hsw_probe(void) { struct rdt_hw_resource *hw_res = &rdt_resources_all[RDT_RESOURCE_L3]; struct rdt_resource *r = &hw_res->r_resctrl; - u32 l, h, max_cbm = BIT_MASK(20) - 1; + u64 max_cbm = BIT_ULL_MASK(20) - 1, l3_cbm_0; - if (wrmsr_safe(MSR_IA32_L3_CBM_BASE, max_cbm, 0)) + if (wrmsrl_safe(MSR_IA32_L3_CBM_BASE, max_cbm)) return; - rdmsr(MSR_IA32_L3_CBM_BASE, l, h); + rdmsrl(MSR_IA32_L3_CBM_BASE, l3_cbm_0); /* If all the bits were set in MSR, return success */ - if (l != max_cbm) + if (l3_cbm_0 != max_cbm) return; hw_res->num_closid = 4; @@ -231,9 +239,7 @@ static bool __get_mem_config_intel(struct rdt_resource *r) static bool __rdt_get_mem_config_amd(struct rdt_resource *r) { struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); - union cpuid_0x10_3_eax eax; - union cpuid_0x10_x_edx edx; - u32 ebx, ecx, subleaf; + u32 eax, ebx, ecx, edx, subleaf; /* * Query CPUID_Fn80000020_EDX_x01 for MBA and @@ -241,9 +247,9 @@ static bool __rdt_get_mem_config_amd(struct rdt_resource *r) */ subleaf = (r->rid == RDT_RESOURCE_SMBA) ? 2 : 1; - cpuid_count(0x80000020, subleaf, &eax.full, &ebx, &ecx, &edx.full); - hw_res->num_closid = edx.split.cos_max + 1; - r->default_ctrl = MAX_MBA_BW_AMD; + cpuid_count(0x80000020, subleaf, &eax, &ebx, &ecx, &edx); + hw_res->num_closid = edx + 1; + r->default_ctrl = 1 << eax; /* AMD does not use delay */ r->membw.delay_linear = false; @@ -512,6 +518,8 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r) struct rdt_domain *d; int err; + lockdep_assert_held(&domain_list_lock); + d = rdt_find_domain(r, id, &add_pos); if (IS_ERR(d)) { pr_warn("Couldn't find cache id for CPU %d\n", cpu); @@ -545,11 +553,12 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r) return; } - list_add_tail(&d->list, add_pos); + list_add_tail_rcu(&d->list, add_pos); err = resctrl_online_domain(r, d); if (err) { - list_del(&d->list); + list_del_rcu(&d->list); + synchronize_rcu(); domain_free(hw_dom); } } @@ -560,6 +569,8 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) struct rdt_hw_domain *hw_dom; struct rdt_domain *d; + lockdep_assert_held(&domain_list_lock); + d = rdt_find_domain(r, id, NULL); if (IS_ERR_OR_NULL(d)) { pr_warn("Couldn't find cache id for CPU %d\n", cpu); @@ -570,7 +581,8 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) cpumask_clear_cpu(cpu, &d->cpu_mask); if (cpumask_empty(&d->cpu_mask)) { resctrl_offline_domain(r, d); - list_del(&d->list); + list_del_rcu(&d->list); + synchronize_rcu(); /* * rdt_domain "d" is going to be freed below, so clear @@ -582,73 +594,47 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) return; } - - if (r == &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl) { - if (is_mbm_enabled() && cpu == d->mbm_work_cpu) { - cancel_delayed_work(&d->mbm_over); - mbm_setup_overflow_handler(d, 0); - } - if (is_llc_occupancy_enabled() && cpu == d->cqm_work_cpu && - has_busy_rmid(r, d)) { - cancel_delayed_work(&d->cqm_limbo); - cqm_setup_limbo_handler(d, 0); - } - } } static void clear_closid_rmid(int cpu) { struct resctrl_pqr_state *state = this_cpu_ptr(&pqr_state); - state->default_closid = 0; - state->default_rmid = 0; - state->cur_closid = 0; - state->cur_rmid = 0; - wrmsr(MSR_IA32_PQR_ASSOC, 0, 0); + state->default_closid = RESCTRL_RESERVED_CLOSID; + state->default_rmid = RESCTRL_RESERVED_RMID; + state->cur_closid = RESCTRL_RESERVED_CLOSID; + state->cur_rmid = RESCTRL_RESERVED_RMID; + wrmsr(MSR_IA32_PQR_ASSOC, RESCTRL_RESERVED_RMID, + RESCTRL_RESERVED_CLOSID); } -static int resctrl_online_cpu(unsigned int cpu) +static int resctrl_arch_online_cpu(unsigned int cpu) { struct rdt_resource *r; - mutex_lock(&rdtgroup_mutex); + mutex_lock(&domain_list_lock); for_each_capable_rdt_resource(r) domain_add_cpu(cpu, r); - /* The cpu is set in default rdtgroup after online. */ - cpumask_set_cpu(cpu, &rdtgroup_default.cpu_mask); + mutex_unlock(&domain_list_lock); + clear_closid_rmid(cpu); - mutex_unlock(&rdtgroup_mutex); + resctrl_online_cpu(cpu); return 0; } -static void clear_childcpus(struct rdtgroup *r, unsigned int cpu) -{ - struct rdtgroup *cr; - - list_for_each_entry(cr, &r->mon.crdtgrp_list, mon.crdtgrp_list) { - if (cpumask_test_and_clear_cpu(cpu, &cr->cpu_mask)) { - break; - } - } -} - -static int resctrl_offline_cpu(unsigned int cpu) +static int resctrl_arch_offline_cpu(unsigned int cpu) { - struct rdtgroup *rdtgrp; struct rdt_resource *r; - mutex_lock(&rdtgroup_mutex); + resctrl_offline_cpu(cpu); + + mutex_lock(&domain_list_lock); for_each_capable_rdt_resource(r) domain_remove_cpu(cpu, r); - list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) { - if (cpumask_test_and_clear_cpu(cpu, &rdtgrp->cpu_mask)) { - clear_childcpus(rdtgrp, cpu); - break; - } - } + mutex_unlock(&domain_list_lock); + clear_closid_rmid(cpu); - mutex_unlock(&rdtgroup_mutex); return 0; } @@ -968,7 +954,8 @@ static int __init resctrl_late_init(void) state = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/resctrl/cat:online:", - resctrl_online_cpu, resctrl_offline_cpu); + resctrl_arch_online_cpu, + resctrl_arch_offline_cpu); if (state < 0) return state; @@ -992,8 +979,14 @@ late_initcall(resctrl_late_init); static void __exit resctrl_exit(void) { + struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; + cpuhp_remove_state(rdt_online); + rdtgroup_exit(); + + if (r->mon_capable) + rdt_put_mon_l3_config(); } __exitcall(resctrl_exit); diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index beccb0e87ba7..7997b47743a2 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -19,6 +19,8 @@ #include <linux/kernfs.h> #include <linux/seq_file.h> #include <linux/slab.h> +#include <linux/tick.h> + #include "internal.h" /* @@ -210,6 +212,9 @@ static int parse_line(char *line, struct resctrl_schema *s, struct rdt_domain *d; unsigned long dom_id; + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP && (r->rid == RDT_RESOURCE_MBA || r->rid == RDT_RESOURCE_SMBA)) { rdt_last_cmd_puts("Cannot pseudo-lock MBA resource\n"); @@ -314,6 +319,9 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid) struct rdt_domain *d; u32 idx; + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) return -ENOMEM; @@ -379,11 +387,9 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, return -EINVAL; buf[nbytes - 1] = '\0'; - cpus_read_lock(); rdtgrp = rdtgroup_kn_lock_live(of->kn); if (!rdtgrp) { rdtgroup_kn_unlock(of->kn); - cpus_read_unlock(); return -ENOENT; } rdt_last_cmd_clear(); @@ -445,7 +451,6 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, out: rdt_staged_configs_clear(); rdtgroup_kn_unlock(of->kn); - cpus_read_unlock(); return ret ?: nbytes; } @@ -465,6 +470,9 @@ static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int clo bool sep = false; u32 ctrl_val; + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + seq_printf(s, "%*s:", max_name_width, schema->name); list_for_each_entry(dom, &r->domains, list) { if (sep) @@ -522,12 +530,24 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of, return ret; } +static int smp_mon_event_count(void *arg) +{ + mon_event_count(arg); + + return 0; +} + void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, struct rdt_domain *d, struct rdtgroup *rdtgrp, int evtid, int first) { + int cpu; + + /* When picking a CPU from cpu_mask, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + /* - * setup the parameters to send to the IPI to read the data. + * Setup the parameters to pass to mon_event_count() to read the data. */ rr->rgrp = rdtgrp; rr->evtid = evtid; @@ -535,8 +555,26 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, rr->d = d; rr->val = 0; rr->first = first; + rr->arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, evtid); + if (IS_ERR(rr->arch_mon_ctx)) { + rr->err = -EINVAL; + return; + } + + cpu = cpumask_any_housekeeping(&d->cpu_mask, RESCTRL_PICK_ANY_CPU); + + /* + * cpumask_any_housekeeping() prefers housekeeping CPUs, but + * are all the CPUs nohz_full? If yes, pick a CPU to IPI. + * MPAM's resctrl_arch_rmid_read() is unable to read the + * counters on some platforms if its called in IRQ context. + */ + if (tick_nohz_full_cpu(cpu)) + smp_call_function_any(&d->cpu_mask, mon_event_count, rr, 1); + else + smp_call_on_cpu(cpu, smp_mon_event_count, rr, false); - smp_call_function_any(&d->cpu_mask, mon_event_count, rr, 1); + resctrl_arch_mon_ctx_free(r, evtid, rr->arch_mon_ctx); } int rdtgroup_mondata_show(struct seq_file *m, void *arg) diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index a4f1aa15f0a2..c99f26ebe7a6 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -7,6 +7,9 @@ #include <linux/kernfs.h> #include <linux/fs_context.h> #include <linux/jump_label.h> +#include <linux/tick.h> + +#include <asm/resctrl.h> #define L3_QOS_CDP_ENABLE 0x01ULL @@ -18,7 +21,6 @@ #define MBM_OVERFLOW_INTERVAL 1000 #define MAX_MBA_BW 100u #define MBA_IS_LINEAR 0x4 -#define MAX_MBA_BW_AMD 0x800 #define MBM_CNTR_WIDTH_OFFSET_AMD 20 #define RMID_VAL_ERROR BIT_ULL(63) @@ -54,6 +56,46 @@ /* Max event bits supported */ #define MAX_EVT_CONFIG_BITS GENMASK(6, 0) +/** + * cpumask_any_housekeeping() - Choose any CPU in @mask, preferring those that + * aren't marked nohz_full + * @mask: The mask to pick a CPU from. + * @exclude_cpu:The CPU to avoid picking. + * + * Returns a CPU from @mask, but not @exclude_cpu. If there are housekeeping + * CPUs that don't use nohz_full, these are preferred. Pass + * RESCTRL_PICK_ANY_CPU to avoid excluding any CPUs. + * + * When a CPU is excluded, returns >= nr_cpu_ids if no CPUs are available. + */ +static inline unsigned int +cpumask_any_housekeeping(const struct cpumask *mask, int exclude_cpu) +{ + unsigned int cpu, hk_cpu; + + if (exclude_cpu == RESCTRL_PICK_ANY_CPU) + cpu = cpumask_any(mask); + else + cpu = cpumask_any_but(mask, exclude_cpu); + + if (!IS_ENABLED(CONFIG_NO_HZ_FULL)) + return cpu; + + /* If the CPU picked isn't marked nohz_full nothing more needs doing. */ + if (cpu < nr_cpu_ids && !tick_nohz_full_cpu(cpu)) + return cpu; + + /* Try to find a CPU that isn't nohz_full to use in preference */ + hk_cpu = cpumask_nth_andnot(0, mask, tick_nohz_full_mask); + if (hk_cpu == exclude_cpu) + hk_cpu = cpumask_nth_andnot(1, mask, tick_nohz_full_mask); + + if (hk_cpu < nr_cpu_ids) + cpu = hk_cpu; + + return cpu; +} + struct rdt_fs_context { struct kernfs_fs_context kfc; bool enable_cdpl2; @@ -69,9 +111,6 @@ static inline struct rdt_fs_context *rdt_fc2context(struct fs_context *fc) return container_of(kfc, struct rdt_fs_context, kfc); } -DECLARE_STATIC_KEY_FALSE(rdt_enable_key); -DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key); - /** * struct mon_evt - Entry in the event list of a resource * @evtid: event id @@ -112,12 +151,12 @@ struct rmid_read { bool first; int err; u64 val; + void *arch_mon_ctx; }; -extern bool rdt_alloc_capable; -extern bool rdt_mon_capable; extern unsigned int rdt_mon_features; extern struct list_head resctrl_schema_all; +extern bool resctrl_mounted; enum rdt_group_type { RDTCTRL_GROUP = 0, @@ -296,14 +335,10 @@ struct rftype { * struct mbm_state - status for each MBM counter in each domain * @prev_bw_bytes: Previous bytes value read for bandwidth calculation * @prev_bw: The most recent bandwidth in MBps - * @delta_bw: Difference between the current and previous bandwidth - * @delta_comp: Indicates whether to compute the delta_bw */ struct mbm_state { u64 prev_bw_bytes; u32 prev_bw; - u32 delta_bw; - bool delta_comp; }; /** @@ -395,6 +430,8 @@ struct rdt_parse_data { * @msr_update: Function pointer to update QOS MSRs * @mon_scale: cqm counter * mon_scale = occupancy in bytes * @mbm_width: Monitor width, to detect and correct for overflow. + * @mbm_cfg_mask: Bandwidth sources that can be tracked when Bandwidth + * Monitoring Event Configuration (BMEC) is supported. * @cdp_enabled: CDP state of this resource * * Members of this structure are either private to the architecture @@ -409,6 +446,7 @@ struct rdt_hw_resource { struct rdt_resource *r); unsigned int mon_scale; unsigned int mbm_width; + unsigned int mbm_cfg_mask; bool cdp_enabled; }; @@ -426,8 +464,6 @@ extern struct mutex rdtgroup_mutex; extern struct rdt_hw_resource rdt_resources_all[]; extern struct rdtgroup rdtgroup_default; -DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key); - extern struct dentry *debugfs_resctrl; enum resctrl_res_level { @@ -543,9 +579,10 @@ void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp); struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r); int closids_supported(void); void closid_free(int closid); -int alloc_rmid(void); -void free_rmid(u32 rmid); +int alloc_rmid(u32 closid); +void free_rmid(u32 closid, u32 rmid); int rdt_get_mon_l3_config(struct rdt_resource *r); +void __exit rdt_put_mon_l3_config(void); bool __init rdt_cpu_has(int flag); void mon_event_count(void *info); int rdtgroup_mondata_show(struct seq_file *m, void *arg); @@ -553,17 +590,21 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, struct rdt_domain *d, struct rdtgroup *rdtgrp, int evtid, int first); void mbm_setup_overflow_handler(struct rdt_domain *dom, - unsigned long delay_ms); + unsigned long delay_ms, + int exclude_cpu); void mbm_handle_overflow(struct work_struct *work); void __init intel_rdt_mbm_apply_quirk(void); bool is_mba_sc(struct rdt_resource *r); -void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms); +void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms, + int exclude_cpu); void cqm_handle_limbo(struct work_struct *work); -bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d); +bool has_busy_rmid(struct rdt_domain *d); void __check_limbo(struct rdt_domain *d, bool force_free); void rdt_domain_reconfigure_cdp(struct rdt_resource *r); void __init thread_throttle_mode_init(void); void __init mbm_config_rftype_init(const char *config); void rdt_staged_configs_clear(void); +bool closid_allocated(unsigned int closid); +int resctrl_find_cleanest_closid(void); #endif /* _ASM_X86_RESCTRL_INTERNAL_H */ diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index f136ac046851..c34a35ec0f03 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -15,6 +15,7 @@ * Software Developer Manual June 2016, volume 3, section 17.17. */ +#include <linux/cpu.h> #include <linux/module.h> #include <linux/sizes.h> #include <linux/slab.h> @@ -24,7 +25,20 @@ #include "internal.h" +/** + * struct rmid_entry - dirty tracking for all RMID. + * @closid: The CLOSID for this entry. + * @rmid: The RMID for this entry. + * @busy: The number of domains with cached data using this RMID. + * @list: Member of the rmid_free_lru list when busy == 0. + * + * Depending on the architecture the correct monitor is accessed using + * both @closid and @rmid, or @rmid only. + * + * Take the rdtgroup_mutex when accessing. + */ struct rmid_entry { + u32 closid; u32 rmid; int busy; struct list_head list; @@ -38,6 +52,13 @@ struct rmid_entry { static LIST_HEAD(rmid_free_lru); /* + * @closid_num_dirty_rmid The number of dirty RMID each CLOSID has. + * Only allocated when CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID is defined. + * Indexed by CLOSID. Protected by rdtgroup_mutex. + */ +static u32 *closid_num_dirty_rmid; + +/* * @rmid_limbo_count - count of currently unused but (potentially) * dirty RMIDs. * This counts RMIDs that no one is currently using but that @@ -136,12 +157,29 @@ static inline u64 get_corrected_mbm_count(u32 rmid, unsigned long val) return val; } -static inline struct rmid_entry *__rmid_entry(u32 rmid) +/* + * x86 and arm64 differ in their handling of monitoring. + * x86's RMID are independent numbers, there is only one source of traffic + * with an RMID value of '1'. + * arm64's PMG extends the PARTID/CLOSID space, there are multiple sources of + * traffic with a PMG value of '1', one for each CLOSID, meaning the RMID + * value is no longer unique. + * To account for this, resctrl uses an index. On x86 this is just the RMID, + * on arm64 it encodes the CLOSID and RMID. This gives a unique number. + * + * The domain's rmid_busy_llc and rmid_ptrs[] are sized by index. The arch code + * must accept an attempt to read every index. + */ +static inline struct rmid_entry *__rmid_entry(u32 idx) { struct rmid_entry *entry; + u32 closid, rmid; + + entry = &rmid_ptrs[idx]; + resctrl_arch_rmid_idx_decode(idx, &closid, &rmid); - entry = &rmid_ptrs[rmid]; - WARN_ON(entry->rmid != rmid); + WARN_ON_ONCE(entry->closid != closid); + WARN_ON_ONCE(entry->rmid != rmid); return entry; } @@ -190,7 +228,8 @@ static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_domain *hw_dom, } void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d, - u32 rmid, enum resctrl_event_id eventid) + u32 unused, u32 rmid, + enum resctrl_event_id eventid) { struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); struct arch_mbm_state *am; @@ -230,7 +269,8 @@ static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width) } int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d, - u32 rmid, enum resctrl_event_id eventid, u64 *val) + u32 unused, u32 rmid, enum resctrl_event_id eventid, + u64 *val, void *ignored) { struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); @@ -238,6 +278,8 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d, u64 msr_val, chunks; int ret; + resctrl_arch_rmid_read_context_check(); + if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask)) return -EINVAL; @@ -260,6 +302,17 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d, return 0; } +static void limbo_release_entry(struct rmid_entry *entry) +{ + lockdep_assert_held(&rdtgroup_mutex); + + rmid_limbo_count--; + list_add_tail(&entry->list, &rmid_free_lru); + + if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) + closid_num_dirty_rmid[entry->closid]--; +} + /* * Check the RMIDs that are marked as busy for this domain. If the * reported LLC occupancy is below the threshold clear the busy bit and @@ -269,11 +322,20 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d, void __check_limbo(struct rdt_domain *d, bool force_free) { struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; + u32 idx_limit = resctrl_arch_system_num_rmid_idx(); struct rmid_entry *entry; - u32 crmid = 1, nrmid; + u32 idx, cur_idx = 1; + void *arch_mon_ctx; bool rmid_dirty; u64 val = 0; + arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, QOS_L3_OCCUP_EVENT_ID); + if (IS_ERR(arch_mon_ctx)) { + pr_warn_ratelimited("Failed to allocate monitor context: %ld", + PTR_ERR(arch_mon_ctx)); + return; + } + /* * Skip RMID 0 and start from RMID 1 and check all the RMIDs that * are marked as busy for occupancy < threshold. If the occupancy @@ -281,53 +343,125 @@ void __check_limbo(struct rdt_domain *d, bool force_free) * RMID and move it to the free list when the counter reaches 0. */ for (;;) { - nrmid = find_next_bit(d->rmid_busy_llc, r->num_rmid, crmid); - if (nrmid >= r->num_rmid) + idx = find_next_bit(d->rmid_busy_llc, idx_limit, cur_idx); + if (idx >= idx_limit) break; - entry = __rmid_entry(nrmid); - - if (resctrl_arch_rmid_read(r, d, entry->rmid, - QOS_L3_OCCUP_EVENT_ID, &val)) { + entry = __rmid_entry(idx); + if (resctrl_arch_rmid_read(r, d, entry->closid, entry->rmid, + QOS_L3_OCCUP_EVENT_ID, &val, + arch_mon_ctx)) { rmid_dirty = true; } else { rmid_dirty = (val >= resctrl_rmid_realloc_threshold); } if (force_free || !rmid_dirty) { - clear_bit(entry->rmid, d->rmid_busy_llc); - if (!--entry->busy) { - rmid_limbo_count--; - list_add_tail(&entry->list, &rmid_free_lru); - } + clear_bit(idx, d->rmid_busy_llc); + if (!--entry->busy) + limbo_release_entry(entry); } - crmid = nrmid + 1; + cur_idx = idx + 1; } + + resctrl_arch_mon_ctx_free(r, QOS_L3_OCCUP_EVENT_ID, arch_mon_ctx); } -bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d) +bool has_busy_rmid(struct rdt_domain *d) { - return find_first_bit(d->rmid_busy_llc, r->num_rmid) != r->num_rmid; + u32 idx_limit = resctrl_arch_system_num_rmid_idx(); + + return find_first_bit(d->rmid_busy_llc, idx_limit) != idx_limit; +} + +static struct rmid_entry *resctrl_find_free_rmid(u32 closid) +{ + struct rmid_entry *itr; + u32 itr_idx, cmp_idx; + + if (list_empty(&rmid_free_lru)) + return rmid_limbo_count ? ERR_PTR(-EBUSY) : ERR_PTR(-ENOSPC); + + list_for_each_entry(itr, &rmid_free_lru, list) { + /* + * Get the index of this free RMID, and the index it would need + * to be if it were used with this CLOSID. + * If the CLOSID is irrelevant on this architecture, the two + * index values are always the same on every entry and thus the + * very first entry will be returned. + */ + itr_idx = resctrl_arch_rmid_idx_encode(itr->closid, itr->rmid); + cmp_idx = resctrl_arch_rmid_idx_encode(closid, itr->rmid); + + if (itr_idx == cmp_idx) + return itr; + } + + return ERR_PTR(-ENOSPC); +} + +/** + * resctrl_find_cleanest_closid() - Find a CLOSID where all the associated + * RMID are clean, or the CLOSID that has + * the most clean RMID. + * + * MPAM's equivalent of RMID are per-CLOSID, meaning a freshly allocated CLOSID + * may not be able to allocate clean RMID. To avoid this the allocator will + * choose the CLOSID with the most clean RMID. + * + * When the CLOSID and RMID are independent numbers, the first free CLOSID will + * be returned. + */ +int resctrl_find_cleanest_closid(void) +{ + u32 cleanest_closid = ~0; + int i = 0; + + lockdep_assert_held(&rdtgroup_mutex); + + if (!IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) + return -EIO; + + for (i = 0; i < closids_supported(); i++) { + int num_dirty; + + if (closid_allocated(i)) + continue; + + num_dirty = closid_num_dirty_rmid[i]; + if (num_dirty == 0) + return i; + + if (cleanest_closid == ~0) + cleanest_closid = i; + + if (num_dirty < closid_num_dirty_rmid[cleanest_closid]) + cleanest_closid = i; + } + + if (cleanest_closid == ~0) + return -ENOSPC; + + return cleanest_closid; } /* - * As of now the RMIDs allocation is global. - * However we keep track of which packages the RMIDs - * are used to optimize the limbo list management. + * For MPAM the RMID value is not unique, and has to be considered with + * the CLOSID. The (CLOSID, RMID) pair is allocated on all domains, which + * allows all domains to be managed by a single free list. + * Each domain also has a rmid_busy_llc to reduce the work of the limbo handler. */ -int alloc_rmid(void) +int alloc_rmid(u32 closid) { struct rmid_entry *entry; lockdep_assert_held(&rdtgroup_mutex); - if (list_empty(&rmid_free_lru)) - return rmid_limbo_count ? -EBUSY : -ENOSPC; + entry = resctrl_find_free_rmid(closid); + if (IS_ERR(entry)) + return PTR_ERR(entry); - entry = list_first_entry(&rmid_free_lru, - struct rmid_entry, list); list_del(&entry->list); - return entry->rmid; } @@ -335,47 +469,50 @@ static void add_rmid_to_limbo(struct rmid_entry *entry) { struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; struct rdt_domain *d; - int cpu, err; - u64 val = 0; + u32 idx; + + lockdep_assert_held(&rdtgroup_mutex); + + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + + idx = resctrl_arch_rmid_idx_encode(entry->closid, entry->rmid); entry->busy = 0; - cpu = get_cpu(); list_for_each_entry(d, &r->domains, list) { - if (cpumask_test_cpu(cpu, &d->cpu_mask)) { - err = resctrl_arch_rmid_read(r, d, entry->rmid, - QOS_L3_OCCUP_EVENT_ID, - &val); - if (err || val <= resctrl_rmid_realloc_threshold) - continue; - } - /* * For the first limbo RMID in the domain, * setup up the limbo worker. */ - if (!has_busy_rmid(r, d)) - cqm_setup_limbo_handler(d, CQM_LIMBOCHECK_INTERVAL); - set_bit(entry->rmid, d->rmid_busy_llc); + if (!has_busy_rmid(d)) + cqm_setup_limbo_handler(d, CQM_LIMBOCHECK_INTERVAL, + RESCTRL_PICK_ANY_CPU); + set_bit(idx, d->rmid_busy_llc); entry->busy++; } - put_cpu(); - if (entry->busy) - rmid_limbo_count++; - else - list_add_tail(&entry->list, &rmid_free_lru); + rmid_limbo_count++; + if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) + closid_num_dirty_rmid[entry->closid]++; } -void free_rmid(u32 rmid) +void free_rmid(u32 closid, u32 rmid) { + u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid); struct rmid_entry *entry; - if (!rmid) - return; - lockdep_assert_held(&rdtgroup_mutex); - entry = __rmid_entry(rmid); + /* + * Do not allow the default rmid to be free'd. Comparing by index + * allows architectures that ignore the closid parameter to avoid an + * unnecessary check. + */ + if (idx == resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID, + RESCTRL_RESERVED_RMID)) + return; + + entry = __rmid_entry(idx); if (is_llc_occupancy_enabled()) add_rmid_to_limbo(entry); @@ -383,33 +520,36 @@ void free_rmid(u32 rmid) list_add_tail(&entry->list, &rmid_free_lru); } -static struct mbm_state *get_mbm_state(struct rdt_domain *d, u32 rmid, - enum resctrl_event_id evtid) +static struct mbm_state *get_mbm_state(struct rdt_domain *d, u32 closid, + u32 rmid, enum resctrl_event_id evtid) { + u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid); + switch (evtid) { case QOS_L3_MBM_TOTAL_EVENT_ID: - return &d->mbm_total[rmid]; + return &d->mbm_total[idx]; case QOS_L3_MBM_LOCAL_EVENT_ID: - return &d->mbm_local[rmid]; + return &d->mbm_local[idx]; default: return NULL; } } -static int __mon_event_count(u32 rmid, struct rmid_read *rr) +static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr) { struct mbm_state *m; u64 tval = 0; if (rr->first) { - resctrl_arch_reset_rmid(rr->r, rr->d, rmid, rr->evtid); - m = get_mbm_state(rr->d, rmid, rr->evtid); + resctrl_arch_reset_rmid(rr->r, rr->d, closid, rmid, rr->evtid); + m = get_mbm_state(rr->d, closid, rmid, rr->evtid); if (m) memset(m, 0, sizeof(struct mbm_state)); return 0; } - rr->err = resctrl_arch_rmid_read(rr->r, rr->d, rmid, rr->evtid, &tval); + rr->err = resctrl_arch_rmid_read(rr->r, rr->d, closid, rmid, rr->evtid, + &tval, rr->arch_mon_ctx); if (rr->err) return rr->err; @@ -421,6 +561,7 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr) /* * mbm_bw_count() - Update bw count from values previously read by * __mon_event_count(). + * @closid: The closid used to identify the cached mbm_state. * @rmid: The rmid used to identify the cached mbm_state. * @rr: The struct rmid_read populated by __mon_event_count(). * @@ -429,9 +570,10 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr) * __mon_event_count() is compared with the chunks value from the previous * invocation. This must be called once per second to maintain values in MBps. */ -static void mbm_bw_count(u32 rmid, struct rmid_read *rr) +static void mbm_bw_count(u32 closid, u32 rmid, struct rmid_read *rr) { - struct mbm_state *m = &rr->d->mbm_local[rmid]; + u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid); + struct mbm_state *m = &rr->d->mbm_local[idx]; u64 cur_bw, bytes, cur_bytes; cur_bytes = rr->val; @@ -440,14 +582,11 @@ static void mbm_bw_count(u32 rmid, struct rmid_read *rr) cur_bw = bytes / SZ_1M; - if (m->delta_comp) - m->delta_bw = abs(cur_bw - m->prev_bw); - m->delta_comp = false; m->prev_bw = cur_bw; } /* - * This is called via IPI to read the CQM/MBM counters + * This is scheduled by mon_event_read() to read the CQM/MBM counters * on a domain. */ void mon_event_count(void *info) @@ -459,7 +598,7 @@ void mon_event_count(void *info) rdtgrp = rr->rgrp; - ret = __mon_event_count(rdtgrp->mon.rmid, rr); + ret = __mon_event_count(rdtgrp->closid, rdtgrp->mon.rmid, rr); /* * For Ctrl groups read data from child monitor groups and @@ -470,7 +609,8 @@ void mon_event_count(void *info) if (rdtgrp->type == RDTCTRL_GROUP) { list_for_each_entry(entry, head, mon.crdtgrp_list) { - if (__mon_event_count(entry->mon.rmid, rr) == 0) + if (__mon_event_count(entry->closid, entry->mon.rmid, + rr) == 0) ret = 0; } } @@ -520,9 +660,9 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) { u32 closid, rmid, cur_msr_val, new_msr_val; struct mbm_state *pmbm_data, *cmbm_data; - u32 cur_bw, delta_bw, user_bw; struct rdt_resource *r_mba; struct rdt_domain *dom_mba; + u32 cur_bw, user_bw, idx; struct list_head *head; struct rdtgroup *entry; @@ -533,7 +673,8 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) closid = rgrp->closid; rmid = rgrp->mon.rmid; - pmbm_data = &dom_mbm->mbm_local[rmid]; + idx = resctrl_arch_rmid_idx_encode(closid, rmid); + pmbm_data = &dom_mbm->mbm_local[idx]; dom_mba = get_domain_from_cpu(smp_processor_id(), r_mba); if (!dom_mba) { @@ -543,7 +684,6 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) cur_bw = pmbm_data->prev_bw; user_bw = dom_mba->mbps_val[closid]; - delta_bw = pmbm_data->delta_bw; /* MBA resource doesn't support CDP */ cur_msr_val = resctrl_arch_get_config(r_mba, dom_mba, closid, CDP_NONE); @@ -555,52 +695,35 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) list_for_each_entry(entry, head, mon.crdtgrp_list) { cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid]; cur_bw += cmbm_data->prev_bw; - delta_bw += cmbm_data->delta_bw; } /* * Scale up/down the bandwidth linearly for the ctrl group. The * bandwidth step is the bandwidth granularity specified by the * hardware. - * - * The delta_bw is used when increasing the bandwidth so that we - * dont alternately increase and decrease the control values - * continuously. - * - * For ex: consider cur_bw = 90MBps, user_bw = 100MBps and if - * bandwidth step is 20MBps(> user_bw - cur_bw), we would keep - * switching between 90 and 110 continuously if we only check - * cur_bw < user_bw. + * Always increase throttling if current bandwidth is above the + * target set by user. + * But avoid thrashing up and down on every poll by checking + * whether a decrease in throttling is likely to push the group + * back over target. E.g. if currently throttling to 30% of bandwidth + * on a system with 10% granularity steps, check whether moving to + * 40% would go past the limit by multiplying current bandwidth by + * "(30 + 10) / 30". */ if (cur_msr_val > r_mba->membw.min_bw && user_bw < cur_bw) { new_msr_val = cur_msr_val - r_mba->membw.bw_gran; } else if (cur_msr_val < MAX_MBA_BW && - (user_bw > (cur_bw + delta_bw))) { + (user_bw > (cur_bw * (cur_msr_val + r_mba->membw.min_bw) / cur_msr_val))) { new_msr_val = cur_msr_val + r_mba->membw.bw_gran; } else { return; } resctrl_arch_update_one(r_mba, dom_mba, closid, CDP_NONE, new_msr_val); - - /* - * Delta values are updated dynamically package wise for each - * rdtgrp every time the throttle MSR changes value. - * - * This is because (1)the increase in bandwidth is not perfectly - * linear and only "approximately" linear even when the hardware - * says it is linear.(2)Also since MBA is a core specific - * mechanism, the delta values vary based on number of cores used - * by the rdtgrp. - */ - pmbm_data->delta_comp = true; - list_for_each_entry(entry, head, mon.crdtgrp_list) { - cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid]; - cmbm_data->delta_comp = true; - } } -static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid) +static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, + u32 closid, u32 rmid) { struct rmid_read rr; @@ -615,12 +738,28 @@ static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid) if (is_mbm_total_enabled()) { rr.evtid = QOS_L3_MBM_TOTAL_EVENT_ID; rr.val = 0; - __mon_event_count(rmid, &rr); + rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid); + if (IS_ERR(rr.arch_mon_ctx)) { + pr_warn_ratelimited("Failed to allocate monitor context: %ld", + PTR_ERR(rr.arch_mon_ctx)); + return; + } + + __mon_event_count(closid, rmid, &rr); + + resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx); } if (is_mbm_local_enabled()) { rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID; rr.val = 0; - __mon_event_count(rmid, &rr); + rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid); + if (IS_ERR(rr.arch_mon_ctx)) { + pr_warn_ratelimited("Failed to allocate monitor context: %ld", + PTR_ERR(rr.arch_mon_ctx)); + return; + } + + __mon_event_count(closid, rmid, &rr); /* * Call the MBA software controller only for the @@ -628,7 +767,9 @@ static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid) * the software controller explicitly. */ if (is_mba_sc(NULL)) - mbm_bw_count(rmid, &rr); + mbm_bw_count(closid, rmid, &rr); + + resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx); } } @@ -639,106 +780,193 @@ static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid) void cqm_handle_limbo(struct work_struct *work) { unsigned long delay = msecs_to_jiffies(CQM_LIMBOCHECK_INTERVAL); - int cpu = smp_processor_id(); - struct rdt_resource *r; struct rdt_domain *d; + cpus_read_lock(); mutex_lock(&rdtgroup_mutex); - r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; d = container_of(work, struct rdt_domain, cqm_limbo.work); __check_limbo(d, false); - if (has_busy_rmid(r, d)) - schedule_delayed_work_on(cpu, &d->cqm_limbo, delay); + if (has_busy_rmid(d)) { + d->cqm_work_cpu = cpumask_any_housekeeping(&d->cpu_mask, + RESCTRL_PICK_ANY_CPU); + schedule_delayed_work_on(d->cqm_work_cpu, &d->cqm_limbo, + delay); + } mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); } -void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms) +/** + * cqm_setup_limbo_handler() - Schedule the limbo handler to run for this + * domain. + * @dom: The domain the limbo handler should run for. + * @delay_ms: How far in the future the handler should run. + * @exclude_cpu: Which CPU the handler should not run on, + * RESCTRL_PICK_ANY_CPU to pick any CPU. + */ +void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms, + int exclude_cpu) { unsigned long delay = msecs_to_jiffies(delay_ms); int cpu; - cpu = cpumask_any(&dom->cpu_mask); + cpu = cpumask_any_housekeeping(&dom->cpu_mask, exclude_cpu); dom->cqm_work_cpu = cpu; - schedule_delayed_work_on(cpu, &dom->cqm_limbo, delay); + if (cpu < nr_cpu_ids) + schedule_delayed_work_on(cpu, &dom->cqm_limbo, delay); } void mbm_handle_overflow(struct work_struct *work) { unsigned long delay = msecs_to_jiffies(MBM_OVERFLOW_INTERVAL); struct rdtgroup *prgrp, *crgrp; - int cpu = smp_processor_id(); struct list_head *head; struct rdt_resource *r; struct rdt_domain *d; + cpus_read_lock(); mutex_lock(&rdtgroup_mutex); - if (!static_branch_likely(&rdt_mon_enable_key)) + /* + * If the filesystem has been unmounted this work no longer needs to + * run. + */ + if (!resctrl_mounted || !resctrl_arch_mon_capable()) goto out_unlock; r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; d = container_of(work, struct rdt_domain, mbm_over.work); list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) { - mbm_update(r, d, prgrp->mon.rmid); + mbm_update(r, d, prgrp->closid, prgrp->mon.rmid); head = &prgrp->mon.crdtgrp_list; list_for_each_entry(crgrp, head, mon.crdtgrp_list) - mbm_update(r, d, crgrp->mon.rmid); + mbm_update(r, d, crgrp->closid, crgrp->mon.rmid); if (is_mba_sc(NULL)) update_mba_bw(prgrp, d); } - schedule_delayed_work_on(cpu, &d->mbm_over, delay); + /* + * Re-check for housekeeping CPUs. This allows the overflow handler to + * move off a nohz_full CPU quickly. + */ + d->mbm_work_cpu = cpumask_any_housekeeping(&d->cpu_mask, + RESCTRL_PICK_ANY_CPU); + schedule_delayed_work_on(d->mbm_work_cpu, &d->mbm_over, delay); out_unlock: mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); } -void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms) +/** + * mbm_setup_overflow_handler() - Schedule the overflow handler to run for this + * domain. + * @dom: The domain the overflow handler should run for. + * @delay_ms: How far in the future the handler should run. + * @exclude_cpu: Which CPU the handler should not run on, + * RESCTRL_PICK_ANY_CPU to pick any CPU. + */ +void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms, + int exclude_cpu) { unsigned long delay = msecs_to_jiffies(delay_ms); int cpu; - if (!static_branch_likely(&rdt_mon_enable_key)) + /* + * When a domain comes online there is no guarantee the filesystem is + * mounted. If not, there is no need to catch counter overflow. + */ + if (!resctrl_mounted || !resctrl_arch_mon_capable()) return; - cpu = cpumask_any(&dom->cpu_mask); + cpu = cpumask_any_housekeeping(&dom->cpu_mask, exclude_cpu); dom->mbm_work_cpu = cpu; - schedule_delayed_work_on(cpu, &dom->mbm_over, delay); + + if (cpu < nr_cpu_ids) + schedule_delayed_work_on(cpu, &dom->mbm_over, delay); } static int dom_data_init(struct rdt_resource *r) { + u32 idx_limit = resctrl_arch_system_num_rmid_idx(); + u32 num_closid = resctrl_arch_get_num_closid(r); struct rmid_entry *entry = NULL; - int i, nr_rmids; + int err = 0, i; + u32 idx; + + mutex_lock(&rdtgroup_mutex); + if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) { + u32 *tmp; + + /* + * If the architecture hasn't provided a sanitised value here, + * this may result in larger arrays than necessary. Resctrl will + * use a smaller system wide value based on the resources in + * use. + */ + tmp = kcalloc(num_closid, sizeof(*tmp), GFP_KERNEL); + if (!tmp) { + err = -ENOMEM; + goto out_unlock; + } - nr_rmids = r->num_rmid; - rmid_ptrs = kcalloc(nr_rmids, sizeof(struct rmid_entry), GFP_KERNEL); - if (!rmid_ptrs) - return -ENOMEM; + closid_num_dirty_rmid = tmp; + } + + rmid_ptrs = kcalloc(idx_limit, sizeof(struct rmid_entry), GFP_KERNEL); + if (!rmid_ptrs) { + if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) { + kfree(closid_num_dirty_rmid); + closid_num_dirty_rmid = NULL; + } + err = -ENOMEM; + goto out_unlock; + } - for (i = 0; i < nr_rmids; i++) { + for (i = 0; i < idx_limit; i++) { entry = &rmid_ptrs[i]; INIT_LIST_HEAD(&entry->list); - entry->rmid = i; + resctrl_arch_rmid_idx_decode(i, &entry->closid, &entry->rmid); list_add_tail(&entry->list, &rmid_free_lru); } /* - * RMID 0 is special and is always allocated. It's used for all - * tasks that are not monitored. + * RESCTRL_RESERVED_CLOSID and RESCTRL_RESERVED_RMID are special and + * are always allocated. These are used for the rdtgroup_default + * control group, which will be setup later in rdtgroup_init(). */ - entry = __rmid_entry(0); + idx = resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID, + RESCTRL_RESERVED_RMID); + entry = __rmid_entry(idx); list_del(&entry->list); - return 0; +out_unlock: + mutex_unlock(&rdtgroup_mutex); + + return err; +} + +static void __exit dom_data_exit(void) +{ + mutex_lock(&rdtgroup_mutex); + + if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) { + kfree(closid_num_dirty_rmid); + closid_num_dirty_rmid = NULL; + } + + kfree(rmid_ptrs); + rmid_ptrs = NULL; + + mutex_unlock(&rdtgroup_mutex); } static struct mon_evt llc_occupancy_event = { @@ -813,6 +1041,12 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r) return ret; if (rdt_cpu_has(X86_FEATURE_BMEC)) { + u32 eax, ebx, ecx, edx; + + /* Detect list of bandwidth sources that can be tracked */ + cpuid_count(0x80000020, 3, &eax, &ebx, &ecx, &edx); + hw_res->mbm_cfg_mask = ecx & MAX_EVT_CONFIG_BITS; + if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) { mbm_total_event.configurable = true; mbm_config_rftype_init("mbm_total_bytes_config"); @@ -830,6 +1064,11 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r) return 0; } +void __exit rdt_put_mon_l3_config(void) +{ + dom_data_exit(); +} + void __init intel_rdt_mbm_apply_quirk(void) { int cf_index; diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c index 8f559eeae08e..884b88e25141 100644 --- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c +++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c @@ -581,7 +581,7 @@ static int rdtgroup_locksetup_user_restrict(struct rdtgroup *rdtgrp) if (ret) goto err_cpus; - if (rdt_mon_capable) { + if (resctrl_arch_mon_capable()) { ret = rdtgroup_kn_mode_restrict(rdtgrp, "mon_groups"); if (ret) goto err_cpus_list; @@ -628,7 +628,7 @@ static int rdtgroup_locksetup_user_restore(struct rdtgroup *rdtgrp) if (ret) goto err_cpus; - if (rdt_mon_capable) { + if (resctrl_arch_mon_capable()) { ret = rdtgroup_kn_mode_restore(rdtgrp, "mon_groups", 0777); if (ret) goto err_cpus_list; @@ -752,7 +752,7 @@ int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp) * anymore when this group would be used for pseudo-locking. This * is safe to call on platforms not capable of monitoring. */ - free_rmid(rdtgrp->mon.rmid); + free_rmid(rdtgrp->closid, rdtgrp->mon.rmid); ret = 0; goto out; @@ -776,8 +776,8 @@ int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp) { int ret; - if (rdt_mon_capable) { - ret = alloc_rmid(); + if (resctrl_arch_mon_capable()) { + ret = alloc_rmid(rdtgrp->closid); if (ret < 0) { rdt_last_cmd_puts("Out of RMIDs\n"); return ret; @@ -787,7 +787,7 @@ int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp) ret = rdtgroup_locksetup_user_restore(rdtgrp); if (ret) { - free_rmid(rdtgrp->mon.rmid); + free_rmid(rdtgrp->closid, rdtgrp->mon.rmid); return ret; } @@ -844,6 +844,9 @@ bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d) struct rdt_domain *d_i; bool ret = false; + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + if (!zalloc_cpumask_var(&cpu_with_psl, GFP_KERNEL)) return true; diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 69a1de92384a..011e17efb1a6 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -35,6 +35,10 @@ DEFINE_STATIC_KEY_FALSE(rdt_enable_key); DEFINE_STATIC_KEY_FALSE(rdt_mon_enable_key); DEFINE_STATIC_KEY_FALSE(rdt_alloc_enable_key); + +/* Mutex to protect rdtgroup access. */ +DEFINE_MUTEX(rdtgroup_mutex); + static struct kernfs_root *rdt_root; struct rdtgroup rdtgroup_default; LIST_HEAD(rdt_all_groups); @@ -42,6 +46,9 @@ LIST_HEAD(rdt_all_groups); /* list of entries for the schemata file */ LIST_HEAD(resctrl_schema_all); +/* The filesystem can only be mounted once. */ +bool resctrl_mounted; + /* Kernel fs node for "info" directory under root */ static struct kernfs_node *kn_info; @@ -102,7 +109,7 @@ void rdt_staged_configs_clear(void) * * Using a global CLOSID across all resources has some advantages and * some drawbacks: - * + We can simply set "current->closid" to assign a task to a resource + * + We can simply set current's closid to assign a task to a resource * group. * + Context switch code can avoid extra memory references deciding which * CLOSID to load into the PQR_ASSOC MSR @@ -111,7 +118,7 @@ void rdt_staged_configs_clear(void) * - Our choices on how to configure each resource become progressively more * limited as the number of resources grows. */ -static int closid_free_map; +static unsigned long closid_free_map; static int closid_free_map_len; int closids_supported(void) @@ -130,26 +137,39 @@ static void closid_init(void) closid_free_map = BIT_MASK(rdt_min_closid) - 1; - /* CLOSID 0 is always reserved for the default group */ - closid_free_map &= ~1; + /* RESCTRL_RESERVED_CLOSID is always reserved for the default group */ + __clear_bit(RESCTRL_RESERVED_CLOSID, &closid_free_map); closid_free_map_len = rdt_min_closid; } static int closid_alloc(void) { - u32 closid = ffs(closid_free_map); + int cleanest_closid; + u32 closid; - if (closid == 0) - return -ENOSPC; - closid--; - closid_free_map &= ~(1 << closid); + lockdep_assert_held(&rdtgroup_mutex); + + if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) { + cleanest_closid = resctrl_find_cleanest_closid(); + if (cleanest_closid < 0) + return cleanest_closid; + closid = cleanest_closid; + } else { + closid = ffs(closid_free_map); + if (closid == 0) + return -ENOSPC; + closid--; + } + __clear_bit(closid, &closid_free_map); return closid; } void closid_free(int closid) { - closid_free_map |= 1 << closid; + lockdep_assert_held(&rdtgroup_mutex); + + __set_bit(closid, &closid_free_map); } /** @@ -159,9 +179,11 @@ void closid_free(int closid) * Return: true if @closid is currently associated with a resource group, * false if @closid is free */ -static bool closid_allocated(unsigned int closid) +bool closid_allocated(unsigned int closid) { - return (closid_free_map & (1 << closid)) == 0; + lockdep_assert_held(&rdtgroup_mutex); + + return !test_bit(closid, &closid_free_map); } /** @@ -559,14 +581,26 @@ static void update_task_closid_rmid(struct task_struct *t) _update_task_closid_rmid(t); } +static bool task_in_rdtgroup(struct task_struct *tsk, struct rdtgroup *rdtgrp) +{ + u32 closid, rmid = rdtgrp->mon.rmid; + + if (rdtgrp->type == RDTCTRL_GROUP) + closid = rdtgrp->closid; + else if (rdtgrp->type == RDTMON_GROUP) + closid = rdtgrp->mon.parent->closid; + else + return false; + + return resctrl_arch_match_closid(tsk, closid) && + resctrl_arch_match_rmid(tsk, closid, rmid); +} + static int __rdtgroup_move_task(struct task_struct *tsk, struct rdtgroup *rdtgrp) { /* If the task is already in rdtgrp, no need to move the task. */ - if ((rdtgrp->type == RDTCTRL_GROUP && tsk->closid == rdtgrp->closid && - tsk->rmid == rdtgrp->mon.rmid) || - (rdtgrp->type == RDTMON_GROUP && tsk->rmid == rdtgrp->mon.rmid && - tsk->closid == rdtgrp->mon.parent->closid)) + if (task_in_rdtgroup(tsk, rdtgrp)) return 0; /* @@ -577,19 +611,19 @@ static int __rdtgroup_move_task(struct task_struct *tsk, * For monitor groups, can move the tasks only from * their parent CTRL group. */ - - if (rdtgrp->type == RDTCTRL_GROUP) { - WRITE_ONCE(tsk->closid, rdtgrp->closid); - WRITE_ONCE(tsk->rmid, rdtgrp->mon.rmid); - } else if (rdtgrp->type == RDTMON_GROUP) { - if (rdtgrp->mon.parent->closid == tsk->closid) { - WRITE_ONCE(tsk->rmid, rdtgrp->mon.rmid); - } else { - rdt_last_cmd_puts("Can't move task to different control group\n"); - return -EINVAL; - } + if (rdtgrp->type == RDTMON_GROUP && + !resctrl_arch_match_closid(tsk, rdtgrp->mon.parent->closid)) { + rdt_last_cmd_puts("Can't move task to different control group\n"); + return -EINVAL; } + if (rdtgrp->type == RDTMON_GROUP) + resctrl_arch_set_closid_rmid(tsk, rdtgrp->mon.parent->closid, + rdtgrp->mon.rmid); + else + resctrl_arch_set_closid_rmid(tsk, rdtgrp->closid, + rdtgrp->mon.rmid); + /* * Ensure the task's closid and rmid are written before determining if * the task is current that will decide if it will be interrupted. @@ -611,14 +645,15 @@ static int __rdtgroup_move_task(struct task_struct *tsk, static bool is_closid_match(struct task_struct *t, struct rdtgroup *r) { - return (rdt_alloc_capable && - (r->type == RDTCTRL_GROUP) && (t->closid == r->closid)); + return (resctrl_arch_alloc_capable() && (r->type == RDTCTRL_GROUP) && + resctrl_arch_match_closid(t, r->closid)); } static bool is_rmid_match(struct task_struct *t, struct rdtgroup *r) { - return (rdt_mon_capable && - (r->type == RDTMON_GROUP) && (t->rmid == r->mon.rmid)); + return (resctrl_arch_mon_capable() && (r->type == RDTMON_GROUP) && + resctrl_arch_match_rmid(t, r->mon.parent->closid, + r->mon.rmid)); } /** @@ -853,7 +888,7 @@ int proc_resctrl_show(struct seq_file *s, struct pid_namespace *ns, mutex_lock(&rdtgroup_mutex); /* Return empty if resctrl has not been mounted. */ - if (!static_branch_unlikely(&rdt_enable_key)) { + if (!resctrl_mounted) { seq_puts(s, "res:\nmon:\n"); goto unlock; } @@ -869,7 +904,7 @@ int proc_resctrl_show(struct seq_file *s, struct pid_namespace *ns, rdtg->mode != RDT_MODE_EXCLUSIVE) continue; - if (rdtg->closid != tsk->closid) + if (!resctrl_arch_match_closid(tsk, rdtg->closid)) continue; seq_printf(s, "res:%s%s\n", (rdtg == &rdtgroup_default) ? "/" : "", @@ -877,7 +912,8 @@ int proc_resctrl_show(struct seq_file *s, struct pid_namespace *ns, seq_puts(s, "mon:"); list_for_each_entry(crg, &rdtg->mon.crdtgrp_list, mon.crdtgrp_list) { - if (tsk->rmid != crg->mon.rmid) + if (!resctrl_arch_match_rmid(tsk, crg->mon.parent->closid, + crg->mon.rmid)) continue; seq_printf(s, "%s", crg->kn->name); break; @@ -982,6 +1018,7 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of, bool sep = false; u32 ctrl_val; + cpus_read_lock(); mutex_lock(&rdtgroup_mutex); hw_shareable = r->cache.shareable_bits; list_for_each_entry(dom, &r->domains, list) { @@ -1042,6 +1079,7 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of, } seq_putc(seq, '\n'); mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); return 0; } @@ -1297,6 +1335,9 @@ static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp) struct rdt_domain *d; u32 ctrl; + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + list_for_each_entry(s, &resctrl_schema_all, list) { r = s->res; if (r->rid == RDT_RESOURCE_MBA || r->rid == RDT_RESOURCE_SMBA) @@ -1561,6 +1602,7 @@ static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid struct rdt_domain *dom; bool sep = false; + cpus_read_lock(); mutex_lock(&rdtgroup_mutex); list_for_each_entry(dom, &r->domains, list) { @@ -1577,6 +1619,7 @@ static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid seq_puts(s, "\n"); mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); return 0; } @@ -1614,17 +1657,10 @@ static void mon_event_config_write(void *info) wrmsr(MSR_IA32_EVT_CFG_BASE + index, mon_info->mon_config, 0); } -static int mbm_config_write_domain(struct rdt_resource *r, - struct rdt_domain *d, u32 evtid, u32 val) +static void mbm_config_write_domain(struct rdt_resource *r, + struct rdt_domain *d, u32 evtid, u32 val) { struct mon_config_info mon_info = {0}; - int ret = 0; - - /* mon_config cannot be more than the supported set of events */ - if (val > MAX_EVT_CONFIG_BITS) { - rdt_last_cmd_puts("Invalid event configuration\n"); - return -EINVAL; - } /* * Read the current config value first. If both are the same then @@ -1633,7 +1669,7 @@ static int mbm_config_write_domain(struct rdt_resource *r, mon_info.evtid = evtid; mondata_config_read(d, &mon_info); if (mon_info.mon_config == val) - goto out; + return; mon_info.mon_config = val; @@ -1656,17 +1692,17 @@ static int mbm_config_write_domain(struct rdt_resource *r, * mbm_local and mbm_total counts for all the RMIDs. */ resctrl_arch_reset_rmid_all(r, d); - -out: - return ret; } static int mon_config_write(struct rdt_resource *r, char *tok, u32 evtid) { + struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); char *dom_str = NULL, *id_str; unsigned long dom_id, val; struct rdt_domain *d; - int ret = 0; + + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); next: if (!tok || tok[0] == '\0') @@ -1686,11 +1722,16 @@ next: return -EINVAL; } + /* Value from user cannot be more than the supported set of events */ + if ((val & hw_res->mbm_cfg_mask) != val) { + rdt_last_cmd_printf("Invalid event configuration: max valid mask is 0x%02x\n", + hw_res->mbm_cfg_mask); + return -EINVAL; + } + list_for_each_entry(d, &r->domains, list) { if (d->id == dom_id) { - ret = mbm_config_write_domain(r, d, evtid, val); - if (ret) - return -EINVAL; + mbm_config_write_domain(r, d, evtid, val); goto next; } } @@ -1709,6 +1750,7 @@ static ssize_t mbm_total_bytes_config_write(struct kernfs_open_file *of, if (nbytes == 0 || buf[nbytes - 1] != '\n') return -EINVAL; + cpus_read_lock(); mutex_lock(&rdtgroup_mutex); rdt_last_cmd_clear(); @@ -1718,6 +1760,7 @@ static ssize_t mbm_total_bytes_config_write(struct kernfs_open_file *of, ret = mon_config_write(r, buf, QOS_L3_MBM_TOTAL_EVENT_ID); mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); return ret ?: nbytes; } @@ -1733,6 +1776,7 @@ static ssize_t mbm_local_bytes_config_write(struct kernfs_open_file *of, if (nbytes == 0 || buf[nbytes - 1] != '\n') return -EINVAL; + cpus_read_lock(); mutex_lock(&rdtgroup_mutex); rdt_last_cmd_clear(); @@ -1742,6 +1786,7 @@ static ssize_t mbm_local_bytes_config_write(struct kernfs_open_file *of, ret = mon_config_write(r, buf, QOS_L3_MBM_LOCAL_EVENT_ID); mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); return ret ?: nbytes; } @@ -2218,6 +2263,9 @@ static int set_cache_qos_cfg(int level, bool enable) struct rdt_domain *d; int cpu; + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + if (level == RDT_RESOURCE_L3) update = l3_qos_cfg_update; else if (level == RDT_RESOURCE_L2) @@ -2417,6 +2465,7 @@ struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn) rdtgroup_kn_get(rdtgrp, kn); + cpus_read_lock(); mutex_lock(&rdtgroup_mutex); /* Was this group deleted while we waited? */ @@ -2434,6 +2483,8 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn) return; mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); + rdtgroup_kn_put(rdtgrp, kn); } @@ -2584,7 +2635,7 @@ static int rdt_get_tree(struct fs_context *fc) /* * resctrl file system can only be mounted once. */ - if (static_branch_unlikely(&rdt_enable_key)) { + if (resctrl_mounted) { ret = -EBUSY; goto out; } @@ -2605,7 +2656,7 @@ static int rdt_get_tree(struct fs_context *fc) closid_init(); - if (rdt_mon_capable) + if (resctrl_arch_mon_capable()) flags |= RFTYPE_MON; ret = rdtgroup_add_files(rdtgroup_default.kn, flags); @@ -2618,7 +2669,7 @@ static int rdt_get_tree(struct fs_context *fc) if (ret < 0) goto out_schemata_free; - if (rdt_mon_capable) { + if (resctrl_arch_mon_capable()) { ret = mongroup_create_dir(rdtgroup_default.kn, &rdtgroup_default, "mon_groups", &kn_mongrp); @@ -2640,18 +2691,19 @@ static int rdt_get_tree(struct fs_context *fc) if (ret < 0) goto out_psl; - if (rdt_alloc_capable) - static_branch_enable_cpuslocked(&rdt_alloc_enable_key); - if (rdt_mon_capable) - static_branch_enable_cpuslocked(&rdt_mon_enable_key); + if (resctrl_arch_alloc_capable()) + resctrl_arch_enable_alloc(); + if (resctrl_arch_mon_capable()) + resctrl_arch_enable_mon(); - if (rdt_alloc_capable || rdt_mon_capable) - static_branch_enable_cpuslocked(&rdt_enable_key); + if (resctrl_arch_alloc_capable() || resctrl_arch_mon_capable()) + resctrl_mounted = true; if (is_mbm_enabled()) { r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; list_for_each_entry(dom, &r->domains, list) - mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL); + mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL, + RESCTRL_PICK_ANY_CPU); } goto out; @@ -2659,10 +2711,10 @@ static int rdt_get_tree(struct fs_context *fc) out_psl: rdt_pseudo_lock_release(); out_mondata: - if (rdt_mon_capable) + if (resctrl_arch_mon_capable()) kernfs_remove(kn_mondata); out_mongrp: - if (rdt_mon_capable) + if (resctrl_arch_mon_capable()) kernfs_remove(kn_mongrp); out_info: kernfs_remove(kn_info); @@ -2765,6 +2817,9 @@ static int reset_all_ctrls(struct rdt_resource *r) struct rdt_domain *d; int i; + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) return -ENOMEM; @@ -2810,8 +2865,8 @@ static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to, for_each_process_thread(p, t) { if (!from || is_closid_match(t, from) || is_rmid_match(t, from)) { - WRITE_ONCE(t->closid, to->closid); - WRITE_ONCE(t->rmid, to->mon.rmid); + resctrl_arch_set_closid_rmid(t, to->closid, + to->mon.rmid); /* * Order the closid/rmid stores above before the loads @@ -2842,7 +2897,7 @@ static void free_all_child_rdtgrp(struct rdtgroup *rdtgrp) head = &rdtgrp->mon.crdtgrp_list; list_for_each_entry_safe(sentry, stmp, head, mon.crdtgrp_list) { - free_rmid(sentry->mon.rmid); + free_rmid(sentry->closid, sentry->mon.rmid); list_del(&sentry->mon.crdtgrp_list); if (atomic_read(&sentry->waitcount) != 0) @@ -2882,7 +2937,7 @@ static void rmdir_all_sub(void) cpumask_or(&rdtgroup_default.cpu_mask, &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask); - free_rmid(rdtgrp->mon.rmid); + free_rmid(rdtgrp->closid, rdtgrp->mon.rmid); kernfs_remove(rdtgrp->kn); list_del(&rdtgrp->rdtgroup_list); @@ -2917,9 +2972,11 @@ static void rdt_kill_sb(struct super_block *sb) rdtgroup_default.mode = RDT_MODE_SHAREABLE; schemata_list_destroy(); rdtgroup_destroy_root(); - static_branch_disable_cpuslocked(&rdt_alloc_enable_key); - static_branch_disable_cpuslocked(&rdt_mon_enable_key); - static_branch_disable_cpuslocked(&rdt_enable_key); + if (resctrl_arch_alloc_capable()) + resctrl_arch_disable_alloc(); + if (resctrl_arch_mon_capable()) + resctrl_arch_disable_mon(); + resctrl_mounted = false; kernfs_kill_sb(sb); mutex_unlock(&rdtgroup_mutex); cpus_read_unlock(); @@ -3047,6 +3104,9 @@ static int mkdir_mondata_subdir_alldom(struct kernfs_node *parent_kn, struct rdt_domain *dom; int ret; + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + list_for_each_entry(dom, &r->domains, list) { ret = mkdir_mondata_subdir(parent_kn, dom, r, prgrp); if (ret) @@ -3293,6 +3353,36 @@ out: return ret; } +static int mkdir_rdt_prepare_rmid_alloc(struct rdtgroup *rdtgrp) +{ + int ret; + + if (!resctrl_arch_mon_capable()) + return 0; + + ret = alloc_rmid(rdtgrp->closid); + if (ret < 0) { + rdt_last_cmd_puts("Out of RMIDs\n"); + return ret; + } + rdtgrp->mon.rmid = ret; + + ret = mkdir_mondata_all(rdtgrp->kn, rdtgrp, &rdtgrp->mon.mon_data_kn); + if (ret) { + rdt_last_cmd_puts("kernfs subdir error\n"); + free_rmid(rdtgrp->closid, rdtgrp->mon.rmid); + return ret; + } + + return 0; +} + +static void mkdir_rdt_prepare_rmid_free(struct rdtgroup *rgrp) +{ + if (resctrl_arch_mon_capable()) + free_rmid(rgrp->closid, rgrp->mon.rmid); +} + static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, const char *name, umode_t mode, enum rdt_group_type rtype, struct rdtgroup **r) @@ -3353,7 +3443,7 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, if (rtype == RDTCTRL_GROUP) { files = RFTYPE_BASE | RFTYPE_CTRL; - if (rdt_mon_capable) + if (resctrl_arch_mon_capable()) files |= RFTYPE_MON; } else { files = RFTYPE_BASE | RFTYPE_MON; @@ -3365,29 +3455,11 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, goto out_destroy; } - if (rdt_mon_capable) { - ret = alloc_rmid(); - if (ret < 0) { - rdt_last_cmd_puts("Out of RMIDs\n"); - goto out_destroy; - } - rdtgrp->mon.rmid = ret; - - ret = mkdir_mondata_all(kn, rdtgrp, &rdtgrp->mon.mon_data_kn); - if (ret) { - rdt_last_cmd_puts("kernfs subdir error\n"); - goto out_idfree; - } - } - kernfs_activate(kn); - /* * The caller unlocks the parent_kn upon success. */ return 0; -out_idfree: - free_rmid(rdtgrp->mon.rmid); out_destroy: kernfs_put(rdtgrp->kn); kernfs_remove(rdtgrp->kn); @@ -3401,7 +3473,6 @@ out_unlock: static void mkdir_rdt_prepare_clean(struct rdtgroup *rgrp) { kernfs_remove(rgrp->kn); - free_rmid(rgrp->mon.rmid); rdtgroup_remove(rgrp); } @@ -3423,12 +3494,21 @@ static int rdtgroup_mkdir_mon(struct kernfs_node *parent_kn, prgrp = rdtgrp->mon.parent; rdtgrp->closid = prgrp->closid; + ret = mkdir_rdt_prepare_rmid_alloc(rdtgrp); + if (ret) { + mkdir_rdt_prepare_clean(rdtgrp); + goto out_unlock; + } + + kernfs_activate(rdtgrp->kn); + /* * Add the rdtgrp to the list of rdtgrps the parent * ctrl_mon group has to track. */ list_add_tail(&rdtgrp->mon.crdtgrp_list, &prgrp->mon.crdtgrp_list); +out_unlock: rdtgroup_kn_unlock(parent_kn); return ret; } @@ -3459,13 +3539,20 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn, ret = 0; rdtgrp->closid = closid; + + ret = mkdir_rdt_prepare_rmid_alloc(rdtgrp); + if (ret) + goto out_closid_free; + + kernfs_activate(rdtgrp->kn); + ret = rdtgroup_init_alloc(rdtgrp); if (ret < 0) - goto out_id_free; + goto out_rmid_free; list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups); - if (rdt_mon_capable) { + if (resctrl_arch_mon_capable()) { /* * Create an empty mon_groups directory to hold the subset * of tasks and cpus to monitor. @@ -3481,7 +3568,9 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn, out_del_list: list_del(&rdtgrp->rdtgroup_list); -out_id_free: +out_rmid_free: + mkdir_rdt_prepare_rmid_free(rdtgrp); +out_closid_free: closid_free(closid); out_common_fail: mkdir_rdt_prepare_clean(rdtgrp); @@ -3518,14 +3607,14 @@ static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name, * allocation is supported, add a control and monitoring * subdirectory */ - if (rdt_alloc_capable && parent_kn == rdtgroup_default.kn) + if (resctrl_arch_alloc_capable() && parent_kn == rdtgroup_default.kn) return rdtgroup_mkdir_ctrl_mon(parent_kn, name, mode); /* * If RDT monitoring is supported and the parent directory is a valid * "mon_groups" directory, add a monitoring subdirectory. */ - if (rdt_mon_capable && is_mon_groups(parent_kn, name)) + if (resctrl_arch_mon_capable() && is_mon_groups(parent_kn, name)) return rdtgroup_mkdir_mon(parent_kn, name, mode); return -EPERM; @@ -3550,7 +3639,7 @@ static int rdtgroup_rmdir_mon(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask) update_closid_rmid(tmpmask, NULL); rdtgrp->flags = RDT_DELETED; - free_rmid(rdtgrp->mon.rmid); + free_rmid(rdtgrp->closid, rdtgrp->mon.rmid); /* * Remove the rdtgrp from the parent ctrl_mon group's list @@ -3596,8 +3685,8 @@ static int rdtgroup_rmdir_ctrl(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask) cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask); update_closid_rmid(tmpmask, NULL); + free_rmid(rdtgrp->closid, rdtgrp->mon.rmid); closid_free(rdtgrp->closid); - free_rmid(rdtgrp->mon.rmid); rdtgroup_ctrl_remove(rdtgrp); @@ -3829,8 +3918,8 @@ static void __init rdtgroup_setup_default(void) { mutex_lock(&rdtgroup_mutex); - rdtgroup_default.closid = 0; - rdtgroup_default.mon.rmid = 0; + rdtgroup_default.closid = RESCTRL_RESERVED_CLOSID; + rdtgroup_default.mon.rmid = RESCTRL_RESERVED_RMID; rdtgroup_default.type = RDTCTRL_GROUP; INIT_LIST_HEAD(&rdtgroup_default.mon.crdtgrp_list); @@ -3848,24 +3937,24 @@ static void domain_destroy_mon_state(struct rdt_domain *d) void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d) { - lockdep_assert_held(&rdtgroup_mutex); + mutex_lock(&rdtgroup_mutex); if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA) mba_sc_domain_destroy(r, d); if (!r->mon_capable) - return; + goto out_unlock; /* * If resctrl is mounted, remove all the * per domain monitor data directories. */ - if (static_branch_unlikely(&rdt_mon_enable_key)) + if (resctrl_mounted && resctrl_arch_mon_capable()) rmdir_mondata_subdir_allrdtgrp(r, d->id); if (is_mbm_enabled()) cancel_delayed_work(&d->mbm_over); - if (is_llc_occupancy_enabled() && has_busy_rmid(r, d)) { + if (is_llc_occupancy_enabled() && has_busy_rmid(d)) { /* * When a package is going down, forcefully * decrement rmid->ebusy. There is no way to know @@ -3879,20 +3968,24 @@ void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d) } domain_destroy_mon_state(d); + +out_unlock: + mutex_unlock(&rdtgroup_mutex); } static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d) { + u32 idx_limit = resctrl_arch_system_num_rmid_idx(); size_t tsize; if (is_llc_occupancy_enabled()) { - d->rmid_busy_llc = bitmap_zalloc(r->num_rmid, GFP_KERNEL); + d->rmid_busy_llc = bitmap_zalloc(idx_limit, GFP_KERNEL); if (!d->rmid_busy_llc) return -ENOMEM; } if (is_mbm_total_enabled()) { tsize = sizeof(*d->mbm_total); - d->mbm_total = kcalloc(r->num_rmid, tsize, GFP_KERNEL); + d->mbm_total = kcalloc(idx_limit, tsize, GFP_KERNEL); if (!d->mbm_total) { bitmap_free(d->rmid_busy_llc); return -ENOMEM; @@ -3900,7 +3993,7 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d) } if (is_mbm_local_enabled()) { tsize = sizeof(*d->mbm_local); - d->mbm_local = kcalloc(r->num_rmid, tsize, GFP_KERNEL); + d->mbm_local = kcalloc(idx_limit, tsize, GFP_KERNEL); if (!d->mbm_local) { bitmap_free(d->rmid_busy_llc); kfree(d->mbm_total); @@ -3913,34 +4006,97 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d) int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d) { - int err; + int err = 0; - lockdep_assert_held(&rdtgroup_mutex); + mutex_lock(&rdtgroup_mutex); - if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA) + if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA) { /* RDT_RESOURCE_MBA is never mon_capable */ - return mba_sc_domain_allocate(r, d); + err = mba_sc_domain_allocate(r, d); + goto out_unlock; + } if (!r->mon_capable) - return 0; + goto out_unlock; err = domain_setup_mon_state(r, d); if (err) - return err; + goto out_unlock; if (is_mbm_enabled()) { INIT_DELAYED_WORK(&d->mbm_over, mbm_handle_overflow); - mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL); + mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL, + RESCTRL_PICK_ANY_CPU); } if (is_llc_occupancy_enabled()) INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo); - /* If resctrl is mounted, add per domain monitor data directories. */ - if (static_branch_unlikely(&rdt_mon_enable_key)) + /* + * If the filesystem is not mounted then only the default resource group + * exists. Creation of its directories is deferred until mount time + * by rdt_get_tree() calling mkdir_mondata_all(). + * If resctrl is mounted, add per domain monitor data directories. + */ + if (resctrl_mounted && resctrl_arch_mon_capable()) mkdir_mondata_subdir_allrdtgrp(r, d); - return 0; +out_unlock: + mutex_unlock(&rdtgroup_mutex); + + return err; +} + +void resctrl_online_cpu(unsigned int cpu) +{ + mutex_lock(&rdtgroup_mutex); + /* The CPU is set in default rdtgroup after online. */ + cpumask_set_cpu(cpu, &rdtgroup_default.cpu_mask); + mutex_unlock(&rdtgroup_mutex); +} + +static void clear_childcpus(struct rdtgroup *r, unsigned int cpu) +{ + struct rdtgroup *cr; + + list_for_each_entry(cr, &r->mon.crdtgrp_list, mon.crdtgrp_list) { + if (cpumask_test_and_clear_cpu(cpu, &cr->cpu_mask)) + break; + } +} + +void resctrl_offline_cpu(unsigned int cpu) +{ + struct rdt_resource *l3 = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; + struct rdtgroup *rdtgrp; + struct rdt_domain *d; + + mutex_lock(&rdtgroup_mutex); + list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) { + if (cpumask_test_and_clear_cpu(cpu, &rdtgrp->cpu_mask)) { + clear_childcpus(rdtgrp, cpu); + break; + } + } + + if (!l3->mon_capable) + goto out_unlock; + + d = get_domain_from_cpu(cpu, l3); + if (d) { + if (is_mbm_enabled() && cpu == d->mbm_work_cpu) { + cancel_delayed_work(&d->mbm_over); + mbm_setup_overflow_handler(d, 0, cpu); + } + if (is_llc_occupancy_enabled() && cpu == d->cqm_work_cpu && + has_busy_rmid(d)) { + cancel_delayed_work(&d->cqm_limbo); + cqm_setup_limbo_handler(d, 0, cpu); + } + } + +out_unlock: + mutex_unlock(&rdtgroup_mutex); } /* diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index b6b044356f1b..e74d0c4286c1 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -26,6 +26,7 @@ #include <linux/vmalloc.h> #include <linux/memblock.h> +#include <asm/bootparam.h> #include <asm/processor.h> #include <asm/hardirq.h> #include <asm/nmi.h> @@ -40,6 +41,7 @@ #include <asm/intel_pt.h> #include <asm/crash.h> #include <asm/cmdline.h> +#include <asm/sev.h> /* Used while preparing memory map entries for second kernel */ struct crash_memmap_data { @@ -59,6 +61,8 @@ static void kdump_nmi_callback(int cpu, struct pt_regs *regs) */ cpu_emergency_stop_pt(); + kdump_sev_callback(); + disable_local_APIC(); } diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index f18ca44c904b..44a91ef5a23b 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -410,7 +410,7 @@ static void __die_header(const char *str, struct pt_regs *regs, long err) IS_ENABLED(CONFIG_SMP) ? " SMP" : "", debug_pagealloc_enabled() ? " DEBUG_PAGEALLOC" : "", IS_ENABLED(CONFIG_KASAN) ? " KASAN" : "", - IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION) ? + IS_ENABLED(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION) ? (boot_cpu_has(X86_FEATURE_PTI) ? " PTI" : " NOPTI") : ""); } NOKPROBE_SYMBOL(__die_header); diff --git a/arch/x86/kernel/fpu/bugs.c b/arch/x86/kernel/fpu/bugs.c index a06b876bbf2d..edbafc5940e3 100644 --- a/arch/x86/kernel/fpu/bugs.c +++ b/arch/x86/kernel/fpu/bugs.c @@ -2,6 +2,8 @@ /* * x86 FPU bug checks: */ +#include <linux/printk.h> + #include <asm/cpufeature.h> #include <asm/fpu/api.h> diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 12df54ff0e81..70139d9d2e01 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -307,7 +307,8 @@ union ftrace_op_code_union { } __attribute__((packed)); }; -#define RET_SIZE (IS_ENABLED(CONFIG_RETPOLINE) ? 5 : 1 + IS_ENABLED(CONFIG_SLS)) +#define RET_SIZE \ + (IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) ? 5 : 1 + IS_ENABLED(CONFIG_MITIGATION_SLS)) static unsigned long create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index dc0956067944..212e8e06aeba 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -22,6 +22,8 @@ #include <linux/cc_platform.h> #include <linux/pgtable.h> +#include <asm/asm.h> +#include <asm/page_64.h> #include <asm/processor.h> #include <asm/proto.h> #include <asm/smp.h> @@ -67,42 +69,11 @@ unsigned long vmemmap_base __ro_after_init = __VMEMMAP_BASE_L4; EXPORT_SYMBOL(vmemmap_base); #endif -/* - * GDT used on the boot CPU before switching to virtual addresses. - */ -static struct desc_struct startup_gdt[GDT_ENTRIES] __initdata = { - [GDT_ENTRY_KERNEL32_CS] = GDT_ENTRY_INIT(DESC_CODE32, 0, 0xfffff), - [GDT_ENTRY_KERNEL_CS] = GDT_ENTRY_INIT(DESC_CODE64, 0, 0xfffff), - [GDT_ENTRY_KERNEL_DS] = GDT_ENTRY_INIT(DESC_DATA64, 0, 0xfffff), -}; - -/* - * Address needs to be set at runtime because it references the startup_gdt - * while the kernel still uses a direct mapping. - */ -static struct desc_ptr startup_gdt_descr __initdata = { - .size = sizeof(startup_gdt)-1, - .address = 0, -}; - -static void __head *fixup_pointer(void *ptr, unsigned long physaddr) -{ - return ptr - (void *)_text + (void *)physaddr; -} - -static unsigned long __head *fixup_long(void *ptr, unsigned long physaddr) -{ - return fixup_pointer(ptr, physaddr); -} - -#ifdef CONFIG_X86_5LEVEL -static unsigned int __head *fixup_int(void *ptr, unsigned long physaddr) +static inline bool check_la57_support(void) { - return fixup_pointer(ptr, physaddr); -} + if (!IS_ENABLED(CONFIG_X86_5LEVEL)) + return false; -static bool __head check_la57_support(unsigned long physaddr) -{ /* * 5-level paging is detected and enabled at kernel decompression * stage. Only check if it has been enabled there. @@ -110,21 +81,8 @@ static bool __head check_la57_support(unsigned long physaddr) if (!(native_read_cr4() & X86_CR4_LA57)) return false; - *fixup_int(&__pgtable_l5_enabled, physaddr) = 1; - *fixup_int(&pgdir_shift, physaddr) = 48; - *fixup_int(&ptrs_per_p4d, physaddr) = 512; - *fixup_long(&page_offset_base, physaddr) = __PAGE_OFFSET_BASE_L5; - *fixup_long(&vmalloc_base, physaddr) = __VMALLOC_BASE_L5; - *fixup_long(&vmemmap_base, physaddr) = __VMEMMAP_BASE_L5; - return true; } -#else -static bool __head check_la57_support(unsigned long physaddr) -{ - return false; -} -#endif static unsigned long __head sme_postprocess_startup(struct boot_params *bp, pmdval_t *pmd) { @@ -173,23 +131,22 @@ static unsigned long __head sme_postprocess_startup(struct boot_params *bp, pmdv * doesn't have to generate PC-relative relocations when accessing globals from * that function. Clang actually does not generate them, which leads to * boot-time crashes. To work around this problem, every global pointer must - * be adjusted using fixup_pointer(). + * be accessed using RIP_REL_REF(). */ unsigned long __head __startup_64(unsigned long physaddr, struct boot_params *bp) { - unsigned long load_delta, *p; + pmd_t (*early_pgts)[PTRS_PER_PMD] = RIP_REL_REF(early_dynamic_pgts); unsigned long pgtable_flags; + unsigned long load_delta; pgdval_t *pgd; p4dval_t *p4d; pudval_t *pud; pmdval_t *pmd, pmd_entry; - pteval_t *mask_ptr; bool la57; int i; - unsigned int *next_pgt_ptr; - la57 = check_la57_support(physaddr); + la57 = check_la57_support(); /* Is the address too large? */ if (physaddr >> MAX_PHYSMEM_BITS) @@ -200,6 +157,7 @@ unsigned long __head __startup_64(unsigned long physaddr, * and the address I am actually running at. */ load_delta = physaddr - (unsigned long)(_text - __START_KERNEL_map); + RIP_REL_REF(phys_base) = load_delta; /* Is the address not 2M aligned? */ if (load_delta & ~PMD_MASK) @@ -210,26 +168,21 @@ unsigned long __head __startup_64(unsigned long physaddr, /* Fixup the physical addresses in the page table */ - pgd = fixup_pointer(early_top_pgt, physaddr); - p = pgd + pgd_index(__START_KERNEL_map); - if (la57) - *p = (unsigned long)level4_kernel_pgt; - else - *p = (unsigned long)level3_kernel_pgt; - *p += _PAGE_TABLE_NOENC - __START_KERNEL_map + load_delta; + pgd = &RIP_REL_REF(early_top_pgt)->pgd; + pgd[pgd_index(__START_KERNEL_map)] += load_delta; if (la57) { - p4d = fixup_pointer(level4_kernel_pgt, physaddr); - p4d[511] += load_delta; + p4d = (p4dval_t *)&RIP_REL_REF(level4_kernel_pgt); + p4d[MAX_PTRS_PER_P4D - 1] += load_delta; + + pgd[pgd_index(__START_KERNEL_map)] = (pgdval_t)p4d | _PAGE_TABLE_NOENC; } - pud = fixup_pointer(level3_kernel_pgt, physaddr); - pud[510] += load_delta; - pud[511] += load_delta; + RIP_REL_REF(level3_kernel_pgt)[PTRS_PER_PUD - 2].pud += load_delta; + RIP_REL_REF(level3_kernel_pgt)[PTRS_PER_PUD - 1].pud += load_delta; - pmd = fixup_pointer(level2_fixmap_pgt, physaddr); for (i = FIXMAP_PMD_TOP; i > FIXMAP_PMD_TOP - FIXMAP_PMD_NUM; i--) - pmd[i] += load_delta; + RIP_REL_REF(level2_fixmap_pgt)[i].pmd += load_delta; /* * Set up the identity mapping for the switchover. These @@ -238,15 +191,14 @@ unsigned long __head __startup_64(unsigned long physaddr, * it avoids problems around wraparound. */ - next_pgt_ptr = fixup_pointer(&next_early_pgt, physaddr); - pud = fixup_pointer(early_dynamic_pgts[(*next_pgt_ptr)++], physaddr); - pmd = fixup_pointer(early_dynamic_pgts[(*next_pgt_ptr)++], physaddr); + pud = &early_pgts[0]->pmd; + pmd = &early_pgts[1]->pmd; + RIP_REL_REF(next_early_pgt) = 2; pgtable_flags = _KERNPG_TABLE_NOENC + sme_get_me_mask(); if (la57) { - p4d = fixup_pointer(early_dynamic_pgts[(*next_pgt_ptr)++], - physaddr); + p4d = &early_pgts[RIP_REL_REF(next_early_pgt)++]->pmd; i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD; pgd[i + 0] = (pgdval_t)p4d + pgtable_flags; @@ -267,8 +219,7 @@ unsigned long __head __startup_64(unsigned long physaddr, pmd_entry = __PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL; /* Filter out unsupported __PAGE_KERNEL_* bits: */ - mask_ptr = fixup_pointer(&__supported_pte_mask, physaddr); - pmd_entry &= *mask_ptr; + pmd_entry &= RIP_REL_REF(__supported_pte_mask); pmd_entry += sme_get_me_mask(); pmd_entry += physaddr; @@ -294,7 +245,7 @@ unsigned long __head __startup_64(unsigned long physaddr, * error, causing the BIOS to halt the system. */ - pmd = fixup_pointer(level2_kernel_pgt, physaddr); + pmd = &RIP_REL_REF(level2_kernel_pgt)->pmd; /* invalidate pages before the kernel image */ for (i = 0; i < pmd_index((unsigned long)_text); i++) @@ -309,12 +260,6 @@ unsigned long __head __startup_64(unsigned long physaddr, for (; i < PTRS_PER_PMD; i++) pmd[i] &= ~_PAGE_PRESENT; - /* - * Fixup phys_base - remove the memory encryption mask to obtain - * the true physical address. - */ - *fixup_long(&phys_base, physaddr) += load_delta - sme_get_me_mask(); - return sme_postprocess_startup(bp, pmd); } @@ -486,6 +431,15 @@ asmlinkage __visible void __init __noreturn x86_64_start_kernel(char * real_mode (__START_KERNEL & PGDIR_MASK))); BUILD_BUG_ON(__fix_to_virt(__end_of_fixed_addresses) <= MODULES_END); + if (check_la57_support()) { + __pgtable_l5_enabled = 1; + pgdir_shift = 48; + ptrs_per_p4d = 512; + page_offset_base = __PAGE_OFFSET_BASE_L5; + vmalloc_base = __VMALLOC_BASE_L5; + vmemmap_base = __VMEMMAP_BASE_L5; + } + cr4_init_shadow(); /* Kill off the identity-map trampoline */ @@ -569,62 +523,52 @@ void __init __noreturn x86_64_start_reservations(char *real_mode_data) */ static gate_desc bringup_idt_table[NUM_EXCEPTION_VECTORS] __page_aligned_data; -static struct desc_ptr bringup_idt_descr = { - .size = (NUM_EXCEPTION_VECTORS * sizeof(gate_desc)) - 1, - .address = 0, /* Set at runtime */ -}; - -static void set_bringup_idt_handler(gate_desc *idt, int n, void *handler) +/* This may run while still in the direct mapping */ +static void __head startup_64_load_idt(void *vc_handler) { -#ifdef CONFIG_AMD_MEM_ENCRYPT + struct desc_ptr desc = { + .address = (unsigned long)&RIP_REL_REF(bringup_idt_table), + .size = sizeof(bringup_idt_table) - 1, + }; struct idt_data data; - gate_desc desc; - - init_idt_data(&data, n, handler); - idt_init_desc(&desc, &data); - native_write_idt_entry(idt, n, &desc); -#endif -} + gate_desc idt_desc; -/* This runs while still in the direct mapping */ -static void __head startup_64_load_idt(unsigned long physbase) -{ - struct desc_ptr *desc = fixup_pointer(&bringup_idt_descr, physbase); - gate_desc *idt = fixup_pointer(bringup_idt_table, physbase); - - - if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) { - void *handler; - - /* VMM Communication Exception */ - handler = fixup_pointer(vc_no_ghcb, physbase); - set_bringup_idt_handler(idt, X86_TRAP_VC, handler); + /* @vc_handler is set only for a VMM Communication Exception */ + if (vc_handler) { + init_idt_data(&data, X86_TRAP_VC, vc_handler); + idt_init_desc(&idt_desc, &data); + native_write_idt_entry((gate_desc *)desc.address, X86_TRAP_VC, &idt_desc); } - desc->address = (unsigned long)idt; - native_load_idt(desc); + native_load_idt(&desc); } /* This is used when running on kernel addresses */ void early_setup_idt(void) { - /* VMM Communication Exception */ + void *handler = NULL; + if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) { setup_ghcb(); - set_bringup_idt_handler(bringup_idt_table, X86_TRAP_VC, vc_boot_ghcb); + handler = vc_boot_ghcb; } - bringup_idt_descr.address = (unsigned long)bringup_idt_table; - native_load_idt(&bringup_idt_descr); + startup_64_load_idt(handler); } /* * Setup boot CPU state needed before kernel switches to virtual addresses. */ -void __head startup_64_setup_env(unsigned long physbase) +void __head startup_64_setup_gdt_idt(void) { + void *handler = NULL; + + struct desc_ptr startup_gdt_descr = { + .address = (unsigned long)&RIP_REL_REF(init_per_cpu_var(gdt_page.gdt)), + .size = GDT_SIZE - 1, + }; + /* Load GDT */ - startup_gdt_descr.address = (unsigned long)fixup_pointer(startup_gdt, physbase); native_load_gdt(&startup_gdt_descr); /* New GDT is live - reload data segment registers */ @@ -632,5 +576,8 @@ void __head startup_64_setup_env(unsigned long physbase) "movl %%eax, %%ss\n" "movl %%eax, %%es\n" : : "a"(__KERNEL_DS) : "memory"); - startup_64_load_idt(physbase); + if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) + handler = &RIP_REL_REF(vc_no_ghcb); + + startup_64_load_idt(handler); } diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 487ac57e2c81..b50f3641c4d6 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -414,7 +414,7 @@ __REFDATA .align 4 SYM_DATA(initial_code, .long i386_start_kernel) -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION #define PGD_ALIGN (2 * PAGE_SIZE) #define PTI_USER_PGD_FILL 1024 #else @@ -474,7 +474,7 @@ SYM_DATA_START(initial_page_table) # endif .align PAGE_SIZE /* needs to be page-sized too */ -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION /* * PTI needs another page so sync_initial_pagetable() works correctly * and does not scribble over the data which is placed behind the diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index c38e43589046..d8198fbd70e5 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -40,7 +40,6 @@ L4_START_KERNEL = l4_index(__START_KERNEL_map) L3_START_KERNEL = pud_index(__START_KERNEL_map) - .text __HEAD .code64 SYM_CODE_START_NOALIGN(startup_64) @@ -69,8 +68,6 @@ SYM_CODE_START_NOALIGN(startup_64) /* Set up the stack for verify_cpu() */ leaq (__end_init_task - TOP_OF_KERNEL_STACK_PADDING - PTREGS_SIZE)(%rip), %rsp - leaq _text(%rip), %rdi - /* Setup GSBASE to allow stack canary access for C code */ movl $MSR_GS_BASE, %ecx leaq INIT_PER_CPU_VAR(fixed_percpu_data)(%rip), %rdx @@ -78,7 +75,7 @@ SYM_CODE_START_NOALIGN(startup_64) shrq $32, %rdx wrmsr - call startup_64_setup_env + call startup_64_setup_gdt_idt /* Now switch to __KERNEL_CS so IRET works reliably */ pushq $__KERNEL_CS @@ -114,13 +111,11 @@ SYM_CODE_START_NOALIGN(startup_64) call __startup_64 /* Form the CR3 value being sure to include the CR3 modifier */ - addq $(early_top_pgt - __START_KERNEL_map), %rax + leaq early_top_pgt(%rip), %rcx + addq %rcx, %rax #ifdef CONFIG_AMD_MEM_ENCRYPT mov %rax, %rdi - mov %rax, %r14 - - addq phys_base(%rip), %rdi /* * For SEV guests: Verify that the C-bit is correct. A malicious @@ -129,17 +124,23 @@ SYM_CODE_START_NOALIGN(startup_64) * the next RET instruction. */ call sev_verify_cbit +#endif /* - * Restore CR3 value without the phys_base which will be added - * below, before writing %cr3. + * Switch to early_top_pgt which still has the identity mappings + * present. */ - mov %r14, %rax -#endif + movq %rax, %cr3 - jmp 1f + /* Branch to the common startup code at its kernel virtual address */ + ANNOTATE_RETPOLINE_SAFE + jmp *0f(%rip) SYM_CODE_END(startup_64) + __INITRODATA +0: .quad common_startup_64 + + .text SYM_CODE_START(secondary_startup_64) UNWIND_HINT_END_OF_STACK ANNOTATE_NOENDBR @@ -172,22 +173,39 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) ANNOTATE_NOENDBR /* Clear %R15 which holds the boot_params pointer on the boot CPU */ - xorq %r15, %r15 + xorl %r15d, %r15d + + /* Derive the runtime physical address of init_top_pgt[] */ + movq phys_base(%rip), %rax + addq $(init_top_pgt - __START_KERNEL_map), %rax /* * Retrieve the modifier (SME encryption mask if SME is active) to be * added to the initial pgdir entry that will be programmed into CR3. */ #ifdef CONFIG_AMD_MEM_ENCRYPT - movq sme_me_mask, %rax -#else - xorq %rax, %rax + addq sme_me_mask(%rip), %rax #endif + /* + * Switch to the init_top_pgt here, away from the trampoline_pgd and + * unmap the identity mapped ranges. + */ + movq %rax, %cr3 - /* Form the CR3 value being sure to include the CR3 modifier */ - addq $(init_top_pgt - __START_KERNEL_map), %rax -1: +SYM_INNER_LABEL(common_startup_64, SYM_L_LOCAL) + UNWIND_HINT_END_OF_STACK + ANNOTATE_NOENDBR + /* + * Create a mask of CR4 bits to preserve. Omit PGE in order to flush + * global 1:1 translations from the TLBs. + * + * From the SDM: + * "If CR4.PGE is changing from 0 to 1, there were no global TLB + * entries before the execution; if CR4.PGE is changing from 1 to 0, + * there will be no global TLB entries after the execution." + */ + movl $(X86_CR4_PAE | X86_CR4_LA57), %edx #ifdef CONFIG_X86_MCE /* * Preserve CR4.MCE if the kernel will enable #MC support. @@ -196,52 +214,20 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) * configured will crash the system regardless of the CR4.MCE value set * here. */ - movq %cr4, %rcx - andl $X86_CR4_MCE, %ecx -#else - movl $0, %ecx + orl $X86_CR4_MCE, %edx #endif + movq %cr4, %rcx + andl %edx, %ecx - /* Enable PAE mode, PSE, PGE and LA57 */ - orl $(X86_CR4_PAE | X86_CR4_PSE | X86_CR4_PGE), %ecx -#ifdef CONFIG_X86_5LEVEL - testb $1, __pgtable_l5_enabled(%rip) - jz 1f - orl $X86_CR4_LA57, %ecx -1: -#endif + /* Even if ignored in long mode, set PSE uniformly on all logical CPUs. */ + btsl $X86_CR4_PSE_BIT, %ecx movq %rcx, %cr4 - /* Setup early boot stage 4-/5-level pagetables. */ - addq phys_base(%rip), %rax - /* - * Switch to new page-table - * - * For the boot CPU this switches to early_top_pgt which still has the - * identity mappings present. The secondary CPUs will switch to the - * init_top_pgt here, away from the trampoline_pgd and unmap the - * identity mapped ranges. + * Set CR4.PGE to re-enable global translations. */ - movq %rax, %cr3 - - /* - * Do a global TLB flush after the CR3 switch to make sure the TLB - * entries from the identity mapping are flushed. - */ - movq %cr4, %rcx - movq %rcx, %rax - xorq $X86_CR4_PGE, %rcx + btsl $X86_CR4_PGE_BIT, %ecx movq %rcx, %cr4 - movq %rax, %cr4 - - /* Ensure I am executing from virtual addresses */ - movq $1f, %rax - ANNOTATE_RETPOLINE_SAFE - jmp *%rax -1: - UNWIND_HINT_END_OF_STACK - ANNOTATE_NOENDBR // above #ifdef CONFIG_SMP /* @@ -298,7 +284,7 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) .Llookup_AP: /* EAX contains the APIC ID of the current CPU */ - xorq %rcx, %rcx + xorl %ecx, %ecx leaq cpuid_to_apicid(%rip), %rbx .Lfind_cpunr: @@ -429,39 +415,10 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) movq %r15, %rdi .Ljump_to_C_code: - /* - * Jump to run C code and to be on a real kernel address. - * Since we are running on identity-mapped space we have to jump - * to the full 64bit address, this is only possible as indirect - * jump. In addition we need to ensure %cs is set so we make this - * a far return. - * - * Note: do not change to far jump indirect with 64bit offset. - * - * AMD does not support far jump indirect with 64bit offset. - * AMD64 Architecture Programmer's Manual, Volume 3: states only - * JMP FAR mem16:16 FF /5 Far jump indirect, - * with the target specified by a far pointer in memory. - * JMP FAR mem16:32 FF /5 Far jump indirect, - * with the target specified by a far pointer in memory. - * - * Intel64 does support 64bit offset. - * Software Developer Manual Vol 2: states: - * FF /5 JMP m16:16 Jump far, absolute indirect, - * address given in m16:16 - * FF /5 JMP m16:32 Jump far, absolute indirect, - * address given in m16:32. - * REX.W + FF /5 JMP m16:64 Jump far, absolute indirect, - * address given in m16:64. - */ - pushq $.Lafter_lret # put return address on stack for unwinder xorl %ebp, %ebp # clear frame pointer - movq initial_code(%rip), %rax - pushq $__KERNEL_CS # set correct cs - pushq %rax # target address in negative space - lretq -.Lafter_lret: - ANNOTATE_NOENDBR + ANNOTATE_RETPOLINE_SAFE + callq *initial_code(%rip) + ud2 SYM_CODE_END(secondary_startup_64) #include "verify_cpu.S" @@ -478,7 +435,7 @@ SYM_CODE_START(soft_restart_cpu) UNWIND_HINT_END_OF_STACK /* Find the idle task stack */ - movq PER_CPU_VAR(pcpu_hot) + X86_current_task, %rcx + movq PER_CPU_VAR(pcpu_hot + X86_current_task), %rcx movq TASK_threadsp(%rcx), %rsp jmp .Ljump_to_C_code @@ -623,7 +580,7 @@ SYM_CODE_END(vc_no_ghcb) #define SYM_DATA_START_PAGE_ALIGNED(name) \ SYM_START(name, SYM_L_GLOBAL, .balign PAGE_SIZE) -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION /* * Each PGD needs to be 8k long and 8k aligned. We do not * ever go out to userspace with these, so we do not @@ -656,7 +613,8 @@ SYM_CODE_END(vc_no_ghcb) .balign 4 SYM_DATA_START_PTI_ALIGNED(early_top_pgt) - .fill 512,8,0 + .fill 511,8,0 + .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC .fill PTI_USER_PGD_FILL,8,0 SYM_DATA_END(early_top_pgt) diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index 2a422e00ed4b..cde167b0ea92 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -503,7 +503,10 @@ static void *bzImage64_load(struct kimage *image, char *kernel, kbuf.bufsz = kernel_len - kern16_size; kbuf.memsz = PAGE_ALIGN(header->init_size); kbuf.buf_align = header->kernel_alignment; - kbuf.buf_min = MIN_KERNEL_LOAD_ADDR; + if (header->pref_address < MIN_KERNEL_LOAD_ADDR) + kbuf.buf_min = MIN_KERNEL_LOAD_ADDR; + else + kbuf.buf_min = header->pref_address; kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; ret = kexec_add_buffer(&kbuf); if (ret) diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 517821b48391..36d6809c6c9e 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -324,7 +324,7 @@ static int can_optimize(unsigned long paddr) * However, the kernel built with retpolines or IBT has jump * tables disabled so the check can be skipped altogether. */ - if (!IS_ENABLED(CONFIG_RETPOLINE) && + if (!IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) && !IS_ENABLED(CONFIG_X86_KERNEL_IBT) && insn_is_indirect_jump(&insn)) return 0; diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index 7a814b41402d..0f19ef355f5f 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -184,7 +184,7 @@ static struct ldt_struct *alloc_ldt_struct(unsigned int num_entries) return new_ldt; } -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION static void do_sanity_check(struct mm_struct *mm, bool had_kernel_mapping, @@ -377,7 +377,7 @@ static void unmap_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt) flush_tlb_mm_range(mm, va, va + nr_pages * PAGE_SIZE, PAGE_SHIFT, false); } -#else /* !CONFIG_PAGE_TABLE_ISOLATION */ +#else /* !CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */ static int map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) @@ -388,11 +388,11 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) static void unmap_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt) { } -#endif /* CONFIG_PAGE_TABLE_ISOLATION */ +#endif /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */ static void free_ldt_pgtables(struct mm_struct *mm) { -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION struct mmu_gather tlb; unsigned long start = LDT_BASE_ADDR; unsigned long end = LDT_END_ADDR; diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 397ef9fcf5e9..9a5b372c706f 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -304,13 +304,13 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs) __this_cpu_add(nmi_stats.unknown, 1); - pr_emerg("Uhhuh. NMI received for unknown reason %02x on CPU %d.\n", - reason, smp_processor_id()); + pr_emerg_ratelimited("Uhhuh. NMI received for unknown reason %02x on CPU %d.\n", + reason, smp_processor_id()); if (unknown_nmi_panic || panic_on_unrecovered_nmi) nmi_panic(regs, "NMI: Not continuing"); - pr_emerg("Dazed and confused, but trying to continue\n"); + pr_emerg_ratelimited("Dazed and confused, but trying to continue\n"); } NOKPROBE_SYMBOL(unknown_nmi_error); @@ -503,7 +503,7 @@ DEFINE_IDTENTRY_RAW(exc_nmi) if (IS_ENABLED(CONFIG_NMI_CHECK_CPU)) raw_atomic_long_inc(&nsp->idt_calls); - if (IS_ENABLED(CONFIG_SMP) && arch_cpu_is_offline(smp_processor_id())) { + if (arch_cpu_is_offline(smp_processor_id())) { if (microcode_nmi_handler_enabled()) microcode_offline_nmi_handler(); return; @@ -637,7 +637,7 @@ void nmi_backtrace_stall_check(const struct cpumask *btp) msgp = nmi_check_stall_msg[idx]; if (nsp->idt_ignored_snap != READ_ONCE(nsp->idt_ignored) && (idx & 0x1)) modp = ", but OK because ignore_nmis was set"; - if (nmi_seq & ~0x1) + if (nmi_seq & 0x1) msghp = " (CPU currently in NMI handler function)"; else if (nsp->idt_nmi_seq_snap + 1 == nmi_seq) msghp = " (CPU exited one NMI handler function)"; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 6121c2b42ecf..b8441147eb5e 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -846,31 +846,6 @@ void __noreturn stop_this_cpu(void *dummy) } /* - * AMD Erratum 400 aware idle routine. We handle it the same way as C3 power - * states (local apic timer and TSC stop). - * - * XXX this function is completely buggered vs RCU and tracing. - */ -static void amd_e400_idle(void) -{ - /* - * We cannot use static_cpu_has_bug() here because X86_BUG_AMD_APIC_C1E - * gets set after static_cpu_has() places have been converted via - * alternatives. - */ - if (!boot_cpu_has_bug(X86_BUG_AMD_APIC_C1E)) { - default_idle(); - return; - } - - tick_broadcast_enter(); - - default_idle(); - - tick_broadcast_exit(); -} - -/* * Prefer MWAIT over HALT if MWAIT is supported, MWAIT_CPUID leaf * exists and whenever MONITOR/MWAIT extensions are present there is at * least one C1 substate. @@ -878,21 +853,22 @@ static void amd_e400_idle(void) * Do not prefer MWAIT if MONITOR instruction has a bug or idle=nomwait * is passed to kernel commandline parameter. */ -static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c) +static __init bool prefer_mwait_c1_over_halt(void) { + const struct cpuinfo_x86 *c = &boot_cpu_data; u32 eax, ebx, ecx, edx; - /* User has disallowed the use of MWAIT. Fallback to HALT */ - if (boot_option_idle_override == IDLE_NOMWAIT) - return 0; + /* If override is enforced on the command line, fall back to HALT. */ + if (boot_option_idle_override != IDLE_NO_OVERRIDE) + return false; /* MWAIT is not supported on this platform. Fallback to HALT */ if (!cpu_has(c, X86_FEATURE_MWAIT)) - return 0; + return false; - /* Monitor has a bug. Fallback to HALT */ - if (boot_cpu_has_bug(X86_BUG_MONITOR)) - return 0; + /* Monitor has a bug or APIC stops in C1E. Fallback to HALT */ + if (boot_cpu_has_bug(X86_BUG_MONITOR) || boot_cpu_has_bug(X86_BUG_AMD_APIC_C1E)) + return false; cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &edx); @@ -901,13 +877,13 @@ static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c) * with EAX=0, ECX=0. */ if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED)) - return 1; + return true; /* * If MWAIT extensions are available, there should be at least one * MWAIT C1 substate present. */ - return (edx & MWAIT_C1_SUBSTATE_MASK); + return !!(edx & MWAIT_C1_SUBSTATE_MASK); } /* @@ -933,26 +909,27 @@ static __cpuidle void mwait_idle(void) __current_clr_polling(); } -void select_idle_routine(const struct cpuinfo_x86 *c) +void __init select_idle_routine(void) { -#ifdef CONFIG_SMP - if (boot_option_idle_override == IDLE_POLL && __max_threads_per_core > 1) - pr_warn_once("WARNING: polling idle and HT enabled, performance may degrade\n"); -#endif - if (x86_idle_set() || boot_option_idle_override == IDLE_POLL) + if (boot_option_idle_override == IDLE_POLL) { + if (IS_ENABLED(CONFIG_SMP) && __max_threads_per_core > 1) + pr_warn_once("WARNING: polling idle and HT enabled, performance may degrade\n"); + return; + } + + /* Required to guard against xen_set_default_idle() */ + if (x86_idle_set()) return; - if (boot_cpu_has_bug(X86_BUG_AMD_E400)) { - pr_info("using AMD E400 aware idle routine\n"); - static_call_update(x86_idle, amd_e400_idle); - } else if (prefer_mwait_c1_over_halt(c)) { + if (prefer_mwait_c1_over_halt()) { pr_info("using mwait in idle threads\n"); static_call_update(x86_idle, mwait_idle); } else if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) { pr_info("using TDX aware idle routine\n"); static_call_update(x86_idle, tdx_safe_halt); - } else + } else { static_call_update(x86_idle, default_idle); + } } void amd_e400_c1e_apic_setup(void) @@ -985,7 +962,10 @@ void __init arch_post_acpi_subsys_init(void) if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC)) mark_tsc_unstable("TSC halt in AMD C1E"); - pr_info("System has AMD C1E enabled\n"); + + if (IS_ENABLED(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST_IDLE)) + static_branch_enable(&arch_needs_tick_broadcast); + pr_info("System has AMD C1E erratum E400. Workaround enabled.\n"); } static int __init idle_setup(char *str) @@ -998,24 +978,14 @@ static int __init idle_setup(char *str) boot_option_idle_override = IDLE_POLL; cpu_idle_poll_ctrl(true); } else if (!strcmp(str, "halt")) { - /* - * When the boot option of idle=halt is added, halt is - * forced to be used for CPU idle. In such case CPU C2/C3 - * won't be used again. - * To continue to load the CPU idle driver, don't touch - * the boot_option_idle_override. - */ - static_call_update(x86_idle, default_idle); + /* 'idle=halt' HALT for idle. C-states are disabled. */ boot_option_idle_override = IDLE_HALT; } else if (!strcmp(str, "nomwait")) { - /* - * If the boot option of "idle=nomwait" is added, - * it means that mwait will be disabled for CPU C1/C2/C3 - * states. - */ + /* 'idle=nomwait' disables MWAIT for idle */ boot_option_idle_override = IDLE_NOMWAIT; - } else - return -1; + } else { + return -EINVAL; + } return 0; } @@ -1030,7 +1000,10 @@ unsigned long arch_align_stack(unsigned long sp) unsigned long arch_randomize_brk(struct mm_struct *mm) { - return randomize_page(mm->brk, 0x02000000); + if (mmap_is_ia32()) + return randomize_page(mm->brk, SZ_32M); + + return randomize_page(mm->brk, SZ_1G); } /* diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 708c87b88cc1..0917c7f25720 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -156,13 +156,12 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) { struct thread_struct *prev = &prev_p->thread, *next = &next_p->thread; - struct fpu *prev_fpu = &prev->fpu; int cpu = smp_processor_id(); /* never put a printk in __switch_to... printk() calls wake_up*() indirectly */ - if (!test_thread_flag(TIF_NEED_FPU_LOAD)) - switch_fpu_prepare(prev_fpu, cpu); + if (!test_tsk_thread_flag(prev_p, TIF_NEED_FPU_LOAD)) + switch_fpu_prepare(prev_p, cpu); /* * Save away %gs. No need to save %fs, as it was saved on the @@ -209,7 +208,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) raw_cpu_write(pcpu_hot.current_task, next_p); - switch_fpu_finish(); + switch_fpu_finish(next_p); /* Load the Intel cache allocation PQR MSR. */ resctrl_sched_in(next_p); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index c075591b7b46..7062b84dd467 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -611,14 +611,13 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) { struct thread_struct *prev = &prev_p->thread; struct thread_struct *next = &next_p->thread; - struct fpu *prev_fpu = &prev->fpu; int cpu = smp_processor_id(); WARN_ON_ONCE(IS_ENABLED(CONFIG_DEBUG_ENTRY) && this_cpu_read(pcpu_hot.hardirq_stack_inuse)); - if (!test_thread_flag(TIF_NEED_FPU_LOAD)) - switch_fpu_prepare(prev_fpu, cpu); + if (!test_tsk_thread_flag(prev_p, TIF_NEED_FPU_LOAD)) + switch_fpu_prepare(prev_p, cpu); /* We must save %fs and %gs before load_TLS() because * %fs and %gs may be cleared by load_TLS(). @@ -672,7 +671,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) raw_cpu_write(pcpu_hot.current_task, next_p); raw_cpu_write(pcpu_hot.top_of_stack, task_top_of_stack(next_p)); - switch_fpu_finish(); + switch_fpu_finish(next_p); /* Reload sp0. */ update_task_stack(next_p); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 4e320d4d3898..46d5a8c520ad 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1206,6 +1206,16 @@ void __init i386_reserve_resources(void) #endif /* CONFIG_X86_32 */ +#ifndef CONFIG_SMP +void __init smp_prepare_boot_cpu(void) +{ + struct cpuinfo_x86 *c = &cpu_data(0); + + *c = boot_cpu_data; + c->initialized = true; +} +#endif + static struct notifier_block kernel_offset_notifier = { .notifier_call = dump_kernel_offset }; diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c index 1d24ec679915..8b04958da5e7 100644 --- a/arch/x86/kernel/sev-shared.c +++ b/arch/x86/kernel/sev-shared.c @@ -9,12 +9,18 @@ * and is included directly into both code-bases. */ +#include <asm/setup_data.h> + #ifndef __BOOT_COMPRESSED -#define error(v) pr_err(v) -#define has_cpuflag(f) boot_cpu_has(f) +#define error(v) pr_err(v) +#define has_cpuflag(f) boot_cpu_has(f) +#define sev_printk(fmt, ...) printk(fmt, ##__VA_ARGS__) +#define sev_printk_rtl(fmt, ...) printk_ratelimited(fmt, ##__VA_ARGS__) #else #undef WARN #define WARN(condition, format...) (!!(condition)) +#define sev_printk(fmt, ...) +#define sev_printk_rtl(fmt, ...) #endif /* I/O parameters for CPUID-related helpers */ @@ -89,7 +95,8 @@ static bool __init sev_es_check_cpu_features(void) return true; } -static void __noreturn sev_es_terminate(unsigned int set, unsigned int reason) +static void __head __noreturn +sev_es_terminate(unsigned int set, unsigned int reason) { u64 val = GHCB_MSR_TERM_REQ; @@ -326,13 +333,7 @@ static int sev_cpuid_hv(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid */ static const struct snp_cpuid_table *snp_cpuid_get_table(void) { - void *ptr; - - asm ("lea cpuid_table_copy(%%rip), %0" - : "=r" (ptr) - : "p" (&cpuid_table_copy)); - - return ptr; + return &RIP_REL_REF(cpuid_table_copy); } /* @@ -391,7 +392,7 @@ static u32 snp_cpuid_calc_xsave_size(u64 xfeatures_en, bool compacted) return xsave_size; } -static bool +static bool __head snp_cpuid_get_validated_func(struct cpuid_leaf *leaf) { const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table(); @@ -528,7 +529,8 @@ static int snp_cpuid_postprocess(struct ghcb *ghcb, struct es_em_ctxt *ctxt, * Returns -EOPNOTSUPP if feature not enabled. Any other non-zero return value * should be treated as fatal by caller. */ -static int snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf) +static int __head +snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf) { const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table(); @@ -556,9 +558,9 @@ static int snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_le leaf->eax = leaf->ebx = leaf->ecx = leaf->edx = 0; /* Skip post-processing for out-of-range zero leafs. */ - if (!(leaf->fn <= cpuid_std_range_max || - (leaf->fn >= 0x40000000 && leaf->fn <= cpuid_hyp_range_max) || - (leaf->fn >= 0x80000000 && leaf->fn <= cpuid_ext_range_max))) + if (!(leaf->fn <= RIP_REL_REF(cpuid_std_range_max) || + (leaf->fn >= 0x40000000 && leaf->fn <= RIP_REL_REF(cpuid_hyp_range_max)) || + (leaf->fn >= 0x80000000 && leaf->fn <= RIP_REL_REF(cpuid_ext_range_max)))) return 0; } @@ -570,10 +572,11 @@ static int snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_le * page yet, so it only supports the MSR based communication with the * hypervisor and only the CPUID exit-code. */ -void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) +void __head do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) { unsigned int subfn = lower_bits(regs->cx, 32); unsigned int fn = lower_bits(regs->ax, 32); + u16 opcode = *(unsigned short *)regs->ip; struct cpuid_leaf leaf; int ret; @@ -581,6 +584,10 @@ void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) if (exit_code != SVM_EXIT_CPUID) goto fail; + /* Is it really a CPUID insn? */ + if (opcode != 0xa20f) + goto fail; + leaf.fn = fn; leaf.subfn = subfn; @@ -1016,7 +1023,8 @@ struct cc_setup_data { * Search for a Confidential Computing blob passed in as a setup_data entry * via the Linux Boot Protocol. */ -static struct cc_blob_sev_info *find_cc_blob_setup_data(struct boot_params *bp) +static __head +struct cc_blob_sev_info *find_cc_blob_setup_data(struct boot_params *bp) { struct cc_setup_data *sd = NULL; struct setup_data *hdr; @@ -1043,7 +1051,7 @@ static struct cc_blob_sev_info *find_cc_blob_setup_data(struct boot_params *bp) * mapping needs to be updated in sync with all the changes to virtual memory * layout and related mapping facilities throughout the boot process. */ -static void __init setup_cpuid_table(const struct cc_blob_sev_info *cc_info) +static void __head setup_cpuid_table(const struct cc_blob_sev_info *cc_info) { const struct snp_cpuid_table *cpuid_table_fw, *cpuid_table; int i; @@ -1063,11 +1071,11 @@ static void __init setup_cpuid_table(const struct cc_blob_sev_info *cc_info) const struct snp_cpuid_fn *fn = &cpuid_table->fn[i]; if (fn->eax_in == 0x0) - cpuid_std_range_max = fn->eax; + RIP_REL_REF(cpuid_std_range_max) = fn->eax; else if (fn->eax_in == 0x40000000) - cpuid_hyp_range_max = fn->eax; + RIP_REL_REF(cpuid_hyp_range_max) = fn->eax; else if (fn->eax_in == 0x80000000) - cpuid_ext_range_max = fn->eax; + RIP_REL_REF(cpuid_ext_range_max) = fn->eax; } } @@ -1170,3 +1178,92 @@ static int vmgexit_psc(struct ghcb *ghcb, struct snp_psc_desc *desc) out: return ret; } + +static enum es_result vc_check_opcode_bytes(struct es_em_ctxt *ctxt, + unsigned long exit_code) +{ + unsigned int opcode = (unsigned int)ctxt->insn.opcode.value; + u8 modrm = ctxt->insn.modrm.value; + + switch (exit_code) { + + case SVM_EXIT_IOIO: + case SVM_EXIT_NPF: + /* handled separately */ + return ES_OK; + + case SVM_EXIT_CPUID: + if (opcode == 0xa20f) + return ES_OK; + break; + + case SVM_EXIT_INVD: + if (opcode == 0x080f) + return ES_OK; + break; + + case SVM_EXIT_MONITOR: + if (opcode == 0x010f && modrm == 0xc8) + return ES_OK; + break; + + case SVM_EXIT_MWAIT: + if (opcode == 0x010f && modrm == 0xc9) + return ES_OK; + break; + + case SVM_EXIT_MSR: + /* RDMSR */ + if (opcode == 0x320f || + /* WRMSR */ + opcode == 0x300f) + return ES_OK; + break; + + case SVM_EXIT_RDPMC: + if (opcode == 0x330f) + return ES_OK; + break; + + case SVM_EXIT_RDTSC: + if (opcode == 0x310f) + return ES_OK; + break; + + case SVM_EXIT_RDTSCP: + if (opcode == 0x010f && modrm == 0xf9) + return ES_OK; + break; + + case SVM_EXIT_READ_DR7: + if (opcode == 0x210f && + X86_MODRM_REG(ctxt->insn.modrm.value) == 7) + return ES_OK; + break; + + case SVM_EXIT_VMMCALL: + if (opcode == 0x010f && modrm == 0xd9) + return ES_OK; + + break; + + case SVM_EXIT_WRITE_DR7: + if (opcode == 0x230f && + X86_MODRM_REG(ctxt->insn.modrm.value) == 7) + return ES_OK; + break; + + case SVM_EXIT_WBINVD: + if (opcode == 0x90f) + return ES_OK; + break; + + default: + break; + } + + sev_printk(KERN_ERR "Wrong/unhandled opcode bytes: 0x%x, exit_code: 0x%lx, rIP: 0x%lx\n", + opcode, exit_code, ctxt->regs->ip); + + return ES_UNSUPPORTED; +} diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index c67285824e82..b59b09c2f284 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -25,6 +25,7 @@ #include <linux/psp-sev.h> #include <uapi/linux/sev-guest.h> +#include <asm/init.h> #include <asm/cpu_entry_area.h> #include <asm/stacktrace.h> #include <asm/sev.h> @@ -59,6 +60,25 @@ #define AP_INIT_CR0_DEFAULT 0x60000010 #define AP_INIT_MXCSR_DEFAULT 0x1f80 +static const char * const sev_status_feat_names[] = { + [MSR_AMD64_SEV_ENABLED_BIT] = "SEV", + [MSR_AMD64_SEV_ES_ENABLED_BIT] = "SEV-ES", + [MSR_AMD64_SEV_SNP_ENABLED_BIT] = "SEV-SNP", + [MSR_AMD64_SNP_VTOM_BIT] = "vTom", + [MSR_AMD64_SNP_REFLECT_VC_BIT] = "ReflectVC", + [MSR_AMD64_SNP_RESTRICTED_INJ_BIT] = "RI", + [MSR_AMD64_SNP_ALT_INJ_BIT] = "AI", + [MSR_AMD64_SNP_DEBUG_SWAP_BIT] = "DebugSwap", + [MSR_AMD64_SNP_PREVENT_HOST_IBS_BIT] = "NoHostIBS", + [MSR_AMD64_SNP_BTB_ISOLATION_BIT] = "BTBIsol", + [MSR_AMD64_SNP_VMPL_SSS_BIT] = "VmplSSS", + [MSR_AMD64_SNP_SECURE_TSC_BIT] = "SecureTSC", + [MSR_AMD64_SNP_VMGEXIT_PARAM_BIT] = "VMGExitParam", + [MSR_AMD64_SNP_IBS_VIRT_BIT] = "IBSVirt", + [MSR_AMD64_SNP_VMSA_REG_PROT_BIT] = "VMSARegProt", + [MSR_AMD64_SNP_SMT_PROT_BIT] = "SMTProt", +}; + /* For early boot hypervisor communication in SEV-ES enabled guests */ static struct ghcb boot_ghcb_page __bss_decrypted __aligned(PAGE_SIZE); @@ -682,8 +702,9 @@ static u64 __init get_jump_table_addr(void) return ret; } -static void early_set_pages_state(unsigned long vaddr, unsigned long paddr, - unsigned long npages, enum psc_op op) +static void __head +early_set_pages_state(unsigned long vaddr, unsigned long paddr, + unsigned long npages, enum psc_op op) { unsigned long paddr_end; u64 val; @@ -739,7 +760,7 @@ e_term: sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC); } -void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, +void __head early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, unsigned long npages) { /* @@ -748,7 +769,7 @@ void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long padd * This eliminates worries about jump tables or checking boot_cpu_data * in the cc_platform_has() function. */ - if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) + if (!(RIP_REL_REF(sev_status) & MSR_AMD64_SEV_SNP_ENABLED)) return; /* @@ -767,7 +788,7 @@ void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr * This eliminates worries about jump tables or checking boot_cpu_data * in the cc_platform_has() function. */ - if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) + if (!(RIP_REL_REF(sev_status) & MSR_AMD64_SEV_SNP_ENABLED)) return; /* Ask hypervisor to mark the memory pages shared in the RMP table. */ @@ -1752,7 +1773,10 @@ static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt, struct ghcb *ghcb, unsigned long exit_code) { - enum es_result result; + enum es_result result = vc_check_opcode_bytes(ctxt, exit_code); + + if (result != ES_OK) + return result; switch (exit_code) { case SVM_EXIT_READ_DR7: @@ -2059,7 +2083,7 @@ fail: * * Scan for the blob in that order. */ -static __init struct cc_blob_sev_info *find_cc_blob(struct boot_params *bp) +static __head struct cc_blob_sev_info *find_cc_blob(struct boot_params *bp) { struct cc_blob_sev_info *cc_info; @@ -2085,7 +2109,7 @@ found_cc_info: return cc_info; } -bool __init snp_init(struct boot_params *bp) +bool __head snp_init(struct boot_params *bp) { struct cc_blob_sev_info *cc_info; @@ -2107,7 +2131,7 @@ bool __init snp_init(struct boot_params *bp) return true; } -void __init __noreturn snp_abort(void) +void __head __noreturn snp_abort(void) { sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED); } @@ -2262,3 +2286,29 @@ static int __init snp_init_platform_device(void) return 0; } device_initcall(snp_init_platform_device); + +void kdump_sev_callback(void) +{ + /* + * Do wbinvd() on remote CPUs when SNP is enabled in order to + * safely do SNP_SHUTDOWN on the local CPU. + */ + if (cpu_feature_enabled(X86_FEATURE_SEV_SNP)) + wbinvd(); +} + +void sev_show_status(void) +{ + int i; + + pr_info("Status: "); + for (i = 0; i < MSR_AMD64_SNP_RESV_BIT; i++) { + if (sev_status & BIT_ULL(i)) { + if (!sev_status_feat_names[i]) + continue; + + pr_cont("%s ", sev_status_feat_names[i]); + } + } + pr_cont("\n"); +} diff --git a/arch/x86/kernel/sev_verify_cbit.S b/arch/x86/kernel/sev_verify_cbit.S index 3355e27c69eb..1ab65f6c6ae7 100644 --- a/arch/x86/kernel/sev_verify_cbit.S +++ b/arch/x86/kernel/sev_verify_cbit.S @@ -77,7 +77,7 @@ SYM_FUNC_START(sev_verify_cbit) * The check failed, prevent any forward progress to prevent ROP * attacks, invalidate the stack and go into a hlt loop. */ - xorq %rsp, %rsp + xorl %esp, %esp subq $0x1000, %rsp 2: hlt jmp 2b diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index 96a771f9f930..2908e063d7d8 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -148,14 +148,16 @@ static int register_stop_handler(void) static void native_stop_other_cpus(int wait) { - unsigned int cpu = smp_processor_id(); + unsigned int old_cpu, this_cpu; unsigned long flags, timeout; if (reboot_force) return; /* Only proceed if this is the first CPU to reach this code */ - if (atomic_cmpxchg(&stopping_cpu, -1, cpu) != -1) + old_cpu = -1; + this_cpu = smp_processor_id(); + if (!atomic_try_cmpxchg(&stopping_cpu, &old_cpu, this_cpu)) return; /* For kexec, ensure that offline CPUs are out of MWAIT and in HLT */ @@ -186,7 +188,7 @@ static void native_stop_other_cpus(int wait) * NMIs. */ cpumask_copy(&cpus_stop_mask, cpu_online_mask); - cpumask_clear_cpu(cpu, &cpus_stop_mask); + cpumask_clear_cpu(this_cpu, &cpus_stop_mask); if (!cpumask_empty(&cpus_stop_mask)) { apic_send_IPI_allbutself(REBOOT_VECTOR); @@ -210,6 +212,8 @@ static void native_stop_other_cpus(int wait) * CPUs to stop. */ if (!smp_no_nmi_ipi && !register_stop_handler()) { + unsigned int cpu; + pr_emerg("Shutting down cpus with NMI\n"); for_each_cpu(cpu, &cpus_stop_mask) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 9c1e1219c28f..fe355c89f6c1 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -101,10 +101,6 @@ EXPORT_PER_CPU_SYMBOL(cpu_core_map); DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_die_map); EXPORT_PER_CPU_SYMBOL(cpu_die_map); -/* Per CPU bogomips and other parameters */ -DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info); -EXPORT_PER_CPU_SYMBOL(cpu_info); - /* CPUs which are the primary SMT threads */ struct cpumask __cpu_primary_thread_mask __read_mostly; @@ -1078,6 +1074,11 @@ void __init smp_prepare_cpus_common(void) set_cpu_sibling_map(0); } +void __init smp_prepare_boot_cpu(void) +{ + smp_ops.smp_prepare_boot_cpu(); +} + #ifdef CONFIG_X86_64 /* Establish whether parallel bringup can be supported. */ bool __init arch_cpuhp_init_parallel_bringup(void) diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index 77a9316da435..4eefaac64c6c 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -172,7 +172,7 @@ void arch_static_call_transform(void *site, void *tramp, void *func, bool tail) } EXPORT_SYMBOL_GPL(arch_static_call_transform); -#ifdef CONFIG_RETHUNK +#ifdef CONFIG_MITIGATION_RETHUNK /* * This is called by apply_returns() to fix up static call trampolines, * specifically ARCH_DEFINE_STATIC_CALL_NULL_TRAMP which is recorded as diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index 8e2b2552b5ee..3e2952679b88 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -6,7 +6,9 @@ #include <linux/sched/task_stack.h> #include <linux/mm.h> #include <linux/ptrace.h> + #include <asm/desc.h> +#include <asm/debugreg.h> #include <asm/mmu_context.h> unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs) diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index c783aeb37dce..cb9fa1d5c66f 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -52,13 +52,6 @@ static unsigned long get_align_bits(void) return va_align.bits & get_align_mask(); } -unsigned long align_vdso_addr(unsigned long addr) -{ - unsigned long align_mask = get_align_mask(); - addr = (addr + align_mask) & ~align_mask; - return addr | get_align_bits(); -} - static int __init control_va_addr_alignment(char *str) { /* guard against enabling this on other CPU families */ diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 6cb31df3d5ff..4fa0b17e5043 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -774,7 +774,7 @@ DEFINE_IDTENTRY_RAW(exc_int3) */ asmlinkage __visible noinstr struct pt_regs *sync_regs(struct pt_regs *eregs) { - struct pt_regs *regs = (struct pt_regs *)this_cpu_read(pcpu_hot.top_of_stack) - 1; + struct pt_regs *regs = (struct pt_regs *)current_top_of_stack() - 1; if (regs != eregs) *regs = *eregs; return regs; @@ -792,7 +792,7 @@ asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *r * trust it and switch to the current kernel stack */ if (ip_within_syscall_gap(regs)) { - sp = this_cpu_read(pcpu_hot.top_of_stack); + sp = current_top_of_stack(); goto sync; } diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index a349dbfc6d5a..56451fd2099e 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -46,6 +46,7 @@ ENTRY(phys_startup_64) #endif jiffies = jiffies_64; +const_pcpu_hot = pcpu_hot; #if defined(CONFIG_X86_64) /* @@ -132,7 +133,7 @@ SECTIONS LOCK_TEXT KPROBES_TEXT SOFTIRQENTRY_TEXT -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE *(.text..__x86.indirect_thunk) *(.text..__x86.return_thunk) #endif @@ -142,7 +143,7 @@ SECTIONS *(.text..__x86.rethunk_untrain) ENTRY_TEXT -#ifdef CONFIG_CPU_SRSO +#ifdef CONFIG_MITIGATION_SRSO /* * See the comment above srso_alias_untrain_ret()'s * definition. @@ -267,7 +268,7 @@ SECTIONS } #endif -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE /* * List of instructions that call/jmp/jcc to retpoline thunks * __x86_indirect_thunk_*(). These instructions can be patched along @@ -504,11 +505,11 @@ INIT_PER_CPU(irq_stack_backing_store); "fixed_percpu_data is not at start of per-cpu area"); #endif -#ifdef CONFIG_CPU_UNRET_ENTRY +#ifdef CONFIG_MITIGATION_UNRET_ENTRY . = ASSERT((retbleed_return_thunk & 0x3f) == 0, "retbleed_return_thunk not cacheline-aligned"); #endif -#ifdef CONFIG_CPU_SRSO +#ifdef CONFIG_MITIGATION_SRSO . = ASSERT((srso_safe_ret & 0x3f) == 0, "srso_safe_ret not cacheline-aligned"); /* * GNU ld cannot do XOR until 2.41. diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 3242f3da2457..1edf93ee3395 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2815,7 +2815,10 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns) vcpu->arch.apic = apic; - apic->regs = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT); + if (kvm_x86_ops.alloc_apic_backing_page) + apic->regs = static_call(kvm_x86_alloc_apic_backing_page)(vcpu); + else + apic->regs = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT); if (!apic->regs) { printk(KERN_ERR "malloc apic regs error for vcpu %x\n", vcpu->vcpu_id); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 0544700ca50b..9a905f10e10c 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -53,12 +53,11 @@ #include <asm/cmpxchg.h> #include <asm/io.h> #include <asm/set_memory.h> +#include <asm/spec-ctrl.h> #include <asm/vmx.h> #include "trace.h" -extern bool itlb_multihit_kvm_mitigation; - static bool nx_hugepage_mitigation_hard_disabled; int __read_mostly nx_huge_pages = -1; @@ -263,7 +262,7 @@ static unsigned long get_guest_cr3(struct kvm_vcpu *vcpu) static inline unsigned long kvm_mmu_get_guest_pgd(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) { - if (IS_ENABLED(CONFIG_RETPOLINE) && mmu->get_guest_pgd == get_guest_cr3) + if (IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) && mmu->get_guest_pgd == get_guest_cr3) return kvm_read_cr3(vcpu); return mmu->get_guest_pgd(vcpu); diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index 0669a8a668ca..5390a591a571 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -315,7 +315,7 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, if (!prefetch) vcpu->stat.pf_taken++; - if (IS_ENABLED(CONFIG_RETPOLINE) && fault.is_tdp) + if (IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) && fault.is_tdp) r = kvm_tdp_page_fault(vcpu, &fault); else r = vcpu->arch.mmu->page_fault(vcpu, &fault); diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index dee62362a360..55b9a6d96bcf 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -1181,7 +1181,7 @@ int svm_allocate_nested(struct vcpu_svm *svm) if (svm->nested.initialized) return 0; - vmcb02_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); + vmcb02_page = snp_safe_alloc_page(&svm->vcpu); if (!vmcb02_page) return -ENOMEM; svm->nested.vmcb02.ptr = page_address(vmcb02_page); diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index a8ce5226b3b5..ae0ac12382b9 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -246,6 +246,7 @@ static void sev_unbind_asid(struct kvm *kvm, unsigned int handle) static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) { struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + struct sev_platform_init_args init_args = {0}; int asid, ret; if (kvm->created_vcpus) @@ -262,7 +263,8 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) goto e_no_asid; sev->asid = asid; - ret = sev_platform_init(&argp->error); + init_args.probe = false; + ret = sev_platform_init(&init_args); if (ret) goto e_free; @@ -274,6 +276,7 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) return 0; e_free: + argp->error = init_args.error; sev_asid_free(sev); sev->asid = 0; e_no_asid: @@ -3165,3 +3168,35 @@ void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, 1); } + +struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu) +{ + unsigned long pfn; + struct page *p; + + if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP)) + return alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); + + /* + * Allocate an SNP-safe page to workaround the SNP erratum where + * the CPU will incorrectly signal an RMP violation #PF if a + * hugepage (2MB or 1GB) collides with the RMP entry of a + * 2MB-aligned VMCB, VMSA, or AVIC backing page. + * + * Allocate one extra page, choose a page which is not + * 2MB-aligned, and free the other. + */ + p = alloc_pages(GFP_KERNEL_ACCOUNT | __GFP_ZERO, 1); + if (!p) + return NULL; + + split_page(p, 1); + + pfn = page_to_pfn(p); + if (IS_ALIGNED(pfn, PTRS_PER_PMD)) + __free_page(p++); + else + __free_page(p + 1); + + return p; +} diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index e90b429c84f1..272d5ed37ce7 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -703,7 +703,7 @@ static int svm_cpu_init(int cpu) int ret = -ENOMEM; memset(sd, 0, sizeof(struct svm_cpu_data)); - sd->save_area = alloc_page(GFP_KERNEL | __GFP_ZERO); + sd->save_area = snp_safe_alloc_page(NULL); if (!sd->save_area) return ret; @@ -1421,7 +1421,7 @@ static int svm_vcpu_create(struct kvm_vcpu *vcpu) svm = to_svm(vcpu); err = -ENOMEM; - vmcb01_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); + vmcb01_page = snp_safe_alloc_page(vcpu); if (!vmcb01_page) goto out; @@ -1430,7 +1430,7 @@ static int svm_vcpu_create(struct kvm_vcpu *vcpu) * SEV-ES guests require a separate VMSA page used to contain * the encrypted register state of the guest. */ - vmsa_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); + vmsa_page = snp_safe_alloc_page(vcpu); if (!vmsa_page) goto error_free_vmcb_page; @@ -3455,7 +3455,7 @@ int svm_invoke_exit_handler(struct kvm_vcpu *vcpu, u64 exit_code) if (!svm_check_exit_valid(exit_code)) return svm_handle_invalid_exit(vcpu, exit_code); -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE if (exit_code == SVM_EXIT_MSR) return msr_interception(vcpu); else if (exit_code == SVM_EXIT_VINTR) @@ -4900,6 +4900,16 @@ static int svm_vm_init(struct kvm *kvm) return 0; } +static void *svm_alloc_apic_backing_page(struct kvm_vcpu *vcpu) +{ + struct page *page = snp_safe_alloc_page(vcpu); + + if (!page) + return NULL; + + return page_address(page); +} + static struct kvm_x86_ops svm_x86_ops __initdata = { .name = KBUILD_MODNAME, @@ -5031,6 +5041,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .vcpu_deliver_sipi_vector = svm_vcpu_deliver_sipi_vector, .vcpu_get_apicv_inhibit_reasons = avic_vcpu_get_apicv_inhibit_reasons, + .alloc_apic_backing_page = svm_alloc_apic_backing_page, }; /* diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 8ef95139cd24..7f1fbd874c45 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -694,6 +694,7 @@ void sev_es_vcpu_reset(struct vcpu_svm *svm); void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector); void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa); void sev_es_unmap_ghcb(struct vcpu_svm *svm); +struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu); /* vmenter.S */ diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S index 9499f9c6b077..187018c424bf 100644 --- a/arch/x86/kvm/svm/vmenter.S +++ b/arch/x86/kvm/svm/vmenter.S @@ -207,7 +207,7 @@ SYM_FUNC_START(__svm_vcpu_run) 7: vmload %_ASM_AX 8: -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE #endif @@ -344,7 +344,7 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run) /* Pop @svm to RDI, guest registers have been saved already. */ pop %_ASM_DI -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE #endif diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 5b8fae9c1f82..305237dcba88 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6553,7 +6553,7 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) if (exit_reason.basic >= kvm_vmx_max_exit_handlers) goto unexpected_vmexit; -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE if (exit_reason.basic == EXIT_REASON_MSR_WRITE) return kvm_emulate_wrmsr(vcpu); else if (exit_reason.basic == EXIT_REASON_PREEMPTION_TIMER) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index e02cc710f56d..ffe580169c93 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1623,7 +1623,8 @@ static bool kvm_is_immutable_feature_msr(u32 msr) ARCH_CAP_SKIP_VMENTRY_L1DFLUSH | ARCH_CAP_SSB_NO | ARCH_CAP_MDS_NO | \ ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \ ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \ - ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO) + ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO | \ + ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR) static u64 kvm_get_arch_capabilities(void) { @@ -1655,6 +1656,8 @@ static u64 kvm_get_arch_capabilities(void) data |= ARCH_CAP_SSB_NO; if (!boot_cpu_has_bug(X86_BUG_MDS)) data |= ARCH_CAP_MDS_NO; + if (!boot_cpu_has_bug(X86_BUG_RFDS)) + data |= ARCH_CAP_RFDS_NO; if (!boot_cpu_has(X86_FEATURE_RTM)) { /* diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index ea3a28e7b613..6da73513f026 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -14,19 +14,6 @@ ifdef CONFIG_KCSAN CFLAGS_REMOVE_delay.o = $(CC_FLAGS_FTRACE) endif -# Early boot use of cmdline; don't instrument it -ifdef CONFIG_AMD_MEM_ENCRYPT -KCOV_INSTRUMENT_cmdline.o := n -KASAN_SANITIZE_cmdline.o := n -KCSAN_SANITIZE_cmdline.o := n - -ifdef CONFIG_FUNCTION_TRACER -CFLAGS_REMOVE_cmdline.o = -pg -endif - -CFLAGS_cmdline.o := -fno-stack-protector -fno-jump-tables -endif - inat_tables_script = $(srctree)/arch/x86/tools/gen-insn-attr-x86.awk inat_tables_maps = $(srctree)/arch/x86/lib/x86-opcode-map.txt quiet_cmd_inat_tables = GEN $@ @@ -49,7 +36,7 @@ lib-$(CONFIG_ARCH_HAS_COPY_MC) += copy_mc.o copy_mc_64.o lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o insn-eval.o lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o lib-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o -lib-$(CONFIG_RETPOLINE) += retpoline.o +lib-$(CONFIG_MITIGATION_RETPOLINE) += retpoline.o obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o obj-y += iomem.o diff --git a/arch/x86/lib/cmpxchg16b_emu.S b/arch/x86/lib/cmpxchg16b_emu.S index 6962df315793..4fb44894ad87 100644 --- a/arch/x86/lib/cmpxchg16b_emu.S +++ b/arch/x86/lib/cmpxchg16b_emu.S @@ -23,14 +23,14 @@ SYM_FUNC_START(this_cpu_cmpxchg16b_emu) cli /* if (*ptr == old) */ - cmpq PER_CPU_VAR(0(%rsi)), %rax + cmpq __percpu (%rsi), %rax jne .Lnot_same - cmpq PER_CPU_VAR(8(%rsi)), %rdx + cmpq __percpu 8(%rsi), %rdx jne .Lnot_same /* *ptr = new */ - movq %rbx, PER_CPU_VAR(0(%rsi)) - movq %rcx, PER_CPU_VAR(8(%rsi)) + movq %rbx, __percpu (%rsi) + movq %rcx, __percpu 8(%rsi) /* set ZF in EFLAGS to indicate success */ orl $X86_EFLAGS_ZF, (%rsp) @@ -42,8 +42,8 @@ SYM_FUNC_START(this_cpu_cmpxchg16b_emu) /* *ptr != old */ /* old = *ptr */ - movq PER_CPU_VAR(0(%rsi)), %rax - movq PER_CPU_VAR(8(%rsi)), %rdx + movq __percpu (%rsi), %rax + movq __percpu 8(%rsi), %rdx /* clear ZF in EFLAGS to indicate failure */ andl $(~X86_EFLAGS_ZF), (%rsp) diff --git a/arch/x86/lib/cmpxchg8b_emu.S b/arch/x86/lib/cmpxchg8b_emu.S index 873e4ef23e49..1c96be769adc 100644 --- a/arch/x86/lib/cmpxchg8b_emu.S +++ b/arch/x86/lib/cmpxchg8b_emu.S @@ -24,12 +24,12 @@ SYM_FUNC_START(cmpxchg8b_emu) pushfl cli - cmpl 0(%esi), %eax + cmpl (%esi), %eax jne .Lnot_same cmpl 4(%esi), %edx jne .Lnot_same - movl %ebx, 0(%esi) + movl %ebx, (%esi) movl %ecx, 4(%esi) orl $X86_EFLAGS_ZF, (%esp) @@ -38,7 +38,7 @@ SYM_FUNC_START(cmpxchg8b_emu) RET .Lnot_same: - movl 0(%esi), %eax + movl (%esi), %eax movl 4(%esi), %edx andl $(~X86_EFLAGS_ZF), (%esp) @@ -53,18 +53,30 @@ EXPORT_SYMBOL(cmpxchg8b_emu) #ifndef CONFIG_UML +/* + * Emulate 'cmpxchg8b %fs:(%rsi)' + * + * Inputs: + * %esi : memory location to compare + * %eax : low 32 bits of old value + * %edx : high 32 bits of old value + * %ebx : low 32 bits of new value + * %ecx : high 32 bits of new value + * + * Notably this is not LOCK prefixed and is not safe against NMIs + */ SYM_FUNC_START(this_cpu_cmpxchg8b_emu) pushfl cli - cmpl PER_CPU_VAR(0(%esi)), %eax + cmpl __percpu (%esi), %eax jne .Lnot_same2 - cmpl PER_CPU_VAR(4(%esi)), %edx + cmpl __percpu 4(%esi), %edx jne .Lnot_same2 - movl %ebx, PER_CPU_VAR(0(%esi)) - movl %ecx, PER_CPU_VAR(4(%esi)) + movl %ebx, __percpu (%esi) + movl %ecx, __percpu 4(%esi) orl $X86_EFLAGS_ZF, (%esp) @@ -72,8 +84,8 @@ SYM_FUNC_START(this_cpu_cmpxchg8b_emu) RET .Lnot_same2: - movl PER_CPU_VAR(0(%esi)), %eax - movl PER_CPU_VAR(4(%esi)), %edx + movl __percpu (%esi), %eax + movl __percpu 4(%esi), %edx andl $(~X86_EFLAGS_ZF), (%esp) diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c index 558a605929db..98631c0e7a11 100644 --- a/arch/x86/lib/insn-eval.c +++ b/arch/x86/lib/insn-eval.c @@ -1129,15 +1129,15 @@ static int get_eff_addr_modrm_16(struct insn *insn, struct pt_regs *regs, * get_eff_addr_sib() - Obtain referenced effective address via SIB * @insn: Instruction. Must be valid. * @regs: Register values as seen when entering kernel mode - * @regoff: Obtained operand offset, in pt_regs, associated with segment + * @base_offset: Obtained operand offset, in pt_regs, associated with segment * @eff_addr: Obtained effective address * * Obtain the effective address referenced by the SIB byte of @insn. After * identifying the registers involved in the indexed, register-indirect memory * reference, its value is obtained from the operands in @regs. The computed * address is stored @eff_addr. Also, the register operand that indicates the - * associated segment is stored in @regoff, this parameter can later be used to - * determine such segment. + * associated segment is stored in @base_offset; this parameter can later be + * used to determine such segment. * * Returns: * diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c index 55e371cc69fd..1bb155a0955b 100644 --- a/arch/x86/lib/insn.c +++ b/arch/x86/lib/insn.c @@ -71,7 +71,7 @@ void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64) insn->kaddr = kaddr; insn->end_kaddr = kaddr + buf_len; insn->next_byte = kaddr; - insn->x86_64 = x86_64 ? 1 : 0; + insn->x86_64 = x86_64; insn->opnd_bytes = 4; if (x86_64) insn->addr_bytes = 8; @@ -268,11 +268,9 @@ int insn_get_opcode(struct insn *insn) if (opcode->got) return 0; - if (!insn->prefixes.got) { - ret = insn_get_prefixes(insn); - if (ret) - return ret; - } + ret = insn_get_prefixes(insn); + if (ret) + return ret; /* Get first opcode */ op = get_next(insn_byte_t, insn); @@ -339,11 +337,9 @@ int insn_get_modrm(struct insn *insn) if (modrm->got) return 0; - if (!insn->opcode.got) { - ret = insn_get_opcode(insn); - if (ret) - return ret; - } + ret = insn_get_opcode(insn); + if (ret) + return ret; if (inat_has_modrm(insn->attr)) { mod = get_next(insn_byte_t, insn); @@ -386,11 +382,9 @@ int insn_rip_relative(struct insn *insn) if (!insn->x86_64) return 0; - if (!modrm->got) { - ret = insn_get_modrm(insn); - if (ret) - return 0; - } + ret = insn_get_modrm(insn); + if (ret) + return 0; /* * For rip-relative instructions, the mod field (top 2 bits) * is zero and the r/m field (bottom 3 bits) is 0x5. @@ -417,11 +411,9 @@ int insn_get_sib(struct insn *insn) if (insn->sib.got) return 0; - if (!insn->modrm.got) { - ret = insn_get_modrm(insn); - if (ret) - return ret; - } + ret = insn_get_modrm(insn); + if (ret) + return ret; if (insn->modrm.nbytes) { modrm = insn->modrm.bytes[0]; @@ -460,11 +452,9 @@ int insn_get_displacement(struct insn *insn) if (insn->displacement.got) return 0; - if (!insn->sib.got) { - ret = insn_get_sib(insn); - if (ret) - return ret; - } + ret = insn_get_sib(insn); + if (ret) + return ret; if (insn->modrm.nbytes) { /* @@ -628,11 +618,9 @@ int insn_get_immediate(struct insn *insn) if (insn->immediate.got) return 0; - if (!insn->displacement.got) { - ret = insn_get_displacement(insn); - if (ret) - return ret; - } + ret = insn_get_displacement(insn); + if (ret) + return ret; if (inat_has_moffset(insn->attr)) { if (!__get_moffset(insn)) @@ -703,11 +691,9 @@ int insn_get_length(struct insn *insn) if (insn->length) return 0; - if (!insn->immediate.got) { - ret = insn_get_immediate(insn); - if (ret) - return ret; - } + ret = insn_get_immediate(insn); + if (ret) + return ret; insn->length = (unsigned char)((unsigned long)insn->next_byte - (unsigned long)insn->kaddr); diff --git a/arch/x86/lib/msr-smp.c b/arch/x86/lib/msr-smp.c index 40bbe56bde32..acd463d887e1 100644 --- a/arch/x86/lib/msr-smp.c +++ b/arch/x86/lib/msr-smp.c @@ -9,10 +9,9 @@ static void __rdmsr_on_cpu(void *info) { struct msr_info *rv = info; struct msr *reg; - int this_cpu = raw_smp_processor_id(); if (rv->msrs) - reg = per_cpu_ptr(rv->msrs, this_cpu); + reg = this_cpu_ptr(rv->msrs); else reg = &rv->reg; @@ -23,10 +22,9 @@ static void __wrmsr_on_cpu(void *info) { struct msr_info *rv = info; struct msr *reg; - int this_cpu = raw_smp_processor_id(); if (rv->msrs) - reg = per_cpu_ptr(rv->msrs, this_cpu); + reg = this_cpu_ptr(rv->msrs); else reg = &rv->reg; @@ -97,7 +95,7 @@ int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q) EXPORT_SYMBOL(wrmsrl_on_cpu); static void __rwmsr_on_cpus(const struct cpumask *mask, u32 msr_no, - struct msr *msrs, + struct msr __percpu *msrs, void (*msr_func) (void *info)) { struct msr_info rv; @@ -124,7 +122,7 @@ static void __rwmsr_on_cpus(const struct cpumask *mask, u32 msr_no, * @msrs: array of MSR values * */ -void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs) +void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr __percpu *msrs) { __rwmsr_on_cpus(mask, msr_no, msrs, __rdmsr_on_cpu); } @@ -138,7 +136,7 @@ EXPORT_SYMBOL(rdmsr_on_cpus); * @msrs: array of MSR values * */ -void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs) +void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr __percpu *msrs) { __rwmsr_on_cpus(mask, msr_no, msrs, __wrmsr_on_cpu); } diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c index 47fd9bd6b91d..4bf4fad5b148 100644 --- a/arch/x86/lib/msr.c +++ b/arch/x86/lib/msr.c @@ -6,9 +6,9 @@ #define CREATE_TRACE_POINTS #include <asm/msr-trace.h> -struct msr *msrs_alloc(void) +struct msr __percpu *msrs_alloc(void) { - struct msr *msrs = NULL; + struct msr __percpu *msrs = NULL; msrs = alloc_percpu(struct msr); if (!msrs) { @@ -20,7 +20,7 @@ struct msr *msrs_alloc(void) } EXPORT_SYMBOL(msrs_alloc); -void msrs_free(struct msr *msrs) +void msrs_free(struct msr __percpu *msrs) { free_percpu(msrs); } diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 7b2589877d06..721b528da9ac 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -71,7 +71,7 @@ SYM_CODE_END(__x86_indirect_thunk_array) #include <asm/GEN-for-each-reg.h> #undef GEN -#ifdef CONFIG_CALL_DEPTH_TRACKING +#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING .macro CALL_THUNK reg .align RETPOLINE_THUNK_SIZE @@ -127,7 +127,7 @@ SYM_CODE_END(__x86_indirect_jump_thunk_array) #undef GEN #endif -#ifdef CONFIG_RETHUNK +#ifdef CONFIG_MITIGATION_RETHUNK /* * Be careful here: that label cannot really be removed because in @@ -138,7 +138,7 @@ SYM_CODE_END(__x86_indirect_jump_thunk_array) */ .section .text..__x86.return_thunk -#ifdef CONFIG_CPU_SRSO +#ifdef CONFIG_MITIGATION_SRSO /* * srso_alias_untrain_ret() and srso_alias_safe_ret() are placed at @@ -225,12 +225,12 @@ SYM_CODE_END(srso_return_thunk) #define JMP_SRSO_UNTRAIN_RET "jmp srso_untrain_ret" #define JMP_SRSO_ALIAS_UNTRAIN_RET "jmp srso_alias_untrain_ret" -#else /* !CONFIG_CPU_SRSO */ +#else /* !CONFIG_MITIGATION_SRSO */ #define JMP_SRSO_UNTRAIN_RET "ud2" #define JMP_SRSO_ALIAS_UNTRAIN_RET "ud2" -#endif /* CONFIG_CPU_SRSO */ +#endif /* CONFIG_MITIGATION_SRSO */ -#ifdef CONFIG_CPU_UNRET_ENTRY +#ifdef CONFIG_MITIGATION_UNRET_ENTRY /* * Some generic notes on the untraining sequences: @@ -312,11 +312,11 @@ SYM_CODE_END(retbleed_return_thunk) SYM_FUNC_END(retbleed_untrain_ret) #define JMP_RETBLEED_UNTRAIN_RET "jmp retbleed_untrain_ret" -#else /* !CONFIG_CPU_UNRET_ENTRY */ +#else /* !CONFIG_MITIGATION_UNRET_ENTRY */ #define JMP_RETBLEED_UNTRAIN_RET "ud2" -#endif /* CONFIG_CPU_UNRET_ENTRY */ +#endif /* CONFIG_MITIGATION_UNRET_ENTRY */ -#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO) +#if defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO) SYM_FUNC_START(entry_untrain_ret) ALTERNATIVE_2 JMP_RETBLEED_UNTRAIN_RET, \ @@ -325,9 +325,9 @@ SYM_FUNC_START(entry_untrain_ret) SYM_FUNC_END(entry_untrain_ret) __EXPORT_THUNK(entry_untrain_ret) -#endif /* CONFIG_CPU_UNRET_ENTRY || CONFIG_CPU_SRSO */ +#endif /* CONFIG_MITIGATION_UNRET_ENTRY || CONFIG_MITIGATION_SRSO */ -#ifdef CONFIG_CALL_DEPTH_TRACKING +#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING .align 64 SYM_FUNC_START(call_depth_return_thunk) @@ -359,7 +359,7 @@ SYM_FUNC_START(call_depth_return_thunk) int3 SYM_FUNC_END(call_depth_return_thunk) -#endif /* CONFIG_CALL_DEPTH_TRACKING */ +#endif /* CONFIG_MITIGATION_CALL_DEPTH_TRACKING */ /* * This function name is magical and is used by -mfunction-return=thunk-extern @@ -369,21 +369,18 @@ SYM_FUNC_END(call_depth_return_thunk) * 'JMP __x86_return_thunk' sites are changed to something else by * apply_returns(). * - * This should be converted eventually to call a warning function which - * should scream loudly when the default return thunk is called after - * alternatives have been applied. - * - * That warning function cannot BUG() because the bug splat cannot be - * displayed in all possible configurations, leading to users not really - * knowing why the machine froze. + * The ALTERNATIVE below adds a really loud warning to catch the case + * where the insufficient default return thunk ends up getting used for + * whatever reason like miscompilation or failure of + * objtool/alternatives/etc to patch all the return sites. */ SYM_CODE_START(__x86_return_thunk) UNWIND_HINT_FUNC ANNOTATE_NOENDBR - ANNOTATE_UNRET_SAFE - ret + ALTERNATIVE __stringify(ANNOTATE_UNRET_SAFE; ret), \ + "jmp warn_thunk_thunk", X86_FEATURE_ALWAYS int3 SYM_CODE_END(__x86_return_thunk) EXPORT_SYMBOL(__x86_return_thunk) -#endif /* CONFIG_RETHUNK */ +#endif /* CONFIG_MITIGATION_RETHUNK */ diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index c80febc44cd2..428048e73bd2 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -16,6 +16,7 @@ KASAN_SANITIZE_pgprot.o := n KCSAN_SANITIZE := n # Avoid recursion by not calling KMSAN hooks for CEA code. KMSAN_SANITIZE_cpu_entry_area.o := n +KMSAN_SANITIZE_mem_encrypt_identity.o := n ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_mem_encrypt.o = -pg @@ -60,7 +61,7 @@ obj-$(CONFIG_NUMA_EMU) += numa_emulation.o obj-$(CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS) += pkeys.o obj-$(CONFIG_RANDOMIZE_MEMORY) += kaslr.o -obj-$(CONFIG_PAGE_TABLE_ISOLATION) += pti.o +obj-$(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION) += pti.o obj-$(CONFIG_X86_MEM_ENCRYPT) += mem_encrypt.o obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt_amd.o diff --git a/arch/x86/mm/debug_pagetables.c b/arch/x86/mm/debug_pagetables.c index b43301cb2a80..ae5c213a1cb0 100644 --- a/arch/x86/mm/debug_pagetables.c +++ b/arch/x86/mm/debug_pagetables.c @@ -22,7 +22,7 @@ static int ptdump_curknl_show(struct seq_file *m, void *v) DEFINE_SHOW_ATTRIBUTE(ptdump_curknl); -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION static int ptdump_curusr_show(struct seq_file *m, void *v) { if (current->mm->pgd) @@ -54,7 +54,7 @@ static int __init pt_dump_debug_init(void) debugfs_create_file("current_kernel", 0400, dir, NULL, &ptdump_curknl_fops); -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION debugfs_create_file("current_user", 0400, dir, NULL, &ptdump_curusr_fops); #endif diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index e1b599ecbbc2..b7b88c1d91ec 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -408,7 +408,7 @@ void ptdump_walk_pgd_level_debugfs(struct seq_file *m, struct mm_struct *mm, bool user) { pgd_t *pgd = mm->pgd; -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION if (user && boot_cpu_has(X86_FEATURE_PTI)) pgd = kernel_to_user_pgdp(pgd); #endif @@ -418,7 +418,7 @@ EXPORT_SYMBOL_GPL(ptdump_walk_pgd_level_debugfs); void ptdump_walk_user_pgd_level_checkwx(void) { -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION pgd_t *pgd = INIT_PGD; if (!(__supported_pte_mask & _PAGE_NX) || diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index e1ac86396446..402e08f6b7ec 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -35,6 +35,7 @@ #include <asm/vdso.h> /* fixup_vdso_exception() */ #include <asm/irq_stack.h> #include <asm/fred.h> +#include <asm/sev.h> /* snp_dump_hva_rmpentry() */ #define CREATE_TRACE_POINTS #include <asm/trace/exceptions.h> @@ -548,6 +549,7 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code, unsigned long ad !(error_code & X86_PF_PROT) ? "not-present page" : (error_code & X86_PF_RSVD) ? "reserved bit violation" : (error_code & X86_PF_PK) ? "protection keys violation" : + (error_code & X86_PF_RMP) ? "RMP violation" : "permissions violation"); if (!(error_code & X86_PF_USER) && user_mode(regs)) { @@ -580,6 +582,9 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code, unsigned long ad } dump_pagetable(address); + + if (error_code & X86_PF_RMP) + snp_dump_hva_rmpentry(address); } static noinline void @@ -1294,21 +1299,14 @@ void do_user_addr_fault(struct pt_regs *regs, return; } - /* - * It's safe to allow irq's after cr2 has been saved and the - * vmalloc fault has been handled. - * - * User-mode registers count as a user access even for any - * potential system fault or CPU buglet: - */ - if (user_mode(regs)) { - local_irq_enable(); - flags |= FAULT_FLAG_USER; - } else { - if (regs->flags & X86_EFLAGS_IF) - local_irq_enable(); + /* Legacy check - remove this after verifying that it doesn't trigger */ + if (WARN_ON_ONCE(!(regs->flags & X86_EFLAGS_IF))) { + bad_area_nosemaphore(regs, error_code, address); + return; } + local_irq_enable(); + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); /* @@ -1324,6 +1322,14 @@ void do_user_addr_fault(struct pt_regs *regs, if (error_code & X86_PF_INSTR) flags |= FAULT_FLAG_INSTRUCTION; + /* + * We set FAULT_FLAG_USER based on the register state, not + * based on X86_PF_USER. User space accesses that cause + * system page faults are still user accesses. + */ + if (user_mode(regs)) + flags |= FAULT_FLAG_USER; + #ifdef CONFIG_X86_64 /* * Faults in the vsyscall page might need emulation. The diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index c290c55b632b..6f3b3e028718 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -14,6 +14,8 @@ #include <linux/mem_encrypt.h> #include <linux/virtio_anchor.h> +#include <asm/sev.h> + /* Override for DMA direct allocation check - ARCH_HAS_FORCE_DMA_UNENCRYPTED */ bool force_dma_unencrypted(struct device *dev) { @@ -42,38 +44,45 @@ bool force_dma_unencrypted(struct device *dev) static void print_mem_encrypt_feature_info(void) { - pr_info("Memory Encryption Features active:"); - - if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) { - pr_cont(" Intel TDX\n"); - return; - } + pr_info("Memory Encryption Features active: "); - pr_cont(" AMD"); + switch (cc_vendor) { + case CC_VENDOR_INTEL: + pr_cont("Intel TDX\n"); + break; + case CC_VENDOR_AMD: + pr_cont("AMD"); - /* Secure Memory Encryption */ - if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) { + /* Secure Memory Encryption */ + if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) { /* * SME is mutually exclusive with any of the SEV * features below. - */ - pr_cont(" SME\n"); - return; - } + */ + pr_cont(" SME\n"); + return; + } - /* Secure Encrypted Virtualization */ - if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) - pr_cont(" SEV"); + /* Secure Encrypted Virtualization */ + if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) + pr_cont(" SEV"); + + /* Encrypted Register State */ + if (cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT)) + pr_cont(" SEV-ES"); - /* Encrypted Register State */ - if (cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT)) - pr_cont(" SEV-ES"); + /* Secure Nested Paging */ + if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + pr_cont(" SEV-SNP"); - /* Secure Nested Paging */ - if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) - pr_cont(" SEV-SNP"); + pr_cont("\n"); - pr_cont("\n"); + sev_show_status(); + + break; + default: + pr_cont("Unknown\n"); + } } /* Architecture __weak replacement functions */ diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c index d73aeb16417f..64b5005d49e5 100644 --- a/arch/x86/mm/mem_encrypt_identity.c +++ b/arch/x86/mm/mem_encrypt_identity.c @@ -41,9 +41,9 @@ #include <linux/mem_encrypt.h> #include <linux/cc_platform.h> +#include <asm/init.h> #include <asm/setup.h> #include <asm/sections.h> -#include <asm/cmdline.h> #include <asm/coco.h> #include <asm/sev.h> @@ -95,11 +95,7 @@ struct sme_populate_pgd_data { */ static char sme_workarea[2 * PMD_SIZE] __section(".init.scratch"); -static char sme_cmdline_arg[] __initdata = "mem_encrypt"; -static char sme_cmdline_on[] __initdata = "on"; -static char sme_cmdline_off[] __initdata = "off"; - -static void __init sme_clear_pgd(struct sme_populate_pgd_data *ppd) +static void __head sme_clear_pgd(struct sme_populate_pgd_data *ppd) { unsigned long pgd_start, pgd_end, pgd_size; pgd_t *pgd_p; @@ -114,7 +110,7 @@ static void __init sme_clear_pgd(struct sme_populate_pgd_data *ppd) memset(pgd_p, 0, pgd_size); } -static pud_t __init *sme_prepare_pgd(struct sme_populate_pgd_data *ppd) +static pud_t __head *sme_prepare_pgd(struct sme_populate_pgd_data *ppd) { pgd_t *pgd; p4d_t *p4d; @@ -151,7 +147,7 @@ static pud_t __init *sme_prepare_pgd(struct sme_populate_pgd_data *ppd) return pud; } -static void __init sme_populate_pgd_large(struct sme_populate_pgd_data *ppd) +static void __head sme_populate_pgd_large(struct sme_populate_pgd_data *ppd) { pud_t *pud; pmd_t *pmd; @@ -167,7 +163,7 @@ static void __init sme_populate_pgd_large(struct sme_populate_pgd_data *ppd) set_pmd(pmd, __pmd(ppd->paddr | ppd->pmd_flags)); } -static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd) +static void __head sme_populate_pgd(struct sme_populate_pgd_data *ppd) { pud_t *pud; pmd_t *pmd; @@ -193,7 +189,7 @@ static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd) set_pte(pte, __pte(ppd->paddr | ppd->pte_flags)); } -static void __init __sme_map_range_pmd(struct sme_populate_pgd_data *ppd) +static void __head __sme_map_range_pmd(struct sme_populate_pgd_data *ppd) { while (ppd->vaddr < ppd->vaddr_end) { sme_populate_pgd_large(ppd); @@ -203,7 +199,7 @@ static void __init __sme_map_range_pmd(struct sme_populate_pgd_data *ppd) } } -static void __init __sme_map_range_pte(struct sme_populate_pgd_data *ppd) +static void __head __sme_map_range_pte(struct sme_populate_pgd_data *ppd) { while (ppd->vaddr < ppd->vaddr_end) { sme_populate_pgd(ppd); @@ -213,7 +209,7 @@ static void __init __sme_map_range_pte(struct sme_populate_pgd_data *ppd) } } -static void __init __sme_map_range(struct sme_populate_pgd_data *ppd, +static void __head __sme_map_range(struct sme_populate_pgd_data *ppd, pmdval_t pmd_flags, pteval_t pte_flags) { unsigned long vaddr_end; @@ -237,22 +233,22 @@ static void __init __sme_map_range(struct sme_populate_pgd_data *ppd, __sme_map_range_pte(ppd); } -static void __init sme_map_range_encrypted(struct sme_populate_pgd_data *ppd) +static void __head sme_map_range_encrypted(struct sme_populate_pgd_data *ppd) { __sme_map_range(ppd, PMD_FLAGS_ENC, PTE_FLAGS_ENC); } -static void __init sme_map_range_decrypted(struct sme_populate_pgd_data *ppd) +static void __head sme_map_range_decrypted(struct sme_populate_pgd_data *ppd) { __sme_map_range(ppd, PMD_FLAGS_DEC, PTE_FLAGS_DEC); } -static void __init sme_map_range_decrypted_wp(struct sme_populate_pgd_data *ppd) +static void __head sme_map_range_decrypted_wp(struct sme_populate_pgd_data *ppd) { __sme_map_range(ppd, PMD_FLAGS_DEC_WP, PTE_FLAGS_DEC_WP); } -static unsigned long __init sme_pgtable_calc(unsigned long len) +static unsigned long __head sme_pgtable_calc(unsigned long len) { unsigned long entries = 0, tables = 0; @@ -289,7 +285,7 @@ static unsigned long __init sme_pgtable_calc(unsigned long len) return entries + tables; } -void __init sme_encrypt_kernel(struct boot_params *bp) +void __head sme_encrypt_kernel(struct boot_params *bp) { unsigned long workarea_start, workarea_end, workarea_len; unsigned long execute_start, execute_end, execute_len; @@ -305,7 +301,8 @@ void __init sme_encrypt_kernel(struct boot_params *bp) * instrumentation or checking boot_cpu_data in the cc_platform_has() * function. */ - if (!sme_get_me_mask() || sev_status & MSR_AMD64_SEV_ENABLED) + if (!sme_get_me_mask() || + RIP_REL_REF(sev_status) & MSR_AMD64_SEV_ENABLED) return; /* @@ -323,9 +320,8 @@ void __init sme_encrypt_kernel(struct boot_params *bp) * memory from being cached. */ - /* Physical addresses gives us the identity mapped virtual addresses */ - kernel_start = __pa_symbol(_text); - kernel_end = ALIGN(__pa_symbol(_end), PMD_SIZE); + kernel_start = (unsigned long)RIP_REL_REF(_text); + kernel_end = ALIGN((unsigned long)RIP_REL_REF(_end), PMD_SIZE); kernel_len = kernel_end - kernel_start; initrd_start = 0; @@ -343,14 +339,6 @@ void __init sme_encrypt_kernel(struct boot_params *bp) #endif /* - * We're running identity mapped, so we must obtain the address to the - * SME encryption workarea using rip-relative addressing. - */ - asm ("lea sme_workarea(%%rip), %0" - : "=r" (workarea_start) - : "p" (sme_workarea)); - - /* * Calculate required number of workarea bytes needed: * executable encryption area size: * stack page (PAGE_SIZE) @@ -359,7 +347,7 @@ void __init sme_encrypt_kernel(struct boot_params *bp) * pagetable structures for the encryption of the kernel * pagetable structures for workarea (in case not currently mapped) */ - execute_start = workarea_start; + execute_start = workarea_start = (unsigned long)RIP_REL_REF(sme_workarea); execute_end = execute_start + (PAGE_SIZE * 2) + PMD_SIZE; execute_len = execute_end - execute_start; @@ -502,14 +490,11 @@ void __init sme_encrypt_kernel(struct boot_params *bp) native_write_cr3(__native_read_cr3()); } -void __init sme_enable(struct boot_params *bp) +void __head sme_enable(struct boot_params *bp) { - const char *cmdline_ptr, *cmdline_arg, *cmdline_on, *cmdline_off; unsigned int eax, ebx, ecx, edx; unsigned long feature_mask; - bool active_by_default; unsigned long me_mask; - char buffer[16]; bool snp; u64 msr; @@ -543,15 +528,18 @@ void __init sme_enable(struct boot_params *bp) me_mask = 1UL << (ebx & 0x3f); /* Check the SEV MSR whether SEV or SME is enabled */ - sev_status = __rdmsr(MSR_AMD64_SEV); - feature_mask = (sev_status & MSR_AMD64_SEV_ENABLED) ? AMD_SEV_BIT : AMD_SME_BIT; + RIP_REL_REF(sev_status) = msr = __rdmsr(MSR_AMD64_SEV); + feature_mask = (msr & MSR_AMD64_SEV_ENABLED) ? AMD_SEV_BIT : AMD_SME_BIT; /* The SEV-SNP CC blob should never be present unless SEV-SNP is enabled. */ - if (snp && !(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) + if (snp && !(msr & MSR_AMD64_SEV_SNP_ENABLED)) snp_abort(); /* Check if memory encryption is enabled */ if (feature_mask == AMD_SME_BIT) { + if (!(bp->hdr.xloadflags & XLF_MEM_ENCRYPTION)) + return; + /* * No SME if Hypervisor bit is set. This check is here to * prevent a guest from trying to enable SME. For running as a @@ -571,48 +559,10 @@ void __init sme_enable(struct boot_params *bp) msr = __rdmsr(MSR_AMD64_SYSCFG); if (!(msr & MSR_AMD64_SYSCFG_MEM_ENCRYPT)) return; - } else { - /* SEV state cannot be controlled by a command line option */ - sme_me_mask = me_mask; - goto out; } - /* - * Fixups have not been applied to phys_base yet and we're running - * identity mapped, so we must obtain the address to the SME command - * line argument data using rip-relative addressing. - */ - asm ("lea sme_cmdline_arg(%%rip), %0" - : "=r" (cmdline_arg) - : "p" (sme_cmdline_arg)); - asm ("lea sme_cmdline_on(%%rip), %0" - : "=r" (cmdline_on) - : "p" (sme_cmdline_on)); - asm ("lea sme_cmdline_off(%%rip), %0" - : "=r" (cmdline_off) - : "p" (sme_cmdline_off)); - - if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT)) - active_by_default = true; - else - active_by_default = false; - - cmdline_ptr = (const char *)((u64)bp->hdr.cmd_line_ptr | - ((u64)bp->ext_cmd_line_ptr << 32)); - - if (cmdline_find_option(cmdline_ptr, cmdline_arg, buffer, sizeof(buffer)) < 0) - return; - - if (!strncmp(buffer, cmdline_on, sizeof(buffer))) - sme_me_mask = me_mask; - else if (!strncmp(buffer, cmdline_off, sizeof(buffer))) - sme_me_mask = 0; - else - sme_me_mask = active_by_default ? me_mask : 0; -out: - if (sme_me_mask) { - physical_mask &= ~sme_me_mask; - cc_vendor = CC_VENDOR_AMD; - cc_set_mask(sme_me_mask); - } + RIP_REL_REF(sme_me_mask) = me_mask; + physical_mask &= ~me_mask; + cc_vendor = CC_VENDOR_AMD; + cc_set_mask(me_mask); } diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index 0904d7e8e126..0d72183b5dd0 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -240,6 +240,8 @@ void pat_cpu_init(void) } wrmsrl(MSR_IA32_CR_PAT, pat_msr_val); + + __flush_tlb_all(); } /** @@ -296,13 +298,8 @@ void __init pat_bp_init(void) /* * Xen PV doesn't allow to set PAT MSR, but all cache modes are * supported. - * When running as TDX guest setting the PAT MSR won't work either - * due to the requirement to set CR0.CD when doing so. Rely on - * firmware to have set the PAT MSR correctly. */ - if (pat_disabled || - cpu_feature_enabled(X86_FEATURE_XENPV) || - cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) { + if (pat_disabled || cpu_feature_enabled(X86_FEATURE_XENPV)) { init_cache_modes(pat_msr_val); return; } diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index 102880404046..e5b2985a7c51 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -2157,7 +2157,7 @@ static int __set_memory_enc_pgtable(unsigned long addr, int numpages, bool enc) /* Notify hypervisor that we are about to set/clr encryption attribute. */ if (!x86_platform.guest.enc_status_change_prepare(addr, numpages, enc)) - return -EIO; + goto vmm_fail; ret = __change_page_attr_set_clr(&cpa, 1); @@ -2170,13 +2170,20 @@ static int __set_memory_enc_pgtable(unsigned long addr, int numpages, bool enc) */ cpa_flush(&cpa, 0); + if (ret) + return ret; + /* Notify hypervisor that we have successfully set/clr encryption attribute. */ - if (!ret) { - if (!x86_platform.guest.enc_status_change_finish(addr, numpages, enc)) - ret = -EIO; - } + if (!x86_platform.guest.enc_status_change_finish(addr, numpages, enc)) + goto vmm_fail; - return ret; + return 0; + +vmm_fail: + WARN_ONCE(1, "CPA VMM failure to convert memory (addr=%p, numpages=%d) to %s.\n", + (void *)addr, numpages, enc ? "private" : "shared"); + + return -EIO; } static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc) diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 0cbc1b8e8e3d..cceb779d882d 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -293,7 +293,7 @@ static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp) for (i = 0; i < PREALLOCATED_PMDS; i++) mop_up_one_pmd(mm, &pgdp[i]); -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION if (!boot_cpu_has(X86_FEATURE_PTI)) return; @@ -325,7 +325,7 @@ static void pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmds[]) } } -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION static void pgd_prepopulate_user_pmd(struct mm_struct *mm, pgd_t *k_pgd, pmd_t *pmds[]) { diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 5768d386efab..4af930947380 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -89,10 +89,10 @@ #define CR3_HW_ASID_BITS 12 /* - * When enabled, PAGE_TABLE_ISOLATION consumes a single bit for + * When enabled, MITIGATION_PAGE_TABLE_ISOLATION consumes a single bit for * user/kernel switches */ -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION # define PTI_CONSUMED_PCID_BITS 1 #else # define PTI_CONSUMED_PCID_BITS 0 @@ -114,7 +114,7 @@ static inline u16 kern_pcid(u16 asid) { VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE); -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION /* * Make sure that the dynamic ASID space does not conflict with the * bit we are using to switch between user and kernel ASIDs. @@ -149,7 +149,7 @@ static inline u16 kern_pcid(u16 asid) static inline u16 user_pcid(u16 asid) { u16 ret = kern_pcid(asid); -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION ret |= 1 << X86_CR3_PTI_PCID_USER_BIT; #endif return ret; @@ -262,7 +262,7 @@ static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen, static inline void invalidate_user_asid(u16 asid) { /* There is no user ASID if address space separation is off */ - if (!IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) + if (!IS_ENABLED(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION)) return; /* diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 919f647c740f..f3b4716317c1 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -553,7 +553,7 @@ static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip) emit_jump(&prog, &__x86_indirect_thunk_array[reg], ip); } else { EMIT2(0xFF, 0xE0 + reg); /* jmp *%\reg */ - if (IS_ENABLED(CONFIG_RETPOLINE) || IS_ENABLED(CONFIG_SLS)) + if (IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) || IS_ENABLED(CONFIG_MITIGATION_SLS)) EMIT1(0xCC); /* int3 */ } @@ -568,7 +568,7 @@ static void emit_return(u8 **pprog, u8 *ip) emit_jump(&prog, x86_return_thunk, ip); } else { EMIT1(0xC3); /* ret */ - if (IS_ENABLED(CONFIG_SLS)) + if (IS_ENABLED(CONFIG_MITIGATION_SLS)) EMIT1(0xCC); /* int3 */ } diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c index b18ce19981ec..c10083a8e68e 100644 --- a/arch/x86/net/bpf_jit_comp32.c +++ b/arch/x86/net/bpf_jit_comp32.c @@ -1273,7 +1273,7 @@ static int emit_jmp_edx(u8 **pprog, u8 *ip) u8 *prog = *pprog; int cnt = 0; -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE EMIT1_off32(0xE9, (u8 *)__x86_indirect_thunk_edx - (ip + 5)); #else EMIT2(0xFF, 0xE2); diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index e9f99c56f3ce..f090ec972d7b 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -950,3 +950,8 @@ umode_t efi_attr_is_visible(struct kobject *kobj, struct attribute *attr, int n) } return attr->mode; } + +enum efi_secureboot_mode __x86_ima_efi_boot_mode(void) +{ + return boot_params.secure_boot; +} diff --git a/arch/x86/platform/pvh/enlighten.c b/arch/x86/platform/pvh/enlighten.c index 00a92cb2c814..944e0290f2c0 100644 --- a/arch/x86/platform/pvh/enlighten.c +++ b/arch/x86/platform/pvh/enlighten.c @@ -3,6 +3,7 @@ #include <xen/hvc-console.h> +#include <asm/bootparam.h> #include <asm/io_apic.h> #include <asm/hypervisor.h> #include <asm/e820/api.h> diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile index 08aa0f25f12a..bc31863c5ee6 100644 --- a/arch/x86/purgatory/Makefile +++ b/arch/x86/purgatory/Makefile @@ -61,7 +61,7 @@ ifdef CONFIG_STACKPROTECTOR_STRONG PURGATORY_CFLAGS_REMOVE += -fstack-protector-strong endif -ifdef CONFIG_RETPOLINE +ifdef CONFIG_MITIGATION_RETPOLINE PURGATORY_CFLAGS_REMOVE += $(RETPOLINE_CFLAGS) endif diff --git a/arch/x86/realmode/rm/trampoline_64.S b/arch/x86/realmode/rm/trampoline_64.S index c9f76fae902e..14d9c7daf90f 100644 --- a/arch/x86/realmode/rm/trampoline_64.S +++ b/arch/x86/realmode/rm/trampoline_64.S @@ -37,13 +37,15 @@ .text .code16 -.macro LOCK_AND_LOAD_REALMODE_ESP lock_pa=0 +.macro LOCK_AND_LOAD_REALMODE_ESP lock_pa=0 lock_rip=0 /* * Make sure only one CPU fiddles with the realmode stack */ .Llock_rm\@: .if \lock_pa lock btsl $0, pa_tr_lock + .elseif \lock_rip + lock btsl $0, tr_lock(%rip) .else lock btsl $0, tr_lock .endif @@ -220,6 +222,35 @@ SYM_CODE_START(trampoline_start64) lidt tr_idt(%rip) lgdt tr_gdt64(%rip) + /* Check if paging mode has to be changed */ + movq %cr4, %rax + xorl tr_cr4(%rip), %eax + testl $X86_CR4_LA57, %eax + jnz .L_switch_paging + + /* Paging mode is correct proceed in 64-bit mode */ + + LOCK_AND_LOAD_REALMODE_ESP lock_rip=1 + + movw $__KERNEL_DS, %dx + movl %edx, %ss + addl $pa_real_mode_base, %esp + movl %edx, %ds + movl %edx, %es + movl %edx, %fs + movl %edx, %gs + + movl $pa_trampoline_pgd, %eax + movq %rax, %cr3 + + pushq $__KERNEL_CS + pushq tr_start(%rip) + lretq +.L_switch_paging: + /* + * To switch between 4- and 5-level paging modes, it is necessary + * to disable paging. This must be done in the compatibility mode. + */ ljmpl *tr_compat(%rip) SYM_CODE_END(trampoline_start64) diff --git a/arch/x86/virt/svm/Makefile b/arch/x86/virt/svm/Makefile new file mode 100644 index 000000000000..ef2a31bdcc70 --- /dev/null +++ b/arch/x86/virt/svm/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-$(CONFIG_KVM_AMD_SEV) += sev.o diff --git a/arch/x86/virt/svm/sev.c b/arch/x86/virt/svm/sev.c new file mode 100644 index 000000000000..cffe1157a90a --- /dev/null +++ b/arch/x86/virt/svm/sev.c @@ -0,0 +1,560 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * AMD SVM-SEV Host Support. + * + * Copyright (C) 2023 Advanced Micro Devices, Inc. + * + * Author: Ashish Kalra <ashish.kalra@amd.com> + * + */ + +#include <linux/cc_platform.h> +#include <linux/printk.h> +#include <linux/mm_types.h> +#include <linux/set_memory.h> +#include <linux/memblock.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/cpumask.h> +#include <linux/iommu.h> +#include <linux/amd-iommu.h> + +#include <asm/sev.h> +#include <asm/processor.h> +#include <asm/setup.h> +#include <asm/svm.h> +#include <asm/smp.h> +#include <asm/cpu.h> +#include <asm/apic.h> +#include <asm/cpuid.h> +#include <asm/cmdline.h> +#include <asm/iommu.h> + +/* + * The RMP entry format is not architectural. The format is defined in PPR + * Family 19h Model 01h, Rev B1 processor. + */ +struct rmpentry { + union { + struct { + u64 assigned : 1, + pagesize : 1, + immutable : 1, + rsvd1 : 9, + gpa : 39, + asid : 10, + vmsa : 1, + validated : 1, + rsvd2 : 1; + }; + u64 lo; + }; + u64 hi; +} __packed; + +/* + * The first 16KB from the RMP_BASE is used by the processor for the + * bookkeeping, the range needs to be added during the RMP entry lookup. + */ +#define RMPTABLE_CPU_BOOKKEEPING_SZ 0x4000 + +/* Mask to apply to a PFN to get the first PFN of a 2MB page */ +#define PFN_PMD_MASK GENMASK_ULL(63, PMD_SHIFT - PAGE_SHIFT) + +static u64 probed_rmp_base, probed_rmp_size; +static struct rmpentry *rmptable __ro_after_init; +static u64 rmptable_max_pfn __ro_after_init; + +static LIST_HEAD(snp_leaked_pages_list); +static DEFINE_SPINLOCK(snp_leaked_pages_list_lock); + +static unsigned long snp_nr_leaked_pages; + +#undef pr_fmt +#define pr_fmt(fmt) "SEV-SNP: " fmt + +static int __mfd_enable(unsigned int cpu) +{ + u64 val; + + if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP)) + return 0; + + rdmsrl(MSR_AMD64_SYSCFG, val); + + val |= MSR_AMD64_SYSCFG_MFDM; + + wrmsrl(MSR_AMD64_SYSCFG, val); + + return 0; +} + +static __init void mfd_enable(void *arg) +{ + __mfd_enable(smp_processor_id()); +} + +static int __snp_enable(unsigned int cpu) +{ + u64 val; + + if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP)) + return 0; + + rdmsrl(MSR_AMD64_SYSCFG, val); + + val |= MSR_AMD64_SYSCFG_SNP_EN; + val |= MSR_AMD64_SYSCFG_SNP_VMPL_EN; + + wrmsrl(MSR_AMD64_SYSCFG, val); + + return 0; +} + +static __init void snp_enable(void *arg) +{ + __snp_enable(smp_processor_id()); +} + +#define RMP_ADDR_MASK GENMASK_ULL(51, 13) + +bool snp_probe_rmptable_info(void) +{ + u64 max_rmp_pfn, calc_rmp_sz, rmp_sz, rmp_base, rmp_end; + + rdmsrl(MSR_AMD64_RMP_BASE, rmp_base); + rdmsrl(MSR_AMD64_RMP_END, rmp_end); + + if (!(rmp_base & RMP_ADDR_MASK) || !(rmp_end & RMP_ADDR_MASK)) { + pr_err("Memory for the RMP table has not been reserved by BIOS\n"); + return false; + } + + if (rmp_base > rmp_end) { + pr_err("RMP configuration not valid: base=%#llx, end=%#llx\n", rmp_base, rmp_end); + return false; + } + + rmp_sz = rmp_end - rmp_base + 1; + + /* + * Calculate the amount the memory that must be reserved by the BIOS to + * address the whole RAM, including the bookkeeping area. The RMP itself + * must also be covered. + */ + max_rmp_pfn = max_pfn; + if (PHYS_PFN(rmp_end) > max_pfn) + max_rmp_pfn = PHYS_PFN(rmp_end); + + calc_rmp_sz = (max_rmp_pfn << 4) + RMPTABLE_CPU_BOOKKEEPING_SZ; + + if (calc_rmp_sz > rmp_sz) { + pr_err("Memory reserved for the RMP table does not cover full system RAM (expected 0x%llx got 0x%llx)\n", + calc_rmp_sz, rmp_sz); + return false; + } + + probed_rmp_base = rmp_base; + probed_rmp_size = rmp_sz; + + pr_info("RMP table physical range [0x%016llx - 0x%016llx]\n", + probed_rmp_base, probed_rmp_base + probed_rmp_size - 1); + + return true; +} + +/* + * Do the necessary preparations which are verified by the firmware as + * described in the SNP_INIT_EX firmware command description in the SNP + * firmware ABI spec. + */ +static int __init snp_rmptable_init(void) +{ + void *rmptable_start; + u64 rmptable_size; + u64 val; + + if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP)) + return 0; + + if (!amd_iommu_snp_en) + return 0; + + if (!probed_rmp_size) + goto nosnp; + + rmptable_start = memremap(probed_rmp_base, probed_rmp_size, MEMREMAP_WB); + if (!rmptable_start) { + pr_err("Failed to map RMP table\n"); + return 1; + } + + /* + * Check if SEV-SNP is already enabled, this can happen in case of + * kexec boot. + */ + rdmsrl(MSR_AMD64_SYSCFG, val); + if (val & MSR_AMD64_SYSCFG_SNP_EN) + goto skip_enable; + + memset(rmptable_start, 0, probed_rmp_size); + + /* Flush the caches to ensure that data is written before SNP is enabled. */ + wbinvd_on_all_cpus(); + + /* MtrrFixDramModEn must be enabled on all the CPUs prior to enabling SNP. */ + on_each_cpu(mfd_enable, NULL, 1); + + on_each_cpu(snp_enable, NULL, 1); + +skip_enable: + rmptable_start += RMPTABLE_CPU_BOOKKEEPING_SZ; + rmptable_size = probed_rmp_size - RMPTABLE_CPU_BOOKKEEPING_SZ; + + rmptable = (struct rmpentry *)rmptable_start; + rmptable_max_pfn = rmptable_size / sizeof(struct rmpentry) - 1; + + cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/rmptable_init:online", __snp_enable, NULL); + + /* + * Setting crash_kexec_post_notifiers to 'true' to ensure that SNP panic + * notifier is invoked to do SNP IOMMU shutdown before kdump. + */ + crash_kexec_post_notifiers = true; + + return 0; + +nosnp: + setup_clear_cpu_cap(X86_FEATURE_SEV_SNP); + return -ENOSYS; +} + +/* + * This must be called after the IOMMU has been initialized. + */ +device_initcall(snp_rmptable_init); + +static struct rmpentry *get_rmpentry(u64 pfn) +{ + if (WARN_ON_ONCE(pfn > rmptable_max_pfn)) + return ERR_PTR(-EFAULT); + + return &rmptable[pfn]; +} + +static struct rmpentry *__snp_lookup_rmpentry(u64 pfn, int *level) +{ + struct rmpentry *large_entry, *entry; + + if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP)) + return ERR_PTR(-ENODEV); + + entry = get_rmpentry(pfn); + if (IS_ERR(entry)) + return entry; + + /* + * Find the authoritative RMP entry for a PFN. This can be either a 4K + * RMP entry or a special large RMP entry that is authoritative for a + * whole 2M area. + */ + large_entry = get_rmpentry(pfn & PFN_PMD_MASK); + if (IS_ERR(large_entry)) + return large_entry; + + *level = RMP_TO_PG_LEVEL(large_entry->pagesize); + + return entry; +} + +int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level) +{ + struct rmpentry *e; + + e = __snp_lookup_rmpentry(pfn, level); + if (IS_ERR(e)) + return PTR_ERR(e); + + *assigned = !!e->assigned; + return 0; +} +EXPORT_SYMBOL_GPL(snp_lookup_rmpentry); + +/* + * Dump the raw RMP entry for a particular PFN. These bits are documented in the + * PPR for a particular CPU model and provide useful information about how a + * particular PFN is being utilized by the kernel/firmware at the time certain + * unexpected events occur, such as RMP faults. + */ +static void dump_rmpentry(u64 pfn) +{ + u64 pfn_i, pfn_end; + struct rmpentry *e; + int level; + + e = __snp_lookup_rmpentry(pfn, &level); + if (IS_ERR(e)) { + pr_err("Failed to read RMP entry for PFN 0x%llx, error %ld\n", + pfn, PTR_ERR(e)); + return; + } + + if (e->assigned) { + pr_info("PFN 0x%llx, RMP entry: [0x%016llx - 0x%016llx]\n", + pfn, e->lo, e->hi); + return; + } + + /* + * If the RMP entry for a particular PFN is not in an assigned state, + * then it is sometimes useful to get an idea of whether or not any RMP + * entries for other PFNs within the same 2MB region are assigned, since + * those too can affect the ability to access a particular PFN in + * certain situations, such as when the PFN is being accessed via a 2MB + * mapping in the host page table. + */ + pfn_i = ALIGN_DOWN(pfn, PTRS_PER_PMD); + pfn_end = pfn_i + PTRS_PER_PMD; + + pr_info("PFN 0x%llx unassigned, dumping non-zero entries in 2M PFN region: [0x%llx - 0x%llx]\n", + pfn, pfn_i, pfn_end); + + while (pfn_i < pfn_end) { + e = __snp_lookup_rmpentry(pfn_i, &level); + if (IS_ERR(e)) { + pr_err("Error %ld reading RMP entry for PFN 0x%llx\n", + PTR_ERR(e), pfn_i); + pfn_i++; + continue; + } + + if (e->lo || e->hi) + pr_info("PFN: 0x%llx, [0x%016llx - 0x%016llx]\n", pfn_i, e->lo, e->hi); + pfn_i++; + } +} + +void snp_dump_hva_rmpentry(unsigned long hva) +{ + unsigned long paddr; + unsigned int level; + pgd_t *pgd; + pte_t *pte; + + pgd = __va(read_cr3_pa()); + pgd += pgd_index(hva); + pte = lookup_address_in_pgd(pgd, hva, &level); + + if (!pte) { + pr_err("Can't dump RMP entry for HVA %lx: no PTE/PFN found\n", hva); + return; + } + + paddr = PFN_PHYS(pte_pfn(*pte)) | (hva & ~page_level_mask(level)); + dump_rmpentry(PHYS_PFN(paddr)); +} + +/* + * PSMASH a 2MB aligned page into 4K pages in the RMP table while preserving the + * Validated bit. + */ +int psmash(u64 pfn) +{ + unsigned long paddr = pfn << PAGE_SHIFT; + int ret; + + if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP)) + return -ENODEV; + + if (!pfn_valid(pfn)) + return -EINVAL; + + /* Binutils version 2.36 supports the PSMASH mnemonic. */ + asm volatile(".byte 0xF3, 0x0F, 0x01, 0xFF" + : "=a" (ret) + : "a" (paddr) + : "memory", "cc"); + + return ret; +} +EXPORT_SYMBOL_GPL(psmash); + +/* + * If the kernel uses a 2MB or larger directmap mapping to write to an address, + * and that mapping contains any 4KB pages that are set to private in the RMP + * table, an RMP #PF will trigger and cause a host crash. Hypervisor code that + * owns the PFNs being transitioned will never attempt such a write, but other + * kernel tasks writing to other PFNs in the range may trigger these checks + * inadvertently due a large directmap mapping that happens to overlap such a + * PFN. + * + * Prevent this by splitting any 2MB+ mappings that might end up containing a + * mix of private/shared PFNs as a result of a subsequent RMPUPDATE for the + * PFN/rmp_level passed in. + * + * Note that there is no attempt here to scan all the RMP entries for the 2MB + * physical range, since it would only be worthwhile in determining if a + * subsequent RMPUPDATE for a 4KB PFN would result in all the entries being of + * the same shared/private state, thus avoiding the need to split the mapping. + * But that would mean the entries are currently in a mixed state, and so the + * mapping would have already been split as a result of prior transitions. + * And since the 4K split is only done if the mapping is 2MB+, and there isn't + * currently a mechanism in place to restore 2MB+ mappings, such a check would + * not provide any usable benefit. + * + * More specifics on how these checks are carried out can be found in APM + * Volume 2, "RMP and VMPL Access Checks". + */ +static int adjust_direct_map(u64 pfn, int rmp_level) +{ + unsigned long vaddr; + unsigned int level; + int npages, ret; + pte_t *pte; + + /* + * pfn_to_kaddr() will return a vaddr only within the direct + * map range. + */ + vaddr = (unsigned long)pfn_to_kaddr(pfn); + + /* Only 4KB/2MB RMP entries are supported by current hardware. */ + if (WARN_ON_ONCE(rmp_level > PG_LEVEL_2M)) + return -EINVAL; + + if (!pfn_valid(pfn)) + return -EINVAL; + + if (rmp_level == PG_LEVEL_2M && + (!IS_ALIGNED(pfn, PTRS_PER_PMD) || !pfn_valid(pfn + PTRS_PER_PMD - 1))) + return -EINVAL; + + /* + * If an entire 2MB physical range is being transitioned, then there is + * no risk of RMP #PFs due to write accesses from overlapping mappings, + * since even accesses from 1GB mappings will be treated as 2MB accesses + * as far as RMP table checks are concerned. + */ + if (rmp_level == PG_LEVEL_2M) + return 0; + + pte = lookup_address(vaddr, &level); + if (!pte || pte_none(*pte)) + return 0; + + if (level == PG_LEVEL_4K) + return 0; + + npages = page_level_size(rmp_level) / PAGE_SIZE; + ret = set_memory_4k(vaddr, npages); + if (ret) + pr_warn("Failed to split direct map for PFN 0x%llx, ret: %d\n", + pfn, ret); + + return ret; +} + +/* + * It is expected that those operations are seldom enough so that no mutual + * exclusion of updaters is needed and thus the overlap error condition below + * should happen very rarely and would get resolved relatively quickly by + * the firmware. + * + * If not, one could consider introducing a mutex or so here to sync concurrent + * RMP updates and thus diminish the amount of cases where firmware needs to + * lock 2M ranges to protect against concurrent updates. + * + * The optimal solution would be range locking to avoid locking disjoint + * regions unnecessarily but there's no support for that yet. + */ +static int rmpupdate(u64 pfn, struct rmp_state *state) +{ + unsigned long paddr = pfn << PAGE_SHIFT; + int ret, level; + + if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP)) + return -ENODEV; + + level = RMP_TO_PG_LEVEL(state->pagesize); + + if (adjust_direct_map(pfn, level)) + return -EFAULT; + + do { + /* Binutils version 2.36 supports the RMPUPDATE mnemonic. */ + asm volatile(".byte 0xF2, 0x0F, 0x01, 0xFE" + : "=a" (ret) + : "a" (paddr), "c" ((unsigned long)state) + : "memory", "cc"); + } while (ret == RMPUPDATE_FAIL_OVERLAP); + + if (ret) { + pr_err("RMPUPDATE failed for PFN %llx, pg_level: %d, ret: %d\n", + pfn, level, ret); + dump_rmpentry(pfn); + dump_stack(); + return -EFAULT; + } + + return 0; +} + +/* Transition a page to guest-owned/private state in the RMP table. */ +int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, u32 asid, bool immutable) +{ + struct rmp_state state; + + memset(&state, 0, sizeof(state)); + state.assigned = 1; + state.asid = asid; + state.immutable = immutable; + state.gpa = gpa; + state.pagesize = PG_LEVEL_TO_RMP(level); + + return rmpupdate(pfn, &state); +} +EXPORT_SYMBOL_GPL(rmp_make_private); + +/* Transition a page to hypervisor-owned/shared state in the RMP table. */ +int rmp_make_shared(u64 pfn, enum pg_level level) +{ + struct rmp_state state; + + memset(&state, 0, sizeof(state)); + state.pagesize = PG_LEVEL_TO_RMP(level); + + return rmpupdate(pfn, &state); +} +EXPORT_SYMBOL_GPL(rmp_make_shared); + +void snp_leak_pages(u64 pfn, unsigned int npages) +{ + struct page *page = pfn_to_page(pfn); + + pr_warn("Leaking PFN range 0x%llx-0x%llx\n", pfn, pfn + npages); + + spin_lock(&snp_leaked_pages_list_lock); + while (npages--) { + + /* + * Reuse the page's buddy list for chaining into the leaked + * pages list. This page should not be on a free list currently + * and is also unsafe to be added to a free list. + */ + if (likely(!PageCompound(page)) || + + /* + * Skip inserting tail pages of compound page as + * page->buddy_list of tail pages is not usable. + */ + (PageHead(page) && compound_nr(page) <= npages)) + list_add_tail(&page->buddy_list, &snp_leaked_pages_list); + + dump_rmpentry(pfn); + snp_nr_leaked_pages++; + pfn++; + page++; + } + spin_unlock(&snp_leaked_pages_list_lock); +} +EXPORT_SYMBOL_GPL(snp_leak_pages); diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c index ada3868c02c2..9e9db601bd52 100644 --- a/arch/x86/xen/enlighten_pvh.c +++ b/arch/x86/xen/enlighten_pvh.c @@ -4,6 +4,7 @@ #include <xen/hvc-console.h> +#include <asm/bootparam.h> #include <asm/io_apic.h> #include <asm/hypervisor.h> #include <asm/e820/api.h> diff --git a/arch/x86/xen/vga.c b/arch/x86/xen/vga.c index d97adab8420f..f7547807b0bd 100644 --- a/arch/x86/xen/vga.c +++ b/arch/x86/xen/vga.c @@ -2,7 +2,6 @@ #include <linux/screen_info.h> #include <linux/init.h> -#include <asm/bootparam.h> #include <asm/setup.h> #include <xen/interface/xen.h> diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index 1a9cd18dfbd3..83189cf5cdce 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -28,7 +28,7 @@ * non-zero. */ SYM_FUNC_START(xen_irq_disable_direct) - movb $1, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask + movb $1, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_mask) RET SYM_FUNC_END(xen_irq_disable_direct) @@ -69,7 +69,7 @@ SYM_FUNC_END(check_events) SYM_FUNC_START(xen_irq_enable_direct) FRAME_BEGIN /* Unmask events */ - movb $0, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask + movb $0, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_mask) /* * Preempt here doesn't matter because that will deal with any @@ -78,7 +78,7 @@ SYM_FUNC_START(xen_irq_enable_direct) */ /* Test for pending */ - testb $0xff, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_pending + testb $0xff, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_pending) jz 1f call check_events @@ -97,7 +97,7 @@ SYM_FUNC_END(xen_irq_enable_direct) * x86 use opposite senses (mask vs enable). */ SYM_FUNC_START(xen_save_fl_direct) - testb $0xff, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask + testb $0xff, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_mask) setz %ah addb %ah, %ah RET @@ -113,7 +113,7 @@ SYM_FUNC_END(xen_read_cr2); SYM_FUNC_START(xen_read_cr2_direct) FRAME_BEGIN - _ASM_MOV PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_arch_cr2, %_ASM_AX + _ASM_MOV PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_arch_cr2), %_ASM_AX FRAME_END RET SYM_FUNC_END(xen_read_cr2_direct); diff --git a/block/blk-settings.c b/block/blk-settings.c index 3c7d8d638ab5..e160d56e8eda 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -267,7 +267,7 @@ int queue_limits_commit_update(struct request_queue *q, EXPORT_SYMBOL_GPL(queue_limits_commit_update); /** - * queue_limits_set - apply queue limits to queue + * queue_limits_commit_set - apply queue limits to queue * @q: queue to update * @lim: limits to apply * diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 47de0f140ba6..0b33e81f9c9b 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -588,6 +588,7 @@ CPU_SHOW_VULN_FALLBACK(mmio_stale_data); CPU_SHOW_VULN_FALLBACK(retbleed); CPU_SHOW_VULN_FALLBACK(spec_rstack_overflow); CPU_SHOW_VULN_FALLBACK(gds); +CPU_SHOW_VULN_FALLBACK(reg_file_data_sampling); static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL); static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL); @@ -602,6 +603,7 @@ static DEVICE_ATTR(mmio_stale_data, 0444, cpu_show_mmio_stale_data, NULL); static DEVICE_ATTR(retbleed, 0444, cpu_show_retbleed, NULL); static DEVICE_ATTR(spec_rstack_overflow, 0444, cpu_show_spec_rstack_overflow, NULL); static DEVICE_ATTR(gather_data_sampling, 0444, cpu_show_gds, NULL); +static DEVICE_ATTR(reg_file_data_sampling, 0444, cpu_show_reg_file_data_sampling, NULL); static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_meltdown.attr, @@ -617,6 +619,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_retbleed.attr, &dev_attr_spec_rstack_overflow.attr, &dev_attr_gather_data_sampling.attr, + &dev_attr_reg_file_data_sampling.attr, NULL }; diff --git a/drivers/crypto/ccp/Kconfig b/drivers/crypto/ccp/Kconfig index 32268e239bf1..f394e45e11ab 100644 --- a/drivers/crypto/ccp/Kconfig +++ b/drivers/crypto/ccp/Kconfig @@ -38,7 +38,7 @@ config CRYPTO_DEV_CCP_CRYPTO config CRYPTO_DEV_SP_PSP bool "Platform Security Processor (PSP) device" default y - depends on CRYPTO_DEV_CCP_DD && X86_64 + depends on CRYPTO_DEV_CCP_DD && X86_64 && AMD_IOMMU help Provide support for the AMD Platform Security Processor (PSP). The PSP is a dedicated processor that provides support for key diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index b04bc1d3d627..f44efbb89c34 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -21,14 +21,18 @@ #include <linux/hw_random.h> #include <linux/ccp.h> #include <linux/firmware.h> +#include <linux/panic_notifier.h> #include <linux/gfp.h> #include <linux/cpufeature.h> #include <linux/fs.h> #include <linux/fs_struct.h> #include <linux/psp.h> +#include <linux/amd-iommu.h> #include <asm/smp.h> #include <asm/cacheflush.h> +#include <asm/e820/types.h> +#include <asm/sev.h> #include "psp-dev.h" #include "sev-dev.h" @@ -37,6 +41,19 @@ #define SEV_FW_FILE "amd/sev.fw" #define SEV_FW_NAME_SIZE 64 +/* Minimum firmware version required for the SEV-SNP support */ +#define SNP_MIN_API_MAJOR 1 +#define SNP_MIN_API_MINOR 51 + +/* + * Maximum number of firmware-writable buffers that might be specified + * in the parameters of a legacy SEV command buffer. + */ +#define CMD_BUF_FW_WRITABLE_MAX 2 + +/* Leave room in the descriptor array for an end-of-list indicator. */ +#define CMD_BUF_DESC_MAX (CMD_BUF_FW_WRITABLE_MAX + 1) + static DEFINE_MUTEX(sev_cmd_mutex); static struct sev_misc_dev *misc_dev; @@ -68,9 +85,14 @@ static int psp_timeout; * The TMR is a 1MB area that must be 1MB aligned. Use the page allocator * to allocate the memory, which will return aligned memory for the specified * allocation order. + * + * When SEV-SNP is enabled the TMR needs to be 2MB aligned and 2MB sized. */ -#define SEV_ES_TMR_SIZE (1024 * 1024) +#define SEV_TMR_SIZE (1024 * 1024) +#define SNP_TMR_SIZE (2 * 1024 * 1024) + static void *sev_es_tmr; +static size_t sev_es_tmr_size = SEV_TMR_SIZE; /* INIT_EX NV Storage: * The NV Storage is a 32Kb area and must be 4Kb page aligned. Use the page @@ -80,6 +102,13 @@ static void *sev_es_tmr; #define NV_LENGTH (32 * 1024) static void *sev_init_ex_buffer; +/* + * SEV_DATA_RANGE_LIST: + * Array containing range of pages that firmware transitions to HV-fixed + * page state. + */ +static struct sev_data_range_list *snp_range_list; + static inline bool sev_version_greater_or_equal(u8 maj, u8 min) { struct sev_device *sev = psp_master->sev_data; @@ -115,6 +144,25 @@ static int sev_wait_cmd_ioc(struct sev_device *sev, { int ret; + /* + * If invoked during panic handling, local interrupts are disabled, + * so the PSP command completion interrupt can't be used. Poll for + * PSP command completion instead. + */ + if (irqs_disabled()) { + unsigned long timeout_usecs = (timeout * USEC_PER_SEC) / 10; + + /* Poll for SEV command completion: */ + while (timeout_usecs--) { + *reg = ioread32(sev->io_regs + sev->vdata->cmdresp_reg); + if (*reg & PSP_CMDRESP_RESP) + return 0; + + udelay(10); + } + return -ETIMEDOUT; + } + ret = wait_event_timeout(sev->int_queue, sev->int_rcvd, timeout * HZ); if (!ret) @@ -130,6 +178,8 @@ static int sev_cmd_buffer_len(int cmd) switch (cmd) { case SEV_CMD_INIT: return sizeof(struct sev_data_init); case SEV_CMD_INIT_EX: return sizeof(struct sev_data_init_ex); + case SEV_CMD_SNP_SHUTDOWN_EX: return sizeof(struct sev_data_snp_shutdown_ex); + case SEV_CMD_SNP_INIT_EX: return sizeof(struct sev_data_snp_init_ex); case SEV_CMD_PLATFORM_STATUS: return sizeof(struct sev_user_data_status); case SEV_CMD_PEK_CSR: return sizeof(struct sev_data_pek_csr); case SEV_CMD_PEK_CERT_IMPORT: return sizeof(struct sev_data_pek_cert_import); @@ -158,23 +208,27 @@ static int sev_cmd_buffer_len(int cmd) case SEV_CMD_GET_ID: return sizeof(struct sev_data_get_id); case SEV_CMD_ATTESTATION_REPORT: return sizeof(struct sev_data_attestation_report); case SEV_CMD_SEND_CANCEL: return sizeof(struct sev_data_send_cancel); + case SEV_CMD_SNP_GCTX_CREATE: return sizeof(struct sev_data_snp_addr); + case SEV_CMD_SNP_LAUNCH_START: return sizeof(struct sev_data_snp_launch_start); + case SEV_CMD_SNP_LAUNCH_UPDATE: return sizeof(struct sev_data_snp_launch_update); + case SEV_CMD_SNP_ACTIVATE: return sizeof(struct sev_data_snp_activate); + case SEV_CMD_SNP_DECOMMISSION: return sizeof(struct sev_data_snp_addr); + case SEV_CMD_SNP_PAGE_RECLAIM: return sizeof(struct sev_data_snp_page_reclaim); + case SEV_CMD_SNP_GUEST_STATUS: return sizeof(struct sev_data_snp_guest_status); + case SEV_CMD_SNP_LAUNCH_FINISH: return sizeof(struct sev_data_snp_launch_finish); + case SEV_CMD_SNP_DBG_DECRYPT: return sizeof(struct sev_data_snp_dbg); + case SEV_CMD_SNP_DBG_ENCRYPT: return sizeof(struct sev_data_snp_dbg); + case SEV_CMD_SNP_PAGE_UNSMASH: return sizeof(struct sev_data_snp_page_unsmash); + case SEV_CMD_SNP_PLATFORM_STATUS: return sizeof(struct sev_data_snp_addr); + case SEV_CMD_SNP_GUEST_REQUEST: return sizeof(struct sev_data_snp_guest_request); + case SEV_CMD_SNP_CONFIG: return sizeof(struct sev_user_data_snp_config); + case SEV_CMD_SNP_COMMIT: return sizeof(struct sev_data_snp_commit); default: return 0; } return 0; } -static void *sev_fw_alloc(unsigned long len) -{ - struct page *page; - - page = alloc_pages(GFP_KERNEL, get_order(len)); - if (!page) - return NULL; - - return page_address(page); -} - static struct file *open_file_as_root(const char *filename, int flags, umode_t mode) { struct file *fp; @@ -305,13 +359,485 @@ static int sev_write_init_ex_file_if_required(int cmd_id) return sev_write_init_ex_file(); } +/* + * snp_reclaim_pages() needs __sev_do_cmd_locked(), and __sev_do_cmd_locked() + * needs snp_reclaim_pages(), so a forward declaration is needed. + */ +static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret); + +static int snp_reclaim_pages(unsigned long paddr, unsigned int npages, bool locked) +{ + int ret, err, i; + + paddr = __sme_clr(ALIGN_DOWN(paddr, PAGE_SIZE)); + + for (i = 0; i < npages; i++, paddr += PAGE_SIZE) { + struct sev_data_snp_page_reclaim data = {0}; + + data.paddr = paddr; + + if (locked) + ret = __sev_do_cmd_locked(SEV_CMD_SNP_PAGE_RECLAIM, &data, &err); + else + ret = sev_do_cmd(SEV_CMD_SNP_PAGE_RECLAIM, &data, &err); + + if (ret) + goto cleanup; + + ret = rmp_make_shared(__phys_to_pfn(paddr), PG_LEVEL_4K); + if (ret) + goto cleanup; + } + + return 0; + +cleanup: + /* + * If there was a failure reclaiming the page then it is no longer safe + * to release it back to the system; leak it instead. + */ + snp_leak_pages(__phys_to_pfn(paddr), npages - i); + return ret; +} + +static int rmp_mark_pages_firmware(unsigned long paddr, unsigned int npages, bool locked) +{ + unsigned long pfn = __sme_clr(paddr) >> PAGE_SHIFT; + int rc, i; + + for (i = 0; i < npages; i++, pfn++) { + rc = rmp_make_private(pfn, 0, PG_LEVEL_4K, 0, true); + if (rc) + goto cleanup; + } + + return 0; + +cleanup: + /* + * Try unrolling the firmware state changes by + * reclaiming the pages which were already changed to the + * firmware state. + */ + snp_reclaim_pages(paddr, i, locked); + + return rc; +} + +static struct page *__snp_alloc_firmware_pages(gfp_t gfp_mask, int order) +{ + unsigned long npages = 1ul << order, paddr; + struct sev_device *sev; + struct page *page; + + if (!psp_master || !psp_master->sev_data) + return NULL; + + page = alloc_pages(gfp_mask, order); + if (!page) + return NULL; + + /* If SEV-SNP is initialized then add the page in RMP table. */ + sev = psp_master->sev_data; + if (!sev->snp_initialized) + return page; + + paddr = __pa((unsigned long)page_address(page)); + if (rmp_mark_pages_firmware(paddr, npages, false)) + return NULL; + + return page; +} + +void *snp_alloc_firmware_page(gfp_t gfp_mask) +{ + struct page *page; + + page = __snp_alloc_firmware_pages(gfp_mask, 0); + + return page ? page_address(page) : NULL; +} +EXPORT_SYMBOL_GPL(snp_alloc_firmware_page); + +static void __snp_free_firmware_pages(struct page *page, int order, bool locked) +{ + struct sev_device *sev = psp_master->sev_data; + unsigned long paddr, npages = 1ul << order; + + if (!page) + return; + + paddr = __pa((unsigned long)page_address(page)); + if (sev->snp_initialized && + snp_reclaim_pages(paddr, npages, locked)) + return; + + __free_pages(page, order); +} + +void snp_free_firmware_page(void *addr) +{ + if (!addr) + return; + + __snp_free_firmware_pages(virt_to_page(addr), 0, false); +} +EXPORT_SYMBOL_GPL(snp_free_firmware_page); + +static void *sev_fw_alloc(unsigned long len) +{ + struct page *page; + + page = __snp_alloc_firmware_pages(GFP_KERNEL, get_order(len)); + if (!page) + return NULL; + + return page_address(page); +} + +/** + * struct cmd_buf_desc - descriptors for managing legacy SEV command address + * parameters corresponding to buffers that may be written to by firmware. + * + * @paddr_ptr: pointer to the address parameter in the command buffer which may + * need to be saved/restored depending on whether a bounce buffer + * is used. In the case of a bounce buffer, the command buffer + * needs to be updated with the address of the new bounce buffer + * snp_map_cmd_buf_desc() has allocated specifically for it. Must + * be NULL if this descriptor is only an end-of-list indicator. + * + * @paddr_orig: storage for the original address parameter, which can be used to + * restore the original value in @paddr_ptr in cases where it is + * replaced with the address of a bounce buffer. + * + * @len: length of buffer located at the address originally stored at @paddr_ptr + * + * @guest_owned: true if the address corresponds to guest-owned pages, in which + * case bounce buffers are not needed. + */ +struct cmd_buf_desc { + u64 *paddr_ptr; + u64 paddr_orig; + u32 len; + bool guest_owned; +}; + +/* + * If a legacy SEV command parameter is a memory address, those pages in + * turn need to be transitioned to/from firmware-owned before/after + * executing the firmware command. + * + * Additionally, in cases where those pages are not guest-owned, a bounce + * buffer is needed in place of the original memory address parameter. + * + * A set of descriptors are used to keep track of this handling, and + * initialized here based on the specific commands being executed. + */ +static void snp_populate_cmd_buf_desc_list(int cmd, void *cmd_buf, + struct cmd_buf_desc *desc_list) +{ + switch (cmd) { + case SEV_CMD_PDH_CERT_EXPORT: { + struct sev_data_pdh_cert_export *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->pdh_cert_address; + desc_list[0].len = data->pdh_cert_len; + desc_list[1].paddr_ptr = &data->cert_chain_address; + desc_list[1].len = data->cert_chain_len; + break; + } + case SEV_CMD_GET_ID: { + struct sev_data_get_id *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->address; + desc_list[0].len = data->len; + break; + } + case SEV_CMD_PEK_CSR: { + struct sev_data_pek_csr *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->address; + desc_list[0].len = data->len; + break; + } + case SEV_CMD_LAUNCH_UPDATE_DATA: { + struct sev_data_launch_update_data *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->address; + desc_list[0].len = data->len; + desc_list[0].guest_owned = true; + break; + } + case SEV_CMD_LAUNCH_UPDATE_VMSA: { + struct sev_data_launch_update_vmsa *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->address; + desc_list[0].len = data->len; + desc_list[0].guest_owned = true; + break; + } + case SEV_CMD_LAUNCH_MEASURE: { + struct sev_data_launch_measure *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->address; + desc_list[0].len = data->len; + break; + } + case SEV_CMD_LAUNCH_UPDATE_SECRET: { + struct sev_data_launch_secret *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->guest_address; + desc_list[0].len = data->guest_len; + desc_list[0].guest_owned = true; + break; + } + case SEV_CMD_DBG_DECRYPT: { + struct sev_data_dbg *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->dst_addr; + desc_list[0].len = data->len; + desc_list[0].guest_owned = true; + break; + } + case SEV_CMD_DBG_ENCRYPT: { + struct sev_data_dbg *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->dst_addr; + desc_list[0].len = data->len; + desc_list[0].guest_owned = true; + break; + } + case SEV_CMD_ATTESTATION_REPORT: { + struct sev_data_attestation_report *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->address; + desc_list[0].len = data->len; + break; + } + case SEV_CMD_SEND_START: { + struct sev_data_send_start *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->session_address; + desc_list[0].len = data->session_len; + break; + } + case SEV_CMD_SEND_UPDATE_DATA: { + struct sev_data_send_update_data *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->hdr_address; + desc_list[0].len = data->hdr_len; + desc_list[1].paddr_ptr = &data->trans_address; + desc_list[1].len = data->trans_len; + break; + } + case SEV_CMD_SEND_UPDATE_VMSA: { + struct sev_data_send_update_vmsa *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->hdr_address; + desc_list[0].len = data->hdr_len; + desc_list[1].paddr_ptr = &data->trans_address; + desc_list[1].len = data->trans_len; + break; + } + case SEV_CMD_RECEIVE_UPDATE_DATA: { + struct sev_data_receive_update_data *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->guest_address; + desc_list[0].len = data->guest_len; + desc_list[0].guest_owned = true; + break; + } + case SEV_CMD_RECEIVE_UPDATE_VMSA: { + struct sev_data_receive_update_vmsa *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->guest_address; + desc_list[0].len = data->guest_len; + desc_list[0].guest_owned = true; + break; + } + default: + break; + } +} + +static int snp_map_cmd_buf_desc(struct cmd_buf_desc *desc) +{ + unsigned int npages; + + if (!desc->len) + return 0; + + /* Allocate a bounce buffer if this isn't a guest owned page. */ + if (!desc->guest_owned) { + struct page *page; + + page = alloc_pages(GFP_KERNEL_ACCOUNT, get_order(desc->len)); + if (!page) { + pr_warn("Failed to allocate bounce buffer for SEV legacy command.\n"); + return -ENOMEM; + } + + desc->paddr_orig = *desc->paddr_ptr; + *desc->paddr_ptr = __psp_pa(page_to_virt(page)); + } + + npages = PAGE_ALIGN(desc->len) >> PAGE_SHIFT; + + /* Transition the buffer to firmware-owned. */ + if (rmp_mark_pages_firmware(*desc->paddr_ptr, npages, true)) { + pr_warn("Error moving pages to firmware-owned state for SEV legacy command.\n"); + return -EFAULT; + } + + return 0; +} + +static int snp_unmap_cmd_buf_desc(struct cmd_buf_desc *desc) +{ + unsigned int npages; + + if (!desc->len) + return 0; + + npages = PAGE_ALIGN(desc->len) >> PAGE_SHIFT; + + /* Transition the buffers back to hypervisor-owned. */ + if (snp_reclaim_pages(*desc->paddr_ptr, npages, true)) { + pr_warn("Failed to reclaim firmware-owned pages while issuing SEV legacy command.\n"); + return -EFAULT; + } + + /* Copy data from bounce buffer and then free it. */ + if (!desc->guest_owned) { + void *bounce_buf = __va(__sme_clr(*desc->paddr_ptr)); + void *dst_buf = __va(__sme_clr(desc->paddr_orig)); + + memcpy(dst_buf, bounce_buf, desc->len); + __free_pages(virt_to_page(bounce_buf), get_order(desc->len)); + + /* Restore the original address in the command buffer. */ + *desc->paddr_ptr = desc->paddr_orig; + } + + return 0; +} + +static int snp_map_cmd_buf_desc_list(int cmd, void *cmd_buf, struct cmd_buf_desc *desc_list) +{ + int i; + + snp_populate_cmd_buf_desc_list(cmd, cmd_buf, desc_list); + + for (i = 0; i < CMD_BUF_DESC_MAX; i++) { + struct cmd_buf_desc *desc = &desc_list[i]; + + if (!desc->paddr_ptr) + break; + + if (snp_map_cmd_buf_desc(desc)) + goto err_unmap; + } + + return 0; + +err_unmap: + for (i--; i >= 0; i--) + snp_unmap_cmd_buf_desc(&desc_list[i]); + + return -EFAULT; +} + +static int snp_unmap_cmd_buf_desc_list(struct cmd_buf_desc *desc_list) +{ + int i, ret = 0; + + for (i = 0; i < CMD_BUF_DESC_MAX; i++) { + struct cmd_buf_desc *desc = &desc_list[i]; + + if (!desc->paddr_ptr) + break; + + if (snp_unmap_cmd_buf_desc(&desc_list[i])) + ret = -EFAULT; + } + + return ret; +} + +static bool sev_cmd_buf_writable(int cmd) +{ + switch (cmd) { + case SEV_CMD_PLATFORM_STATUS: + case SEV_CMD_GUEST_STATUS: + case SEV_CMD_LAUNCH_START: + case SEV_CMD_RECEIVE_START: + case SEV_CMD_LAUNCH_MEASURE: + case SEV_CMD_SEND_START: + case SEV_CMD_SEND_UPDATE_DATA: + case SEV_CMD_SEND_UPDATE_VMSA: + case SEV_CMD_PEK_CSR: + case SEV_CMD_PDH_CERT_EXPORT: + case SEV_CMD_GET_ID: + case SEV_CMD_ATTESTATION_REPORT: + return true; + default: + return false; + } +} + +/* After SNP is INIT'ed, the behavior of legacy SEV commands is changed. */ +static bool snp_legacy_handling_needed(int cmd) +{ + struct sev_device *sev = psp_master->sev_data; + + return cmd < SEV_CMD_SNP_INIT && sev->snp_initialized; +} + +static int snp_prep_cmd_buf(int cmd, void *cmd_buf, struct cmd_buf_desc *desc_list) +{ + if (!snp_legacy_handling_needed(cmd)) + return 0; + + if (snp_map_cmd_buf_desc_list(cmd, cmd_buf, desc_list)) + return -EFAULT; + + /* + * Before command execution, the command buffer needs to be put into + * the firmware-owned state. + */ + if (sev_cmd_buf_writable(cmd)) { + if (rmp_mark_pages_firmware(__pa(cmd_buf), 1, true)) + return -EFAULT; + } + + return 0; +} + +static int snp_reclaim_cmd_buf(int cmd, void *cmd_buf) +{ + if (!snp_legacy_handling_needed(cmd)) + return 0; + + /* + * After command completion, the command buffer needs to be put back + * into the hypervisor-owned state. + */ + if (sev_cmd_buf_writable(cmd)) + if (snp_reclaim_pages(__pa(cmd_buf), 1, true)) + return -EFAULT; + + return 0; +} + static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret) { + struct cmd_buf_desc desc_list[CMD_BUF_DESC_MAX] = {0}; struct psp_device *psp = psp_master; struct sev_device *sev; unsigned int cmdbuff_hi, cmdbuff_lo; unsigned int phys_lsb, phys_msb; unsigned int reg, ret = 0; + void *cmd_buf; int buf_len; if (!psp || !psp->sev_data) @@ -331,12 +857,47 @@ static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret) * work for some memory, e.g. vmalloc'd addresses, and @data may not be * physically contiguous. */ - if (data) - memcpy(sev->cmd_buf, data, buf_len); + if (data) { + /* + * Commands are generally issued one at a time and require the + * sev_cmd_mutex, but there could be recursive firmware requests + * due to SEV_CMD_SNP_PAGE_RECLAIM needing to be issued while + * preparing buffers for another command. This is the only known + * case of nesting in the current code, so exactly one + * additional command buffer is available for that purpose. + */ + if (!sev->cmd_buf_active) { + cmd_buf = sev->cmd_buf; + sev->cmd_buf_active = true; + } else if (!sev->cmd_buf_backup_active) { + cmd_buf = sev->cmd_buf_backup; + sev->cmd_buf_backup_active = true; + } else { + dev_err(sev->dev, + "SEV: too many firmware commands in progress, no command buffers available.\n"); + return -EBUSY; + } + + memcpy(cmd_buf, data, buf_len); + + /* + * The behavior of the SEV-legacy commands is altered when the + * SNP firmware is in the INIT state. + */ + ret = snp_prep_cmd_buf(cmd, cmd_buf, desc_list); + if (ret) { + dev_err(sev->dev, + "SEV: failed to prepare buffer for legacy command 0x%x. Error: %d\n", + cmd, ret); + return ret; + } + } else { + cmd_buf = sev->cmd_buf; + } /* Get the physical address of the command buffer */ - phys_lsb = data ? lower_32_bits(__psp_pa(sev->cmd_buf)) : 0; - phys_msb = data ? upper_32_bits(__psp_pa(sev->cmd_buf)) : 0; + phys_lsb = data ? lower_32_bits(__psp_pa(cmd_buf)) : 0; + phys_msb = data ? upper_32_bits(__psp_pa(cmd_buf)) : 0; dev_dbg(sev->dev, "sev command id %#x buffer 0x%08x%08x timeout %us\n", cmd, phys_msb, phys_lsb, psp_timeout); @@ -390,20 +951,41 @@ static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret) ret = sev_write_init_ex_file_if_required(cmd); } - print_hex_dump_debug("(out): ", DUMP_PREFIX_OFFSET, 16, 2, data, - buf_len, false); - /* * Copy potential output from the PSP back to data. Do this even on * failure in case the caller wants to glean something from the error. */ - if (data) - memcpy(data, sev->cmd_buf, buf_len); + if (data) { + int ret_reclaim; + /* + * Restore the page state after the command completes. + */ + ret_reclaim = snp_reclaim_cmd_buf(cmd, cmd_buf); + if (ret_reclaim) { + dev_err(sev->dev, + "SEV: failed to reclaim buffer for legacy command %#x. Error: %d\n", + cmd, ret_reclaim); + return ret_reclaim; + } + + memcpy(data, cmd_buf, buf_len); + + if (sev->cmd_buf_backup_active) + sev->cmd_buf_backup_active = false; + else + sev->cmd_buf_active = false; + + if (snp_unmap_cmd_buf_desc_list(desc_list)) + return -EFAULT; + } + + print_hex_dump_debug("(out): ", DUMP_PREFIX_OFFSET, 16, 2, data, + buf_len, false); return ret; } -static int sev_do_cmd(int cmd, void *data, int *psp_ret) +int sev_do_cmd(int cmd, void *data, int *psp_ret) { int rc; @@ -413,6 +995,7 @@ static int sev_do_cmd(int cmd, void *data, int *psp_ret) return rc; } +EXPORT_SYMBOL_GPL(sev_do_cmd); static int __sev_init_locked(int *error) { @@ -427,7 +1010,7 @@ static int __sev_init_locked(int *error) data.tmr_address = __pa(sev_es_tmr); data.flags |= SEV_INIT_FLAGS_SEV_ES; - data.tmr_len = SEV_ES_TMR_SIZE; + data.tmr_len = sev_es_tmr_size; } return __sev_do_cmd_locked(SEV_CMD_INIT, &data, error); @@ -450,7 +1033,7 @@ static int __sev_init_ex_locked(int *error) data.tmr_address = __pa(sev_es_tmr); data.flags |= SEV_INIT_FLAGS_SEV_ES; - data.tmr_len = SEV_ES_TMR_SIZE; + data.tmr_len = sev_es_tmr_size; } return __sev_do_cmd_locked(SEV_CMD_INIT_EX, &data, error); @@ -464,26 +1047,218 @@ static inline int __sev_do_init_locked(int *psp_ret) return __sev_init_locked(psp_ret); } -static int __sev_platform_init_locked(int *error) +static void snp_set_hsave_pa(void *arg) +{ + wrmsrl(MSR_VM_HSAVE_PA, 0); +} + +static int snp_filter_reserved_mem_regions(struct resource *rs, void *arg) +{ + struct sev_data_range_list *range_list = arg; + struct sev_data_range *range = &range_list->ranges[range_list->num_elements]; + size_t size; + + /* + * Ensure the list of HV_FIXED pages that will be passed to firmware + * do not exceed the page-sized argument buffer. + */ + if ((range_list->num_elements * sizeof(struct sev_data_range) + + sizeof(struct sev_data_range_list)) > PAGE_SIZE) + return -E2BIG; + + switch (rs->desc) { + case E820_TYPE_RESERVED: + case E820_TYPE_PMEM: + case E820_TYPE_ACPI: + range->base = rs->start & PAGE_MASK; + size = PAGE_ALIGN((rs->end + 1) - rs->start); + range->page_count = size >> PAGE_SHIFT; + range_list->num_elements++; + break; + default: + break; + } + + return 0; +} + +static int __sev_snp_init_locked(int *error) { - int rc = 0, psp_ret = SEV_RET_NO_FW_CALL; struct psp_device *psp = psp_master; + struct sev_data_snp_init_ex data; struct sev_device *sev; + void *arg = &data; + int cmd, rc = 0; - if (!psp || !psp->sev_data) + if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP)) return -ENODEV; sev = psp->sev_data; - if (sev->state == SEV_STATE_INIT) + if (sev->snp_initialized) return 0; - if (sev_init_ex_buffer) { - rc = sev_read_init_ex_file(); - if (rc) + if (!sev_version_greater_or_equal(SNP_MIN_API_MAJOR, SNP_MIN_API_MINOR)) { + dev_dbg(sev->dev, "SEV-SNP support requires firmware version >= %d:%d\n", + SNP_MIN_API_MAJOR, SNP_MIN_API_MINOR); + return 0; + } + + /* SNP_INIT requires MSR_VM_HSAVE_PA to be cleared on all CPUs. */ + on_each_cpu(snp_set_hsave_pa, NULL, 1); + + /* + * Starting in SNP firmware v1.52, the SNP_INIT_EX command takes a list + * of system physical address ranges to convert into HV-fixed page + * states during the RMP initialization. For instance, the memory that + * UEFI reserves should be included in the that list. This allows system + * components that occasionally write to memory (e.g. logging to UEFI + * reserved regions) to not fail due to RMP initialization and SNP + * enablement. + * + */ + if (sev_version_greater_or_equal(SNP_MIN_API_MAJOR, 52)) { + /* + * Firmware checks that the pages containing the ranges enumerated + * in the RANGES structure are either in the default page state or in the + * firmware page state. + */ + snp_range_list = kzalloc(PAGE_SIZE, GFP_KERNEL); + if (!snp_range_list) { + dev_err(sev->dev, + "SEV: SNP_INIT_EX range list memory allocation failed\n"); + return -ENOMEM; + } + + /* + * Retrieve all reserved memory regions from the e820 memory map + * to be setup as HV-fixed pages. + */ + rc = walk_iomem_res_desc(IORES_DESC_NONE, IORESOURCE_MEM, 0, ~0, + snp_range_list, snp_filter_reserved_mem_regions); + if (rc) { + dev_err(sev->dev, + "SEV: SNP_INIT_EX walk_iomem_res_desc failed rc = %d\n", rc); return rc; + } + + memset(&data, 0, sizeof(data)); + data.init_rmp = 1; + data.list_paddr_en = 1; + data.list_paddr = __psp_pa(snp_range_list); + cmd = SEV_CMD_SNP_INIT_EX; + } else { + cmd = SEV_CMD_SNP_INIT; + arg = NULL; + } + + /* + * The following sequence must be issued before launching the first SNP + * guest to ensure all dirty cache lines are flushed, including from + * updates to the RMP table itself via the RMPUPDATE instruction: + * + * - WBINVD on all running CPUs + * - SEV_CMD_SNP_INIT[_EX] firmware command + * - WBINVD on all running CPUs + * - SEV_CMD_SNP_DF_FLUSH firmware command + */ + wbinvd_on_all_cpus(); + + rc = __sev_do_cmd_locked(cmd, arg, error); + if (rc) + return rc; + + /* Prepare for first SNP guest launch after INIT. */ + wbinvd_on_all_cpus(); + rc = __sev_do_cmd_locked(SEV_CMD_SNP_DF_FLUSH, NULL, error); + if (rc) + return rc; + + sev->snp_initialized = true; + dev_dbg(sev->dev, "SEV-SNP firmware initialized\n"); + + sev_es_tmr_size = SNP_TMR_SIZE; + + return rc; +} + +static void __sev_platform_init_handle_tmr(struct sev_device *sev) +{ + if (sev_es_tmr) + return; + + /* Obtain the TMR memory area for SEV-ES use */ + sev_es_tmr = sev_fw_alloc(sev_es_tmr_size); + if (sev_es_tmr) { + /* Must flush the cache before giving it to the firmware */ + if (!sev->snp_initialized) + clflush_cache_range(sev_es_tmr, sev_es_tmr_size); + } else { + dev_warn(sev->dev, "SEV: TMR allocation failed, SEV-ES support unavailable\n"); + } +} + +/* + * If an init_ex_path is provided allocate a buffer for the file and + * read in the contents. Additionally, if SNP is initialized, convert + * the buffer pages to firmware pages. + */ +static int __sev_platform_init_handle_init_ex_path(struct sev_device *sev) +{ + struct page *page; + int rc; + + if (!init_ex_path) + return 0; + + if (sev_init_ex_buffer) + return 0; + + page = alloc_pages(GFP_KERNEL, get_order(NV_LENGTH)); + if (!page) { + dev_err(sev->dev, "SEV: INIT_EX NV memory allocation failed\n"); + return -ENOMEM; + } + + sev_init_ex_buffer = page_address(page); + + rc = sev_read_init_ex_file(); + if (rc) + return rc; + + /* If SEV-SNP is initialized, transition to firmware page. */ + if (sev->snp_initialized) { + unsigned long npages; + + npages = 1UL << get_order(NV_LENGTH); + if (rmp_mark_pages_firmware(__pa(sev_init_ex_buffer), npages, false)) { + dev_err(sev->dev, "SEV: INIT_EX NV memory page state change failed.\n"); + return -ENOMEM; + } } + return 0; +} + +static int __sev_platform_init_locked(int *error) +{ + int rc, psp_ret = SEV_RET_NO_FW_CALL; + struct sev_device *sev; + + if (!psp_master || !psp_master->sev_data) + return -ENODEV; + + sev = psp_master->sev_data; + + if (sev->state == SEV_STATE_INIT) + return 0; + + __sev_platform_init_handle_tmr(sev); + + rc = __sev_platform_init_handle_init_ex_path(sev); + if (rc) + return rc; + rc = __sev_do_init_locked(&psp_ret); if (rc && psp_ret == SEV_RET_SECURE_DATA_INVALID) { /* @@ -520,12 +1295,46 @@ static int __sev_platform_init_locked(int *error) return 0; } -int sev_platform_init(int *error) +static int _sev_platform_init_locked(struct sev_platform_init_args *args) +{ + struct sev_device *sev; + int rc; + + if (!psp_master || !psp_master->sev_data) + return -ENODEV; + + sev = psp_master->sev_data; + + if (sev->state == SEV_STATE_INIT) + return 0; + + /* + * Legacy guests cannot be running while SNP_INIT(_EX) is executing, + * so perform SEV-SNP initialization at probe time. + */ + rc = __sev_snp_init_locked(&args->error); + if (rc && rc != -ENODEV) { + /* + * Don't abort the probe if SNP INIT failed, + * continue to initialize the legacy SEV firmware. + */ + dev_err(sev->dev, "SEV-SNP: failed to INIT rc %d, error %#x\n", + rc, args->error); + } + + /* Defer legacy SEV/SEV-ES support if allowed by caller/module. */ + if (args->probe && !psp_init_on_probe) + return 0; + + return __sev_platform_init_locked(&args->error); +} + +int sev_platform_init(struct sev_platform_init_args *args) { int rc; mutex_lock(&sev_cmd_mutex); - rc = __sev_platform_init_locked(error); + rc = _sev_platform_init_locked(args); mutex_unlock(&sev_cmd_mutex); return rc; @@ -556,17 +1365,6 @@ static int __sev_platform_shutdown_locked(int *error) return ret; } -static int sev_platform_shutdown(int *error) -{ - int rc; - - mutex_lock(&sev_cmd_mutex); - rc = __sev_platform_shutdown_locked(NULL); - mutex_unlock(&sev_cmd_mutex); - - return rc; -} - static int sev_get_platform_state(int *state, int *error) { struct sev_user_data_status data; @@ -842,6 +1640,72 @@ fw_err: return ret; } +static int __sev_snp_shutdown_locked(int *error, bool panic) +{ + struct sev_device *sev = psp_master->sev_data; + struct sev_data_snp_shutdown_ex data; + int ret; + + if (!sev->snp_initialized) + return 0; + + memset(&data, 0, sizeof(data)); + data.len = sizeof(data); + data.iommu_snp_shutdown = 1; + + /* + * If invoked during panic handling, local interrupts are disabled + * and all CPUs are stopped, so wbinvd_on_all_cpus() can't be called. + * In that case, a wbinvd() is done on remote CPUs via the NMI + * callback, so only a local wbinvd() is needed here. + */ + if (!panic) + wbinvd_on_all_cpus(); + else + wbinvd(); + + ret = __sev_do_cmd_locked(SEV_CMD_SNP_SHUTDOWN_EX, &data, error); + /* SHUTDOWN may require DF_FLUSH */ + if (*error == SEV_RET_DFFLUSH_REQUIRED) { + ret = __sev_do_cmd_locked(SEV_CMD_SNP_DF_FLUSH, NULL, NULL); + if (ret) { + dev_err(sev->dev, "SEV-SNP DF_FLUSH failed\n"); + return ret; + } + /* reissue the shutdown command */ + ret = __sev_do_cmd_locked(SEV_CMD_SNP_SHUTDOWN_EX, &data, + error); + } + if (ret) { + dev_err(sev->dev, "SEV-SNP firmware shutdown failed\n"); + return ret; + } + + /* + * SNP_SHUTDOWN_EX with IOMMU_SNP_SHUTDOWN set to 1 disables SNP + * enforcement by the IOMMU and also transitions all pages + * associated with the IOMMU to the Reclaim state. + * Firmware was transitioning the IOMMU pages to Hypervisor state + * before version 1.53. But, accounting for the number of assigned + * 4kB pages in a 2M page was done incorrectly by not transitioning + * to the Reclaim state. This resulted in RMP #PF when later accessing + * the 2M page containing those pages during kexec boot. Hence, the + * firmware now transitions these pages to Reclaim state and hypervisor + * needs to transition these pages to shared state. SNP Firmware + * version 1.53 and above are needed for kexec boot. + */ + ret = amd_iommu_snp_disable(); + if (ret) { + dev_err(sev->dev, "SNP IOMMU shutdown failed\n"); + return ret; + } + + sev->snp_initialized = false; + dev_dbg(sev->dev, "SEV-SNP firmware shutdown\n"); + + return ret; +} + static int sev_ioctl_do_pek_import(struct sev_issue_cmd *argp, bool writable) { struct sev_device *sev = psp_master->sev_data; @@ -1084,6 +1948,85 @@ e_free_pdh: return ret; } +static int sev_ioctl_do_snp_platform_status(struct sev_issue_cmd *argp) +{ + struct sev_device *sev = psp_master->sev_data; + struct sev_data_snp_addr buf; + struct page *status_page; + void *data; + int ret; + + if (!sev->snp_initialized || !argp->data) + return -EINVAL; + + status_page = alloc_page(GFP_KERNEL_ACCOUNT); + if (!status_page) + return -ENOMEM; + + data = page_address(status_page); + + /* + * Firmware expects status page to be in firmware-owned state, otherwise + * it will report firmware error code INVALID_PAGE_STATE (0x1A). + */ + if (rmp_mark_pages_firmware(__pa(data), 1, true)) { + ret = -EFAULT; + goto cleanup; + } + + buf.address = __psp_pa(data); + ret = __sev_do_cmd_locked(SEV_CMD_SNP_PLATFORM_STATUS, &buf, &argp->error); + + /* + * Status page will be transitioned to Reclaim state upon success, or + * left in Firmware state in failure. Use snp_reclaim_pages() to + * transition either case back to Hypervisor-owned state. + */ + if (snp_reclaim_pages(__pa(data), 1, true)) + return -EFAULT; + + if (ret) + goto cleanup; + + if (copy_to_user((void __user *)argp->data, data, + sizeof(struct sev_user_data_snp_status))) + ret = -EFAULT; + +cleanup: + __free_pages(status_page, 0); + return ret; +} + +static int sev_ioctl_do_snp_commit(struct sev_issue_cmd *argp) +{ + struct sev_device *sev = psp_master->sev_data; + struct sev_data_snp_commit buf; + + if (!sev->snp_initialized) + return -EINVAL; + + buf.len = sizeof(buf); + + return __sev_do_cmd_locked(SEV_CMD_SNP_COMMIT, &buf, &argp->error); +} + +static int sev_ioctl_do_snp_set_config(struct sev_issue_cmd *argp, bool writable) +{ + struct sev_device *sev = psp_master->sev_data; + struct sev_user_data_snp_config config; + + if (!sev->snp_initialized || !argp->data) + return -EINVAL; + + if (!writable) + return -EPERM; + + if (copy_from_user(&config, (void __user *)argp->data, sizeof(config))) + return -EFAULT; + + return __sev_do_cmd_locked(SEV_CMD_SNP_CONFIG, &config, &argp->error); +} + static long sev_ioctl(struct file *file, unsigned int ioctl, unsigned long arg) { void __user *argp = (void __user *)arg; @@ -1135,6 +2078,15 @@ static long sev_ioctl(struct file *file, unsigned int ioctl, unsigned long arg) case SEV_GET_ID2: ret = sev_ioctl_do_get_id2(&input); break; + case SNP_PLATFORM_STATUS: + ret = sev_ioctl_do_snp_platform_status(&input); + break; + case SNP_COMMIT: + ret = sev_ioctl_do_snp_commit(&input); + break; + case SNP_SET_CONFIG: + ret = sev_ioctl_do_snp_set_config(&input, writable); + break; default: ret = -EINVAL; goto out; @@ -1245,10 +2197,12 @@ int sev_dev_init(struct psp_device *psp) if (!sev) goto e_err; - sev->cmd_buf = (void *)devm_get_free_pages(dev, GFP_KERNEL, 0); + sev->cmd_buf = (void *)devm_get_free_pages(dev, GFP_KERNEL, 1); if (!sev->cmd_buf) goto e_sev; + sev->cmd_buf_backup = (uint8_t *)sev->cmd_buf + PAGE_SIZE; + psp->sev_data = sev; sev->dev = dev; @@ -1287,24 +2241,51 @@ e_err: return ret; } -static void sev_firmware_shutdown(struct sev_device *sev) +static void __sev_firmware_shutdown(struct sev_device *sev, bool panic) { - sev_platform_shutdown(NULL); + int error; + + __sev_platform_shutdown_locked(NULL); if (sev_es_tmr) { - /* The TMR area was encrypted, flush it from the cache */ - wbinvd_on_all_cpus(); + /* + * The TMR area was encrypted, flush it from the cache. + * + * If invoked during panic handling, local interrupts are + * disabled and all CPUs are stopped, so wbinvd_on_all_cpus() + * can't be used. In that case, wbinvd() is done on remote CPUs + * via the NMI callback, and done for this CPU later during + * SNP shutdown, so wbinvd_on_all_cpus() can be skipped. + */ + if (!panic) + wbinvd_on_all_cpus(); - free_pages((unsigned long)sev_es_tmr, - get_order(SEV_ES_TMR_SIZE)); + __snp_free_firmware_pages(virt_to_page(sev_es_tmr), + get_order(sev_es_tmr_size), + true); sev_es_tmr = NULL; } if (sev_init_ex_buffer) { - free_pages((unsigned long)sev_init_ex_buffer, - get_order(NV_LENGTH)); + __snp_free_firmware_pages(virt_to_page(sev_init_ex_buffer), + get_order(NV_LENGTH), + true); sev_init_ex_buffer = NULL; } + + if (snp_range_list) { + kfree(snp_range_list); + snp_range_list = NULL; + } + + __sev_snp_shutdown_locked(&error, panic); +} + +static void sev_firmware_shutdown(struct sev_device *sev) +{ + mutex_lock(&sev_cmd_mutex); + __sev_firmware_shutdown(sev, false); + mutex_unlock(&sev_cmd_mutex); } void sev_dev_destroy(struct psp_device *psp) @@ -1322,6 +2303,29 @@ void sev_dev_destroy(struct psp_device *psp) psp_clear_sev_irq_handler(psp); } +static int snp_shutdown_on_panic(struct notifier_block *nb, + unsigned long reason, void *arg) +{ + struct sev_device *sev = psp_master->sev_data; + + /* + * If sev_cmd_mutex is already acquired, then it's likely + * another PSP command is in flight and issuing a shutdown + * would fail in unexpected ways. Rather than create even + * more confusion during a panic, just bail out here. + */ + if (mutex_is_locked(&sev_cmd_mutex)) + return NOTIFY_DONE; + + __sev_firmware_shutdown(sev, true); + + return NOTIFY_DONE; +} + +static struct notifier_block snp_panic_notifier = { + .notifier_call = snp_shutdown_on_panic, +}; + int sev_issue_cmd_external_user(struct file *filep, unsigned int cmd, void *data, int *error) { @@ -1335,7 +2339,8 @@ EXPORT_SYMBOL_GPL(sev_issue_cmd_external_user); void sev_pci_init(void) { struct sev_device *sev = psp_master->sev_data; - int error, rc; + struct sev_platform_init_args args = {0}; + int rc; if (!sev) return; @@ -1348,36 +2353,18 @@ void sev_pci_init(void) if (sev_update_firmware(sev->dev) == 0) sev_get_api_version(); - /* If an init_ex_path is provided rely on INIT_EX for PSP initialization - * instead of INIT. - */ - if (init_ex_path) { - sev_init_ex_buffer = sev_fw_alloc(NV_LENGTH); - if (!sev_init_ex_buffer) { - dev_err(sev->dev, - "SEV: INIT_EX NV memory allocation failed\n"); - goto err; - } - } - - /* Obtain the TMR memory area for SEV-ES use */ - sev_es_tmr = sev_fw_alloc(SEV_ES_TMR_SIZE); - if (sev_es_tmr) - /* Must flush the cache before giving it to the firmware */ - clflush_cache_range(sev_es_tmr, SEV_ES_TMR_SIZE); - else - dev_warn(sev->dev, - "SEV: TMR allocation failed, SEV-ES support unavailable\n"); - - if (!psp_init_on_probe) - return; - /* Initialize the platform */ - rc = sev_platform_init(&error); + args.probe = true; + rc = sev_platform_init(&args); if (rc) dev_err(sev->dev, "SEV: failed to INIT error %#x, rc %d\n", - error, rc); + args.error, rc); + dev_info(sev->dev, "SEV%s API:%d.%d build:%d\n", sev->snp_initialized ? + "-SNP" : "", sev->api_major, sev->api_minor, sev->build); + + atomic_notifier_chain_register(&panic_notifier_list, + &snp_panic_notifier); return; err: @@ -1392,4 +2379,7 @@ void sev_pci_exit(void) return; sev_firmware_shutdown(sev); + + atomic_notifier_chain_unregister(&panic_notifier_list, + &snp_panic_notifier); } diff --git a/drivers/crypto/ccp/sev-dev.h b/drivers/crypto/ccp/sev-dev.h index 778c95155e74..3e4e5574e88a 100644 --- a/drivers/crypto/ccp/sev-dev.h +++ b/drivers/crypto/ccp/sev-dev.h @@ -52,6 +52,11 @@ struct sev_device { u8 build; void *cmd_buf; + void *cmd_buf_backup; + bool cmd_buf_active; + bool cmd_buf_backup_active; + + bool snp_initialized; }; int sev_dev_init(struct psp_device *psp); diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig index 5a7f3fabee22..16c8de5050e5 100644 --- a/drivers/edac/Kconfig +++ b/drivers/edac/Kconfig @@ -78,6 +78,7 @@ config EDAC_GHES config EDAC_AMD64 tristate "AMD64 (Opteron, Athlon64)" depends on AMD_NB && EDAC_DECODE_MCE + imply AMD_ATL help Support for error detection and correction of DRAM ECC errors on the AMD64 families (>= K8) of memory controllers. diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index 2b8c20bb926a..1f3520d76861 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only +#include <linux/ras.h> #include "amd64_edac.h" #include <asm/amd_nb.h> @@ -1051,281 +1052,6 @@ static int fixup_node_id(int node_id, struct mce *m) return nid - gpu_node_map.base_node_id + 1; } -/* Protect the PCI config register pairs used for DF indirect access. */ -static DEFINE_MUTEX(df_indirect_mutex); - -/* - * Data Fabric Indirect Access uses FICAA/FICAD. - * - * Fabric Indirect Configuration Access Address (FICAA): Constructed based - * on the device's Instance Id and the PCI function and register offset of - * the desired register. - * - * Fabric Indirect Configuration Access Data (FICAD): There are FICAD LO - * and FICAD HI registers but so far we only need the LO register. - * - * Use Instance Id 0xFF to indicate a broadcast read. - */ -#define DF_BROADCAST 0xFF -static int __df_indirect_read(u16 node, u8 func, u16 reg, u8 instance_id, u32 *lo) -{ - struct pci_dev *F4; - u32 ficaa; - int err = -ENODEV; - - if (node >= amd_nb_num()) - goto out; - - F4 = node_to_amd_nb(node)->link; - if (!F4) - goto out; - - ficaa = (instance_id == DF_BROADCAST) ? 0 : 1; - ficaa |= reg & 0x3FC; - ficaa |= (func & 0x7) << 11; - ficaa |= instance_id << 16; - - mutex_lock(&df_indirect_mutex); - - err = pci_write_config_dword(F4, 0x5C, ficaa); - if (err) { - pr_warn("Error writing DF Indirect FICAA, FICAA=0x%x\n", ficaa); - goto out_unlock; - } - - err = pci_read_config_dword(F4, 0x98, lo); - if (err) - pr_warn("Error reading DF Indirect FICAD LO, FICAA=0x%x.\n", ficaa); - -out_unlock: - mutex_unlock(&df_indirect_mutex); - -out: - return err; -} - -static int df_indirect_read_instance(u16 node, u8 func, u16 reg, u8 instance_id, u32 *lo) -{ - return __df_indirect_read(node, func, reg, instance_id, lo); -} - -static int df_indirect_read_broadcast(u16 node, u8 func, u16 reg, u32 *lo) -{ - return __df_indirect_read(node, func, reg, DF_BROADCAST, lo); -} - -struct addr_ctx { - u64 ret_addr; - u32 tmp; - u16 nid; - u8 inst_id; -}; - -static int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr) -{ - u64 dram_base_addr, dram_limit_addr, dram_hole_base; - - u8 die_id_shift, die_id_mask, socket_id_shift, socket_id_mask; - u8 intlv_num_dies, intlv_num_chan, intlv_num_sockets; - u8 intlv_addr_sel, intlv_addr_bit; - u8 num_intlv_bits, hashed_bit; - u8 lgcy_mmio_hole_en, base = 0; - u8 cs_mask, cs_id = 0; - bool hash_enabled = false; - - struct addr_ctx ctx; - - memset(&ctx, 0, sizeof(ctx)); - - /* Start from the normalized address */ - ctx.ret_addr = norm_addr; - - ctx.nid = nid; - ctx.inst_id = umc; - - /* Read D18F0x1B4 (DramOffset), check if base 1 is used. */ - if (df_indirect_read_instance(nid, 0, 0x1B4, umc, &ctx.tmp)) - goto out_err; - - /* Remove HiAddrOffset from normalized address, if enabled: */ - if (ctx.tmp & BIT(0)) { - u64 hi_addr_offset = (ctx.tmp & GENMASK_ULL(31, 20)) << 8; - - if (norm_addr >= hi_addr_offset) { - ctx.ret_addr -= hi_addr_offset; - base = 1; - } - } - - /* Read D18F0x110 (DramBaseAddress). */ - if (df_indirect_read_instance(nid, 0, 0x110 + (8 * base), umc, &ctx.tmp)) - goto out_err; - - /* Check if address range is valid. */ - if (!(ctx.tmp & BIT(0))) { - pr_err("%s: Invalid DramBaseAddress range: 0x%x.\n", - __func__, ctx.tmp); - goto out_err; - } - - lgcy_mmio_hole_en = ctx.tmp & BIT(1); - intlv_num_chan = (ctx.tmp >> 4) & 0xF; - intlv_addr_sel = (ctx.tmp >> 8) & 0x7; - dram_base_addr = (ctx.tmp & GENMASK_ULL(31, 12)) << 16; - - /* {0, 1, 2, 3} map to address bits {8, 9, 10, 11} respectively */ - if (intlv_addr_sel > 3) { - pr_err("%s: Invalid interleave address select %d.\n", - __func__, intlv_addr_sel); - goto out_err; - } - - /* Read D18F0x114 (DramLimitAddress). */ - if (df_indirect_read_instance(nid, 0, 0x114 + (8 * base), umc, &ctx.tmp)) - goto out_err; - - intlv_num_sockets = (ctx.tmp >> 8) & 0x1; - intlv_num_dies = (ctx.tmp >> 10) & 0x3; - dram_limit_addr = ((ctx.tmp & GENMASK_ULL(31, 12)) << 16) | GENMASK_ULL(27, 0); - - intlv_addr_bit = intlv_addr_sel + 8; - - /* Re-use intlv_num_chan by setting it equal to log2(#channels) */ - switch (intlv_num_chan) { - case 0: intlv_num_chan = 0; break; - case 1: intlv_num_chan = 1; break; - case 3: intlv_num_chan = 2; break; - case 5: intlv_num_chan = 3; break; - case 7: intlv_num_chan = 4; break; - - case 8: intlv_num_chan = 1; - hash_enabled = true; - break; - default: - pr_err("%s: Invalid number of interleaved channels %d.\n", - __func__, intlv_num_chan); - goto out_err; - } - - num_intlv_bits = intlv_num_chan; - - if (intlv_num_dies > 2) { - pr_err("%s: Invalid number of interleaved nodes/dies %d.\n", - __func__, intlv_num_dies); - goto out_err; - } - - num_intlv_bits += intlv_num_dies; - - /* Add a bit if sockets are interleaved. */ - num_intlv_bits += intlv_num_sockets; - - /* Assert num_intlv_bits <= 4 */ - if (num_intlv_bits > 4) { - pr_err("%s: Invalid interleave bits %d.\n", - __func__, num_intlv_bits); - goto out_err; - } - - if (num_intlv_bits > 0) { - u64 temp_addr_x, temp_addr_i, temp_addr_y; - u8 die_id_bit, sock_id_bit, cs_fabric_id; - - /* - * Read FabricBlockInstanceInformation3_CS[BlockFabricID]. - * This is the fabric id for this coherent slave. Use - * umc/channel# as instance id of the coherent slave - * for FICAA. - */ - if (df_indirect_read_instance(nid, 0, 0x50, umc, &ctx.tmp)) - goto out_err; - - cs_fabric_id = (ctx.tmp >> 8) & 0xFF; - die_id_bit = 0; - - /* If interleaved over more than 1 channel: */ - if (intlv_num_chan) { - die_id_bit = intlv_num_chan; - cs_mask = (1 << die_id_bit) - 1; - cs_id = cs_fabric_id & cs_mask; - } - - sock_id_bit = die_id_bit; - - /* Read D18F1x208 (SystemFabricIdMask). */ - if (intlv_num_dies || intlv_num_sockets) - if (df_indirect_read_broadcast(nid, 1, 0x208, &ctx.tmp)) - goto out_err; - - /* If interleaved over more than 1 die. */ - if (intlv_num_dies) { - sock_id_bit = die_id_bit + intlv_num_dies; - die_id_shift = (ctx.tmp >> 24) & 0xF; - die_id_mask = (ctx.tmp >> 8) & 0xFF; - - cs_id |= ((cs_fabric_id & die_id_mask) >> die_id_shift) << die_id_bit; - } - - /* If interleaved over more than 1 socket. */ - if (intlv_num_sockets) { - socket_id_shift = (ctx.tmp >> 28) & 0xF; - socket_id_mask = (ctx.tmp >> 16) & 0xFF; - - cs_id |= ((cs_fabric_id & socket_id_mask) >> socket_id_shift) << sock_id_bit; - } - - /* - * The pre-interleaved address consists of XXXXXXIIIYYYYY - * where III is the ID for this CS, and XXXXXXYYYYY are the - * address bits from the post-interleaved address. - * "num_intlv_bits" has been calculated to tell us how many "I" - * bits there are. "intlv_addr_bit" tells us how many "Y" bits - * there are (where "I" starts). - */ - temp_addr_y = ctx.ret_addr & GENMASK_ULL(intlv_addr_bit - 1, 0); - temp_addr_i = (cs_id << intlv_addr_bit); - temp_addr_x = (ctx.ret_addr & GENMASK_ULL(63, intlv_addr_bit)) << num_intlv_bits; - ctx.ret_addr = temp_addr_x | temp_addr_i | temp_addr_y; - } - - /* Add dram base address */ - ctx.ret_addr += dram_base_addr; - - /* If legacy MMIO hole enabled */ - if (lgcy_mmio_hole_en) { - if (df_indirect_read_broadcast(nid, 0, 0x104, &ctx.tmp)) - goto out_err; - - dram_hole_base = ctx.tmp & GENMASK(31, 24); - if (ctx.ret_addr >= dram_hole_base) - ctx.ret_addr += (BIT_ULL(32) - dram_hole_base); - } - - if (hash_enabled) { - /* Save some parentheses and grab ls-bit at the end. */ - hashed_bit = (ctx.ret_addr >> 12) ^ - (ctx.ret_addr >> 18) ^ - (ctx.ret_addr >> 21) ^ - (ctx.ret_addr >> 30) ^ - cs_id; - - hashed_bit &= BIT(0); - - if (hashed_bit != ((ctx.ret_addr >> intlv_addr_bit) & BIT(0))) - ctx.ret_addr ^= BIT(intlv_addr_bit); - } - - /* Is calculated system address is above DRAM limit address? */ - if (ctx.ret_addr > dram_limit_addr) - goto out_err; - - *sys_addr = ctx.ret_addr; - return 0; - -out_err: - return -EINVAL; -} - static int get_channel_from_ecc_syndrome(struct mem_ctl_info *, u16); /* @@ -3073,9 +2799,10 @@ static void decode_umc_error(int node_id, struct mce *m) { u8 ecc_type = (m->status >> 45) & 0x3; struct mem_ctl_info *mci; + unsigned long sys_addr; struct amd64_pvt *pvt; + struct atl_err a_err; struct err_info err; - u64 sys_addr; node_id = fixup_node_id(node_id, m); @@ -3106,7 +2833,12 @@ static void decode_umc_error(int node_id, struct mce *m) pvt->ops->get_err_info(m, &err); - if (umc_normaddr_to_sysaddr(m->addr, pvt->mc_node_id, err.channel, &sys_addr)) { + a_err.addr = m->addr; + a_err.ipid = m->ipid; + a_err.cpu = m->extcpu; + + sys_addr = amd_convert_umc_mca_addr_to_sys_addr(&a_err); + if (IS_ERR_VALUE(sys_addr)) { err.err_code = ERR_NORM_ADDR; goto log_error; } diff --git a/drivers/edac/i10nm_base.c b/drivers/edac/i10nm_base.c index 2b83d6de9352..3fd22a1eb1a9 100644 --- a/drivers/edac/i10nm_base.c +++ b/drivers/edac/i10nm_base.c @@ -951,6 +951,7 @@ static const struct x86_cpu_id i10nm_cpuids[] = { X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(EMERALDRAPIDS_X, X86_STEPPINGS(0x0, 0xf), &spr_cfg), X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(GRANITERAPIDS_X, X86_STEPPINGS(0x0, 0xf), &gnr_cfg), X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(ATOM_CRESTMONT_X, X86_STEPPINGS(0x0, 0xf), &gnr_cfg), + X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(ATOM_CRESTMONT, X86_STEPPINGS(0x0, 0xf), &gnr_cfg), {} }; MODULE_DEVICE_TABLE(x86cpu, i10nm_cpuids); diff --git a/drivers/edac/igen6_edac.c b/drivers/edac/igen6_edac.c index 2b0ecdeba5cd..cdd8480e7368 100644 --- a/drivers/edac/igen6_edac.c +++ b/drivers/edac/igen6_edac.c @@ -238,6 +238,7 @@ static struct work_struct ecclog_work; #define DID_ADL_N_SKU9 0x4678 #define DID_ADL_N_SKU10 0x4679 #define DID_ADL_N_SKU11 0x467c +#define DID_ADL_N_SKU12 0x4632 /* Compute die IDs for Raptor Lake-P with IBECC */ #define DID_RPL_P_SKU1 0xa706 @@ -583,6 +584,7 @@ static const struct pci_device_id igen6_pci_tbl[] = { { PCI_VDEVICE(INTEL, DID_ADL_N_SKU9), (kernel_ulong_t)&adl_n_cfg }, { PCI_VDEVICE(INTEL, DID_ADL_N_SKU10), (kernel_ulong_t)&adl_n_cfg }, { PCI_VDEVICE(INTEL, DID_ADL_N_SKU11), (kernel_ulong_t)&adl_n_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU12), (kernel_ulong_t)&adl_n_cfg }, { PCI_VDEVICE(INTEL, DID_RPL_P_SKU1), (kernel_ulong_t)&rpl_p_cfg }, { PCI_VDEVICE(INTEL, DID_RPL_P_SKU2), (kernel_ulong_t)&rpl_p_cfg }, { PCI_VDEVICE(INTEL, DID_RPL_P_SKU3), (kernel_ulong_t)&rpl_p_cfg }, diff --git a/drivers/edac/synopsys_edac.c b/drivers/edac/synopsys_edac.c index 709babce43ba..5527055b0964 100644 --- a/drivers/edac/synopsys_edac.c +++ b/drivers/edac/synopsys_edac.c @@ -1324,11 +1324,9 @@ static int mc_probe(struct platform_device *pdev) struct synps_edac_priv *priv; struct mem_ctl_info *mci; void __iomem *baseaddr; - struct resource *res; int rc; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - baseaddr = devm_ioremap_resource(&pdev->dev, res); + baseaddr = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(baseaddr)) return PTR_ERR(baseaddr); diff --git a/drivers/edac/versal_edac.c b/drivers/edac/versal_edac.c index 62caf454b567..1688a5050f63 100644 --- a/drivers/edac/versal_edac.c +++ b/drivers/edac/versal_edac.c @@ -42,8 +42,11 @@ #define ECCW0_FLIP_CTRL 0x109C #define ECCW0_FLIP0_OFFSET 0x10A0 +#define ECCW0_FLIP0_BITS 31 +#define ECCW0_FLIP1_OFFSET 0x10A4 #define ECCW1_FLIP_CTRL 0x10AC #define ECCW1_FLIP0_OFFSET 0x10B0 +#define ECCW1_FLIP1_OFFSET 0x10B4 #define ECCR0_CERR_STAT_OFFSET 0x10BC #define ECCR0_CE_ADDR_LO_OFFSET 0x10C0 #define ECCR0_CE_ADDR_HI_OFFSET 0x10C4 @@ -116,9 +119,6 @@ #define XDDR_BUS_WIDTH_32 1 #define XDDR_BUS_WIDTH_16 2 -#define ECC_CEPOISON_MASK 0x1 -#define ECC_UEPOISON_MASK 0x3 - #define XDDR_MAX_ROW_CNT 18 #define XDDR_MAX_COL_CNT 10 #define XDDR_MAX_RANK_CNT 2 @@ -133,6 +133,7 @@ * https://docs.xilinx.com/r/en-US/am012-versal-register-reference/PCSR_LOCK-XRAM_SLCR-Register */ #define PCSR_UNLOCK_VAL 0xF9E8D7C6 +#define PCSR_LOCK_VAL 1 #define XDDR_ERR_TYPE_CE 0 #define XDDR_ERR_TYPE_UE 1 @@ -142,6 +143,7 @@ #define XILINX_DRAM_SIZE_12G 3 #define XILINX_DRAM_SIZE_16G 4 #define XILINX_DRAM_SIZE_32G 5 +#define NUM_UE_BITPOS 2 /** * struct ecc_error_info - ECC error log information. @@ -479,7 +481,7 @@ static void err_callback(const u32 *payload, void *data) writel(regval, priv->ddrmc_baseaddr + XDDR_ISR_OFFSET); /* Lock the PCSR registers */ - writel(1, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET); + writel(PCSR_LOCK_VAL, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET); edac_dbg(3, "Total error count CE %d UE %d\n", priv->ce_cnt, priv->ue_cnt); } @@ -650,7 +652,7 @@ static void enable_intr(struct edac_priv *priv) writel(XDDR_IRQ_UE_MASK, priv->ddrmc_baseaddr + XDDR_IRQ1_EN_OFFSET); /* Lock the PCSR registers */ - writel(1, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET); + writel(PCSR_LOCK_VAL, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET); } static void disable_intr(struct edac_priv *priv) @@ -663,7 +665,7 @@ static void disable_intr(struct edac_priv *priv) priv->ddrmc_baseaddr + XDDR_IRQ_DIS_OFFSET); /* Lock the PCSR registers */ - writel(1, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET); + writel(PCSR_LOCK_VAL, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET); } #define to_mci(k) container_of(k, struct mem_ctl_info, dev) @@ -734,38 +736,63 @@ static void poison_setup(struct edac_priv *priv) writel(regval, priv->ddrmc_noc_baseaddr + XDDR_NOC_REG_ADEC15_OFFSET); } -static ssize_t xddr_inject_data_poison_store(struct mem_ctl_info *mci, - const char __user *data) +static void xddr_inject_data_ce_store(struct mem_ctl_info *mci, u8 ce_bitpos) { + u32 ecc0_flip0, ecc1_flip0, ecc0_flip1, ecc1_flip1; struct edac_priv *priv = mci->pvt_info; - writel(0, priv->ddrmc_baseaddr + ECCW0_FLIP0_OFFSET); - writel(0, priv->ddrmc_baseaddr + ECCW1_FLIP0_OFFSET); - - if (strncmp(data, "CE", 2) == 0) { - writel(ECC_CEPOISON_MASK, priv->ddrmc_baseaddr + - ECCW0_FLIP0_OFFSET); - writel(ECC_CEPOISON_MASK, priv->ddrmc_baseaddr + - ECCW1_FLIP0_OFFSET); + if (ce_bitpos < ECCW0_FLIP0_BITS) { + ecc0_flip0 = BIT(ce_bitpos); + ecc1_flip0 = BIT(ce_bitpos); + ecc0_flip1 = 0; + ecc1_flip1 = 0; } else { - writel(ECC_UEPOISON_MASK, priv->ddrmc_baseaddr + - ECCW0_FLIP0_OFFSET); - writel(ECC_UEPOISON_MASK, priv->ddrmc_baseaddr + - ECCW1_FLIP0_OFFSET); + ce_bitpos = ce_bitpos - ECCW0_FLIP0_BITS; + ecc0_flip1 = BIT(ce_bitpos); + ecc1_flip1 = BIT(ce_bitpos); + ecc0_flip0 = 0; + ecc1_flip0 = 0; } - /* Lock the PCSR registers */ - writel(1, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET); - - return 0; + writel(ecc0_flip0, priv->ddrmc_baseaddr + ECCW0_FLIP0_OFFSET); + writel(ecc1_flip0, priv->ddrmc_baseaddr + ECCW1_FLIP0_OFFSET); + writel(ecc0_flip1, priv->ddrmc_baseaddr + ECCW0_FLIP1_OFFSET); + writel(ecc1_flip1, priv->ddrmc_baseaddr + ECCW1_FLIP1_OFFSET); } -static ssize_t inject_data_poison_store(struct file *file, const char __user *data, - size_t count, loff_t *ppos) +/* + * To inject a correctable error, the following steps are needed: + * + * - Write the correctable error bit position value: + * echo <bit_pos val> > /sys/kernel/debug/edac/<controller instance>/inject_ce + * + * poison_setup() derives the row, column, bank, group and rank and + * writes to the ADEC registers based on the address given by the user. + * + * The ADEC12 and ADEC13 are mask registers; write 0 to make sure default + * configuration is there and no addresses are masked. + * + * The row, column, bank, group and rank registers are written to the + * match ADEC bit to generate errors at the particular address. ADEC14 + * and ADEC15 have the match bits. + * + * xddr_inject_data_ce_store() updates the ECC FLIP registers with the + * bits to be corrupted based on the bit position given by the user. + * + * Upon doing a read to the address the errors are injected. + */ +static ssize_t inject_data_ce_store(struct file *file, const char __user *data, + size_t count, loff_t *ppos) { struct device *dev = file->private_data; struct mem_ctl_info *mci = to_mci(dev); struct edac_priv *priv = mci->pvt_info; + u8 ce_bitpos; + int ret; + + ret = kstrtou8_from_user(data, count, 0, &ce_bitpos); + if (ret) + return ret; /* Unlock the PCSR registers */ writel(PCSR_UNLOCK_VAL, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET); @@ -773,17 +800,110 @@ static ssize_t inject_data_poison_store(struct file *file, const char __user *da poison_setup(priv); + xddr_inject_data_ce_store(mci, ce_bitpos); + ret = count; + /* Lock the PCSR registers */ - writel(1, priv->ddrmc_noc_baseaddr + XDDR_PCSR_OFFSET); + writel(PCSR_LOCK_VAL, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET); + writel(PCSR_LOCK_VAL, priv->ddrmc_noc_baseaddr + XDDR_PCSR_OFFSET); + + return ret; +} + +static const struct file_operations xddr_inject_ce_fops = { + .open = simple_open, + .write = inject_data_ce_store, + .llseek = generic_file_llseek, +}; + +static void xddr_inject_data_ue_store(struct mem_ctl_info *mci, u32 val0, u32 val1) +{ + struct edac_priv *priv = mci->pvt_info; + + writel(val0, priv->ddrmc_baseaddr + ECCW0_FLIP0_OFFSET); + writel(val0, priv->ddrmc_baseaddr + ECCW0_FLIP1_OFFSET); + writel(val1, priv->ddrmc_baseaddr + ECCW1_FLIP1_OFFSET); + writel(val1, priv->ddrmc_baseaddr + ECCW1_FLIP1_OFFSET); +} + +/* + * To inject an uncorrectable error, the following steps are needed: + * echo <bit_pos val> > /sys/kernel/debug/edac/<controller instance>/inject_ue + * + * poison_setup() derives the row, column, bank, group and rank and + * writes to the ADEC registers based on the address given by the user. + * + * The ADEC12 and ADEC13 are mask registers; write 0 so that none of the + * addresses are masked. The row, column, bank, group and rank registers + * are written to the match ADEC bit to generate errors at the + * particular address. ADEC14 and ADEC15 have the match bits. + * + * xddr_inject_data_ue_store() updates the ECC FLIP registers with the + * bits to be corrupted based on the bit position given by the user. For + * uncorrectable errors + * 2 bit errors are injected. + * + * Upon doing a read to the address the errors are injected. + */ +static ssize_t inject_data_ue_store(struct file *file, const char __user *data, + size_t count, loff_t *ppos) +{ + struct device *dev = file->private_data; + struct mem_ctl_info *mci = to_mci(dev); + struct edac_priv *priv = mci->pvt_info; + char buf[6], *pbuf, *token[2]; + u32 val0 = 0, val1 = 0; + u8 len, ue0, ue1; + int i, ret; + + len = min_t(size_t, count, sizeof(buf)); + if (copy_from_user(buf, data, len)) + return -EFAULT; + + buf[len] = '\0'; + pbuf = &buf[0]; + for (i = 0; i < NUM_UE_BITPOS; i++) + token[i] = strsep(&pbuf, ","); + + ret = kstrtou8(token[0], 0, &ue0); + if (ret) + return ret; + + ret = kstrtou8(token[1], 0, &ue1); + if (ret) + return ret; + + if (ue0 < ECCW0_FLIP0_BITS) { + val0 = BIT(ue0); + } else { + ue0 = ue0 - ECCW0_FLIP0_BITS; + val1 = BIT(ue0); + } + + if (ue1 < ECCW0_FLIP0_BITS) { + val0 |= BIT(ue1); + } else { + ue1 = ue1 - ECCW0_FLIP0_BITS; + val1 |= BIT(ue1); + } - xddr_inject_data_poison_store(mci, data); + /* Unlock the PCSR registers */ + writel(PCSR_UNLOCK_VAL, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET); + writel(PCSR_UNLOCK_VAL, priv->ddrmc_noc_baseaddr + XDDR_PCSR_OFFSET); + poison_setup(priv); + + xddr_inject_data_ue_store(mci, val0, val1); + + /* Lock the PCSR registers */ + writel(PCSR_LOCK_VAL, priv->ddrmc_noc_baseaddr + XDDR_PCSR_OFFSET); + writel(PCSR_LOCK_VAL, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET); return count; } -static const struct file_operations xddr_inject_enable_fops = { +static const struct file_operations xddr_inject_ue_fops = { .open = simple_open, - .write = inject_data_poison_store, + .write = inject_data_ue_store, .llseek = generic_file_llseek, }; @@ -795,8 +915,17 @@ static void create_debugfs_attributes(struct mem_ctl_info *mci) if (!priv->debugfs) return; - edac_debugfs_create_file("inject_error", 0200, priv->debugfs, - &mci->dev, &xddr_inject_enable_fops); + if (!edac_debugfs_create_file("inject_ce", 0200, priv->debugfs, + &mci->dev, &xddr_inject_ce_fops)) { + debugfs_remove_recursive(priv->debugfs); + return; + } + + if (!edac_debugfs_create_file("inject_ue", 0200, priv->debugfs, + &mci->dev, &xddr_inject_ue_fops)) { + debugfs_remove_recursive(priv->debugfs); + return; + } debugfs_create_x64("address", 0600, priv->debugfs, &priv->err_inject_addr); mci->debugfs = priv->debugfs; @@ -1031,7 +1160,7 @@ free_edac_mc: return rc; } -static int mc_remove(struct platform_device *pdev) +static void mc_remove(struct platform_device *pdev) { struct mem_ctl_info *mci = platform_get_drvdata(pdev); struct edac_priv *priv = mci->pvt_info; @@ -1049,8 +1178,6 @@ static int mc_remove(struct platform_device *pdev) XPM_EVENT_ERROR_MASK_DDRMC_NCR, err_callback, mci); edac_mc_del_mc(&pdev->dev); edac_mc_free(mci); - - return 0; } static struct platform_driver xilinx_ddr_edac_mc_driver = { @@ -1059,7 +1186,7 @@ static struct platform_driver xilinx_ddr_edac_mc_driver = { .of_match_table = xlnx_edac_match, }, .probe = mc_probe, - .remove = mc_remove, + .remove_new = mc_remove, }; module_platform_driver(xilinx_ddr_edac_mc_driver); diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c index bfa30625f5d0..3dc2f9aaf08d 100644 --- a/drivers/firmware/efi/libstub/efi-stub-helper.c +++ b/drivers/firmware/efi/libstub/efi-stub-helper.c @@ -24,6 +24,8 @@ static bool efi_noinitrd; static bool efi_nosoftreserve; static bool efi_disable_pci_dma = IS_ENABLED(CONFIG_EFI_DISABLE_PCI_DMA); +int efi_mem_encrypt; + bool __pure __efi_soft_reserve_enabled(void) { return !efi_nosoftreserve; @@ -75,6 +77,12 @@ efi_status_t efi_parse_options(char const *cmdline) efi_noinitrd = true; } else if (IS_ENABLED(CONFIG_X86_64) && !strcmp(param, "no5lvl")) { efi_no5lvl = true; + } else if (IS_ENABLED(CONFIG_ARCH_HAS_MEM_ENCRYPT) && + !strcmp(param, "mem_encrypt") && val) { + if (parse_option_str(val, "on")) + efi_mem_encrypt = 1; + else if (parse_option_str(val, "off")) + efi_mem_encrypt = -1; } else if (!strcmp(param, "efi") && val) { efi_nochunk = parse_option_str(val, "nochunk"); efi_novamap |= parse_option_str(val, "novamap"); diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h index c04b82ea40f2..fc18fd649ed7 100644 --- a/drivers/firmware/efi/libstub/efistub.h +++ b/drivers/firmware/efi/libstub/efistub.h @@ -37,8 +37,8 @@ extern bool efi_no5lvl; extern bool efi_nochunk; extern bool efi_nokaslr; extern int efi_loglevel; +extern int efi_mem_encrypt; extern bool efi_novamap; - extern const efi_system_table_t *efi_system_table; typedef union efi_dxe_services_table efi_dxe_services_table_t; diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c index 99429bc4b0c7..0336ed175e67 100644 --- a/drivers/firmware/efi/libstub/x86-stub.c +++ b/drivers/firmware/efi/libstub/x86-stub.c @@ -884,6 +884,9 @@ void __noreturn efi_stub_entry(efi_handle_t handle, } } + if (efi_mem_encrypt > 0) + hdr->xloadflags |= XLF_MEM_ENCRYPTION; + status = efi_decompress_kernel(&kernel_entry); if (status != EFI_SUCCESS) { efi_err("Failed to decompress kernel\n"); diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h index 8b3601f285fd..c970eae2313d 100644 --- a/drivers/iommu/amd/amd_iommu.h +++ b/drivers/iommu/amd/amd_iommu.h @@ -164,5 +164,4 @@ void amd_iommu_domain_set_pgtable(struct protection_domain *domain, u64 *root, int mode); struct dev_table_entry *get_dev_table(struct amd_iommu *iommu); -extern bool amd_iommu_snp_en; #endif diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index c83bd0c2a1c9..480e7681f4f3 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -30,6 +30,7 @@ #include <asm/io_apic.h> #include <asm/irq_remapping.h> #include <asm/set_memory.h> +#include <asm/sev.h> #include <linux/crash_dump.h> @@ -3221,6 +3222,36 @@ out: return true; } +static void iommu_snp_enable(void) +{ +#ifdef CONFIG_KVM_AMD_SEV + if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP)) + return; + /* + * The SNP support requires that IOMMU must be enabled, and is + * not configured in the passthrough mode. + */ + if (no_iommu || iommu_default_passthrough()) { + pr_err("SNP: IOMMU disabled or configured in passthrough mode, SNP cannot be supported.\n"); + return; + } + + amd_iommu_snp_en = check_feature(FEATURE_SNP); + if (!amd_iommu_snp_en) { + pr_err("SNP: IOMMU SNP feature not enabled, SNP cannot be supported.\n"); + return; + } + + pr_info("IOMMU SNP support enabled.\n"); + + /* Enforce IOMMU v1 pagetable when SNP is enabled. */ + if (amd_iommu_pgtable != AMD_IOMMU_V1) { + pr_warn("Forcing use of AMD IOMMU v1 page table due to SNP.\n"); + amd_iommu_pgtable = AMD_IOMMU_V1; + } +#endif +} + /**************************************************************************** * * AMD IOMMU Initialization State Machine @@ -3256,6 +3287,7 @@ static int __init state_next(void) break; case IOMMU_ENABLED: register_syscore_ops(&amd_iommu_syscore_ops); + iommu_snp_enable(); ret = amd_iommu_init_pci(); init_state = ret ? IOMMU_INIT_ERROR : IOMMU_PCI_INIT; break; @@ -3767,40 +3799,85 @@ int amd_iommu_pc_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, u8 fxn, u64 return iommu_pc_get_set_reg(iommu, bank, cntr, fxn, value, true); } -#ifdef CONFIG_AMD_MEM_ENCRYPT -int amd_iommu_snp_enable(void) +#ifdef CONFIG_KVM_AMD_SEV +static int iommu_page_make_shared(void *page) { - /* - * The SNP support requires that IOMMU must be enabled, and is - * not configured in the passthrough mode. - */ - if (no_iommu || iommu_default_passthrough()) { - pr_err("SNP: IOMMU is disabled or configured in passthrough mode, SNP cannot be supported"); - return -EINVAL; + unsigned long paddr, pfn; + + paddr = iommu_virt_to_phys(page); + /* Cbit maybe set in the paddr */ + pfn = __sme_clr(paddr) >> PAGE_SHIFT; + + if (!(pfn % PTRS_PER_PMD)) { + int ret, level; + bool assigned; + + ret = snp_lookup_rmpentry(pfn, &assigned, &level); + if (ret) { + pr_warn("IOMMU PFN %lx RMP lookup failed, ret %d\n", pfn, ret); + return ret; + } + + if (!assigned) { + pr_warn("IOMMU PFN %lx not assigned in RMP table\n", pfn); + return -EINVAL; + } + + if (level > PG_LEVEL_4K) { + ret = psmash(pfn); + if (!ret) + goto done; + + pr_warn("PSMASH failed for IOMMU PFN %lx huge RMP entry, ret: %d, level: %d\n", + pfn, ret, level); + return ret; + } } - /* - * Prevent enabling SNP after IOMMU_ENABLED state because this process - * affect how IOMMU driver sets up data structures and configures - * IOMMU hardware. - */ - if (init_state > IOMMU_ENABLED) { - pr_err("SNP: Too late to enable SNP for IOMMU.\n"); - return -EINVAL; +done: + return rmp_make_shared(pfn, PG_LEVEL_4K); +} + +static int iommu_make_shared(void *va, size_t size) +{ + void *page; + int ret; + + if (!va) + return 0; + + for (page = va; page < (va + size); page += PAGE_SIZE) { + ret = iommu_page_make_shared(page); + if (ret) + return ret; } - amd_iommu_snp_en = check_feature(FEATURE_SNP); + return 0; +} + +int amd_iommu_snp_disable(void) +{ + struct amd_iommu *iommu; + int ret; + if (!amd_iommu_snp_en) - return -EINVAL; + return 0; + + for_each_iommu(iommu) { + ret = iommu_make_shared(iommu->evt_buf, EVT_BUFFER_SIZE); + if (ret) + return ret; - pr_info("SNP enabled\n"); + ret = iommu_make_shared(iommu->ppr_log, PPR_LOG_SIZE); + if (ret) + return ret; - /* Enforce IOMMU v1 pagetable when SNP is enabled. */ - if (amd_iommu_pgtable != AMD_IOMMU_V1) { - pr_warn("Force to using AMD IOMMU v1 page table due to SNP\n"); - amd_iommu_pgtable = AMD_IOMMU_V1; + ret = iommu_make_shared((void *)iommu->cmd_sem, PAGE_SIZE); + if (ret) + return ret; } return 0; } +EXPORT_SYMBOL_GPL(amd_iommu_snp_disable); #endif diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 95077c06ec4a..9836745f5fde 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -2027,27 +2027,26 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, bool wc = false, fua = false; int r; + /* + * Copy table's limits to the DM device's request_queue + */ + q->limits = *limits; + if (dm_table_supports_nowait(t)) blk_queue_flag_set(QUEUE_FLAG_NOWAIT, q); else blk_queue_flag_clear(QUEUE_FLAG_NOWAIT, q); if (!dm_table_supports_discards(t)) { - limits->max_hw_discard_sectors = 0; - limits->discard_granularity = 0; - limits->discard_alignment = 0; - limits->discard_misaligned = 0; + q->limits.max_discard_sectors = 0; + q->limits.max_hw_discard_sectors = 0; + q->limits.discard_granularity = 0; + q->limits.discard_alignment = 0; + q->limits.discard_misaligned = 0; } - if (!dm_table_supports_write_zeroes(t)) - limits->max_write_zeroes_sectors = 0; - if (!dm_table_supports_secure_erase(t)) - limits->max_secure_erase_sectors = 0; - - r = queue_limits_set(q, limits); - if (r) - return r; + q->limits.max_secure_erase_sectors = 0; if (dm_table_supports_flush(t, (1UL << QUEUE_FLAG_WC))) { wc = true; @@ -2072,6 +2071,9 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, else blk_queue_flag_set(QUEUE_FLAG_NONROT, q); + if (!dm_table_supports_write_zeroes(t)) + q->limits.max_write_zeroes_sectors = 0; + dm_table_verify_integrity(t); /* @@ -2109,6 +2111,7 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, } dm_update_crypto_profile(q, t); + disk_update_readahead(t->md->disk); /* * Check for request-based device is left to diff --git a/drivers/pci/hotplug/s390_pci_hpc.c b/drivers/pci/hotplug/s390_pci_hpc.c index a89b7de72dcf..7333b305f2a5 100644 --- a/drivers/pci/hotplug/s390_pci_hpc.c +++ b/drivers/pci/hotplug/s390_pci_hpc.c @@ -26,58 +26,79 @@ static int enable_slot(struct hotplug_slot *hotplug_slot) hotplug_slot); int rc; - if (zdev->state != ZPCI_FN_STATE_STANDBY) - return -EIO; + mutex_lock(&zdev->state_lock); + if (zdev->state != ZPCI_FN_STATE_STANDBY) { + rc = -EIO; + goto out; + } rc = sclp_pci_configure(zdev->fid); zpci_dbg(3, "conf fid:%x, rc:%d\n", zdev->fid, rc); if (rc) - return rc; + goto out; zdev->state = ZPCI_FN_STATE_CONFIGURED; - return zpci_scan_configured_device(zdev, zdev->fh); + rc = zpci_scan_configured_device(zdev, zdev->fh); +out: + mutex_unlock(&zdev->state_lock); + return rc; } static int disable_slot(struct hotplug_slot *hotplug_slot) { struct zpci_dev *zdev = container_of(hotplug_slot, struct zpci_dev, hotplug_slot); - struct pci_dev *pdev; + struct pci_dev *pdev = NULL; + int rc; - if (zdev->state != ZPCI_FN_STATE_CONFIGURED) - return -EIO; + mutex_lock(&zdev->state_lock); + if (zdev->state != ZPCI_FN_STATE_CONFIGURED) { + rc = -EIO; + goto out; + } pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn); if (pdev && pci_num_vf(pdev)) { pci_dev_put(pdev); - return -EBUSY; + rc = -EBUSY; + goto out; } - pci_dev_put(pdev); - return zpci_deconfigure_device(zdev); + rc = zpci_deconfigure_device(zdev); +out: + mutex_unlock(&zdev->state_lock); + if (pdev) + pci_dev_put(pdev); + return rc; } static int reset_slot(struct hotplug_slot *hotplug_slot, bool probe) { struct zpci_dev *zdev = container_of(hotplug_slot, struct zpci_dev, hotplug_slot); + int rc = -EIO; - if (zdev->state != ZPCI_FN_STATE_CONFIGURED) - return -EIO; /* - * We can't take the zdev->lock as reset_slot may be called during - * probing and/or device removal which already happens under the - * zdev->lock. Instead the user should use the higher level - * pci_reset_function() or pci_bus_reset() which hold the PCI device - * lock preventing concurrent removal. If not using these functions - * holding the PCI device lock is required. + * If we can't get the zdev->state_lock the device state is + * currently undergoing a transition and we bail out - just + * the same as if the device's state is not configured at all. */ + if (!mutex_trylock(&zdev->state_lock)) + return rc; - /* As long as the function is configured we can reset */ - if (probe) - return 0; + /* We can reset only if the function is configured */ + if (zdev->state != ZPCI_FN_STATE_CONFIGURED) + goto out; + + if (probe) { + rc = 0; + goto out; + } - return zpci_hot_reset_device(zdev); + rc = zpci_hot_reset_device(zdev); +out: + mutex_unlock(&zdev->state_lock); + return rc; } static int get_power_status(struct hotplug_slot *hotplug_slot, u8 *value) diff --git a/drivers/ras/Kconfig b/drivers/ras/Kconfig index c2a236f2e846..fc4f4bb94a4c 100644 --- a/drivers/ras/Kconfig +++ b/drivers/ras/Kconfig @@ -32,5 +32,18 @@ menuconfig RAS if RAS source "arch/x86/ras/Kconfig" +source "drivers/ras/amd/atl/Kconfig" + +config RAS_FMPM + tristate "FRU Memory Poison Manager" + default m + depends on AMD_ATL && ACPI_APEI + help + Support saving and restoring memory error information across reboot + using ACPI ERST as persistent storage. Error information is saved with + the UEFI CPER "FRU Memory Poison" section format. + + Memory will be retired during boot time and run time depending on + platform-specific policies. endif diff --git a/drivers/ras/Makefile b/drivers/ras/Makefile index 6f0404f50107..11f95d59d397 100644 --- a/drivers/ras/Makefile +++ b/drivers/ras/Makefile @@ -2,3 +2,6 @@ obj-$(CONFIG_RAS) += ras.o obj-$(CONFIG_DEBUG_FS) += debugfs.o obj-$(CONFIG_RAS_CEC) += cec.o + +obj-$(CONFIG_RAS_FMPM) += amd/fmpm.o +obj-y += amd/atl/ diff --git a/drivers/ras/amd/atl/Kconfig b/drivers/ras/amd/atl/Kconfig new file mode 100644 index 000000000000..df49c23e7f62 --- /dev/null +++ b/drivers/ras/amd/atl/Kconfig @@ -0,0 +1,21 @@ +# SPDX-License-Identifier: GPL-2.0-or-later +# +# AMD Address Translation Library Kconfig +# +# Copyright (c) 2023, Advanced Micro Devices, Inc. +# All Rights Reserved. +# +# Author: Yazen Ghannam <Yazen.Ghannam@amd.com> + +config AMD_ATL + tristate "AMD Address Translation Library" + depends on AMD_NB && X86_64 && RAS + depends on MEMORY_FAILURE + default N + help + This library includes support for implementation-specific + address translation procedures needed for various error + handling cases. + + Enable this option if using DRAM ECC on Zen-based systems + and OS-based error handling. diff --git a/drivers/ras/amd/atl/Makefile b/drivers/ras/amd/atl/Makefile new file mode 100644 index 000000000000..4acd5f05bd9c --- /dev/null +++ b/drivers/ras/amd/atl/Makefile @@ -0,0 +1,18 @@ +# SPDX-License-Identifier: GPL-2.0-or-later +# +# AMD Address Translation Library Makefile +# +# Copyright (c) 2023, Advanced Micro Devices, Inc. +# All Rights Reserved. +# +# Author: Yazen Ghannam <Yazen.Ghannam@amd.com> + +amd_atl-y := access.o +amd_atl-y += core.o +amd_atl-y += dehash.o +amd_atl-y += denormalize.o +amd_atl-y += map.o +amd_atl-y += system.o +amd_atl-y += umc.o + +obj-$(CONFIG_AMD_ATL) += amd_atl.o diff --git a/drivers/ras/amd/atl/access.c b/drivers/ras/amd/atl/access.c new file mode 100644 index 000000000000..ee4661ed28ba --- /dev/null +++ b/drivers/ras/amd/atl/access.c @@ -0,0 +1,133 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * AMD Address Translation Library + * + * access.c : DF Indirect Access functions + * + * Copyright (c) 2023, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Author: Yazen Ghannam <Yazen.Ghannam@amd.com> + */ + +#include "internal.h" + +/* Protect the PCI config register pairs used for DF indirect access. */ +static DEFINE_MUTEX(df_indirect_mutex); + +/* + * Data Fabric Indirect Access uses FICAA/FICAD. + * + * Fabric Indirect Configuration Access Address (FICAA): constructed based + * on the device's Instance Id and the PCI function and register offset of + * the desired register. + * + * Fabric Indirect Configuration Access Data (FICAD): there are FICAD + * low and high registers but so far only the low register is needed. + * + * Use Instance Id 0xFF to indicate a broadcast read. + */ +#define DF_BROADCAST 0xFF + +#define DF_FICAA_INST_EN BIT(0) +#define DF_FICAA_REG_NUM GENMASK(10, 1) +#define DF_FICAA_FUNC_NUM GENMASK(13, 11) +#define DF_FICAA_INST_ID GENMASK(23, 16) + +#define DF_FICAA_REG_NUM_LEGACY GENMASK(10, 2) + +static u16 get_accessible_node(u16 node) +{ + /* + * On heterogeneous systems, not all AMD Nodes are accessible + * through software-visible registers. The Node ID needs to be + * adjusted for register accesses. But its value should not be + * changed for the translation methods. + */ + if (df_cfg.flags.heterogeneous) { + /* Only Node 0 is accessible on DF3.5 systems. */ + if (df_cfg.rev == DF3p5) + node = 0; + + /* + * Only the first Node in each Socket is accessible on + * DF4.5 systems, and this is visible to software as one + * Fabric per Socket. The Socket ID can be derived from + * the Node ID and global shift values. + */ + if (df_cfg.rev == DF4p5) + node >>= df_cfg.socket_id_shift - df_cfg.node_id_shift; + } + + return node; +} + +static int __df_indirect_read(u16 node, u8 func, u16 reg, u8 instance_id, u32 *lo) +{ + u32 ficaa_addr = 0x8C, ficad_addr = 0xB8; + struct pci_dev *F4; + int err = -ENODEV; + u32 ficaa = 0; + + node = get_accessible_node(node); + if (node >= amd_nb_num()) + goto out; + + F4 = node_to_amd_nb(node)->link; + if (!F4) + goto out; + + /* Enable instance-specific access. */ + if (instance_id != DF_BROADCAST) { + ficaa |= FIELD_PREP(DF_FICAA_INST_EN, 1); + ficaa |= FIELD_PREP(DF_FICAA_INST_ID, instance_id); + } + + /* + * The two least-significant bits are masked when inputing the + * register offset to FICAA. + */ + reg >>= 2; + + if (df_cfg.flags.legacy_ficaa) { + ficaa_addr = 0x5C; + ficad_addr = 0x98; + + ficaa |= FIELD_PREP(DF_FICAA_REG_NUM_LEGACY, reg); + } else { + ficaa |= FIELD_PREP(DF_FICAA_REG_NUM, reg); + } + + ficaa |= FIELD_PREP(DF_FICAA_FUNC_NUM, func); + + mutex_lock(&df_indirect_mutex); + + err = pci_write_config_dword(F4, ficaa_addr, ficaa); + if (err) { + pr_warn("Error writing DF Indirect FICAA, FICAA=0x%x\n", ficaa); + goto out_unlock; + } + + err = pci_read_config_dword(F4, ficad_addr, lo); + if (err) + pr_warn("Error reading DF Indirect FICAD LO, FICAA=0x%x.\n", ficaa); + + pr_debug("node=%u inst=0x%x func=0x%x reg=0x%x val=0x%x", + node, instance_id, func, reg << 2, *lo); + +out_unlock: + mutex_unlock(&df_indirect_mutex); + +out: + return err; +} + +int df_indirect_read_instance(u16 node, u8 func, u16 reg, u8 instance_id, u32 *lo) +{ + return __df_indirect_read(node, func, reg, instance_id, lo); +} + +int df_indirect_read_broadcast(u16 node, u8 func, u16 reg, u32 *lo) +{ + return __df_indirect_read(node, func, reg, DF_BROADCAST, lo); +} diff --git a/drivers/ras/amd/atl/core.c b/drivers/ras/amd/atl/core.c new file mode 100644 index 000000000000..6dc4e06305f7 --- /dev/null +++ b/drivers/ras/amd/atl/core.c @@ -0,0 +1,225 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * AMD Address Translation Library + * + * core.c : Module init and base translation functions + * + * Copyright (c) 2023, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Author: Yazen Ghannam <Yazen.Ghannam@amd.com> + */ + +#include <linux/module.h> +#include <asm/cpu_device_id.h> + +#include "internal.h" + +struct df_config df_cfg __read_mostly; + +static int addr_over_limit(struct addr_ctx *ctx) +{ + u64 dram_limit_addr; + + if (df_cfg.rev >= DF4) + dram_limit_addr = FIELD_GET(DF4_DRAM_LIMIT_ADDR, ctx->map.limit); + else + dram_limit_addr = FIELD_GET(DF2_DRAM_LIMIT_ADDR, ctx->map.limit); + + dram_limit_addr <<= DF_DRAM_BASE_LIMIT_LSB; + dram_limit_addr |= GENMASK(DF_DRAM_BASE_LIMIT_LSB - 1, 0); + + /* Is calculated system address above DRAM limit address? */ + if (ctx->ret_addr > dram_limit_addr) { + atl_debug(ctx, "Calculated address (0x%016llx) > DRAM limit (0x%016llx)", + ctx->ret_addr, dram_limit_addr); + return -EINVAL; + } + + return 0; +} + +static bool legacy_hole_en(struct addr_ctx *ctx) +{ + u32 reg = ctx->map.base; + + if (df_cfg.rev >= DF4) + reg = ctx->map.ctl; + + return FIELD_GET(DF_LEGACY_MMIO_HOLE_EN, reg); +} + +static int add_legacy_hole(struct addr_ctx *ctx) +{ + u32 dram_hole_base; + u8 func = 0; + + if (!legacy_hole_en(ctx)) + return 0; + + if (df_cfg.rev >= DF4) + func = 7; + + if (df_indirect_read_broadcast(ctx->node_id, func, 0x104, &dram_hole_base)) + return -EINVAL; + + dram_hole_base &= DF_DRAM_HOLE_BASE_MASK; + + if (ctx->ret_addr >= dram_hole_base) + ctx->ret_addr += (BIT_ULL(32) - dram_hole_base); + + return 0; +} + +static u64 get_base_addr(struct addr_ctx *ctx) +{ + u64 base_addr; + + if (df_cfg.rev >= DF4) + base_addr = FIELD_GET(DF4_BASE_ADDR, ctx->map.base); + else + base_addr = FIELD_GET(DF2_BASE_ADDR, ctx->map.base); + + return base_addr << DF_DRAM_BASE_LIMIT_LSB; +} + +static int add_base_and_hole(struct addr_ctx *ctx) +{ + ctx->ret_addr += get_base_addr(ctx); + + if (add_legacy_hole(ctx)) + return -EINVAL; + + return 0; +} + +static bool late_hole_remove(struct addr_ctx *ctx) +{ + if (df_cfg.rev == DF3p5) + return true; + + if (df_cfg.rev == DF4) + return true; + + if (ctx->map.intlv_mode == DF3_6CHAN) + return true; + + return false; +} + +unsigned long norm_to_sys_addr(u8 socket_id, u8 die_id, u8 coh_st_inst_id, unsigned long addr) +{ + struct addr_ctx ctx; + + if (df_cfg.rev == UNKNOWN) + return -EINVAL; + + memset(&ctx, 0, sizeof(ctx)); + + /* Start from the normalized address */ + ctx.ret_addr = addr; + ctx.inst_id = coh_st_inst_id; + + ctx.inputs.norm_addr = addr; + ctx.inputs.socket_id = socket_id; + ctx.inputs.die_id = die_id; + ctx.inputs.coh_st_inst_id = coh_st_inst_id; + + if (determine_node_id(&ctx, socket_id, die_id)) + return -EINVAL; + + if (get_address_map(&ctx)) + return -EINVAL; + + if (denormalize_address(&ctx)) + return -EINVAL; + + if (!late_hole_remove(&ctx) && add_base_and_hole(&ctx)) + return -EINVAL; + + if (dehash_address(&ctx)) + return -EINVAL; + + if (late_hole_remove(&ctx) && add_base_and_hole(&ctx)) + return -EINVAL; + + if (addr_over_limit(&ctx)) + return -EINVAL; + + return ctx.ret_addr; +} + +static void check_for_legacy_df_access(void) +{ + /* + * All Zen-based systems before Family 19h use the legacy + * DF Indirect Access (FICAA/FICAD) offsets. + */ + if (boot_cpu_data.x86 < 0x19) { + df_cfg.flags.legacy_ficaa = true; + return; + } + + /* All systems after Family 19h use the current offsets. */ + if (boot_cpu_data.x86 > 0x19) + return; + + /* Some Family 19h systems use the legacy offsets. */ + switch (boot_cpu_data.x86_model) { + case 0x00 ... 0x0f: + case 0x20 ... 0x5f: + df_cfg.flags.legacy_ficaa = true; + } +} + +/* + * This library provides functionality for AMD-based systems with a Data Fabric. + * The set of systems with a Data Fabric is equivalent to the set of Zen-based systems + * and the set of systems with the Scalable MCA feature at this time. However, these + * are technically independent things. + * + * It's possible to match on the PCI IDs of the Data Fabric devices, but this will be + * an ever expanding list. Instead, match on the SMCA and Zen features to cover all + * relevant systems. + */ +static const struct x86_cpu_id amd_atl_cpuids[] = { + X86_MATCH_FEATURE(X86_FEATURE_SMCA, NULL), + X86_MATCH_FEATURE(X86_FEATURE_ZEN, NULL), + { } +}; +MODULE_DEVICE_TABLE(x86cpu, amd_atl_cpuids); + +static int __init amd_atl_init(void) +{ + if (!x86_match_cpu(amd_atl_cpuids)) + return -ENODEV; + + if (!amd_nb_num()) + return -ENODEV; + + check_for_legacy_df_access(); + + if (get_df_system_info()) + return -ENODEV; + + /* Increment this module's recount so that it can't be easily unloaded. */ + __module_get(THIS_MODULE); + amd_atl_register_decoder(convert_umc_mca_addr_to_sys_addr); + + pr_info("AMD Address Translation Library initialized"); + return 0; +} + +/* + * Exit function is only needed for testing and debug. Module unload must be + * forced to override refcount check. + */ +static void __exit amd_atl_exit(void) +{ + amd_atl_unregister_decoder(); +} + +module_init(amd_atl_init); +module_exit(amd_atl_exit); + +MODULE_LICENSE("GPL"); diff --git a/drivers/ras/amd/atl/dehash.c b/drivers/ras/amd/atl/dehash.c new file mode 100644 index 000000000000..4ea46262c4f5 --- /dev/null +++ b/drivers/ras/amd/atl/dehash.c @@ -0,0 +1,500 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * AMD Address Translation Library + * + * dehash.c : Functions to account for hashing bits + * + * Copyright (c) 2023, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Author: Yazen Ghannam <Yazen.Ghannam@amd.com> + */ + +#include "internal.h" + +/* + * Verify the interleave bits are correct in the different interleaving + * settings. + * + * If @num_intlv_dies and/or @num_intlv_sockets are 1, it means the + * respective interleaving is disabled. + */ +static inline bool map_bits_valid(struct addr_ctx *ctx, u8 bit1, u8 bit2, + u8 num_intlv_dies, u8 num_intlv_sockets) +{ + if (!(ctx->map.intlv_bit_pos == bit1 || ctx->map.intlv_bit_pos == bit2)) { + pr_debug("Invalid interleave bit: %u", ctx->map.intlv_bit_pos); + return false; + } + + if (ctx->map.num_intlv_dies > num_intlv_dies) { + pr_debug("Invalid number of interleave dies: %u", ctx->map.num_intlv_dies); + return false; + } + + if (ctx->map.num_intlv_sockets > num_intlv_sockets) { + pr_debug("Invalid number of interleave sockets: %u", ctx->map.num_intlv_sockets); + return false; + } + + return true; +} + +static int df2_dehash_addr(struct addr_ctx *ctx) +{ + u8 hashed_bit, intlv_bit, intlv_bit_pos; + + if (!map_bits_valid(ctx, 8, 9, 1, 1)) + return -EINVAL; + + intlv_bit_pos = ctx->map.intlv_bit_pos; + intlv_bit = !!(BIT_ULL(intlv_bit_pos) & ctx->ret_addr); + + hashed_bit = intlv_bit; + hashed_bit ^= FIELD_GET(BIT_ULL(12), ctx->ret_addr); + hashed_bit ^= FIELD_GET(BIT_ULL(18), ctx->ret_addr); + hashed_bit ^= FIELD_GET(BIT_ULL(21), ctx->ret_addr); + hashed_bit ^= FIELD_GET(BIT_ULL(30), ctx->ret_addr); + + if (hashed_bit != intlv_bit) + ctx->ret_addr ^= BIT_ULL(intlv_bit_pos); + + return 0; +} + +static int df3_dehash_addr(struct addr_ctx *ctx) +{ + bool hash_ctl_64k, hash_ctl_2M, hash_ctl_1G; + u8 hashed_bit, intlv_bit, intlv_bit_pos; + + if (!map_bits_valid(ctx, 8, 9, 1, 1)) + return -EINVAL; + + hash_ctl_64k = FIELD_GET(DF3_HASH_CTL_64K, ctx->map.ctl); + hash_ctl_2M = FIELD_GET(DF3_HASH_CTL_2M, ctx->map.ctl); + hash_ctl_1G = FIELD_GET(DF3_HASH_CTL_1G, ctx->map.ctl); + + intlv_bit_pos = ctx->map.intlv_bit_pos; + intlv_bit = !!(BIT_ULL(intlv_bit_pos) & ctx->ret_addr); + + hashed_bit = intlv_bit; + hashed_bit ^= FIELD_GET(BIT_ULL(14), ctx->ret_addr); + hashed_bit ^= FIELD_GET(BIT_ULL(18), ctx->ret_addr) & hash_ctl_64k; + hashed_bit ^= FIELD_GET(BIT_ULL(23), ctx->ret_addr) & hash_ctl_2M; + hashed_bit ^= FIELD_GET(BIT_ULL(32), ctx->ret_addr) & hash_ctl_1G; + + if (hashed_bit != intlv_bit) + ctx->ret_addr ^= BIT_ULL(intlv_bit_pos); + + /* Calculation complete for 2 channels. Continue for 4 and 8 channels. */ + if (ctx->map.intlv_mode == DF3_COD4_2CHAN_HASH) + return 0; + + intlv_bit = FIELD_GET(BIT_ULL(12), ctx->ret_addr); + + hashed_bit = intlv_bit; + hashed_bit ^= FIELD_GET(BIT_ULL(16), ctx->ret_addr) & hash_ctl_64k; + hashed_bit ^= FIELD_GET(BIT_ULL(21), ctx->ret_addr) & hash_ctl_2M; + hashed_bit ^= FIELD_GET(BIT_ULL(30), ctx->ret_addr) & hash_ctl_1G; + + if (hashed_bit != intlv_bit) + ctx->ret_addr ^= BIT_ULL(12); + + /* Calculation complete for 4 channels. Continue for 8 channels. */ + if (ctx->map.intlv_mode == DF3_COD2_4CHAN_HASH) + return 0; + + intlv_bit = FIELD_GET(BIT_ULL(13), ctx->ret_addr); + + hashed_bit = intlv_bit; + hashed_bit ^= FIELD_GET(BIT_ULL(17), ctx->ret_addr) & hash_ctl_64k; + hashed_bit ^= FIELD_GET(BIT_ULL(22), ctx->ret_addr) & hash_ctl_2M; + hashed_bit ^= FIELD_GET(BIT_ULL(31), ctx->ret_addr) & hash_ctl_1G; + + if (hashed_bit != intlv_bit) + ctx->ret_addr ^= BIT_ULL(13); + + return 0; +} + +static int df3_6chan_dehash_addr(struct addr_ctx *ctx) +{ + u8 intlv_bit_pos = ctx->map.intlv_bit_pos; + u8 hashed_bit, intlv_bit, num_intlv_bits; + bool hash_ctl_2M, hash_ctl_1G; + + if (ctx->map.intlv_mode != DF3_6CHAN) { + atl_debug_on_bad_intlv_mode(ctx); + return -EINVAL; + } + + num_intlv_bits = ilog2(ctx->map.num_intlv_chan) + 1; + + hash_ctl_2M = FIELD_GET(DF3_HASH_CTL_2M, ctx->map.ctl); + hash_ctl_1G = FIELD_GET(DF3_HASH_CTL_1G, ctx->map.ctl); + + intlv_bit = !!(BIT_ULL(intlv_bit_pos) & ctx->ret_addr); + + hashed_bit = intlv_bit; + hashed_bit ^= !!(BIT_ULL(intlv_bit_pos + num_intlv_bits) & ctx->ret_addr); + hashed_bit ^= FIELD_GET(BIT_ULL(23), ctx->ret_addr) & hash_ctl_2M; + hashed_bit ^= FIELD_GET(BIT_ULL(32), ctx->ret_addr) & hash_ctl_1G; + + if (hashed_bit != intlv_bit) + ctx->ret_addr ^= BIT_ULL(intlv_bit_pos); + + intlv_bit_pos++; + intlv_bit = !!(BIT_ULL(intlv_bit_pos) & ctx->ret_addr); + + hashed_bit = intlv_bit; + hashed_bit ^= FIELD_GET(BIT_ULL(21), ctx->ret_addr) & hash_ctl_2M; + hashed_bit ^= FIELD_GET(BIT_ULL(30), ctx->ret_addr) & hash_ctl_1G; + + if (hashed_bit != intlv_bit) + ctx->ret_addr ^= BIT_ULL(intlv_bit_pos); + + intlv_bit_pos++; + intlv_bit = !!(BIT_ULL(intlv_bit_pos) & ctx->ret_addr); + + hashed_bit = intlv_bit; + hashed_bit ^= FIELD_GET(BIT_ULL(22), ctx->ret_addr) & hash_ctl_2M; + hashed_bit ^= FIELD_GET(BIT_ULL(31), ctx->ret_addr) & hash_ctl_1G; + + if (hashed_bit != intlv_bit) + ctx->ret_addr ^= BIT_ULL(intlv_bit_pos); + + return 0; +} + +static int df4_dehash_addr(struct addr_ctx *ctx) +{ + bool hash_ctl_64k, hash_ctl_2M, hash_ctl_1G; + u8 hashed_bit, intlv_bit; + + if (!map_bits_valid(ctx, 8, 8, 1, 2)) + return -EINVAL; + + hash_ctl_64k = FIELD_GET(DF4_HASH_CTL_64K, ctx->map.ctl); + hash_ctl_2M = FIELD_GET(DF4_HASH_CTL_2M, ctx->map.ctl); + hash_ctl_1G = FIELD_GET(DF4_HASH_CTL_1G, ctx->map.ctl); + + intlv_bit = FIELD_GET(BIT_ULL(8), ctx->ret_addr); + + hashed_bit = intlv_bit; + hashed_bit ^= FIELD_GET(BIT_ULL(16), ctx->ret_addr) & hash_ctl_64k; + hashed_bit ^= FIELD_GET(BIT_ULL(21), ctx->ret_addr) & hash_ctl_2M; + hashed_bit ^= FIELD_GET(BIT_ULL(30), ctx->ret_addr) & hash_ctl_1G; + + if (ctx->map.num_intlv_sockets == 1) + hashed_bit ^= FIELD_GET(BIT_ULL(14), ctx->ret_addr); + + if (hashed_bit != intlv_bit) + ctx->ret_addr ^= BIT_ULL(8); + + /* + * Hashing is possible with socket interleaving, so check the total number + * of channels in the system rather than DRAM map interleaving mode. + * + * Calculation complete for 2 channels. Continue for 4, 8, and 16 channels. + */ + if (ctx->map.total_intlv_chan <= 2) + return 0; + + intlv_bit = FIELD_GET(BIT_ULL(12), ctx->ret_addr); + + hashed_bit = intlv_bit; + hashed_bit ^= FIELD_GET(BIT_ULL(17), ctx->ret_addr) & hash_ctl_64k; + hashed_bit ^= FIELD_GET(BIT_ULL(22), ctx->ret_addr) & hash_ctl_2M; + hashed_bit ^= FIELD_GET(BIT_ULL(31), ctx->ret_addr) & hash_ctl_1G; + + if (hashed_bit != intlv_bit) + ctx->ret_addr ^= BIT_ULL(12); + + /* Calculation complete for 4 channels. Continue for 8 and 16 channels. */ + if (ctx->map.total_intlv_chan <= 4) + return 0; + + intlv_bit = FIELD_GET(BIT_ULL(13), ctx->ret_addr); + + hashed_bit = intlv_bit; + hashed_bit ^= FIELD_GET(BIT_ULL(18), ctx->ret_addr) & hash_ctl_64k; + hashed_bit ^= FIELD_GET(BIT_ULL(23), ctx->ret_addr) & hash_ctl_2M; + hashed_bit ^= FIELD_GET(BIT_ULL(32), ctx->ret_addr) & hash_ctl_1G; + + if (hashed_bit != intlv_bit) + ctx->ret_addr ^= BIT_ULL(13); + + /* Calculation complete for 8 channels. Continue for 16 channels. */ + if (ctx->map.total_intlv_chan <= 8) + return 0; + + intlv_bit = FIELD_GET(BIT_ULL(14), ctx->ret_addr); + + hashed_bit = intlv_bit; + hashed_bit ^= FIELD_GET(BIT_ULL(19), ctx->ret_addr) & hash_ctl_64k; + hashed_bit ^= FIELD_GET(BIT_ULL(24), ctx->ret_addr) & hash_ctl_2M; + hashed_bit ^= FIELD_GET(BIT_ULL(33), ctx->ret_addr) & hash_ctl_1G; + + if (hashed_bit != intlv_bit) + ctx->ret_addr ^= BIT_ULL(14); + + return 0; +} + +static int df4p5_dehash_addr(struct addr_ctx *ctx) +{ + bool hash_ctl_64k, hash_ctl_2M, hash_ctl_1G, hash_ctl_1T; + u8 hashed_bit, intlv_bit; + u64 rehash_vector; + + if (!map_bits_valid(ctx, 8, 8, 1, 2)) + return -EINVAL; + + hash_ctl_64k = FIELD_GET(DF4_HASH_CTL_64K, ctx->map.ctl); + hash_ctl_2M = FIELD_GET(DF4_HASH_CTL_2M, ctx->map.ctl); + hash_ctl_1G = FIELD_GET(DF4_HASH_CTL_1G, ctx->map.ctl); + hash_ctl_1T = FIELD_GET(DF4p5_HASH_CTL_1T, ctx->map.ctl); + + /* + * Generate a unique address to determine which bits + * need to be dehashed. + * + * Start with a contiguous bitmask for the total + * number of channels starting at bit 8. + * + * Then make a gap in the proper place based on + * interleave mode. + */ + rehash_vector = ctx->map.total_intlv_chan - 1; + rehash_vector <<= 8; + + if (ctx->map.intlv_mode == DF4p5_NPS2_4CHAN_1K_HASH || + ctx->map.intlv_mode == DF4p5_NPS1_8CHAN_1K_HASH || + ctx->map.intlv_mode == DF4p5_NPS1_16CHAN_1K_HASH) + rehash_vector = expand_bits(10, 2, rehash_vector); + else + rehash_vector = expand_bits(9, 3, rehash_vector); + + if (rehash_vector & BIT_ULL(8)) { + intlv_bit = FIELD_GET(BIT_ULL(8), ctx->ret_addr); + + hashed_bit = intlv_bit; + hashed_bit ^= FIELD_GET(BIT_ULL(16), ctx->ret_addr) & hash_ctl_64k; + hashed_bit ^= FIELD_GET(BIT_ULL(21), ctx->ret_addr) & hash_ctl_2M; + hashed_bit ^= FIELD_GET(BIT_ULL(30), ctx->ret_addr) & hash_ctl_1G; + hashed_bit ^= FIELD_GET(BIT_ULL(40), ctx->ret_addr) & hash_ctl_1T; + + if (hashed_bit != intlv_bit) + ctx->ret_addr ^= BIT_ULL(8); + } + + if (rehash_vector & BIT_ULL(9)) { + intlv_bit = FIELD_GET(BIT_ULL(9), ctx->ret_addr); + + hashed_bit = intlv_bit; + hashed_bit ^= FIELD_GET(BIT_ULL(17), ctx->ret_addr) & hash_ctl_64k; + hashed_bit ^= FIELD_GET(BIT_ULL(22), ctx->ret_addr) & hash_ctl_2M; + hashed_bit ^= FIELD_GET(BIT_ULL(31), ctx->ret_addr) & hash_ctl_1G; + hashed_bit ^= FIELD_GET(BIT_ULL(41), ctx->ret_addr) & hash_ctl_1T; + + if (hashed_bit != intlv_bit) + ctx->ret_addr ^= BIT_ULL(9); + } + + if (rehash_vector & BIT_ULL(12)) { + intlv_bit = FIELD_GET(BIT_ULL(12), ctx->ret_addr); + + hashed_bit = intlv_bit; + hashed_bit ^= FIELD_GET(BIT_ULL(18), ctx->ret_addr) & hash_ctl_64k; + hashed_bit ^= FIELD_GET(BIT_ULL(23), ctx->ret_addr) & hash_ctl_2M; + hashed_bit ^= FIELD_GET(BIT_ULL(32), ctx->ret_addr) & hash_ctl_1G; + hashed_bit ^= FIELD_GET(BIT_ULL(42), ctx->ret_addr) & hash_ctl_1T; + + if (hashed_bit != intlv_bit) + ctx->ret_addr ^= BIT_ULL(12); + } + + if (rehash_vector & BIT_ULL(13)) { + intlv_bit = FIELD_GET(BIT_ULL(13), ctx->ret_addr); + + hashed_bit = intlv_bit; + hashed_bit ^= FIELD_GET(BIT_ULL(19), ctx->ret_addr) & hash_ctl_64k; + hashed_bit ^= FIELD_GET(BIT_ULL(24), ctx->ret_addr) & hash_ctl_2M; + hashed_bit ^= FIELD_GET(BIT_ULL(33), ctx->ret_addr) & hash_ctl_1G; + hashed_bit ^= FIELD_GET(BIT_ULL(43), ctx->ret_addr) & hash_ctl_1T; + + if (hashed_bit != intlv_bit) + ctx->ret_addr ^= BIT_ULL(13); + } + + if (rehash_vector & BIT_ULL(14)) { + intlv_bit = FIELD_GET(BIT_ULL(14), ctx->ret_addr); + + hashed_bit = intlv_bit; + hashed_bit ^= FIELD_GET(BIT_ULL(20), ctx->ret_addr) & hash_ctl_64k; + hashed_bit ^= FIELD_GET(BIT_ULL(25), ctx->ret_addr) & hash_ctl_2M; + hashed_bit ^= FIELD_GET(BIT_ULL(34), ctx->ret_addr) & hash_ctl_1G; + hashed_bit ^= FIELD_GET(BIT_ULL(44), ctx->ret_addr) & hash_ctl_1T; + + if (hashed_bit != intlv_bit) + ctx->ret_addr ^= BIT_ULL(14); + } + + return 0; +} + +/* + * MI300 hash bits + * 4K 64K 2M 1G 1T 1T + * COH_ST_Select[0] = XOR of addr{8, 12, 15, 22, 29, 36, 43} + * COH_ST_Select[1] = XOR of addr{9, 13, 16, 23, 30, 37, 44} + * COH_ST_Select[2] = XOR of addr{10, 14, 17, 24, 31, 38, 45} + * COH_ST_Select[3] = XOR of addr{11, 18, 25, 32, 39, 46} + * COH_ST_Select[4] = XOR of addr{14, 19, 26, 33, 40, 47} aka Stack + * DieID[0] = XOR of addr{12, 20, 27, 34, 41 } + * DieID[1] = XOR of addr{13, 21, 28, 35, 42 } + */ +static int mi300_dehash_addr(struct addr_ctx *ctx) +{ + bool hash_ctl_4k, hash_ctl_64k, hash_ctl_2M, hash_ctl_1G, hash_ctl_1T; + bool hashed_bit, intlv_bit, test_bit; + u8 num_intlv_bits, base_bit, i; + + if (!map_bits_valid(ctx, 8, 8, 4, 1)) + return -EINVAL; + + hash_ctl_4k = FIELD_GET(DF4p5_HASH_CTL_4K, ctx->map.ctl); + hash_ctl_64k = FIELD_GET(DF4_HASH_CTL_64K, ctx->map.ctl); + hash_ctl_2M = FIELD_GET(DF4_HASH_CTL_2M, ctx->map.ctl); + hash_ctl_1G = FIELD_GET(DF4_HASH_CTL_1G, ctx->map.ctl); + hash_ctl_1T = FIELD_GET(DF4p5_HASH_CTL_1T, ctx->map.ctl); + + /* Channel bits */ + num_intlv_bits = ilog2(ctx->map.num_intlv_chan); + + for (i = 0; i < num_intlv_bits; i++) { + base_bit = 8 + i; + + /* COH_ST_Select[4] jumps to a base bit of 14. */ + if (i == 4) + base_bit = 14; + + intlv_bit = BIT_ULL(base_bit) & ctx->ret_addr; + + hashed_bit = intlv_bit; + + /* 4k hash bit only applies to the first 3 bits. */ + if (i <= 2) { + test_bit = BIT_ULL(12 + i) & ctx->ret_addr; + hashed_bit ^= test_bit & hash_ctl_4k; + } + + /* Use temporary 'test_bit' value to avoid Sparse warnings. */ + test_bit = BIT_ULL(15 + i) & ctx->ret_addr; + hashed_bit ^= test_bit & hash_ctl_64k; + test_bit = BIT_ULL(22 + i) & ctx->ret_addr; + hashed_bit ^= test_bit & hash_ctl_2M; + test_bit = BIT_ULL(29 + i) & ctx->ret_addr; + hashed_bit ^= test_bit & hash_ctl_1G; + test_bit = BIT_ULL(36 + i) & ctx->ret_addr; + hashed_bit ^= test_bit & hash_ctl_1T; + test_bit = BIT_ULL(43 + i) & ctx->ret_addr; + hashed_bit ^= test_bit & hash_ctl_1T; + + if (hashed_bit != intlv_bit) + ctx->ret_addr ^= BIT_ULL(base_bit); + } + + /* Die bits */ + num_intlv_bits = ilog2(ctx->map.num_intlv_dies); + + for (i = 0; i < num_intlv_bits; i++) { + base_bit = 12 + i; + + intlv_bit = BIT_ULL(base_bit) & ctx->ret_addr; + + hashed_bit = intlv_bit; + + test_bit = BIT_ULL(20 + i) & ctx->ret_addr; + hashed_bit ^= test_bit & hash_ctl_64k; + test_bit = BIT_ULL(27 + i) & ctx->ret_addr; + hashed_bit ^= test_bit & hash_ctl_2M; + test_bit = BIT_ULL(34 + i) & ctx->ret_addr; + hashed_bit ^= test_bit & hash_ctl_1G; + test_bit = BIT_ULL(41 + i) & ctx->ret_addr; + hashed_bit ^= test_bit & hash_ctl_1T; + + if (hashed_bit != intlv_bit) + ctx->ret_addr ^= BIT_ULL(base_bit); + } + + return 0; +} + +int dehash_address(struct addr_ctx *ctx) +{ + switch (ctx->map.intlv_mode) { + /* No hashing cases. */ + case NONE: + case NOHASH_2CHAN: + case NOHASH_4CHAN: + case NOHASH_8CHAN: + case NOHASH_16CHAN: + case NOHASH_32CHAN: + /* Hashing bits handled earlier during CS ID calculation. */ + case DF4_NPS4_3CHAN_HASH: + case DF4_NPS2_5CHAN_HASH: + case DF4_NPS2_6CHAN_HASH: + case DF4_NPS1_10CHAN_HASH: + case DF4_NPS1_12CHAN_HASH: + case DF4p5_NPS2_6CHAN_1K_HASH: + case DF4p5_NPS2_6CHAN_2K_HASH: + case DF4p5_NPS1_10CHAN_1K_HASH: + case DF4p5_NPS1_10CHAN_2K_HASH: + case DF4p5_NPS1_12CHAN_1K_HASH: + case DF4p5_NPS1_12CHAN_2K_HASH: + case DF4p5_NPS0_24CHAN_1K_HASH: + case DF4p5_NPS0_24CHAN_2K_HASH: + /* No hash physical address bits, so nothing to do. */ + case DF4p5_NPS4_3CHAN_1K_HASH: + case DF4p5_NPS4_3CHAN_2K_HASH: + case DF4p5_NPS2_5CHAN_1K_HASH: + case DF4p5_NPS2_5CHAN_2K_HASH: + return 0; + + case DF2_2CHAN_HASH: + return df2_dehash_addr(ctx); + + case DF3_COD4_2CHAN_HASH: + case DF3_COD2_4CHAN_HASH: + case DF3_COD1_8CHAN_HASH: + return df3_dehash_addr(ctx); + + case DF3_6CHAN: + return df3_6chan_dehash_addr(ctx); + + case DF4_NPS4_2CHAN_HASH: + case DF4_NPS2_4CHAN_HASH: + case DF4_NPS1_8CHAN_HASH: + return df4_dehash_addr(ctx); + + case DF4p5_NPS4_2CHAN_1K_HASH: + case DF4p5_NPS4_2CHAN_2K_HASH: + case DF4p5_NPS2_4CHAN_2K_HASH: + case DF4p5_NPS2_4CHAN_1K_HASH: + case DF4p5_NPS1_8CHAN_1K_HASH: + case DF4p5_NPS1_8CHAN_2K_HASH: + case DF4p5_NPS1_16CHAN_1K_HASH: + case DF4p5_NPS1_16CHAN_2K_HASH: + return df4p5_dehash_addr(ctx); + + case MI3_HASH_8CHAN: + case MI3_HASH_16CHAN: + case MI3_HASH_32CHAN: + return mi300_dehash_addr(ctx); + + default: + atl_debug_on_bad_intlv_mode(ctx); + return -EINVAL; + } +} diff --git a/drivers/ras/amd/atl/denormalize.c b/drivers/ras/amd/atl/denormalize.c new file mode 100644 index 000000000000..e279224288d6 --- /dev/null +++ b/drivers/ras/amd/atl/denormalize.c @@ -0,0 +1,718 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * AMD Address Translation Library + * + * denormalize.c : Functions to account for interleaving bits + * + * Copyright (c) 2023, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Author: Yazen Ghannam <Yazen.Ghannam@amd.com> + */ + +#include "internal.h" + +/* + * Returns the Destination Fabric ID. This is the first (lowest) + * COH_ST Fabric ID used within a DRAM Address map. + */ +static u16 get_dst_fabric_id(struct addr_ctx *ctx) +{ + switch (df_cfg.rev) { + case DF2: return FIELD_GET(DF2_DST_FABRIC_ID, ctx->map.limit); + case DF3: return FIELD_GET(DF3_DST_FABRIC_ID, ctx->map.limit); + case DF3p5: return FIELD_GET(DF3p5_DST_FABRIC_ID, ctx->map.limit); + case DF4: return FIELD_GET(DF4_DST_FABRIC_ID, ctx->map.ctl); + case DF4p5: return FIELD_GET(DF4p5_DST_FABRIC_ID, ctx->map.ctl); + default: + atl_debug_on_bad_df_rev(); + return 0; + } +} + +/* + * Make a contiguous gap in address for N bits starting at bit P. + * + * Example: + * address bits: [20:0] + * # of interleave bits (n): 3 + * starting interleave bit (p): 8 + * + * expanded address bits: [20+n : n+p][n+p-1 : p][p-1 : 0] + * [23 : 11][10 : 8][7 : 0] + */ +static u64 make_space_for_coh_st_id_at_intlv_bit(struct addr_ctx *ctx) +{ + return expand_bits(ctx->map.intlv_bit_pos, + ctx->map.total_intlv_bits, + ctx->ret_addr); +} + +/* + * Make two gaps in address for N bits. + * First gap is a single bit at bit P. + * Second gap is the remaining N-1 bits at bit 12. + * + * Example: + * address bits: [20:0] + * # of interleave bits (n): 3 + * starting interleave bit (p): 8 + * + * First gap + * expanded address bits: [20+1 : p+1][p][p-1 : 0] + * [21 : 9][8][7 : 0] + * + * Second gap uses result from first. + * r = n - 1; remaining interleave bits + * expanded address bits: [21+r : 12+r][12+r-1: 12][11 : 0] + * [23 : 14][13 : 12][11 : 0] + */ +static u64 make_space_for_coh_st_id_split_2_1(struct addr_ctx *ctx) +{ + /* Make a single space at the interleave bit. */ + u64 denorm_addr = expand_bits(ctx->map.intlv_bit_pos, 1, ctx->ret_addr); + + /* Done if there's only a single interleave bit. */ + if (ctx->map.total_intlv_bits <= 1) + return denorm_addr; + + /* Make spaces for the remaining interleave bits starting at bit 12. */ + return expand_bits(12, ctx->map.total_intlv_bits - 1, denorm_addr); +} + +/* + * Make space for CS ID at bits [14:8] as follows: + * + * 8 channels -> bits [10:8] + * 16 channels -> bits [11:8] + * 32 channels -> bits [14,11:8] + * + * 1 die -> N/A + * 2 dies -> bit [12] + * 4 dies -> bits [13:12] + */ +static u64 make_space_for_coh_st_id_mi300(struct addr_ctx *ctx) +{ + u8 num_intlv_bits = ilog2(ctx->map.num_intlv_chan); + u64 denorm_addr; + + if (ctx->map.intlv_bit_pos != 8) { + pr_debug("Invalid interleave bit: %u", ctx->map.intlv_bit_pos); + return ~0ULL; + } + + /* Channel bits. Covers up to 4 bits at [11:8]. */ + denorm_addr = expand_bits(8, min(num_intlv_bits, 4), ctx->ret_addr); + + /* Die bits. Always starts at [12]. */ + denorm_addr = expand_bits(12, ilog2(ctx->map.num_intlv_dies), denorm_addr); + + /* Additional channel bit at [14]. */ + if (num_intlv_bits > 4) + denorm_addr = expand_bits(14, 1, denorm_addr); + + return denorm_addr; +} + +/* + * Take the current calculated address and shift enough bits in the middle + * to make a gap where the interleave bits will be inserted. + */ +static u64 make_space_for_coh_st_id(struct addr_ctx *ctx) +{ + switch (ctx->map.intlv_mode) { + case NOHASH_2CHAN: + case NOHASH_4CHAN: + case NOHASH_8CHAN: + case NOHASH_16CHAN: + case NOHASH_32CHAN: + case DF2_2CHAN_HASH: + return make_space_for_coh_st_id_at_intlv_bit(ctx); + + case DF3_COD4_2CHAN_HASH: + case DF3_COD2_4CHAN_HASH: + case DF3_COD1_8CHAN_HASH: + case DF4_NPS4_2CHAN_HASH: + case DF4_NPS2_4CHAN_HASH: + case DF4_NPS1_8CHAN_HASH: + case DF4p5_NPS4_2CHAN_1K_HASH: + case DF4p5_NPS4_2CHAN_2K_HASH: + case DF4p5_NPS2_4CHAN_2K_HASH: + case DF4p5_NPS1_8CHAN_2K_HASH: + case DF4p5_NPS1_16CHAN_2K_HASH: + return make_space_for_coh_st_id_split_2_1(ctx); + + case MI3_HASH_8CHAN: + case MI3_HASH_16CHAN: + case MI3_HASH_32CHAN: + return make_space_for_coh_st_id_mi300(ctx); + + default: + atl_debug_on_bad_intlv_mode(ctx); + return ~0ULL; + } +} + +static u16 get_coh_st_id_df2(struct addr_ctx *ctx) +{ + u8 num_socket_intlv_bits = ilog2(ctx->map.num_intlv_sockets); + u8 num_die_intlv_bits = ilog2(ctx->map.num_intlv_dies); + u8 num_intlv_bits; + u16 coh_st_id, mask; + + coh_st_id = ctx->coh_st_fabric_id - get_dst_fabric_id(ctx); + + /* Channel interleave bits */ + num_intlv_bits = order_base_2(ctx->map.num_intlv_chan); + mask = GENMASK(num_intlv_bits - 1, 0); + coh_st_id &= mask; + + /* Die interleave bits */ + if (num_die_intlv_bits) { + u16 die_bits; + + mask = GENMASK(num_die_intlv_bits - 1, 0); + die_bits = ctx->coh_st_fabric_id & df_cfg.die_id_mask; + die_bits >>= df_cfg.die_id_shift; + + coh_st_id |= (die_bits & mask) << num_intlv_bits; + num_intlv_bits += num_die_intlv_bits; + } + + /* Socket interleave bits */ + if (num_socket_intlv_bits) { + u16 socket_bits; + + mask = GENMASK(num_socket_intlv_bits - 1, 0); + socket_bits = ctx->coh_st_fabric_id & df_cfg.socket_id_mask; + socket_bits >>= df_cfg.socket_id_shift; + + coh_st_id |= (socket_bits & mask) << num_intlv_bits; + } + + return coh_st_id; +} + +static u16 get_coh_st_id_df4(struct addr_ctx *ctx) +{ + /* + * Start with the original component mask and the number of interleave + * bits for the channels in this map. + */ + u8 num_intlv_bits = ilog2(ctx->map.num_intlv_chan); + u16 mask = df_cfg.component_id_mask; + + u16 socket_bits; + + /* Set the derived Coherent Station ID to the input Coherent Station Fabric ID. */ + u16 coh_st_id = ctx->coh_st_fabric_id & mask; + + /* + * Subtract the "base" Destination Fabric ID. + * This accounts for systems with disabled Coherent Stations. + */ + coh_st_id -= get_dst_fabric_id(ctx) & mask; + + /* + * Generate and use a new mask based on the number of bits + * needed for channel interleaving in this map. + */ + mask = GENMASK(num_intlv_bits - 1, 0); + coh_st_id &= mask; + + /* Done if socket interleaving is not enabled. */ + if (ctx->map.num_intlv_sockets <= 1) + return coh_st_id; + + /* + * Figure out how many bits are needed for the number of + * interleaved sockets. And shift the derived Coherent Station ID to account + * for these. + */ + num_intlv_bits = ilog2(ctx->map.num_intlv_sockets); + coh_st_id <<= num_intlv_bits; + + /* Generate a new mask for the socket interleaving bits. */ + mask = GENMASK(num_intlv_bits - 1, 0); + + /* Get the socket interleave bits from the original Coherent Station Fabric ID. */ + socket_bits = (ctx->coh_st_fabric_id & df_cfg.socket_id_mask) >> df_cfg.socket_id_shift; + + /* Apply the appropriate socket bits to the derived Coherent Station ID. */ + coh_st_id |= socket_bits & mask; + + return coh_st_id; +} + +/* + * MI300 hash has: + * (C)hannel[3:0] = coh_st_id[3:0] + * (S)tack[0] = coh_st_id[4] + * (D)ie[1:0] = coh_st_id[6:5] + * + * Hashed coh_st_id is swizzled so that Stack bit is at the end. + * coh_st_id = SDDCCCC + */ +static u16 get_coh_st_id_mi300(struct addr_ctx *ctx) +{ + u8 channel_bits, die_bits, stack_bit; + u16 die_id; + + /* Subtract the "base" Destination Fabric ID. */ + ctx->coh_st_fabric_id -= get_dst_fabric_id(ctx); + + die_id = (ctx->coh_st_fabric_id & df_cfg.die_id_mask) >> df_cfg.die_id_shift; + + channel_bits = FIELD_GET(GENMASK(3, 0), ctx->coh_st_fabric_id); + stack_bit = FIELD_GET(BIT(4), ctx->coh_st_fabric_id) << 6; + die_bits = die_id << 4; + + return stack_bit | die_bits | channel_bits; +} + +/* + * Derive the correct Coherent Station ID that represents the interleave bits + * used within the system physical address. This accounts for the + * interleave mode, number of interleaved channels/dies/sockets, and + * other system/mode-specific bit swizzling. + * + * Returns: Coherent Station ID on success. + * All bits set on error. + */ +static u16 calculate_coh_st_id(struct addr_ctx *ctx) +{ + switch (ctx->map.intlv_mode) { + case NOHASH_2CHAN: + case NOHASH_4CHAN: + case NOHASH_8CHAN: + case NOHASH_16CHAN: + case NOHASH_32CHAN: + case DF3_COD4_2CHAN_HASH: + case DF3_COD2_4CHAN_HASH: + case DF3_COD1_8CHAN_HASH: + case DF2_2CHAN_HASH: + return get_coh_st_id_df2(ctx); + + case DF4_NPS4_2CHAN_HASH: + case DF4_NPS2_4CHAN_HASH: + case DF4_NPS1_8CHAN_HASH: + case DF4p5_NPS4_2CHAN_1K_HASH: + case DF4p5_NPS4_2CHAN_2K_HASH: + case DF4p5_NPS2_4CHAN_2K_HASH: + case DF4p5_NPS1_8CHAN_2K_HASH: + case DF4p5_NPS1_16CHAN_2K_HASH: + return get_coh_st_id_df4(ctx); + + case MI3_HASH_8CHAN: + case MI3_HASH_16CHAN: + case MI3_HASH_32CHAN: + return get_coh_st_id_mi300(ctx); + + /* COH_ST ID is simply the COH_ST Fabric ID adjusted by the Destination Fabric ID. */ + case DF4p5_NPS2_4CHAN_1K_HASH: + case DF4p5_NPS1_8CHAN_1K_HASH: + case DF4p5_NPS1_16CHAN_1K_HASH: + return ctx->coh_st_fabric_id - get_dst_fabric_id(ctx); + + default: + atl_debug_on_bad_intlv_mode(ctx); + return ~0; + } +} + +static u64 insert_coh_st_id_at_intlv_bit(struct addr_ctx *ctx, u64 denorm_addr, u16 coh_st_id) +{ + return denorm_addr | (coh_st_id << ctx->map.intlv_bit_pos); +} + +static u64 insert_coh_st_id_split_2_1(struct addr_ctx *ctx, u64 denorm_addr, u16 coh_st_id) +{ + /* Insert coh_st_id[0] at the interleave bit. */ + denorm_addr |= (coh_st_id & BIT(0)) << ctx->map.intlv_bit_pos; + + /* Insert coh_st_id[2:1] at bit 12. */ + denorm_addr |= (coh_st_id & GENMASK(2, 1)) << 11; + + return denorm_addr; +} + +static u64 insert_coh_st_id_split_2_2(struct addr_ctx *ctx, u64 denorm_addr, u16 coh_st_id) +{ + /* Insert coh_st_id[1:0] at bit 8. */ + denorm_addr |= (coh_st_id & GENMASK(1, 0)) << 8; + + /* + * Insert coh_st_id[n:2] at bit 12. 'n' could be 2 or 3. + * Grab both because bit 3 will be clear if unused. + */ + denorm_addr |= (coh_st_id & GENMASK(3, 2)) << 10; + + return denorm_addr; +} + +static u64 insert_coh_st_id(struct addr_ctx *ctx, u64 denorm_addr, u16 coh_st_id) +{ + switch (ctx->map.intlv_mode) { + case NOHASH_2CHAN: + case NOHASH_4CHAN: + case NOHASH_8CHAN: + case NOHASH_16CHAN: + case NOHASH_32CHAN: + case MI3_HASH_8CHAN: + case MI3_HASH_16CHAN: + case MI3_HASH_32CHAN: + case DF2_2CHAN_HASH: + return insert_coh_st_id_at_intlv_bit(ctx, denorm_addr, coh_st_id); + + case DF3_COD4_2CHAN_HASH: + case DF3_COD2_4CHAN_HASH: + case DF3_COD1_8CHAN_HASH: + case DF4_NPS4_2CHAN_HASH: + case DF4_NPS2_4CHAN_HASH: + case DF4_NPS1_8CHAN_HASH: + case DF4p5_NPS4_2CHAN_1K_HASH: + case DF4p5_NPS4_2CHAN_2K_HASH: + case DF4p5_NPS2_4CHAN_2K_HASH: + case DF4p5_NPS1_8CHAN_2K_HASH: + case DF4p5_NPS1_16CHAN_2K_HASH: + return insert_coh_st_id_split_2_1(ctx, denorm_addr, coh_st_id); + + case DF4p5_NPS2_4CHAN_1K_HASH: + case DF4p5_NPS1_8CHAN_1K_HASH: + case DF4p5_NPS1_16CHAN_1K_HASH: + return insert_coh_st_id_split_2_2(ctx, denorm_addr, coh_st_id); + + default: + atl_debug_on_bad_intlv_mode(ctx); + return ~0ULL; + } +} + +/* + * MI300 systems have a fixed, hardware-defined physical-to-logical + * Coherent Station mapping. The Remap registers are not used. + */ +static const u16 phy_to_log_coh_st_map_mi300[] = { + 12, 13, 14, 15, + 8, 9, 10, 11, + 4, 5, 6, 7, + 0, 1, 2, 3, + 28, 29, 30, 31, + 24, 25, 26, 27, + 20, 21, 22, 23, + 16, 17, 18, 19, +}; + +static u16 get_logical_coh_st_fabric_id_mi300(struct addr_ctx *ctx) +{ + if (ctx->inst_id >= ARRAY_SIZE(phy_to_log_coh_st_map_mi300)) { + atl_debug(ctx, "Instance ID out of range"); + return ~0; + } + + return phy_to_log_coh_st_map_mi300[ctx->inst_id] | (ctx->node_id << df_cfg.node_id_shift); +} + +static u16 get_logical_coh_st_fabric_id(struct addr_ctx *ctx) +{ + u16 component_id, log_fabric_id; + + /* Start with the physical COH_ST Fabric ID. */ + u16 phys_fabric_id = ctx->coh_st_fabric_id; + + if (df_cfg.rev == DF4p5 && df_cfg.flags.heterogeneous) + return get_logical_coh_st_fabric_id_mi300(ctx); + + /* Skip logical ID lookup if remapping is disabled. */ + if (!FIELD_GET(DF4_REMAP_EN, ctx->map.ctl) && + ctx->map.intlv_mode != DF3_6CHAN) + return phys_fabric_id; + + /* Mask off the Node ID bits to get the "local" Component ID. */ + component_id = phys_fabric_id & df_cfg.component_id_mask; + + /* + * Search the list of logical Component IDs for the one that + * matches this physical Component ID. + */ + for (log_fabric_id = 0; log_fabric_id < MAX_COH_ST_CHANNELS; log_fabric_id++) { + if (ctx->map.remap_array[log_fabric_id] == component_id) + break; + } + + if (log_fabric_id == MAX_COH_ST_CHANNELS) + atl_debug(ctx, "COH_ST remap entry not found for 0x%x", + log_fabric_id); + + /* Get the Node ID bits from the physical and apply to the logical. */ + return (phys_fabric_id & df_cfg.node_id_mask) | log_fabric_id; +} + +static int denorm_addr_common(struct addr_ctx *ctx) +{ + u64 denorm_addr; + u16 coh_st_id; + + /* + * Convert the original physical COH_ST Fabric ID to a logical value. + * This is required for non-power-of-two and other interleaving modes. + */ + ctx->coh_st_fabric_id = get_logical_coh_st_fabric_id(ctx); + + denorm_addr = make_space_for_coh_st_id(ctx); + coh_st_id = calculate_coh_st_id(ctx); + ctx->ret_addr = insert_coh_st_id(ctx, denorm_addr, coh_st_id); + return 0; +} + +static int denorm_addr_df3_6chan(struct addr_ctx *ctx) +{ + u16 coh_st_id = ctx->coh_st_fabric_id & df_cfg.component_id_mask; + u8 total_intlv_bits = ctx->map.total_intlv_bits; + u8 low_bit, intlv_bit = ctx->map.intlv_bit_pos; + u64 msb_intlv_bits, temp_addr_a, temp_addr_b; + u8 np2_bits = ctx->map.np2_bits; + + if (ctx->map.intlv_mode != DF3_6CHAN) + return -EINVAL; + + /* + * 'np2_bits' holds the number of bits needed to cover the + * amount of memory (rounded up) in this map using 64K chunks. + * + * Example: + * Total memory in map: 6GB + * Rounded up to next power-of-2: 8GB + * Number of 64K chunks: 0x20000 + * np2_bits = log2(# of chunks): 17 + * + * Get the two most-significant interleave bits from the + * input address based on the following: + * + * [15 + np2_bits - total_intlv_bits : 14 + np2_bits - total_intlv_bits] + */ + low_bit = 14 + np2_bits - total_intlv_bits; + msb_intlv_bits = ctx->ret_addr >> low_bit; + msb_intlv_bits &= 0x3; + + /* + * If MSB are 11b, then logical COH_ST ID is 6 or 7. + * Need to adjust based on the mod3 result. + */ + if (msb_intlv_bits == 3) { + u8 addr_mod, phys_addr_msb, msb_coh_st_id; + + /* Get the remaining interleave bits from the input address. */ + temp_addr_b = GENMASK_ULL(low_bit - 1, intlv_bit) & ctx->ret_addr; + temp_addr_b >>= intlv_bit; + + /* Calculate the logical COH_ST offset based on mod3. */ + addr_mod = temp_addr_b % 3; + + /* Get COH_ST ID bits [2:1]. */ + msb_coh_st_id = (coh_st_id >> 1) & 0x3; + + /* Get the bit that starts the physical address bits. */ + phys_addr_msb = (intlv_bit + np2_bits + 1); + phys_addr_msb &= BIT(0); + phys_addr_msb++; + phys_addr_msb *= 3 - addr_mod + msb_coh_st_id; + phys_addr_msb %= 3; + + /* Move the physical address MSB to the correct place. */ + temp_addr_b |= phys_addr_msb << (low_bit - total_intlv_bits - intlv_bit); + + /* Generate a new COH_ST ID as follows: coh_st_id = [1, 1, coh_st_id[0]] */ + coh_st_id &= BIT(0); + coh_st_id |= GENMASK(2, 1); + } else { + temp_addr_b = GENMASK_ULL(63, intlv_bit) & ctx->ret_addr; + temp_addr_b >>= intlv_bit; + } + + temp_addr_a = GENMASK_ULL(intlv_bit - 1, 0) & ctx->ret_addr; + temp_addr_b <<= intlv_bit + total_intlv_bits; + + ctx->ret_addr = temp_addr_a | temp_addr_b; + ctx->ret_addr |= coh_st_id << intlv_bit; + return 0; +} + +static int denorm_addr_df4_np2(struct addr_ctx *ctx) +{ + bool hash_ctl_64k, hash_ctl_2M, hash_ctl_1G; + u16 group, group_offset, log_coh_st_offset; + unsigned int mod_value, shift_value; + u16 mask = df_cfg.component_id_mask; + u64 temp_addr_a, temp_addr_b; + bool hash_pa8, hashed_bit; + + switch (ctx->map.intlv_mode) { + case DF4_NPS4_3CHAN_HASH: + mod_value = 3; + shift_value = 13; + break; + case DF4_NPS2_6CHAN_HASH: + mod_value = 3; + shift_value = 12; + break; + case DF4_NPS1_12CHAN_HASH: + mod_value = 3; + shift_value = 11; + break; + case DF4_NPS2_5CHAN_HASH: + mod_value = 5; + shift_value = 13; + break; + case DF4_NPS1_10CHAN_HASH: + mod_value = 5; + shift_value = 12; + break; + default: + atl_debug_on_bad_intlv_mode(ctx); + return -EINVAL; + }; + + if (ctx->map.num_intlv_sockets == 1) { + hash_pa8 = BIT_ULL(shift_value) & ctx->ret_addr; + temp_addr_a = remove_bits(shift_value, shift_value, ctx->ret_addr); + } else { + hash_pa8 = ctx->coh_st_fabric_id & df_cfg.socket_id_mask; + temp_addr_a = ctx->ret_addr; + } + + /* Make a gap for the real bit [8]. */ + temp_addr_a = expand_bits(8, 1, temp_addr_a); + + /* Make an additional gap for bits [13:12], as appropriate.*/ + if (ctx->map.intlv_mode == DF4_NPS2_6CHAN_HASH || + ctx->map.intlv_mode == DF4_NPS1_10CHAN_HASH) { + temp_addr_a = expand_bits(13, 1, temp_addr_a); + } else if (ctx->map.intlv_mode == DF4_NPS1_12CHAN_HASH) { + temp_addr_a = expand_bits(12, 2, temp_addr_a); + } + + /* Keep bits [13:0]. */ + temp_addr_a &= GENMASK_ULL(13, 0); + + /* Get the appropriate high bits. */ + shift_value += 1 - ilog2(ctx->map.num_intlv_sockets); + temp_addr_b = GENMASK_ULL(63, shift_value) & ctx->ret_addr; + temp_addr_b >>= shift_value; + temp_addr_b *= mod_value; + + /* + * Coherent Stations are divided into groups. + * + * Multiples of 3 (mod3) are divided into quadrants. + * e.g. NP4_3CHAN -> [0, 1, 2] [6, 7, 8] + * [3, 4, 5] [9, 10, 11] + * + * Multiples of 5 (mod5) are divided into sides. + * e.g. NP2_5CHAN -> [0, 1, 2, 3, 4] [5, 6, 7, 8, 9] + */ + + /* + * Calculate the logical offset for the COH_ST within its DRAM Address map. + * e.g. if map includes [5, 6, 7, 8, 9] and target instance is '8', then + * log_coh_st_offset = 8 - 5 = 3 + */ + log_coh_st_offset = (ctx->coh_st_fabric_id & mask) - (get_dst_fabric_id(ctx) & mask); + + /* + * Figure out the group number. + * + * Following above example, + * log_coh_st_offset = 3 + * mod_value = 5 + * group = 3 / 5 = 0 + */ + group = log_coh_st_offset / mod_value; + + /* + * Figure out the offset within the group. + * + * Following above example, + * log_coh_st_offset = 3 + * mod_value = 5 + * group_offset = 3 % 5 = 3 + */ + group_offset = log_coh_st_offset % mod_value; + + /* Adjust group_offset if the hashed bit [8] is set. */ + if (hash_pa8) { + if (!group_offset) + group_offset = mod_value - 1; + else + group_offset--; + } + + /* Add in the group offset to the high bits. */ + temp_addr_b += group_offset; + + /* Shift the high bits to the proper starting position. */ + temp_addr_b <<= 14; + + /* Combine the high and low bits together. */ + ctx->ret_addr = temp_addr_a | temp_addr_b; + + /* Account for hashing here instead of in dehash_address(). */ + hash_ctl_64k = FIELD_GET(DF4_HASH_CTL_64K, ctx->map.ctl); + hash_ctl_2M = FIELD_GET(DF4_HASH_CTL_2M, ctx->map.ctl); + hash_ctl_1G = FIELD_GET(DF4_HASH_CTL_1G, ctx->map.ctl); + + hashed_bit = !!hash_pa8; + hashed_bit ^= FIELD_GET(BIT_ULL(14), ctx->ret_addr); + hashed_bit ^= FIELD_GET(BIT_ULL(16), ctx->ret_addr) & hash_ctl_64k; + hashed_bit ^= FIELD_GET(BIT_ULL(21), ctx->ret_addr) & hash_ctl_2M; + hashed_bit ^= FIELD_GET(BIT_ULL(30), ctx->ret_addr) & hash_ctl_1G; + + ctx->ret_addr |= hashed_bit << 8; + + /* Done for 3 and 5 channel. */ + if (ctx->map.intlv_mode == DF4_NPS4_3CHAN_HASH || + ctx->map.intlv_mode == DF4_NPS2_5CHAN_HASH) + return 0; + + /* Select the proper 'group' bit to use for Bit 13. */ + if (ctx->map.intlv_mode == DF4_NPS1_12CHAN_HASH) + hashed_bit = !!(group & BIT(1)); + else + hashed_bit = group & BIT(0); + + hashed_bit ^= FIELD_GET(BIT_ULL(18), ctx->ret_addr) & hash_ctl_64k; + hashed_bit ^= FIELD_GET(BIT_ULL(23), ctx->ret_addr) & hash_ctl_2M; + hashed_bit ^= FIELD_GET(BIT_ULL(32), ctx->ret_addr) & hash_ctl_1G; + + ctx->ret_addr |= hashed_bit << 13; + + /* Done for 6 and 10 channel. */ + if (ctx->map.intlv_mode != DF4_NPS1_12CHAN_HASH) + return 0; + + hashed_bit = group & BIT(0); + hashed_bit ^= FIELD_GET(BIT_ULL(17), ctx->ret_addr) & hash_ctl_64k; + hashed_bit ^= FIELD_GET(BIT_ULL(22), ctx->ret_addr) & hash_ctl_2M; + hashed_bit ^= FIELD_GET(BIT_ULL(31), ctx->ret_addr) & hash_ctl_1G; + + ctx->ret_addr |= hashed_bit << 12; + return 0; +} + +int denormalize_address(struct addr_ctx *ctx) +{ + switch (ctx->map.intlv_mode) { + case NONE: + return 0; + case DF4_NPS4_3CHAN_HASH: + case DF4_NPS2_6CHAN_HASH: + case DF4_NPS1_12CHAN_HASH: + case DF4_NPS2_5CHAN_HASH: + case DF4_NPS1_10CHAN_HASH: + return denorm_addr_df4_np2(ctx); + case DF3_6CHAN: + return denorm_addr_df3_6chan(ctx); + default: + return denorm_addr_common(ctx); + } +} diff --git a/drivers/ras/amd/atl/internal.h b/drivers/ras/amd/atl/internal.h new file mode 100644 index 000000000000..5de69e0bb0f9 --- /dev/null +++ b/drivers/ras/amd/atl/internal.h @@ -0,0 +1,306 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * AMD Address Translation Library + * + * internal.h : Helper functions and common defines + * + * Copyright (c) 2023, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Author: Yazen Ghannam <Yazen.Ghannam@amd.com> + */ + +#ifndef __AMD_ATL_INTERNAL_H__ +#define __AMD_ATL_INTERNAL_H__ + +#include <linux/bitfield.h> +#include <linux/bitops.h> +#include <linux/ras.h> + +#include <asm/amd_nb.h> + +#include "reg_fields.h" + +/* Maximum possible number of Coherent Stations within a single Data Fabric. */ +#define MAX_COH_ST_CHANNELS 32 + +/* PCI ID for Zen4 Server DF Function 0. */ +#define DF_FUNC0_ID_ZEN4_SERVER 0x14AD1022 + +/* PCI IDs for MI300 DF Function 0. */ +#define DF_FUNC0_ID_MI300 0x15281022 + +/* Shift needed for adjusting register values to true values. */ +#define DF_DRAM_BASE_LIMIT_LSB 28 +#define MI300_DRAM_LIMIT_LSB 20 + +enum df_revisions { + UNKNOWN, + DF2, + DF3, + DF3p5, + DF4, + DF4p5, +}; + +/* These are mapped 1:1 to the hardware values. Special cases are set at > 0x20. */ +enum intlv_modes { + NONE = 0x00, + NOHASH_2CHAN = 0x01, + NOHASH_4CHAN = 0x03, + NOHASH_8CHAN = 0x05, + DF3_6CHAN = 0x06, + NOHASH_16CHAN = 0x07, + NOHASH_32CHAN = 0x08, + DF3_COD4_2CHAN_HASH = 0x0C, + DF3_COD2_4CHAN_HASH = 0x0D, + DF3_COD1_8CHAN_HASH = 0x0E, + DF4_NPS4_2CHAN_HASH = 0x10, + DF4_NPS2_4CHAN_HASH = 0x11, + DF4_NPS1_8CHAN_HASH = 0x12, + DF4_NPS4_3CHAN_HASH = 0x13, + DF4_NPS2_6CHAN_HASH = 0x14, + DF4_NPS1_12CHAN_HASH = 0x15, + DF4_NPS2_5CHAN_HASH = 0x16, + DF4_NPS1_10CHAN_HASH = 0x17, + MI3_HASH_8CHAN = 0x18, + MI3_HASH_16CHAN = 0x19, + MI3_HASH_32CHAN = 0x1A, + DF2_2CHAN_HASH = 0x21, + /* DF4.5 modes are all IntLvNumChan + 0x20 */ + DF4p5_NPS1_16CHAN_1K_HASH = 0x2C, + DF4p5_NPS0_24CHAN_1K_HASH = 0x2E, + DF4p5_NPS4_2CHAN_1K_HASH = 0x30, + DF4p5_NPS2_4CHAN_1K_HASH = 0x31, + DF4p5_NPS1_8CHAN_1K_HASH = 0x32, + DF4p5_NPS4_3CHAN_1K_HASH = 0x33, + DF4p5_NPS2_6CHAN_1K_HASH = 0x34, + DF4p5_NPS1_12CHAN_1K_HASH = 0x35, + DF4p5_NPS2_5CHAN_1K_HASH = 0x36, + DF4p5_NPS1_10CHAN_1K_HASH = 0x37, + DF4p5_NPS4_2CHAN_2K_HASH = 0x40, + DF4p5_NPS2_4CHAN_2K_HASH = 0x41, + DF4p5_NPS1_8CHAN_2K_HASH = 0x42, + DF4p5_NPS1_16CHAN_2K_HASH = 0x43, + DF4p5_NPS4_3CHAN_2K_HASH = 0x44, + DF4p5_NPS2_6CHAN_2K_HASH = 0x45, + DF4p5_NPS1_12CHAN_2K_HASH = 0x46, + DF4p5_NPS0_24CHAN_2K_HASH = 0x47, + DF4p5_NPS2_5CHAN_2K_HASH = 0x48, + DF4p5_NPS1_10CHAN_2K_HASH = 0x49, +}; + +struct df_flags { + __u8 legacy_ficaa : 1, + socket_id_shift_quirk : 1, + heterogeneous : 1, + __reserved_0 : 5; +}; + +struct df_config { + enum df_revisions rev; + + /* + * These masks operate on the 16-bit Coherent Station IDs, + * e.g. Instance, Fabric, Destination, etc. + */ + u16 component_id_mask; + u16 die_id_mask; + u16 node_id_mask; + u16 socket_id_mask; + + /* + * Least-significant bit of Node ID portion of the + * system-wide Coherent Station Fabric ID. + */ + u8 node_id_shift; + + /* + * Least-significant bit of Die portion of the Node ID. + * Adjusted to include the Node ID shift in order to apply + * to the Coherent Station Fabric ID. + */ + u8 die_id_shift; + + /* + * Least-significant bit of Socket portion of the Node ID. + * Adjusted to include the Node ID shift in order to apply + * to the Coherent Station Fabric ID. + */ + u8 socket_id_shift; + + /* Number of DRAM Address maps visible in a Coherent Station. */ + u8 num_coh_st_maps; + + /* Global flags to handle special cases. */ + struct df_flags flags; +}; + +extern struct df_config df_cfg; + +struct dram_addr_map { + /* + * Each DRAM Address Map can operate independently + * in different interleaving modes. + */ + enum intlv_modes intlv_mode; + + /* System-wide number for this address map. */ + u8 num; + + /* Raw register values */ + u32 base; + u32 limit; + u32 ctl; + u32 intlv; + + /* + * Logical to Physical Coherent Station Remapping array + * + * Index: Logical Coherent Station Instance ID + * Value: Physical Coherent Station Instance ID + * + * phys_coh_st_inst_id = remap_array[log_coh_st_inst_id] + */ + u8 remap_array[MAX_COH_ST_CHANNELS]; + + /* + * Number of bits covering DRAM Address map 0 + * when interleaving is non-power-of-2. + * + * Used only for DF3_6CHAN. + */ + u8 np2_bits; + + /* Position of the 'interleave bit'. */ + u8 intlv_bit_pos; + /* Number of channels interleaved in this map. */ + u8 num_intlv_chan; + /* Number of dies interleaved in this map. */ + u8 num_intlv_dies; + /* Number of sockets interleaved in this map. */ + u8 num_intlv_sockets; + /* + * Total number of channels interleaved accounting + * for die and socket interleaving. + */ + u8 total_intlv_chan; + /* Total bits needed to cover 'total_intlv_chan'. */ + u8 total_intlv_bits; +}; + +/* Original input values cached for debug printing. */ +struct addr_ctx_inputs { + u64 norm_addr; + u8 socket_id; + u8 die_id; + u8 coh_st_inst_id; +}; + +struct addr_ctx { + u64 ret_addr; + + struct addr_ctx_inputs inputs; + struct dram_addr_map map; + + /* AMD Node ID calculated from Socket and Die IDs. */ + u8 node_id; + + /* + * Coherent Station Instance ID + * Local ID used within a 'node'. + */ + u16 inst_id; + + /* + * Coherent Station Fabric ID + * System-wide ID that includes 'node' bits. + */ + u16 coh_st_fabric_id; +}; + +int df_indirect_read_instance(u16 node, u8 func, u16 reg, u8 instance_id, u32 *lo); +int df_indirect_read_broadcast(u16 node, u8 func, u16 reg, u32 *lo); + +int get_df_system_info(void); +int determine_node_id(struct addr_ctx *ctx, u8 socket_num, u8 die_num); +int get_addr_hash_mi300(void); + +int get_address_map(struct addr_ctx *ctx); + +int denormalize_address(struct addr_ctx *ctx); +int dehash_address(struct addr_ctx *ctx); + +unsigned long norm_to_sys_addr(u8 socket_id, u8 die_id, u8 coh_st_inst_id, unsigned long addr); +unsigned long convert_umc_mca_addr_to_sys_addr(struct atl_err *err); + +/* + * Make a gap in @data that is @num_bits long starting at @bit_num. + * e.g. data = 11111111'b + * bit_num = 3 + * num_bits = 2 + * result = 1111100111'b + */ +static inline u64 expand_bits(u8 bit_num, u8 num_bits, u64 data) +{ + u64 temp1, temp2; + + if (!num_bits) + return data; + + if (!bit_num) { + WARN_ON_ONCE(num_bits >= BITS_PER_LONG); + return data << num_bits; + } + + WARN_ON_ONCE(bit_num >= BITS_PER_LONG); + + temp1 = data & GENMASK_ULL(bit_num - 1, 0); + + temp2 = data & GENMASK_ULL(63, bit_num); + temp2 <<= num_bits; + + return temp1 | temp2; +} + +/* + * Remove bits in @data between @low_bit and @high_bit inclusive. + * e.g. data = XXXYYZZZ'b + * low_bit = 3 + * high_bit = 4 + * result = XXXZZZ'b + */ +static inline u64 remove_bits(u8 low_bit, u8 high_bit, u64 data) +{ + u64 temp1, temp2; + + WARN_ON_ONCE(high_bit >= BITS_PER_LONG); + WARN_ON_ONCE(low_bit >= BITS_PER_LONG); + WARN_ON_ONCE(low_bit > high_bit); + + if (!low_bit) + return data >> (high_bit++); + + temp1 = GENMASK_ULL(low_bit - 1, 0) & data; + temp2 = GENMASK_ULL(63, high_bit + 1) & data; + temp2 >>= high_bit - low_bit + 1; + + return temp1 | temp2; +} + +#define atl_debug(ctx, fmt, arg...) \ + pr_debug("socket_id=%u die_id=%u coh_st_inst_id=%u norm_addr=0x%016llx: " fmt,\ + (ctx)->inputs.socket_id, (ctx)->inputs.die_id,\ + (ctx)->inputs.coh_st_inst_id, (ctx)->inputs.norm_addr, ##arg) + +static inline void atl_debug_on_bad_df_rev(void) +{ + pr_debug("Unrecognized DF rev: %u", df_cfg.rev); +} + +static inline void atl_debug_on_bad_intlv_mode(struct addr_ctx *ctx) +{ + atl_debug(ctx, "Unrecognized interleave mode: %u", ctx->map.intlv_mode); +} + +#endif /* __AMD_ATL_INTERNAL_H__ */ diff --git a/drivers/ras/amd/atl/map.c b/drivers/ras/amd/atl/map.c new file mode 100644 index 000000000000..8b908e8d7495 --- /dev/null +++ b/drivers/ras/amd/atl/map.c @@ -0,0 +1,682 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * AMD Address Translation Library + * + * map.c : Functions to read and decode DRAM address maps + * + * Copyright (c) 2023, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Author: Yazen Ghannam <Yazen.Ghannam@amd.com> + */ + +#include "internal.h" + +static int df2_get_intlv_mode(struct addr_ctx *ctx) +{ + ctx->map.intlv_mode = FIELD_GET(DF2_INTLV_NUM_CHAN, ctx->map.base); + + if (ctx->map.intlv_mode == 8) + ctx->map.intlv_mode = DF2_2CHAN_HASH; + + if (ctx->map.intlv_mode != NONE && + ctx->map.intlv_mode != NOHASH_2CHAN && + ctx->map.intlv_mode != DF2_2CHAN_HASH) + return -EINVAL; + + return 0; +} + +static int df3_get_intlv_mode(struct addr_ctx *ctx) +{ + ctx->map.intlv_mode = FIELD_GET(DF3_INTLV_NUM_CHAN, ctx->map.base); + return 0; +} + +static int df3p5_get_intlv_mode(struct addr_ctx *ctx) +{ + ctx->map.intlv_mode = FIELD_GET(DF3p5_INTLV_NUM_CHAN, ctx->map.base); + + if (ctx->map.intlv_mode == DF3_6CHAN) + return -EINVAL; + + return 0; +} + +static int df4_get_intlv_mode(struct addr_ctx *ctx) +{ + ctx->map.intlv_mode = FIELD_GET(DF4_INTLV_NUM_CHAN, ctx->map.intlv); + + if (ctx->map.intlv_mode == DF3_COD4_2CHAN_HASH || + ctx->map.intlv_mode == DF3_COD2_4CHAN_HASH || + ctx->map.intlv_mode == DF3_COD1_8CHAN_HASH || + ctx->map.intlv_mode == DF3_6CHAN) + return -EINVAL; + + return 0; +} + +static int df4p5_get_intlv_mode(struct addr_ctx *ctx) +{ + ctx->map.intlv_mode = FIELD_GET(DF4p5_INTLV_NUM_CHAN, ctx->map.intlv); + + if (ctx->map.intlv_mode <= NOHASH_32CHAN) + return 0; + + if (ctx->map.intlv_mode >= MI3_HASH_8CHAN && + ctx->map.intlv_mode <= MI3_HASH_32CHAN) + return 0; + + /* + * Modes matching the ranges above are returned as-is. + * + * All other modes are "fixed up" by adding 20h to make a unique value. + */ + ctx->map.intlv_mode += 0x20; + + return 0; +} + +static int get_intlv_mode(struct addr_ctx *ctx) +{ + int ret; + + switch (df_cfg.rev) { + case DF2: + ret = df2_get_intlv_mode(ctx); + break; + case DF3: + ret = df3_get_intlv_mode(ctx); + break; + case DF3p5: + ret = df3p5_get_intlv_mode(ctx); + break; + case DF4: + ret = df4_get_intlv_mode(ctx); + break; + case DF4p5: + ret = df4p5_get_intlv_mode(ctx); + break; + default: + ret = -EINVAL; + } + + if (ret) + atl_debug_on_bad_df_rev(); + + return ret; +} + +static u64 get_hi_addr_offset(u32 reg_dram_offset) +{ + u8 shift = DF_DRAM_BASE_LIMIT_LSB; + u64 hi_addr_offset; + + switch (df_cfg.rev) { + case DF2: + hi_addr_offset = FIELD_GET(DF2_HI_ADDR_OFFSET, reg_dram_offset); + break; + case DF3: + case DF3p5: + hi_addr_offset = FIELD_GET(DF3_HI_ADDR_OFFSET, reg_dram_offset); + break; + case DF4: + case DF4p5: + hi_addr_offset = FIELD_GET(DF4_HI_ADDR_OFFSET, reg_dram_offset); + break; + default: + hi_addr_offset = 0; + atl_debug_on_bad_df_rev(); + } + + if (df_cfg.rev == DF4p5 && df_cfg.flags.heterogeneous) + shift = MI300_DRAM_LIMIT_LSB; + + return hi_addr_offset << shift; +} + +/* + * Returns: 0 if offset is disabled. + * 1 if offset is enabled. + * -EINVAL on error. + */ +static int get_dram_offset(struct addr_ctx *ctx, u64 *norm_offset) +{ + u32 reg_dram_offset; + u8 map_num; + + /* Should not be called for map 0. */ + if (!ctx->map.num) { + atl_debug(ctx, "Trying to find DRAM offset for map 0"); + return -EINVAL; + } + + /* + * DramOffset registers don't exist for map 0, so the base register + * actually refers to map 1. + * Adjust the map_num for the register offsets. + */ + map_num = ctx->map.num - 1; + + if (df_cfg.rev >= DF4) { + /* Read D18F7x140 (DramOffset) */ + if (df_indirect_read_instance(ctx->node_id, 7, 0x140 + (4 * map_num), + ctx->inst_id, ®_dram_offset)) + return -EINVAL; + + } else { + /* Read D18F0x1B4 (DramOffset) */ + if (df_indirect_read_instance(ctx->node_id, 0, 0x1B4 + (4 * map_num), + ctx->inst_id, ®_dram_offset)) + return -EINVAL; + } + + if (!FIELD_GET(DF_HI_ADDR_OFFSET_EN, reg_dram_offset)) + return 0; + + *norm_offset = get_hi_addr_offset(reg_dram_offset); + + return 1; +} + +static int df3_6ch_get_dram_addr_map(struct addr_ctx *ctx) +{ + u16 dst_fabric_id = FIELD_GET(DF3_DST_FABRIC_ID, ctx->map.limit); + u8 i, j, shift = 4, mask = 0xF; + u32 reg, offset = 0x60; + u16 dst_node_id; + + /* Get Socket 1 register. */ + if (dst_fabric_id & df_cfg.socket_id_mask) + offset = 0x68; + + /* Read D18F0x06{0,8} (DF::Skt0CsTargetRemap0)/(DF::Skt0CsTargetRemap1) */ + if (df_indirect_read_broadcast(ctx->node_id, 0, offset, ®)) + return -EINVAL; + + /* Save 8 remap entries. */ + for (i = 0, j = 0; i < 8; i++, j++) + ctx->map.remap_array[i] = (reg >> (j * shift)) & mask; + + dst_node_id = dst_fabric_id & df_cfg.node_id_mask; + dst_node_id >>= df_cfg.node_id_shift; + + /* Read D18F2x090 (DF::Np2ChannelConfig) */ + if (df_indirect_read_broadcast(dst_node_id, 2, 0x90, ®)) + return -EINVAL; + + ctx->map.np2_bits = FIELD_GET(DF_LOG2_ADDR_64K_SPACE0, reg); + return 0; +} + +static int df2_get_dram_addr_map(struct addr_ctx *ctx) +{ + /* Read D18F0x110 (DramBaseAddress). */ + if (df_indirect_read_instance(ctx->node_id, 0, 0x110 + (8 * ctx->map.num), + ctx->inst_id, &ctx->map.base)) + return -EINVAL; + + /* Read D18F0x114 (DramLimitAddress). */ + if (df_indirect_read_instance(ctx->node_id, 0, 0x114 + (8 * ctx->map.num), + ctx->inst_id, &ctx->map.limit)) + return -EINVAL; + + return 0; +} + +static int df3_get_dram_addr_map(struct addr_ctx *ctx) +{ + if (df2_get_dram_addr_map(ctx)) + return -EINVAL; + + /* Read D18F0x3F8 (DfGlobalCtl). */ + if (df_indirect_read_instance(ctx->node_id, 0, 0x3F8, + ctx->inst_id, &ctx->map.ctl)) + return -EINVAL; + + return 0; +} + +static int df4_get_dram_addr_map(struct addr_ctx *ctx) +{ + u8 remap_sel, i, j, shift = 4, mask = 0xF; + u32 remap_reg; + + /* Read D18F7xE00 (DramBaseAddress). */ + if (df_indirect_read_instance(ctx->node_id, 7, 0xE00 + (16 * ctx->map.num), + ctx->inst_id, &ctx->map.base)) + return -EINVAL; + + /* Read D18F7xE04 (DramLimitAddress). */ + if (df_indirect_read_instance(ctx->node_id, 7, 0xE04 + (16 * ctx->map.num), + ctx->inst_id, &ctx->map.limit)) + return -EINVAL; + + /* Read D18F7xE08 (DramAddressCtl). */ + if (df_indirect_read_instance(ctx->node_id, 7, 0xE08 + (16 * ctx->map.num), + ctx->inst_id, &ctx->map.ctl)) + return -EINVAL; + + /* Read D18F7xE0C (DramAddressIntlv). */ + if (df_indirect_read_instance(ctx->node_id, 7, 0xE0C + (16 * ctx->map.num), + ctx->inst_id, &ctx->map.intlv)) + return -EINVAL; + + /* Check if Remap Enable bit is valid. */ + if (!FIELD_GET(DF4_REMAP_EN, ctx->map.ctl)) + return 0; + + /* Fill with bogus values, because '0' is a valid value. */ + memset(&ctx->map.remap_array, 0xFF, sizeof(ctx->map.remap_array)); + + /* Get Remap registers. */ + remap_sel = FIELD_GET(DF4_REMAP_SEL, ctx->map.ctl); + + /* Read D18F7x180 (CsTargetRemap0A). */ + if (df_indirect_read_instance(ctx->node_id, 7, 0x180 + (8 * remap_sel), + ctx->inst_id, &remap_reg)) + return -EINVAL; + + /* Save first 8 remap entries. */ + for (i = 0, j = 0; i < 8; i++, j++) + ctx->map.remap_array[i] = (remap_reg >> (j * shift)) & mask; + + /* Read D18F7x184 (CsTargetRemap0B). */ + if (df_indirect_read_instance(ctx->node_id, 7, 0x184 + (8 * remap_sel), + ctx->inst_id, &remap_reg)) + return -EINVAL; + + /* Save next 8 remap entries. */ + for (i = 8, j = 0; i < 16; i++, j++) + ctx->map.remap_array[i] = (remap_reg >> (j * shift)) & mask; + + return 0; +} + +static int df4p5_get_dram_addr_map(struct addr_ctx *ctx) +{ + u8 remap_sel, i, j, shift = 5, mask = 0x1F; + u32 remap_reg; + + /* Read D18F7x200 (DramBaseAddress). */ + if (df_indirect_read_instance(ctx->node_id, 7, 0x200 + (16 * ctx->map.num), + ctx->inst_id, &ctx->map.base)) + return -EINVAL; + + /* Read D18F7x204 (DramLimitAddress). */ + if (df_indirect_read_instance(ctx->node_id, 7, 0x204 + (16 * ctx->map.num), + ctx->inst_id, &ctx->map.limit)) + return -EINVAL; + + /* Read D18F7x208 (DramAddressCtl). */ + if (df_indirect_read_instance(ctx->node_id, 7, 0x208 + (16 * ctx->map.num), + ctx->inst_id, &ctx->map.ctl)) + return -EINVAL; + + /* Read D18F7x20C (DramAddressIntlv). */ + if (df_indirect_read_instance(ctx->node_id, 7, 0x20C + (16 * ctx->map.num), + ctx->inst_id, &ctx->map.intlv)) + return -EINVAL; + + /* Check if Remap Enable bit is valid. */ + if (!FIELD_GET(DF4_REMAP_EN, ctx->map.ctl)) + return 0; + + /* Fill with bogus values, because '0' is a valid value. */ + memset(&ctx->map.remap_array, 0xFF, sizeof(ctx->map.remap_array)); + + /* Get Remap registers. */ + remap_sel = FIELD_GET(DF4p5_REMAP_SEL, ctx->map.ctl); + + /* Read D18F7x180 (CsTargetRemap0A). */ + if (df_indirect_read_instance(ctx->node_id, 7, 0x180 + (24 * remap_sel), + ctx->inst_id, &remap_reg)) + return -EINVAL; + + /* Save first 6 remap entries. */ + for (i = 0, j = 0; i < 6; i++, j++) + ctx->map.remap_array[i] = (remap_reg >> (j * shift)) & mask; + + /* Read D18F7x184 (CsTargetRemap0B). */ + if (df_indirect_read_instance(ctx->node_id, 7, 0x184 + (24 * remap_sel), + ctx->inst_id, &remap_reg)) + return -EINVAL; + + /* Save next 6 remap entries. */ + for (i = 6, j = 0; i < 12; i++, j++) + ctx->map.remap_array[i] = (remap_reg >> (j * shift)) & mask; + + /* Read D18F7x188 (CsTargetRemap0C). */ + if (df_indirect_read_instance(ctx->node_id, 7, 0x188 + (24 * remap_sel), + ctx->inst_id, &remap_reg)) + return -EINVAL; + + /* Save next 6 remap entries. */ + for (i = 12, j = 0; i < 18; i++, j++) + ctx->map.remap_array[i] = (remap_reg >> (j * shift)) & mask; + + return 0; +} + +static int get_dram_addr_map(struct addr_ctx *ctx) +{ + switch (df_cfg.rev) { + case DF2: return df2_get_dram_addr_map(ctx); + case DF3: + case DF3p5: return df3_get_dram_addr_map(ctx); + case DF4: return df4_get_dram_addr_map(ctx); + case DF4p5: return df4p5_get_dram_addr_map(ctx); + default: + atl_debug_on_bad_df_rev(); + return -EINVAL; + } +} + +static int get_coh_st_fabric_id(struct addr_ctx *ctx) +{ + u32 reg; + + /* + * On MI300 systems, the Coherent Station Fabric ID is derived + * later. And it does not depend on the register value. + */ + if (df_cfg.rev == DF4p5 && df_cfg.flags.heterogeneous) + return 0; + + /* Read D18F0x50 (FabricBlockInstanceInformation3). */ + if (df_indirect_read_instance(ctx->node_id, 0, 0x50, ctx->inst_id, ®)) + return -EINVAL; + + if (df_cfg.rev < DF4p5) + ctx->coh_st_fabric_id = FIELD_GET(DF2_COH_ST_FABRIC_ID, reg); + else + ctx->coh_st_fabric_id = FIELD_GET(DF4p5_COH_ST_FABRIC_ID, reg); + + return 0; +} + +static int find_normalized_offset(struct addr_ctx *ctx, u64 *norm_offset) +{ + u64 last_offset = 0; + int ret; + + for (ctx->map.num = 1; ctx->map.num < df_cfg.num_coh_st_maps; ctx->map.num++) { + ret = get_dram_offset(ctx, norm_offset); + if (ret < 0) + return ret; + + /* Continue search if this map's offset is not enabled. */ + if (!ret) + continue; + + /* Enabled offsets should never be 0. */ + if (*norm_offset == 0) { + atl_debug(ctx, "Enabled map %u offset is 0", ctx->map.num); + return -EINVAL; + } + + /* Offsets should always increase from one map to the next. */ + if (*norm_offset <= last_offset) { + atl_debug(ctx, "Map %u offset (0x%016llx) <= previous (0x%016llx)", + ctx->map.num, *norm_offset, last_offset); + return -EINVAL; + } + + /* Match if this map's offset is less than the current calculated address. */ + if (ctx->ret_addr >= *norm_offset) + break; + + last_offset = *norm_offset; + } + + /* + * Finished search without finding a match. + * Reset to map 0 and no offset. + */ + if (ctx->map.num >= df_cfg.num_coh_st_maps) { + ctx->map.num = 0; + *norm_offset = 0; + } + + return 0; +} + +static bool valid_map(struct addr_ctx *ctx) +{ + if (df_cfg.rev >= DF4) + return FIELD_GET(DF_ADDR_RANGE_VAL, ctx->map.ctl); + else + return FIELD_GET(DF_ADDR_RANGE_VAL, ctx->map.base); +} + +static int get_address_map_common(struct addr_ctx *ctx) +{ + u64 norm_offset = 0; + + if (get_coh_st_fabric_id(ctx)) + return -EINVAL; + + if (find_normalized_offset(ctx, &norm_offset)) + return -EINVAL; + + if (get_dram_addr_map(ctx)) + return -EINVAL; + + if (!valid_map(ctx)) + return -EINVAL; + + ctx->ret_addr -= norm_offset; + + return 0; +} + +static u8 get_num_intlv_chan(struct addr_ctx *ctx) +{ + switch (ctx->map.intlv_mode) { + case NONE: + return 1; + case NOHASH_2CHAN: + case DF2_2CHAN_HASH: + case DF3_COD4_2CHAN_HASH: + case DF4_NPS4_2CHAN_HASH: + case DF4p5_NPS4_2CHAN_1K_HASH: + case DF4p5_NPS4_2CHAN_2K_HASH: + return 2; + case DF4_NPS4_3CHAN_HASH: + case DF4p5_NPS4_3CHAN_1K_HASH: + case DF4p5_NPS4_3CHAN_2K_HASH: + return 3; + case NOHASH_4CHAN: + case DF3_COD2_4CHAN_HASH: + case DF4_NPS2_4CHAN_HASH: + case DF4p5_NPS2_4CHAN_1K_HASH: + case DF4p5_NPS2_4CHAN_2K_HASH: + return 4; + case DF4_NPS2_5CHAN_HASH: + case DF4p5_NPS2_5CHAN_1K_HASH: + case DF4p5_NPS2_5CHAN_2K_HASH: + return 5; + case DF3_6CHAN: + case DF4_NPS2_6CHAN_HASH: + case DF4p5_NPS2_6CHAN_1K_HASH: + case DF4p5_NPS2_6CHAN_2K_HASH: + return 6; + case NOHASH_8CHAN: + case DF3_COD1_8CHAN_HASH: + case DF4_NPS1_8CHAN_HASH: + case MI3_HASH_8CHAN: + case DF4p5_NPS1_8CHAN_1K_HASH: + case DF4p5_NPS1_8CHAN_2K_HASH: + return 8; + case DF4_NPS1_10CHAN_HASH: + case DF4p5_NPS1_10CHAN_1K_HASH: + case DF4p5_NPS1_10CHAN_2K_HASH: + return 10; + case DF4_NPS1_12CHAN_HASH: + case DF4p5_NPS1_12CHAN_1K_HASH: + case DF4p5_NPS1_12CHAN_2K_HASH: + return 12; + case NOHASH_16CHAN: + case MI3_HASH_16CHAN: + case DF4p5_NPS1_16CHAN_1K_HASH: + case DF4p5_NPS1_16CHAN_2K_HASH: + return 16; + case DF4p5_NPS0_24CHAN_1K_HASH: + case DF4p5_NPS0_24CHAN_2K_HASH: + return 24; + case NOHASH_32CHAN: + case MI3_HASH_32CHAN: + return 32; + default: + atl_debug_on_bad_intlv_mode(ctx); + return 0; + } +} + +static void calculate_intlv_bits(struct addr_ctx *ctx) +{ + ctx->map.num_intlv_chan = get_num_intlv_chan(ctx); + + ctx->map.total_intlv_chan = ctx->map.num_intlv_chan; + ctx->map.total_intlv_chan *= ctx->map.num_intlv_dies; + ctx->map.total_intlv_chan *= ctx->map.num_intlv_sockets; + + /* + * Get the number of bits needed to cover this many channels. + * order_base_2() rounds up automatically. + */ + ctx->map.total_intlv_bits = order_base_2(ctx->map.total_intlv_chan); +} + +static u8 get_intlv_bit_pos(struct addr_ctx *ctx) +{ + u8 addr_sel = 0; + + switch (df_cfg.rev) { + case DF2: + addr_sel = FIELD_GET(DF2_INTLV_ADDR_SEL, ctx->map.base); + break; + case DF3: + case DF3p5: + addr_sel = FIELD_GET(DF3_INTLV_ADDR_SEL, ctx->map.base); + break; + case DF4: + case DF4p5: + addr_sel = FIELD_GET(DF4_INTLV_ADDR_SEL, ctx->map.intlv); + break; + default: + atl_debug_on_bad_df_rev(); + break; + } + + /* Add '8' to get the 'interleave bit position'. */ + return addr_sel + 8; +} + +static u8 get_num_intlv_dies(struct addr_ctx *ctx) +{ + u8 dies = 0; + + switch (df_cfg.rev) { + case DF2: + dies = FIELD_GET(DF2_INTLV_NUM_DIES, ctx->map.limit); + break; + case DF3: + dies = FIELD_GET(DF3_INTLV_NUM_DIES, ctx->map.base); + break; + case DF3p5: + dies = FIELD_GET(DF3p5_INTLV_NUM_DIES, ctx->map.base); + break; + case DF4: + case DF4p5: + dies = FIELD_GET(DF4_INTLV_NUM_DIES, ctx->map.intlv); + break; + default: + atl_debug_on_bad_df_rev(); + break; + } + + /* Register value is log2, e.g. 0 -> 1 die, 1 -> 2 dies, etc. */ + return 1 << dies; +} + +static u8 get_num_intlv_sockets(struct addr_ctx *ctx) +{ + u8 sockets = 0; + + switch (df_cfg.rev) { + case DF2: + sockets = FIELD_GET(DF2_INTLV_NUM_SOCKETS, ctx->map.limit); + break; + case DF3: + case DF3p5: + sockets = FIELD_GET(DF2_INTLV_NUM_SOCKETS, ctx->map.base); + break; + case DF4: + case DF4p5: + sockets = FIELD_GET(DF4_INTLV_NUM_SOCKETS, ctx->map.intlv); + break; + default: + atl_debug_on_bad_df_rev(); + break; + } + + /* Register value is log2, e.g. 0 -> 1 sockets, 1 -> 2 sockets, etc. */ + return 1 << sockets; +} + +static int get_global_map_data(struct addr_ctx *ctx) +{ + if (get_intlv_mode(ctx)) + return -EINVAL; + + if (ctx->map.intlv_mode == DF3_6CHAN && + df3_6ch_get_dram_addr_map(ctx)) + return -EINVAL; + + ctx->map.intlv_bit_pos = get_intlv_bit_pos(ctx); + ctx->map.num_intlv_dies = get_num_intlv_dies(ctx); + ctx->map.num_intlv_sockets = get_num_intlv_sockets(ctx); + calculate_intlv_bits(ctx); + + return 0; +} + +static void dump_address_map(struct dram_addr_map *map) +{ + u8 i; + + pr_debug("intlv_mode=0x%x", map->intlv_mode); + pr_debug("num=0x%x", map->num); + pr_debug("base=0x%x", map->base); + pr_debug("limit=0x%x", map->limit); + pr_debug("ctl=0x%x", map->ctl); + pr_debug("intlv=0x%x", map->intlv); + + for (i = 0; i < MAX_COH_ST_CHANNELS; i++) + pr_debug("remap_array[%u]=0x%x", i, map->remap_array[i]); + + pr_debug("intlv_bit_pos=%u", map->intlv_bit_pos); + pr_debug("num_intlv_chan=%u", map->num_intlv_chan); + pr_debug("num_intlv_dies=%u", map->num_intlv_dies); + pr_debug("num_intlv_sockets=%u", map->num_intlv_sockets); + pr_debug("total_intlv_chan=%u", map->total_intlv_chan); + pr_debug("total_intlv_bits=%u", map->total_intlv_bits); +} + +int get_address_map(struct addr_ctx *ctx) +{ + int ret; + + ret = get_address_map_common(ctx); + if (ret) + return ret; + + ret = get_global_map_data(ctx); + if (ret) + return ret; + + dump_address_map(&ctx->map); + + return ret; +} diff --git a/drivers/ras/amd/atl/reg_fields.h b/drivers/ras/amd/atl/reg_fields.h new file mode 100644 index 000000000000..9dcdf6e4a856 --- /dev/null +++ b/drivers/ras/amd/atl/reg_fields.h @@ -0,0 +1,606 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * AMD Address Translation Library + * + * reg_fields.h : Register field definitions + * + * Copyright (c) 2023, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Author: Yazen Ghannam <Yazen.Ghannam@amd.com> + */ + +/* + * Notes on naming: + * 1) Use "DF_" prefix for fields that are the same for all revisions. + * 2) Use "DFx_" prefix for fields that differ between revisions. + * a) "x" is the first major revision where the new field appears. + * b) E.g., if DF2 and DF3 have the same field, then call it DF2. + * c) E.g., if DF3p5 and DF4 have the same field, then call it DF4. + */ + +/* + * Coherent Station Fabric ID + * + * Access type: Instance + * + * Register + * Rev Fieldname Bits + * + * D18F0x50 [Fabric Block Instance Information 3] + * DF2 BlockFabricId [19:8] + * DF3 BlockFabricId [19:8] + * DF3p5 BlockFabricId [19:8] + * DF4 BlockFabricId [19:8] + * DF4p5 BlockFabricId [15:8] + */ +#define DF2_COH_ST_FABRIC_ID GENMASK(19, 8) +#define DF4p5_COH_ST_FABRIC_ID GENMASK(15, 8) + +/* + * Component ID Mask + * + * Access type: Broadcast + * + * Register + * Rev Fieldname Bits + * + * DF2 N/A + * + * D18F1x208 [System Fabric ID Mask 0] + * DF3 ComponentIdMask [9:0] + * + * D18F1x150 [System Fabric ID Mask 0] + * DF3p5 ComponentIdMask [15:0] + * + * D18F4x1B0 [System Fabric ID Mask 0] + * DF4 ComponentIdMask [15:0] + * DF4p5 ComponentIdMask [15:0] + */ +#define DF3_COMPONENT_ID_MASK GENMASK(9, 0) +#define DF4_COMPONENT_ID_MASK GENMASK(15, 0) + +/* + * Destination Fabric ID + * + * Access type: Instance + * + * Register + * Rev Fieldname Bits + * + * D18F0x114 [DRAM Limit Address] + * DF2 DstFabricID [7:0] + * DF3 DstFabricID [9:0] + * DF3 DstFabricID [11:0] + * + * D18F7xE08 [DRAM Address Control] + * DF4 DstFabricID [27:16] + * + * D18F7x208 [DRAM Address Control] + * DF4p5 DstFabricID [23:16] + */ +#define DF2_DST_FABRIC_ID GENMASK(7, 0) +#define DF3_DST_FABRIC_ID GENMASK(9, 0) +#define DF3p5_DST_FABRIC_ID GENMASK(11, 0) +#define DF4_DST_FABRIC_ID GENMASK(27, 16) +#define DF4p5_DST_FABRIC_ID GENMASK(23, 16) + +/* + * Die ID Mask + * + * Access type: Broadcast + * + * Register + * Rev Fieldname Bits + * + * D18F1x208 [System Fabric ID Mask] + * DF2 DieIdMask [15:8] + * + * D18F1x20C [System Fabric ID Mask 1] + * DF3 DieIdMask [18:16] + * + * D18F1x158 [System Fabric ID Mask 2] + * DF3p5 DieIdMask [15:0] + * + * D18F4x1B8 [System Fabric ID Mask 2] + * DF4 DieIdMask [15:0] + * DF4p5 DieIdMask [15:0] + */ +#define DF2_DIE_ID_MASK GENMASK(15, 8) +#define DF3_DIE_ID_MASK GENMASK(18, 16) +#define DF4_DIE_ID_MASK GENMASK(15, 0) + +/* + * Die ID Shift + * + * Access type: Broadcast + * + * Register + * Rev Fieldname Bits + * + * D18F1x208 [System Fabric ID Mask] + * DF2 DieIdShift [27:24] + * + * DF3 N/A + * DF3p5 N/A + * DF4 N/A + * DF4p5 N/A + */ +#define DF2_DIE_ID_SHIFT GENMASK(27, 24) + +/* + * DRAM Address Range Valid + * + * Access type: Instance + * + * Register + * Rev Fieldname Bits + * + * D18F0x110 [DRAM Base Address] + * DF2 AddrRngVal [0] + * DF3 AddrRngVal [0] + * DF3p5 AddrRngVal [0] + * + * D18F7xE08 [DRAM Address Control] + * DF4 AddrRngVal [0] + * + * D18F7x208 [DRAM Address Control] + * DF4p5 AddrRngVal [0] + */ +#define DF_ADDR_RANGE_VAL BIT(0) + +/* + * DRAM Base Address + * + * Access type: Instance + * + * Register + * Rev Fieldname Bits + * + * D18F0x110 [DRAM Base Address] + * DF2 DramBaseAddr [31:12] + * DF3 DramBaseAddr [31:12] + * DF3p5 DramBaseAddr [31:12] + * + * D18F7xE00 [DRAM Base Address] + * DF4 DramBaseAddr [27:0] + * + * D18F7x200 [DRAM Base Address] + * DF4p5 DramBaseAddr [27:0] + */ +#define DF2_BASE_ADDR GENMASK(31, 12) +#define DF4_BASE_ADDR GENMASK(27, 0) + +/* + * DRAM Hole Base + * + * Access type: Broadcast + * + * Register + * Rev Fieldname Bits + * + * D18F0x104 [DRAM Hole Control] + * DF2 DramHoleBase [31:24] + * DF3 DramHoleBase [31:24] + * DF3p5 DramHoleBase [31:24] + * + * D18F7x104 [DRAM Hole Control] + * DF4 DramHoleBase [31:24] + * DF4p5 DramHoleBase [31:24] + */ +#define DF_DRAM_HOLE_BASE_MASK GENMASK(31, 24) + +/* + * DRAM Limit Address + * + * Access type: Instance + * + * Register + * Rev Fieldname Bits + * + * D18F0x114 [DRAM Limit Address] + * DF2 DramLimitAddr [31:12] + * DF3 DramLimitAddr [31:12] + * DF3p5 DramLimitAddr [31:12] + * + * D18F7xE04 [DRAM Limit Address] + * DF4 DramLimitAddr [27:0] + * + * D18F7x204 [DRAM Limit Address] + * DF4p5 DramLimitAddr [27:0] + */ +#define DF2_DRAM_LIMIT_ADDR GENMASK(31, 12) +#define DF4_DRAM_LIMIT_ADDR GENMASK(27, 0) + +/* + * Hash Interleave Controls + * + * Access type: Instance + * + * Register + * Rev Fieldname Bits + * + * DF2 N/A + * + * D18F0x3F8 [DF Global Control] + * DF3 GlbHashIntlvCtl64K [20] + * GlbHashIntlvCtl2M [21] + * GlbHashIntlvCtl1G [22] + * + * DF3p5 GlbHashIntlvCtl64K [20] + * GlbHashIntlvCtl2M [21] + * GlbHashIntlvCtl1G [22] + * + * D18F7xE08 [DRAM Address Control] + * DF4 HashIntlvCtl64K [8] + * HashIntlvCtl2M [9] + * HashIntlvCtl1G [10] + * + * D18F7x208 [DRAM Address Control] + * DF4p5 HashIntlvCtl4K [7] + * HashIntlvCtl64K [8] + * HashIntlvCtl2M [9] + * HashIntlvCtl1G [10] + * HashIntlvCtl1T [15] + */ +#define DF3_HASH_CTL_64K BIT(20) +#define DF3_HASH_CTL_2M BIT(21) +#define DF3_HASH_CTL_1G BIT(22) +#define DF4_HASH_CTL_64K BIT(8) +#define DF4_HASH_CTL_2M BIT(9) +#define DF4_HASH_CTL_1G BIT(10) +#define DF4p5_HASH_CTL_4K BIT(7) +#define DF4p5_HASH_CTL_1T BIT(15) + +/* + * High Address Offset + * + * Access type: Instance + * + * Register + * Rev Fieldname Bits + * + * D18F0x1B4 [DRAM Offset] + * DF2 HiAddrOffset [31:20] + * DF3 HiAddrOffset [31:12] + * DF3p5 HiAddrOffset [31:12] + * + * D18F7x140 [DRAM Offset] + * DF4 HiAddrOffset [24:1] + * DF4p5 HiAddrOffset [24:1] + * MI300 HiAddrOffset [31:1] + */ +#define DF2_HI_ADDR_OFFSET GENMASK(31, 20) +#define DF3_HI_ADDR_OFFSET GENMASK(31, 12) + +/* Follow reference code by including reserved bits for simplicity. */ +#define DF4_HI_ADDR_OFFSET GENMASK(31, 1) + +/* + * High Address Offset Enable + * + * Access type: Instance + * + * Register + * Rev Fieldname Bits + * + * D18F0x1B4 [DRAM Offset] + * DF2 HiAddrOffsetEn [0] + * DF3 HiAddrOffsetEn [0] + * DF3p5 HiAddrOffsetEn [0] + * + * D18F7x140 [DRAM Offset] + * DF4 HiAddrOffsetEn [0] + * DF4p5 HiAddrOffsetEn [0] + */ +#define DF_HI_ADDR_OFFSET_EN BIT(0) + +/* + * Interleave Address Select + * + * Access type: Instance + * + * Register + * Rev Fieldname Bits + * + * D18F0x110 [DRAM Base Address] + * DF2 IntLvAddrSel [10:8] + * DF3 IntLvAddrSel [11:9] + * DF3p5 IntLvAddrSel [11:9] + * + * D18F7xE0C [DRAM Address Interleave] + * DF4 IntLvAddrSel [2:0] + * + * D18F7x20C [DRAM Address Interleave] + * DF4p5 IntLvAddrSel [2:0] + */ +#define DF2_INTLV_ADDR_SEL GENMASK(10, 8) +#define DF3_INTLV_ADDR_SEL GENMASK(11, 9) +#define DF4_INTLV_ADDR_SEL GENMASK(2, 0) + +/* + * Interleave Number of Channels + * + * Access type: Instance + * + * Register + * Rev Fieldname Bits + * + * D18F0x110 [DRAM Base Address] + * DF2 IntLvNumChan [7:4] + * DF3 IntLvNumChan [5:2] + * DF3p5 IntLvNumChan [6:2] + * + * D18F7xE0C [DRAM Address Interleave] + * DF4 IntLvNumChan [8:4] + * + * D18F7x20C [DRAM Address Interleave] + * DF4p5 IntLvNumChan [9:4] + */ +#define DF2_INTLV_NUM_CHAN GENMASK(7, 4) +#define DF3_INTLV_NUM_CHAN GENMASK(5, 2) +#define DF3p5_INTLV_NUM_CHAN GENMASK(6, 2) +#define DF4_INTLV_NUM_CHAN GENMASK(8, 4) +#define DF4p5_INTLV_NUM_CHAN GENMASK(9, 4) + +/* + * Interleave Number of Dies + * + * Access type: Instance + * + * Register + * Rev Fieldname Bits + * + * D18F0x114 [DRAM Limit Address] + * DF2 IntLvNumDies [11:10] + * + * D18F0x110 [DRAM Base Address] + * DF3 IntLvNumDies [7:6] + * DF3p5 IntLvNumDies [7] + * + * D18F7xE0C [DRAM Address Interleave] + * DF4 IntLvNumDies [13:12] + * + * D18F7x20C [DRAM Address Interleave] + * DF4p5 IntLvNumDies [13:12] + */ +#define DF2_INTLV_NUM_DIES GENMASK(11, 10) +#define DF3_INTLV_NUM_DIES GENMASK(7, 6) +#define DF3p5_INTLV_NUM_DIES BIT(7) +#define DF4_INTLV_NUM_DIES GENMASK(13, 12) + +/* + * Interleave Number of Sockets + * + * Access type: Instance + * + * Register + * Rev Fieldname Bits + * + * D18F0x114 [DRAM Limit Address] + * DF2 IntLvNumSockets [8] + * + * D18F0x110 [DRAM Base Address] + * DF3 IntLvNumSockets [8] + * DF3p5 IntLvNumSockets [8] + * + * D18F7xE0C [DRAM Address Interleave] + * DF4 IntLvNumSockets [18] + * + * D18F7x20C [DRAM Address Interleave] + * DF4p5 IntLvNumSockets [18] + */ +#define DF2_INTLV_NUM_SOCKETS BIT(8) +#define DF4_INTLV_NUM_SOCKETS BIT(18) + +/* + * Legacy MMIO Hole Enable + * + * Access type: Instance + * + * Register + * Rev Fieldname Bits + * + * D18F0x110 [DRAM Base Address] + * DF2 LgcyMmioHoleEn [1] + * DF3 LgcyMmioHoleEn [1] + * DF3p5 LgcyMmioHoleEn [1] + * + * D18F7xE08 [DRAM Address Control] + * DF4 LgcyMmioHoleEn [1] + * + * D18F7x208 [DRAM Address Control] + * DF4p5 LgcyMmioHoleEn [1] + */ +#define DF_LEGACY_MMIO_HOLE_EN BIT(1) + +/* + * Log2 Address 64K Space 0 + * + * Access type: Instance + * + * Register + * Rev Fieldname Bits + * + * DF2 N/A + * + * D18F2x90 [Non-power-of-2 channel Configuration Register for COH_ST DRAM Address Maps] + * DF3 Log2Addr64KSpace0 [5:0] + * + * DF3p5 N/A + * DF4 N/A + * DF4p5 N/A + */ +#define DF_LOG2_ADDR_64K_SPACE0 GENMASK(5, 0) + +/* + * Major Revision + * + * Access type: Broadcast + * + * Register + * Rev Fieldname Bits + * + * DF2 N/A + * DF3 N/A + * DF3p5 N/A + * + * D18F0x040 [Fabric Block Instance Count] + * DF4 MajorRevision [27:24] + * DF4p5 MajorRevision [27:24] + */ +#define DF_MAJOR_REVISION GENMASK(27, 24) + +/* + * Minor Revision + * + * Access type: Broadcast + * + * Register + * Rev Fieldname Bits + * + * DF2 N/A + * DF3 N/A + * DF3p5 N/A + * + * D18F0x040 [Fabric Block Instance Count] + * DF4 MinorRevision [23:16] + * DF4p5 MinorRevision [23:16] + */ +#define DF_MINOR_REVISION GENMASK(23, 16) + +/* + * Node ID Mask + * + * Access type: Broadcast + * + * Register + * Rev Fieldname Bits + * + * DF2 N/A + * + * D18F1x208 [System Fabric ID Mask 0] + * DF3 NodeIdMask [25:16] + * + * D18F1x150 [System Fabric ID Mask 0] + * DF3p5 NodeIdMask [31:16] + * + * D18F4x1B0 [System Fabric ID Mask 0] + * DF4 NodeIdMask [31:16] + * DF4p5 NodeIdMask [31:16] + */ +#define DF3_NODE_ID_MASK GENMASK(25, 16) +#define DF4_NODE_ID_MASK GENMASK(31, 16) + +/* + * Node ID Shift + * + * Access type: Broadcast + * + * Register + * Rev Fieldname Bits + * + * DF2 N/A + * + * D18F1x20C [System Fabric ID Mask 1] + * DF3 NodeIdShift [3:0] + * + * D18F1x154 [System Fabric ID Mask 1] + * DF3p5 NodeIdShift [3:0] + * + * D18F4x1B4 [System Fabric ID Mask 1] + * DF4 NodeIdShift [3:0] + * DF4p5 NodeIdShift [3:0] + */ +#define DF3_NODE_ID_SHIFT GENMASK(3, 0) + +/* + * Remap Enable + * + * Access type: Instance + * + * Register + * Rev Fieldname Bits + * + * DF2 N/A + * DF3 N/A + * DF3p5 N/A + * + * D18F7xE08 [DRAM Address Control] + * DF4 RemapEn [4] + * + * D18F7x208 [DRAM Address Control] + * DF4p5 RemapEn [4] + */ +#define DF4_REMAP_EN BIT(4) + +/* + * Remap Select + * + * Access type: Instance + * + * Register + * Rev Fieldname Bits + * + * DF2 N/A + * DF3 N/A + * DF3p5 N/A + * + * D18F7xE08 [DRAM Address Control] + * DF4 RemapSel [7:5] + * + * D18F7x208 [DRAM Address Control] + * DF4p5 RemapSel [6:5] + */ +#define DF4_REMAP_SEL GENMASK(7, 5) +#define DF4p5_REMAP_SEL GENMASK(6, 5) + +/* + * Socket ID Mask + * + * Access type: Broadcast + * + * Register + * Rev Fieldname Bits + * + * D18F1x208 [System Fabric ID Mask] + * DF2 SocketIdMask [23:16] + * + * D18F1x20C [System Fabric ID Mask 1] + * DF3 SocketIdMask [26:24] + * + * D18F1x158 [System Fabric ID Mask 2] + * DF3p5 SocketIdMask [31:16] + * + * D18F4x1B8 [System Fabric ID Mask 2] + * DF4 SocketIdMask [31:16] + * DF4p5 SocketIdMask [31:16] + */ +#define DF2_SOCKET_ID_MASK GENMASK(23, 16) +#define DF3_SOCKET_ID_MASK GENMASK(26, 24) +#define DF4_SOCKET_ID_MASK GENMASK(31, 16) + +/* + * Socket ID Shift + * + * Access type: Broadcast + * + * Register + * Rev Fieldname Bits + * + * D18F1x208 [System Fabric ID Mask] + * DF2 SocketIdShift [31:28] + * + * D18F1x20C [System Fabric ID Mask 1] + * DF3 SocketIdShift [9:8] + * + * D18F1x158 [System Fabric ID Mask 2] + * DF3p5 SocketIdShift [11:8] + * + * D18F4x1B4 [System Fabric ID Mask 1] + * DF4 SocketIdShift [11:8] + * DF4p5 SocketIdShift [11:8] + */ +#define DF2_SOCKET_ID_SHIFT GENMASK(31, 28) +#define DF3_SOCKET_ID_SHIFT GENMASK(9, 8) +#define DF4_SOCKET_ID_SHIFT GENMASK(11, 8) diff --git a/drivers/ras/amd/atl/system.c b/drivers/ras/amd/atl/system.c new file mode 100644 index 000000000000..701349e84942 --- /dev/null +++ b/drivers/ras/amd/atl/system.c @@ -0,0 +1,288 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * AMD Address Translation Library + * + * system.c : Functions to read and save system-wide data + * + * Copyright (c) 2023, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Author: Yazen Ghannam <Yazen.Ghannam@amd.com> + */ + +#include "internal.h" + +int determine_node_id(struct addr_ctx *ctx, u8 socket_id, u8 die_id) +{ + u16 socket_id_bits, die_id_bits; + + if (socket_id > 0 && df_cfg.socket_id_mask == 0) { + atl_debug(ctx, "Invalid socket inputs: socket_id=%u socket_id_mask=0x%x", + socket_id, df_cfg.socket_id_mask); + return -EINVAL; + } + + /* Do each step independently to avoid shift out-of-bounds issues. */ + socket_id_bits = socket_id; + socket_id_bits <<= df_cfg.socket_id_shift; + socket_id_bits &= df_cfg.socket_id_mask; + + if (die_id > 0 && df_cfg.die_id_mask == 0) { + atl_debug(ctx, "Invalid die inputs: die_id=%u die_id_mask=0x%x", + die_id, df_cfg.die_id_mask); + return -EINVAL; + } + + /* Do each step independently to avoid shift out-of-bounds issues. */ + die_id_bits = die_id; + die_id_bits <<= df_cfg.die_id_shift; + die_id_bits &= df_cfg.die_id_mask; + + ctx->node_id = (socket_id_bits | die_id_bits) >> df_cfg.node_id_shift; + return 0; +} + +static void df2_get_masks_shifts(u32 mask0) +{ + df_cfg.socket_id_shift = FIELD_GET(DF2_SOCKET_ID_SHIFT, mask0); + df_cfg.socket_id_mask = FIELD_GET(DF2_SOCKET_ID_MASK, mask0); + df_cfg.die_id_shift = FIELD_GET(DF2_DIE_ID_SHIFT, mask0); + df_cfg.die_id_mask = FIELD_GET(DF2_DIE_ID_MASK, mask0); + df_cfg.node_id_shift = df_cfg.die_id_shift; + df_cfg.node_id_mask = df_cfg.socket_id_mask | df_cfg.die_id_mask; + df_cfg.component_id_mask = ~df_cfg.node_id_mask; +} + +static void df3_get_masks_shifts(u32 mask0, u32 mask1) +{ + df_cfg.component_id_mask = FIELD_GET(DF3_COMPONENT_ID_MASK, mask0); + df_cfg.node_id_mask = FIELD_GET(DF3_NODE_ID_MASK, mask0); + + df_cfg.node_id_shift = FIELD_GET(DF3_NODE_ID_SHIFT, mask1); + df_cfg.socket_id_shift = FIELD_GET(DF3_SOCKET_ID_SHIFT, mask1); + df_cfg.socket_id_mask = FIELD_GET(DF3_SOCKET_ID_MASK, mask1); + df_cfg.die_id_mask = FIELD_GET(DF3_DIE_ID_MASK, mask1); +} + +static void df3p5_get_masks_shifts(u32 mask0, u32 mask1, u32 mask2) +{ + df_cfg.component_id_mask = FIELD_GET(DF4_COMPONENT_ID_MASK, mask0); + df_cfg.node_id_mask = FIELD_GET(DF4_NODE_ID_MASK, mask0); + + df_cfg.node_id_shift = FIELD_GET(DF3_NODE_ID_SHIFT, mask1); + df_cfg.socket_id_shift = FIELD_GET(DF4_SOCKET_ID_SHIFT, mask1); + + df_cfg.socket_id_mask = FIELD_GET(DF4_SOCKET_ID_MASK, mask2); + df_cfg.die_id_mask = FIELD_GET(DF4_DIE_ID_MASK, mask2); +} + +static void df4_get_masks_shifts(u32 mask0, u32 mask1, u32 mask2) +{ + df3p5_get_masks_shifts(mask0, mask1, mask2); + + if (!(df_cfg.flags.socket_id_shift_quirk && df_cfg.socket_id_shift == 1)) + return; + + df_cfg.socket_id_shift = 0; + df_cfg.socket_id_mask = 1; + df_cfg.die_id_shift = 0; + df_cfg.die_id_mask = 0; + df_cfg.node_id_shift = 8; + df_cfg.node_id_mask = 0x100; +} + +static int df4_get_fabric_id_mask_registers(void) +{ + u32 mask0, mask1, mask2; + + /* Read D18F4x1B0 (SystemFabricIdMask0) */ + if (df_indirect_read_broadcast(0, 4, 0x1B0, &mask0)) + return -EINVAL; + + /* Read D18F4x1B4 (SystemFabricIdMask1) */ + if (df_indirect_read_broadcast(0, 4, 0x1B4, &mask1)) + return -EINVAL; + + /* Read D18F4x1B8 (SystemFabricIdMask2) */ + if (df_indirect_read_broadcast(0, 4, 0x1B8, &mask2)) + return -EINVAL; + + df4_get_masks_shifts(mask0, mask1, mask2); + return 0; +} + +static int df4_determine_df_rev(u32 reg) +{ + df_cfg.rev = FIELD_GET(DF_MINOR_REVISION, reg) < 5 ? DF4 : DF4p5; + + /* Check for special cases or quirks based on Device/Vendor IDs.*/ + + /* Read D18F0x000 (DeviceVendorId0) */ + if (df_indirect_read_broadcast(0, 0, 0, ®)) + return -EINVAL; + + if (reg == DF_FUNC0_ID_ZEN4_SERVER) + df_cfg.flags.socket_id_shift_quirk = 1; + + if (reg == DF_FUNC0_ID_MI300) { + df_cfg.flags.heterogeneous = 1; + + if (get_addr_hash_mi300()) + return -EINVAL; + } + + return df4_get_fabric_id_mask_registers(); +} + +static int determine_df_rev_legacy(void) +{ + u32 fabric_id_mask0, fabric_id_mask1, fabric_id_mask2; + + /* + * Check for DF3.5. + * + * Component ID Mask must be non-zero. Register D18F1x150 is + * reserved pre-DF3.5, so value will be Read-as-Zero. + */ + + /* Read D18F1x150 (SystemFabricIdMask0). */ + if (df_indirect_read_broadcast(0, 1, 0x150, &fabric_id_mask0)) + return -EINVAL; + + if (FIELD_GET(DF4_COMPONENT_ID_MASK, fabric_id_mask0)) { + df_cfg.rev = DF3p5; + + /* Read D18F1x154 (SystemFabricIdMask1) */ + if (df_indirect_read_broadcast(0, 1, 0x154, &fabric_id_mask1)) + return -EINVAL; + + /* Read D18F1x158 (SystemFabricIdMask2) */ + if (df_indirect_read_broadcast(0, 1, 0x158, &fabric_id_mask2)) + return -EINVAL; + + df3p5_get_masks_shifts(fabric_id_mask0, fabric_id_mask1, fabric_id_mask2); + return 0; + } + + /* + * Check for DF3. + * + * Component ID Mask must be non-zero. Field is Read-as-Zero on DF2. + */ + + /* Read D18F1x208 (SystemFabricIdMask). */ + if (df_indirect_read_broadcast(0, 1, 0x208, &fabric_id_mask0)) + return -EINVAL; + + if (FIELD_GET(DF3_COMPONENT_ID_MASK, fabric_id_mask0)) { + df_cfg.rev = DF3; + + /* Read D18F1x20C (SystemFabricIdMask1) */ + if (df_indirect_read_broadcast(0, 1, 0x20C, &fabric_id_mask1)) + return -EINVAL; + + df3_get_masks_shifts(fabric_id_mask0, fabric_id_mask1); + return 0; + } + + /* Default to DF2. */ + df_cfg.rev = DF2; + df2_get_masks_shifts(fabric_id_mask0); + return 0; +} + +static int determine_df_rev(void) +{ + u32 reg; + u8 rev; + + if (df_cfg.rev != UNKNOWN) + return 0; + + /* Read D18F0x40 (FabricBlockInstanceCount). */ + if (df_indirect_read_broadcast(0, 0, 0x40, ®)) + return -EINVAL; + + /* + * Revision fields added for DF4 and later. + * + * Major revision of '0' is found pre-DF4. Field is Read-as-Zero. + */ + rev = FIELD_GET(DF_MAJOR_REVISION, reg); + if (!rev) + return determine_df_rev_legacy(); + + /* + * Fail out for major revisions other than '4'. + * + * Explicit support should be added for newer systems to avoid issues. + */ + if (rev == 4) + return df4_determine_df_rev(reg); + + return -EINVAL; +} + +static void get_num_maps(void) +{ + switch (df_cfg.rev) { + case DF2: + case DF3: + case DF3p5: + df_cfg.num_coh_st_maps = 2; + break; + case DF4: + case DF4p5: + df_cfg.num_coh_st_maps = 4; + break; + default: + atl_debug_on_bad_df_rev(); + } +} + +static void apply_node_id_shift(void) +{ + if (df_cfg.rev == DF2) + return; + + df_cfg.die_id_shift = df_cfg.node_id_shift; + df_cfg.die_id_mask <<= df_cfg.node_id_shift; + df_cfg.socket_id_mask <<= df_cfg.node_id_shift; + df_cfg.socket_id_shift += df_cfg.node_id_shift; +} + +static void dump_df_cfg(void) +{ + pr_debug("rev=0x%x", df_cfg.rev); + + pr_debug("component_id_mask=0x%x", df_cfg.component_id_mask); + pr_debug("die_id_mask=0x%x", df_cfg.die_id_mask); + pr_debug("node_id_mask=0x%x", df_cfg.node_id_mask); + pr_debug("socket_id_mask=0x%x", df_cfg.socket_id_mask); + + pr_debug("die_id_shift=0x%x", df_cfg.die_id_shift); + pr_debug("node_id_shift=0x%x", df_cfg.node_id_shift); + pr_debug("socket_id_shift=0x%x", df_cfg.socket_id_shift); + + pr_debug("num_coh_st_maps=%u", df_cfg.num_coh_st_maps); + + pr_debug("flags.legacy_ficaa=%u", df_cfg.flags.legacy_ficaa); + pr_debug("flags.socket_id_shift_quirk=%u", df_cfg.flags.socket_id_shift_quirk); +} + +int get_df_system_info(void) +{ + if (determine_df_rev()) { + pr_warn("amd_atl: Failed to determine DF Revision"); + df_cfg.rev = UNKNOWN; + return -EINVAL; + } + + apply_node_id_shift(); + + get_num_maps(); + + dump_df_cfg(); + + return 0; +} diff --git a/drivers/ras/amd/atl/umc.c b/drivers/ras/amd/atl/umc.c new file mode 100644 index 000000000000..59b6169093f7 --- /dev/null +++ b/drivers/ras/amd/atl/umc.c @@ -0,0 +1,341 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * AMD Address Translation Library + * + * umc.c : Unified Memory Controller (UMC) topology helpers + * + * Copyright (c) 2023, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Author: Yazen Ghannam <Yazen.Ghannam@amd.com> + */ + +#include "internal.h" + +/* + * MI300 has a fixed, model-specific mapping between a UMC instance and + * its related Data Fabric Coherent Station instance. + * + * The MCA_IPID_UMC[InstanceId] field holds a unique identifier for the + * UMC instance within a Node. Use this to find the appropriate Coherent + * Station ID. + * + * Redundant bits were removed from the map below. + */ +static const u16 umc_coh_st_map[32] = { + 0x393, 0x293, 0x193, 0x093, + 0x392, 0x292, 0x192, 0x092, + 0x391, 0x291, 0x191, 0x091, + 0x390, 0x290, 0x190, 0x090, + 0x793, 0x693, 0x593, 0x493, + 0x792, 0x692, 0x592, 0x492, + 0x791, 0x691, 0x591, 0x491, + 0x790, 0x690, 0x590, 0x490, +}; + +#define UMC_ID_MI300 GENMASK(23, 12) +static u8 get_coh_st_inst_id_mi300(struct atl_err *err) +{ + u16 umc_id = FIELD_GET(UMC_ID_MI300, err->ipid); + u8 i; + + for (i = 0; i < ARRAY_SIZE(umc_coh_st_map); i++) { + if (umc_id == umc_coh_st_map[i]) + break; + } + + WARN_ON_ONCE(i >= ARRAY_SIZE(umc_coh_st_map)); + + return i; +} + +/* XOR the bits in @val. */ +static u16 bitwise_xor_bits(u16 val) +{ + u16 tmp = 0; + u8 i; + + for (i = 0; i < 16; i++) + tmp ^= (val >> i) & 0x1; + + return tmp; +} + +struct xor_bits { + bool xor_enable; + u16 col_xor; + u32 row_xor; +}; + +#define NUM_BANK_BITS 4 + +static struct { + /* UMC::CH::AddrHashBank */ + struct xor_bits bank[NUM_BANK_BITS]; + + /* UMC::CH::AddrHashPC */ + struct xor_bits pc; + + /* UMC::CH::AddrHashPC2 */ + u8 bank_xor; +} addr_hash; + +#define MI300_UMC_CH_BASE 0x90000 +#define MI300_ADDR_HASH_BANK0 (MI300_UMC_CH_BASE + 0xC8) +#define MI300_ADDR_HASH_PC (MI300_UMC_CH_BASE + 0xE0) +#define MI300_ADDR_HASH_PC2 (MI300_UMC_CH_BASE + 0xE4) + +#define ADDR_HASH_XOR_EN BIT(0) +#define ADDR_HASH_COL_XOR GENMASK(13, 1) +#define ADDR_HASH_ROW_XOR GENMASK(31, 14) +#define ADDR_HASH_BANK_XOR GENMASK(5, 0) + +/* + * Read UMC::CH::AddrHash{Bank,PC,PC2} registers to get XOR bits used + * for hashing. Do this during module init, since the values will not + * change during run time. + * + * These registers are instantiated for each UMC across each AMD Node. + * However, they should be identically programmed due to the fixed hardware + * design of MI300 systems. So read the values from Node 0 UMC 0 and keep a + * single global structure for simplicity. + */ +int get_addr_hash_mi300(void) +{ + u32 temp; + int ret; + u8 i; + + for (i = 0; i < NUM_BANK_BITS; i++) { + ret = amd_smn_read(0, MI300_ADDR_HASH_BANK0 + (i * 4), &temp); + if (ret) + return ret; + + addr_hash.bank[i].xor_enable = FIELD_GET(ADDR_HASH_XOR_EN, temp); + addr_hash.bank[i].col_xor = FIELD_GET(ADDR_HASH_COL_XOR, temp); + addr_hash.bank[i].row_xor = FIELD_GET(ADDR_HASH_ROW_XOR, temp); + } + + ret = amd_smn_read(0, MI300_ADDR_HASH_PC, &temp); + if (ret) + return ret; + + addr_hash.pc.xor_enable = FIELD_GET(ADDR_HASH_XOR_EN, temp); + addr_hash.pc.col_xor = FIELD_GET(ADDR_HASH_COL_XOR, temp); + addr_hash.pc.row_xor = FIELD_GET(ADDR_HASH_ROW_XOR, temp); + + ret = amd_smn_read(0, MI300_ADDR_HASH_PC2, &temp); + if (ret) + return ret; + + addr_hash.bank_xor = FIELD_GET(ADDR_HASH_BANK_XOR, temp); + + return 0; +} + +/* + * MI300 systems report a DRAM address in MCA_ADDR for DRAM ECC errors. This must + * be converted to the intermediate normalized address (NA) before translating to a + * system physical address. + * + * The DRAM address includes bank, row, and column. Also included are bits for + * pseudochannel (PC) and stack ID (SID). + * + * Abbreviations: (S)tack ID, (P)seudochannel, (R)ow, (B)ank, (C)olumn, (Z)ero + * + * The MCA address format is as follows: + * MCA_ADDR[27:0] = {S[1:0], P[0], R[14:0], B[3:0], C[4:0], Z[0]} + * + * The normalized address format is fixed in hardware and is as follows: + * NA[30:0] = {S[1:0], R[13:0], C4, B[1:0], B[3:2], C[3:2], P, C[1:0], Z[4:0]} + * + * Additionally, the PC and Bank bits may be hashed. This must be accounted for before + * reconstructing the normalized address. + */ +#define MI300_UMC_MCA_COL GENMASK(5, 1) +#define MI300_UMC_MCA_BANK GENMASK(9, 6) +#define MI300_UMC_MCA_ROW GENMASK(24, 10) +#define MI300_UMC_MCA_PC BIT(25) +#define MI300_UMC_MCA_SID GENMASK(27, 26) + +#define MI300_NA_COL_1_0 GENMASK(6, 5) +#define MI300_NA_PC BIT(7) +#define MI300_NA_COL_3_2 GENMASK(9, 8) +#define MI300_NA_BANK_3_2 GENMASK(11, 10) +#define MI300_NA_BANK_1_0 GENMASK(13, 12) +#define MI300_NA_COL_4 BIT(14) +#define MI300_NA_ROW GENMASK(28, 15) +#define MI300_NA_SID GENMASK(30, 29) + +static unsigned long convert_dram_to_norm_addr_mi300(unsigned long addr) +{ + u16 i, col, row, bank, pc, sid, temp; + + col = FIELD_GET(MI300_UMC_MCA_COL, addr); + bank = FIELD_GET(MI300_UMC_MCA_BANK, addr); + row = FIELD_GET(MI300_UMC_MCA_ROW, addr); + pc = FIELD_GET(MI300_UMC_MCA_PC, addr); + sid = FIELD_GET(MI300_UMC_MCA_SID, addr); + + /* Calculate hash for each Bank bit. */ + for (i = 0; i < NUM_BANK_BITS; i++) { + if (!addr_hash.bank[i].xor_enable) + continue; + + temp = bitwise_xor_bits(col & addr_hash.bank[i].col_xor); + temp ^= bitwise_xor_bits(row & addr_hash.bank[i].row_xor); + bank ^= temp << i; + } + + /* Calculate hash for PC bit. */ + if (addr_hash.pc.xor_enable) { + /* Bits SID[1:0] act as Bank[6:5] for PC hash, so apply them here. */ + bank |= sid << 5; + + temp = bitwise_xor_bits(col & addr_hash.pc.col_xor); + temp ^= bitwise_xor_bits(row & addr_hash.pc.row_xor); + temp ^= bitwise_xor_bits(bank & addr_hash.bank_xor); + pc ^= temp; + + /* Drop SID bits for the sake of debug printing later. */ + bank &= 0x1F; + } + + /* Reconstruct the normalized address starting with NA[4:0] = 0 */ + addr = 0; + + /* NA[6:5] = Column[1:0] */ + temp = col & 0x3; + addr |= FIELD_PREP(MI300_NA_COL_1_0, temp); + + /* NA[7] = PC */ + addr |= FIELD_PREP(MI300_NA_PC, pc); + + /* NA[9:8] = Column[3:2] */ + temp = (col >> 2) & 0x3; + addr |= FIELD_PREP(MI300_NA_COL_3_2, temp); + + /* NA[11:10] = Bank[3:2] */ + temp = (bank >> 2) & 0x3; + addr |= FIELD_PREP(MI300_NA_BANK_3_2, temp); + + /* NA[13:12] = Bank[1:0] */ + temp = bank & 0x3; + addr |= FIELD_PREP(MI300_NA_BANK_1_0, temp); + + /* NA[14] = Column[4] */ + temp = (col >> 4) & 0x1; + addr |= FIELD_PREP(MI300_NA_COL_4, temp); + + /* NA[28:15] = Row[13:0] */ + addr |= FIELD_PREP(MI300_NA_ROW, row); + + /* NA[30:29] = SID[1:0] */ + addr |= FIELD_PREP(MI300_NA_SID, sid); + + pr_debug("Addr=0x%016lx", addr); + pr_debug("Bank=%u Row=%u Column=%u PC=%u SID=%u", bank, row, col, pc, sid); + + return addr; +} + +/* + * When a DRAM ECC error occurs on MI300 systems, it is recommended to retire + * all memory within that DRAM row. This applies to the memory with a DRAM + * bank. + * + * To find the memory addresses, loop through permutations of the DRAM column + * bits and find the System Physical address of each. The column bits are used + * to calculate the intermediate Normalized address, so all permutations should + * be checked. + * + * See amd_atl::convert_dram_to_norm_addr_mi300() for MI300 address formats. + */ +#define MI300_NUM_COL BIT(HWEIGHT(MI300_UMC_MCA_COL)) +static void retire_row_mi300(struct atl_err *a_err) +{ + unsigned long addr; + struct page *p; + u8 col; + + for (col = 0; col < MI300_NUM_COL; col++) { + a_err->addr &= ~MI300_UMC_MCA_COL; + a_err->addr |= FIELD_PREP(MI300_UMC_MCA_COL, col); + + addr = amd_convert_umc_mca_addr_to_sys_addr(a_err); + if (IS_ERR_VALUE(addr)) + continue; + + addr = PHYS_PFN(addr); + + /* + * Skip invalid or already poisoned pages to avoid unnecessary + * error messages from memory_failure(). + */ + p = pfn_to_online_page(addr); + if (!p) + continue; + + if (PageHWPoison(p)) + continue; + + memory_failure(addr, 0); + } +} + +void amd_retire_dram_row(struct atl_err *a_err) +{ + if (df_cfg.rev == DF4p5 && df_cfg.flags.heterogeneous) + return retire_row_mi300(a_err); +} +EXPORT_SYMBOL_GPL(amd_retire_dram_row); + +static unsigned long get_addr(unsigned long addr) +{ + if (df_cfg.rev == DF4p5 && df_cfg.flags.heterogeneous) + return convert_dram_to_norm_addr_mi300(addr); + + return addr; +} + +#define MCA_IPID_INST_ID_HI GENMASK_ULL(47, 44) +static u8 get_die_id(struct atl_err *err) +{ + /* + * AMD Node ID is provided in MCA_IPID[InstanceIdHi], and this + * needs to be divided by 4 to get the internal Die ID. + */ + if (df_cfg.rev == DF4p5 && df_cfg.flags.heterogeneous) { + u8 node_id = FIELD_GET(MCA_IPID_INST_ID_HI, err->ipid); + + return node_id >> 2; + } + + /* + * For CPUs, this is the AMD Node ID modulo the number + * of AMD Nodes per socket. + */ + return topology_amd_node_id(err->cpu) % topology_amd_nodes_per_pkg(); +} + +#define UMC_CHANNEL_NUM GENMASK(31, 20) +static u8 get_coh_st_inst_id(struct atl_err *err) +{ + if (df_cfg.rev == DF4p5 && df_cfg.flags.heterogeneous) + return get_coh_st_inst_id_mi300(err); + + return FIELD_GET(UMC_CHANNEL_NUM, err->ipid); +} + +unsigned long convert_umc_mca_addr_to_sys_addr(struct atl_err *err) +{ + u8 socket_id = topology_physical_package_id(err->cpu); + u8 coh_st_inst_id = get_coh_st_inst_id(err); + unsigned long addr = get_addr(err->addr); + u8 die_id = get_die_id(err); + + pr_debug("socket_id=0x%x die_id=0x%x coh_st_inst_id=0x%x addr=0x%016lx", + socket_id, die_id, coh_st_inst_id, addr); + + return norm_to_sys_addr(socket_id, die_id, coh_st_inst_id, addr); +} diff --git a/drivers/ras/amd/fmpm.c b/drivers/ras/amd/fmpm.c new file mode 100644 index 000000000000..2f4ac9591c8f --- /dev/null +++ b/drivers/ras/amd/fmpm.c @@ -0,0 +1,1013 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * FRU (Field-Replaceable Unit) Memory Poison Manager + * + * Copyright (c) 2024, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Authors: + * Naveen Krishna Chatradhi <naveenkrishna.chatradhi@amd.com> + * Muralidhara M K <muralidhara.mk@amd.com> + * Yazen Ghannam <Yazen.Ghannam@amd.com> + * + * Implementation notes, assumptions, and limitations: + * + * - FRU memory poison section and memory poison descriptor definitions are not yet + * included in the UEFI specification. So they are defined here. Afterwards, they + * may be moved to linux/cper.h, if appropriate. + * + * - Platforms based on AMD MI300 systems will be the first to use these structures. + * There are a number of assumptions made here that will need to be generalized + * to support other platforms. + * + * AMD MI300-based platform(s) assumptions: + * - Memory errors are reported through x86 MCA. + * - The entire DRAM row containing a memory error should be retired. + * - There will be (1) FRU memory poison section per CPER. + * - The FRU will be the CPU package (processor socket). + * - The default number of memory poison descriptor entries should be (8). + * - The platform will use ACPI ERST for persistent storage. + * - All FRU records should be saved to persistent storage. Module init will + * fail if any FRU record is not successfully written. + * + * - Boot time memory retirement may occur later than ideal due to dependencies + * on other libraries and drivers. This leaves a gap where bad memory may be + * accessed during early boot stages. + * + * - Enough memory should be pre-allocated for each FRU record to be able to hold + * the expected number of descriptor entries. This, mostly empty, record is + * written to storage during init time. Subsequent writes to the same record + * should allow the Platform to update the stored record in-place. Otherwise, + * if the record is extended, then the Platform may need to perform costly memory + * management operations on the storage. For example, the Platform may spend time + * in Firmware copying and invalidating memory on a relatively slow SPI ROM. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/cper.h> +#include <linux/ras.h> +#include <linux/cpu.h> + +#include <acpi/apei.h> + +#include <asm/cpu_device_id.h> +#include <asm/mce.h> + +#include "../debugfs.h" + +#define INVALID_CPU UINT_MAX + +/* Validation Bits */ +#define FMP_VALID_ARCH_TYPE BIT_ULL(0) +#define FMP_VALID_ARCH BIT_ULL(1) +#define FMP_VALID_ID_TYPE BIT_ULL(2) +#define FMP_VALID_ID BIT_ULL(3) +#define FMP_VALID_LIST_ENTRIES BIT_ULL(4) +#define FMP_VALID_LIST BIT_ULL(5) + +/* FRU Architecture Types */ +#define FMP_ARCH_TYPE_X86_CPUID_1_EAX 0 + +/* FRU ID Types */ +#define FMP_ID_TYPE_X86_PPIN 0 + +/* FRU Memory Poison Section */ +struct cper_sec_fru_mem_poison { + u32 checksum; + u64 validation_bits; + u32 fru_arch_type; + u64 fru_arch; + u32 fru_id_type; + u64 fru_id; + u32 nr_entries; +} __packed; + +/* FRU Descriptor ID Types */ +#define FPD_HW_ID_TYPE_MCA_IPID 0 + +/* FRU Descriptor Address Types */ +#define FPD_ADDR_TYPE_MCA_ADDR 0 + +/* Memory Poison Descriptor */ +struct cper_fru_poison_desc { + u64 timestamp; + u32 hw_id_type; + u64 hw_id; + u32 addr_type; + u64 addr; +} __packed; + +/* Collection of headers and sections for easy pointer use. */ +struct fru_rec { + struct cper_record_header hdr; + struct cper_section_descriptor sec_desc; + struct cper_sec_fru_mem_poison fmp; + struct cper_fru_poison_desc entries[]; +} __packed; + +/* + * Pointers to the complete CPER record of each FRU. + * + * Memory allocation will include padded space for descriptor entries. + */ +static struct fru_rec **fru_records; + +/* system physical addresses array */ +static u64 *spa_entries; + +#define INVALID_SPA ~0ULL + +static struct dentry *fmpm_dfs_dir; +static struct dentry *fmpm_dfs_entries; + +#define CPER_CREATOR_FMP \ + GUID_INIT(0xcd5c2993, 0xf4b2, 0x41b2, 0xb5, 0xd4, 0xf9, 0xc3, \ + 0xa0, 0x33, 0x08, 0x75) + +#define CPER_SECTION_TYPE_FMP \ + GUID_INIT(0x5e4706c1, 0x5356, 0x48c6, 0x93, 0x0b, 0x52, 0xf2, \ + 0x12, 0x0a, 0x44, 0x58) + +/** + * DOC: max_nr_entries (byte) + * Maximum number of descriptor entries possible for each FRU. + * + * Values between '1' and '255' are valid. + * No input or '0' will default to FMPM_DEFAULT_MAX_NR_ENTRIES. + */ +static u8 max_nr_entries; +module_param(max_nr_entries, byte, 0644); +MODULE_PARM_DESC(max_nr_entries, + "Maximum number of memory poison descriptor entries per FRU"); + +#define FMPM_DEFAULT_MAX_NR_ENTRIES 8 + +/* Maximum number of FRUs in the system. */ +#define FMPM_MAX_NR_FRU 256 +static unsigned int max_nr_fru; + +/* Total length of record including headers and list of descriptor entries. */ +static size_t max_rec_len; + +/* Total number of SPA entries across all FRUs. */ +static unsigned int spa_nr_entries; + +/* + * Protect the local records cache in fru_records and prevent concurrent + * writes to storage. This is only needed after init once notifier block + * registration is done. + * + * The majority of a record is fixed at module init and will not change + * during run time. The entries within a record will be updated as new + * errors are reported. The mutex should be held whenever the entries are + * accessed during run time. + */ +static DEFINE_MUTEX(fmpm_update_mutex); + +#define for_each_fru(i, rec) \ + for (i = 0; rec = fru_records[i], i < max_nr_fru; i++) + +static inline u32 get_fmp_len(struct fru_rec *rec) +{ + return rec->sec_desc.section_length - sizeof(struct cper_section_descriptor); +} + +static struct fru_rec *get_fru_record(u64 fru_id) +{ + struct fru_rec *rec; + unsigned int i; + + for_each_fru(i, rec) { + if (rec->fmp.fru_id == fru_id) + return rec; + } + + pr_debug("Record not found for FRU 0x%016llx\n", fru_id); + + return NULL; +} + +/* + * Sum up all bytes within the FRU Memory Poison Section including the Memory + * Poison Descriptor entries. + * + * Don't include the old checksum here. It's a u32 value, so summing each of its + * bytes will give the wrong total. + */ +static u32 do_fmp_checksum(struct cper_sec_fru_mem_poison *fmp, u32 len) +{ + u32 checksum = 0; + u8 *buf, *end; + + /* Skip old checksum. */ + buf = (u8 *)fmp + sizeof(u32); + end = buf + len; + + while (buf < end) + checksum += (u8)(*(buf++)); + + return checksum; +} + +static int update_record_on_storage(struct fru_rec *rec) +{ + u32 len, checksum; + int ret; + + /* Calculate a new checksum. */ + len = get_fmp_len(rec); + + /* Get the current total. */ + checksum = do_fmp_checksum(&rec->fmp, len); + + /* Use the complement value. */ + rec->fmp.checksum = -checksum; + + pr_debug("Writing to storage\n"); + + ret = erst_write(&rec->hdr); + if (ret) { + pr_warn("Storage update failed for FRU 0x%016llx\n", rec->fmp.fru_id); + + if (ret == -ENOSPC) + pr_warn("Not enough space on storage\n"); + } + + return ret; +} + +static bool rec_has_valid_entries(struct fru_rec *rec) +{ + if (!(rec->fmp.validation_bits & FMP_VALID_LIST_ENTRIES)) + return false; + + if (!(rec->fmp.validation_bits & FMP_VALID_LIST)) + return false; + + return true; +} + +static bool fpds_equal(struct cper_fru_poison_desc *old, struct cper_fru_poison_desc *new) +{ + /* + * Ignore timestamp field. + * The same physical error may be reported multiple times due to stuck bits, etc. + * + * Also, order the checks from most->least likely to fail to shortcut the code. + */ + if (old->addr != new->addr) + return false; + + if (old->hw_id != new->hw_id) + return false; + + if (old->addr_type != new->addr_type) + return false; + + if (old->hw_id_type != new->hw_id_type) + return false; + + return true; +} + +static bool rec_has_fpd(struct fru_rec *rec, struct cper_fru_poison_desc *fpd) +{ + unsigned int i; + + for (i = 0; i < rec->fmp.nr_entries; i++) { + struct cper_fru_poison_desc *fpd_i = &rec->entries[i]; + + if (fpds_equal(fpd_i, fpd)) { + pr_debug("Found duplicate record\n"); + return true; + } + } + + return false; +} + +static void save_spa(struct fru_rec *rec, unsigned int entry, + u64 addr, u64 id, unsigned int cpu) +{ + unsigned int i, fru_idx, spa_entry; + struct atl_err a_err; + unsigned long spa; + + if (entry >= max_nr_entries) { + pr_warn_once("FRU descriptor entry %d out-of-bounds (max: %d)\n", + entry, max_nr_entries); + return; + } + + /* spa_nr_entries is always multiple of max_nr_entries */ + for (i = 0; i < spa_nr_entries; i += max_nr_entries) { + fru_idx = i / max_nr_entries; + if (fru_records[fru_idx] == rec) + break; + } + + if (i >= spa_nr_entries) { + pr_warn_once("FRU record %d not found\n", i); + return; + } + + spa_entry = i + entry; + if (spa_entry >= spa_nr_entries) { + pr_warn_once("spa_entries[] index out-of-bounds\n"); + return; + } + + memset(&a_err, 0, sizeof(struct atl_err)); + + a_err.addr = addr; + a_err.ipid = id; + a_err.cpu = cpu; + + spa = amd_convert_umc_mca_addr_to_sys_addr(&a_err); + if (IS_ERR_VALUE(spa)) { + pr_debug("Failed to get system address\n"); + return; + } + + spa_entries[spa_entry] = spa; + pr_debug("fru_idx: %u, entry: %u, spa_entry: %u, spa: 0x%016llx\n", + fru_idx, entry, spa_entry, spa_entries[spa_entry]); +} + +static void update_fru_record(struct fru_rec *rec, struct mce *m) +{ + struct cper_sec_fru_mem_poison *fmp = &rec->fmp; + struct cper_fru_poison_desc fpd, *fpd_dest; + u32 entry = 0; + + mutex_lock(&fmpm_update_mutex); + + memset(&fpd, 0, sizeof(struct cper_fru_poison_desc)); + + fpd.timestamp = m->time; + fpd.hw_id_type = FPD_HW_ID_TYPE_MCA_IPID; + fpd.hw_id = m->ipid; + fpd.addr_type = FPD_ADDR_TYPE_MCA_ADDR; + fpd.addr = m->addr; + + /* This is the first entry, so just save it. */ + if (!rec_has_valid_entries(rec)) + goto save_fpd; + + /* Ignore already recorded errors. */ + if (rec_has_fpd(rec, &fpd)) + goto out_unlock; + + if (rec->fmp.nr_entries >= max_nr_entries) { + pr_warn("Exceeded number of entries for FRU 0x%016llx\n", rec->fmp.fru_id); + goto out_unlock; + } + + entry = fmp->nr_entries; + +save_fpd: + save_spa(rec, entry, m->addr, m->ipid, m->extcpu); + fpd_dest = &rec->entries[entry]; + memcpy(fpd_dest, &fpd, sizeof(struct cper_fru_poison_desc)); + + fmp->nr_entries = entry + 1; + fmp->validation_bits |= FMP_VALID_LIST_ENTRIES; + fmp->validation_bits |= FMP_VALID_LIST; + + pr_debug("Updated FRU 0x%016llx entry #%u\n", fmp->fru_id, entry); + + update_record_on_storage(rec); + +out_unlock: + mutex_unlock(&fmpm_update_mutex); +} + +static void retire_dram_row(u64 addr, u64 id, u32 cpu) +{ + struct atl_err a_err; + + memset(&a_err, 0, sizeof(struct atl_err)); + + a_err.addr = addr; + a_err.ipid = id; + a_err.cpu = cpu; + + amd_retire_dram_row(&a_err); +} + +static int fru_handle_mem_poison(struct notifier_block *nb, unsigned long val, void *data) +{ + struct mce *m = (struct mce *)data; + struct fru_rec *rec; + + if (!mce_is_memory_error(m)) + return NOTIFY_DONE; + + retire_dram_row(m->addr, m->ipid, m->extcpu); + + /* + * An invalid FRU ID should not happen on real errors. But it + * could happen from software error injection, etc. + */ + rec = get_fru_record(m->ppin); + if (!rec) + return NOTIFY_DONE; + + update_fru_record(rec, m); + + return NOTIFY_OK; +} + +static struct notifier_block fru_mem_poison_nb = { + .notifier_call = fru_handle_mem_poison, + .priority = MCE_PRIO_LOWEST, +}; + +static void retire_mem_fmp(struct fru_rec *rec) +{ + struct cper_sec_fru_mem_poison *fmp = &rec->fmp; + unsigned int i, cpu; + + for (i = 0; i < fmp->nr_entries; i++) { + struct cper_fru_poison_desc *fpd = &rec->entries[i]; + unsigned int err_cpu = INVALID_CPU; + + if (fpd->hw_id_type != FPD_HW_ID_TYPE_MCA_IPID) + continue; + + if (fpd->addr_type != FPD_ADDR_TYPE_MCA_ADDR) + continue; + + cpus_read_lock(); + for_each_online_cpu(cpu) { + if (topology_ppin(cpu) == fmp->fru_id) { + err_cpu = cpu; + break; + } + } + cpus_read_unlock(); + + if (err_cpu == INVALID_CPU) + continue; + + retire_dram_row(fpd->addr, fpd->hw_id, err_cpu); + save_spa(rec, i, fpd->addr, fpd->hw_id, err_cpu); + } +} + +static void retire_mem_records(void) +{ + struct fru_rec *rec; + unsigned int i; + + for_each_fru(i, rec) { + if (!rec_has_valid_entries(rec)) + continue; + + retire_mem_fmp(rec); + } +} + +/* Set the CPER Record Header and CPER Section Descriptor fields. */ +static void set_rec_fields(struct fru_rec *rec) +{ + struct cper_section_descriptor *sec_desc = &rec->sec_desc; + struct cper_record_header *hdr = &rec->hdr; + + memcpy(hdr->signature, CPER_SIG_RECORD, CPER_SIG_SIZE); + hdr->revision = CPER_RECORD_REV; + hdr->signature_end = CPER_SIG_END; + + /* + * Currently, it is assumed that there is one FRU Memory Poison + * section per CPER. But this may change for other implementations. + */ + hdr->section_count = 1; + + /* The logged errors are recoverable. Otherwise, they'd never make it here. */ + hdr->error_severity = CPER_SEV_RECOVERABLE; + + hdr->validation_bits = 0; + hdr->record_length = max_rec_len; + hdr->creator_id = CPER_CREATOR_FMP; + hdr->notification_type = CPER_NOTIFY_MCE; + hdr->record_id = cper_next_record_id(); + hdr->flags = CPER_HW_ERROR_FLAGS_PREVERR; + + sec_desc->section_offset = sizeof(struct cper_record_header); + sec_desc->section_length = max_rec_len - sizeof(struct cper_record_header); + sec_desc->revision = CPER_SEC_REV; + sec_desc->validation_bits = 0; + sec_desc->flags = CPER_SEC_PRIMARY; + sec_desc->section_type = CPER_SECTION_TYPE_FMP; + sec_desc->section_severity = CPER_SEV_RECOVERABLE; +} + +static int save_new_records(void) +{ + DECLARE_BITMAP(new_records, FMPM_MAX_NR_FRU); + struct fru_rec *rec; + unsigned int i; + int ret = 0; + + for_each_fru(i, rec) { + if (rec->hdr.record_length) + continue; + + set_rec_fields(rec); + + ret = update_record_on_storage(rec); + if (ret) + goto out_clear; + + set_bit(i, new_records); + } + + return ret; + +out_clear: + for_each_fru(i, rec) { + if (!test_bit(i, new_records)) + continue; + + erst_clear(rec->hdr.record_id); + } + + return ret; +} + +/* Check that the record matches expected types for the current system.*/ +static bool fmp_is_usable(struct fru_rec *rec) +{ + struct cper_sec_fru_mem_poison *fmp = &rec->fmp; + u64 cpuid; + + pr_debug("Validation bits: 0x%016llx\n", fmp->validation_bits); + + if (!(fmp->validation_bits & FMP_VALID_ARCH_TYPE)) { + pr_debug("Arch type unknown\n"); + return false; + } + + if (fmp->fru_arch_type != FMP_ARCH_TYPE_X86_CPUID_1_EAX) { + pr_debug("Arch type not 'x86 Family/Model/Stepping'\n"); + return false; + } + + if (!(fmp->validation_bits & FMP_VALID_ARCH)) { + pr_debug("Arch value unknown\n"); + return false; + } + + cpuid = cpuid_eax(1); + if (fmp->fru_arch != cpuid) { + pr_debug("Arch value mismatch: record = 0x%016llx, system = 0x%016llx\n", + fmp->fru_arch, cpuid); + return false; + } + + if (!(fmp->validation_bits & FMP_VALID_ID_TYPE)) { + pr_debug("FRU ID type unknown\n"); + return false; + } + + if (fmp->fru_id_type != FMP_ID_TYPE_X86_PPIN) { + pr_debug("FRU ID type is not 'x86 PPIN'\n"); + return false; + } + + if (!(fmp->validation_bits & FMP_VALID_ID)) { + pr_debug("FRU ID value unknown\n"); + return false; + } + + return true; +} + +static bool fmp_is_valid(struct fru_rec *rec) +{ + struct cper_sec_fru_mem_poison *fmp = &rec->fmp; + u32 checksum, len; + + len = get_fmp_len(rec); + if (len < sizeof(struct cper_sec_fru_mem_poison)) { + pr_debug("fmp length is too small\n"); + return false; + } + + /* Checksum must sum to zero for the entire section. */ + checksum = do_fmp_checksum(fmp, len) + fmp->checksum; + if (checksum) { + pr_debug("fmp checksum failed: sum = 0x%x\n", checksum); + print_hex_dump_debug("fmp record: ", DUMP_PREFIX_NONE, 16, 1, fmp, len, false); + return false; + } + + if (!fmp_is_usable(rec)) + return false; + + return true; +} + +static struct fru_rec *get_valid_record(struct fru_rec *old) +{ + struct fru_rec *new; + + if (!fmp_is_valid(old)) { + pr_debug("Ignoring invalid record\n"); + return NULL; + } + + new = get_fru_record(old->fmp.fru_id); + if (!new) + pr_debug("Ignoring record for absent FRU\n"); + + return new; +} + +/* + * Fetch saved records from persistent storage. + * + * For each found record: + * - If it was not created by this module, then ignore it. + * - If it is valid, then copy its data to the local cache. + * - If it is not valid, then erase it. + */ +static int get_saved_records(void) +{ + struct fru_rec *old, *new; + u64 record_id; + int ret, pos; + ssize_t len; + + /* + * Assume saved records match current max size. + * + * However, this may not be true depending on module parameters. + */ + old = kmalloc(max_rec_len, GFP_KERNEL); + if (!old) { + ret = -ENOMEM; + goto out; + } + + ret = erst_get_record_id_begin(&pos); + if (ret < 0) + goto out_end; + + while (!erst_get_record_id_next(&pos, &record_id)) { + if (record_id == APEI_ERST_INVALID_RECORD_ID) + goto out_end; + /* + * Make sure to clear temporary buffer between reads to avoid + * leftover data from records of various sizes. + */ + memset(old, 0, max_rec_len); + + len = erst_read_record(record_id, &old->hdr, max_rec_len, + sizeof(struct fru_rec), &CPER_CREATOR_FMP); + if (len < 0) + continue; + + if (len > max_rec_len) { + pr_debug("Found record larger than max_rec_len\n"); + continue; + } + + new = get_valid_record(old); + if (!new) + erst_clear(record_id); + + /* Restore the record */ + memcpy(new, old, len); + } + +out_end: + erst_get_record_id_end(); + kfree(old); +out: + return ret; +} + +static void set_fmp_fields(struct fru_rec *rec, unsigned int cpu) +{ + struct cper_sec_fru_mem_poison *fmp = &rec->fmp; + + fmp->fru_arch_type = FMP_ARCH_TYPE_X86_CPUID_1_EAX; + fmp->validation_bits |= FMP_VALID_ARCH_TYPE; + + /* Assume all CPUs in the system have the same value for now. */ + fmp->fru_arch = cpuid_eax(1); + fmp->validation_bits |= FMP_VALID_ARCH; + + fmp->fru_id_type = FMP_ID_TYPE_X86_PPIN; + fmp->validation_bits |= FMP_VALID_ID_TYPE; + + fmp->fru_id = topology_ppin(cpu); + fmp->validation_bits |= FMP_VALID_ID; +} + +static int init_fmps(void) +{ + struct fru_rec *rec; + unsigned int i, cpu; + int ret = 0; + + for_each_fru(i, rec) { + unsigned int fru_cpu = INVALID_CPU; + + cpus_read_lock(); + for_each_online_cpu(cpu) { + if (topology_physical_package_id(cpu) == i) { + fru_cpu = cpu; + break; + } + } + cpus_read_unlock(); + + if (fru_cpu == INVALID_CPU) { + pr_debug("Failed to find matching CPU for FRU #%u\n", i); + ret = -ENODEV; + break; + } + + set_fmp_fields(rec, fru_cpu); + } + + return ret; +} + +static int get_system_info(void) +{ + /* Only load on MI300A systems for now. */ + if (!(boot_cpu_data.x86_model >= 0x90 && + boot_cpu_data.x86_model <= 0x9f)) + return -ENODEV; + + if (!cpu_feature_enabled(X86_FEATURE_AMD_PPIN)) { + pr_debug("PPIN feature not available\n"); + return -ENODEV; + } + + /* Use CPU socket as FRU for MI300 systems. */ + max_nr_fru = topology_max_packages(); + if (!max_nr_fru) + return -ENODEV; + + if (max_nr_fru > FMPM_MAX_NR_FRU) { + pr_warn("Too many FRUs to manage: found: %u, max: %u\n", + max_nr_fru, FMPM_MAX_NR_FRU); + return -ENODEV; + } + + if (!max_nr_entries) + max_nr_entries = FMPM_DEFAULT_MAX_NR_ENTRIES; + + spa_nr_entries = max_nr_fru * max_nr_entries; + + max_rec_len = sizeof(struct fru_rec); + max_rec_len += sizeof(struct cper_fru_poison_desc) * max_nr_entries; + + pr_info("max FRUs: %u, max entries: %u, max record length: %lu\n", + max_nr_fru, max_nr_entries, max_rec_len); + + return 0; +} + +static void free_records(void) +{ + struct fru_rec *rec; + int i; + + for_each_fru(i, rec) + kfree(rec); + + kfree(fru_records); + kfree(spa_entries); +} + +static int allocate_records(void) +{ + int i, ret = 0; + + fru_records = kcalloc(max_nr_fru, sizeof(struct fru_rec *), GFP_KERNEL); + if (!fru_records) { + ret = -ENOMEM; + goto out; + } + + for (i = 0; i < max_nr_fru; i++) { + fru_records[i] = kzalloc(max_rec_len, GFP_KERNEL); + if (!fru_records[i]) { + ret = -ENOMEM; + goto out_free; + } + } + + spa_entries = kcalloc(spa_nr_entries, sizeof(u64), GFP_KERNEL); + if (!spa_entries) { + ret = -ENOMEM; + goto out_free; + } + + for (i = 0; i < spa_nr_entries; i++) + spa_entries[i] = INVALID_SPA; + + return ret; + +out_free: + while (--i >= 0) + kfree(fru_records[i]); + + kfree(fru_records); +out: + return ret; +} + +static void *fmpm_start(struct seq_file *f, loff_t *pos) +{ + if (*pos >= (spa_nr_entries + 1)) + return NULL; + return pos; +} + +static void *fmpm_next(struct seq_file *f, void *data, loff_t *pos) +{ + if (++(*pos) >= (spa_nr_entries + 1)) + return NULL; + return pos; +} + +static void fmpm_stop(struct seq_file *f, void *data) +{ +} + +#define SHORT_WIDTH 8 +#define U64_WIDTH 18 +#define TIMESTAMP_WIDTH 19 +#define LONG_WIDTH 24 +#define U64_PAD (LONG_WIDTH - U64_WIDTH) +#define TS_PAD (LONG_WIDTH - TIMESTAMP_WIDTH) +static int fmpm_show(struct seq_file *f, void *data) +{ + unsigned int fru_idx, entry, spa_entry, line; + struct cper_fru_poison_desc *fpd; + struct fru_rec *rec; + + line = *(loff_t *)data; + if (line == 0) { + seq_printf(f, "%-*s", SHORT_WIDTH, "fru_idx"); + seq_printf(f, "%-*s", LONG_WIDTH, "fru_id"); + seq_printf(f, "%-*s", SHORT_WIDTH, "entry"); + seq_printf(f, "%-*s", LONG_WIDTH, "timestamp"); + seq_printf(f, "%-*s", LONG_WIDTH, "hw_id"); + seq_printf(f, "%-*s", LONG_WIDTH, "addr"); + seq_printf(f, "%-*s", LONG_WIDTH, "spa"); + goto out_newline; + } + + spa_entry = line - 1; + fru_idx = spa_entry / max_nr_entries; + entry = spa_entry % max_nr_entries; + + rec = fru_records[fru_idx]; + if (!rec) + goto out; + + seq_printf(f, "%-*u", SHORT_WIDTH, fru_idx); + seq_printf(f, "0x%016llx%-*s", rec->fmp.fru_id, U64_PAD, ""); + seq_printf(f, "%-*u", SHORT_WIDTH, entry); + + mutex_lock(&fmpm_update_mutex); + + if (entry >= rec->fmp.nr_entries) { + seq_printf(f, "%-*s", LONG_WIDTH, "*"); + seq_printf(f, "%-*s", LONG_WIDTH, "*"); + seq_printf(f, "%-*s", LONG_WIDTH, "*"); + seq_printf(f, "%-*s", LONG_WIDTH, "*"); + goto out_unlock; + } + + fpd = &rec->entries[entry]; + + seq_printf(f, "%ptT%-*s", &fpd->timestamp, TS_PAD, ""); + seq_printf(f, "0x%016llx%-*s", fpd->hw_id, U64_PAD, ""); + seq_printf(f, "0x%016llx%-*s", fpd->addr, U64_PAD, ""); + + if (spa_entries[spa_entry] == INVALID_SPA) + seq_printf(f, "%-*s", LONG_WIDTH, "*"); + else + seq_printf(f, "0x%016llx%-*s", spa_entries[spa_entry], U64_PAD, ""); + +out_unlock: + mutex_unlock(&fmpm_update_mutex); +out_newline: + seq_putc(f, '\n'); +out: + return 0; +} + +static const struct seq_operations fmpm_seq_ops = { + .start = fmpm_start, + .next = fmpm_next, + .stop = fmpm_stop, + .show = fmpm_show, +}; + +static int fmpm_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &fmpm_seq_ops); +} + +static const struct file_operations fmpm_fops = { + .open = fmpm_open, + .release = seq_release, + .read = seq_read, + .llseek = seq_lseek, +}; + +static void setup_debugfs(void) +{ + struct dentry *dfs = ras_get_debugfs_root(); + + if (!dfs) + return; + + fmpm_dfs_dir = debugfs_create_dir("fmpm", dfs); + if (!fmpm_dfs_dir) + return; + + fmpm_dfs_entries = debugfs_create_file("entries", 0400, fmpm_dfs_dir, NULL, &fmpm_fops); + if (!fmpm_dfs_entries) + debugfs_remove(fmpm_dfs_dir); +} + +static const struct x86_cpu_id fmpm_cpuids[] = { + X86_MATCH_VENDOR_FAM(AMD, 0x19, NULL), + { } +}; +MODULE_DEVICE_TABLE(x86cpu, fmpm_cpuids); + +static int __init fru_mem_poison_init(void) +{ + int ret; + + if (!x86_match_cpu(fmpm_cpuids)) { + ret = -ENODEV; + goto out; + } + + if (erst_disable) { + pr_debug("ERST not available\n"); + ret = -ENODEV; + goto out; + } + + ret = get_system_info(); + if (ret) + goto out; + + ret = allocate_records(); + if (ret) + goto out; + + ret = init_fmps(); + if (ret) + goto out_free; + + ret = get_saved_records(); + if (ret) + goto out_free; + + ret = save_new_records(); + if (ret) + goto out_free; + + setup_debugfs(); + + retire_mem_records(); + + mce_register_decode_chain(&fru_mem_poison_nb); + + pr_info("FRU Memory Poison Manager initialized\n"); + return 0; + +out_free: + free_records(); +out: + return ret; +} + +static void __exit fru_mem_poison_exit(void) +{ + mce_unregister_decode_chain(&fru_mem_poison_nb); + debugfs_remove(fmpm_dfs_dir); + free_records(); +} + +module_init(fru_mem_poison_init); +module_exit(fru_mem_poison_exit); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("FRU Memory Poison Manager"); diff --git a/drivers/ras/cec.c b/drivers/ras/cec.c index 321af498ee11..e440b15fbabc 100644 --- a/drivers/ras/cec.c +++ b/drivers/ras/cec.c @@ -480,9 +480,15 @@ DEFINE_SHOW_ATTRIBUTE(array); static int __init create_debugfs_nodes(void) { - struct dentry *d, *pfn, *decay, *count, *array; + struct dentry *d, *pfn, *decay, *count, *array, *dfs; - d = debugfs_create_dir("cec", ras_debugfs_dir); + dfs = ras_get_debugfs_root(); + if (!dfs) { + pr_warn("Error getting RAS debugfs root!\n"); + return -1; + } + + d = debugfs_create_dir("cec", dfs); if (!d) { pr_warn("Error creating cec debugfs node!\n"); return -1; diff --git a/drivers/ras/debugfs.c b/drivers/ras/debugfs.c index ffb973c328e3..42afd3de68b2 100644 --- a/drivers/ras/debugfs.c +++ b/drivers/ras/debugfs.c @@ -3,10 +3,16 @@ #include <linux/ras.h> #include "debugfs.h" -struct dentry *ras_debugfs_dir; +static struct dentry *ras_debugfs_dir; static atomic_t trace_count = ATOMIC_INIT(0); +struct dentry *ras_get_debugfs_root(void) +{ + return ras_debugfs_dir; +} +EXPORT_SYMBOL_GPL(ras_get_debugfs_root); + int ras_userspace_consumers(void) { return atomic_read(&trace_count); diff --git a/drivers/ras/debugfs.h b/drivers/ras/debugfs.h index c07443b462ad..4749ccdeeba1 100644 --- a/drivers/ras/debugfs.h +++ b/drivers/ras/debugfs.h @@ -4,6 +4,6 @@ #include <linux/debugfs.h> -extern struct dentry *ras_debugfs_dir; +struct dentry *ras_get_debugfs_root(void); #endif /* __RAS_DEBUGFS_H__ */ diff --git a/drivers/ras/ras.c b/drivers/ras/ras.c index 95540ea8dd9d..a6e4792a1b2e 100644 --- a/drivers/ras/ras.c +++ b/drivers/ras/ras.c @@ -10,6 +10,37 @@ #include <linux/ras.h> #include <linux/uuid.h> +#if IS_ENABLED(CONFIG_AMD_ATL) +/* + * Once set, this function pointer should never be unset. + * + * The library module will set this pointer if it successfully loads. The module + * should not be unloaded except for testing and debug purposes. + */ +static unsigned long (*amd_atl_umc_na_to_spa)(struct atl_err *err); + +void amd_atl_register_decoder(unsigned long (*f)(struct atl_err *)) +{ + amd_atl_umc_na_to_spa = f; +} +EXPORT_SYMBOL_GPL(amd_atl_register_decoder); + +void amd_atl_unregister_decoder(void) +{ + amd_atl_umc_na_to_spa = NULL; +} +EXPORT_SYMBOL_GPL(amd_atl_unregister_decoder); + +unsigned long amd_convert_umc_mca_addr_to_sys_addr(struct atl_err *err) +{ + if (!amd_atl_umc_na_to_spa) + return -EINVAL; + + return amd_atl_umc_na_to_spa(err); +} +EXPORT_SYMBOL_GPL(amd_convert_umc_mca_addr_to_sys_addr); +#endif /* CONFIG_AMD_ATL */ + #define CREATE_TRACE_POINTS #define TRACE_INCLUDE_PATH ../../include/ras #include <ras/ras_event.h> diff --git a/drivers/s390/char/vmur.c b/drivers/s390/char/vmur.c index 82efdd20ad01..1d17a83569ce 100644 --- a/drivers/s390/char/vmur.c +++ b/drivers/s390/char/vmur.c @@ -195,7 +195,7 @@ static void free_chan_prog(struct ccw1 *cpa) struct ccw1 *ptr = cpa; while (ptr->cda) { - kfree((void *)(addr_t) ptr->cda); + kfree(phys_to_virt(ptr->cda)); ptr++; } kfree(cpa); @@ -237,7 +237,7 @@ static struct ccw1 *alloc_chan_prog(const char __user *ubuf, int rec_count, free_chan_prog(cpa); return ERR_PTR(-ENOMEM); } - cpa[i].cda = (u32)(addr_t) kbuf; + cpa[i].cda = (u32)virt_to_phys(kbuf); if (copy_from_user(kbuf, ubuf, reclen)) { free_chan_prog(cpa); return ERR_PTR(-EFAULT); diff --git a/drivers/s390/char/zcore.c b/drivers/s390/char/zcore.c index bc3be0330f1d..0969fa01df58 100644 --- a/drivers/s390/char/zcore.c +++ b/drivers/s390/char/zcore.c @@ -29,7 +29,6 @@ #include <asm/irqflags.h> #include <asm/checksum.h> #include <asm/os_info.h> -#include <asm/switch_to.h> #include <asm/maccess.h> #include "sclp.h" diff --git a/drivers/s390/cio/ccwgroup.c b/drivers/s390/cio/ccwgroup.c index aa3292e57e38..6eb8bcd948dc 100644 --- a/drivers/s390/cio/ccwgroup.c +++ b/drivers/s390/cio/ccwgroup.c @@ -31,7 +31,7 @@ * to devices that use multiple subchannels. */ -static struct bus_type ccwgroup_bus_type; +static const struct bus_type ccwgroup_bus_type; static void __ccwgroup_remove_symlinks(struct ccwgroup_device *gdev) { @@ -465,7 +465,7 @@ static void ccwgroup_shutdown(struct device *dev) gdrv->shutdown(gdev); } -static struct bus_type ccwgroup_bus_type = { +static const struct bus_type ccwgroup_bus_type = { .name = "ccwgroup", .dev_groups = ccwgroup_dev_groups, .remove = ccwgroup_remove, diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c index 64ed55c3aed6..3d88899dff7c 100644 --- a/drivers/s390/cio/chsc.c +++ b/drivers/s390/cio/chsc.c @@ -1091,8 +1091,8 @@ int __init chsc_init(void) { int ret; - sei_page = (void *)get_zeroed_page(GFP_KERNEL | GFP_DMA); - chsc_page = (void *)get_zeroed_page(GFP_KERNEL | GFP_DMA); + sei_page = (void *)get_zeroed_page(GFP_KERNEL); + chsc_page = (void *)get_zeroed_page(GFP_KERNEL); if (!sei_page || !chsc_page) { ret = -ENOMEM; goto out_err; diff --git a/drivers/s390/cio/chsc_sch.c b/drivers/s390/cio/chsc_sch.c index 902237d0baef..e6c800653f98 100644 --- a/drivers/s390/cio/chsc_sch.c +++ b/drivers/s390/cio/chsc_sch.c @@ -293,7 +293,7 @@ static int chsc_ioctl_start(void __user *user_area) if (!css_general_characteristics.dynio) /* It makes no sense to try. */ return -EOPNOTSUPP; - chsc_area = (void *)get_zeroed_page(GFP_DMA | GFP_KERNEL); + chsc_area = (void *)get_zeroed_page(GFP_KERNEL); if (!chsc_area) return -ENOMEM; request = kzalloc(sizeof(*request), GFP_KERNEL); @@ -341,7 +341,7 @@ static int chsc_ioctl_on_close_set(void __user *user_area) ret = -ENOMEM; goto out_unlock; } - on_close_chsc_area = (void *)get_zeroed_page(GFP_DMA | GFP_KERNEL); + on_close_chsc_area = (void *)get_zeroed_page(GFP_KERNEL); if (!on_close_chsc_area) { ret = -ENOMEM; goto out_free_request; @@ -393,7 +393,7 @@ static int chsc_ioctl_start_sync(void __user *user_area) struct chsc_sync_area *chsc_area; int ret, ccode; - chsc_area = (void *)get_zeroed_page(GFP_KERNEL | GFP_DMA); + chsc_area = (void *)get_zeroed_page(GFP_KERNEL); if (!chsc_area) return -ENOMEM; if (copy_from_user(chsc_area, user_area, PAGE_SIZE)) { @@ -439,7 +439,7 @@ static int chsc_ioctl_info_channel_path(void __user *user_cd) u8 data[PAGE_SIZE - 20]; } __attribute__ ((packed)) *scpcd_area; - scpcd_area = (void *)get_zeroed_page(GFP_KERNEL | GFP_DMA); + scpcd_area = (void *)get_zeroed_page(GFP_KERNEL); if (!scpcd_area) return -ENOMEM; cd = kzalloc(sizeof(*cd), GFP_KERNEL); @@ -501,7 +501,7 @@ static int chsc_ioctl_info_cu(void __user *user_cd) u8 data[PAGE_SIZE - 20]; } __attribute__ ((packed)) *scucd_area; - scucd_area = (void *)get_zeroed_page(GFP_KERNEL | GFP_DMA); + scucd_area = (void *)get_zeroed_page(GFP_KERNEL); if (!scucd_area) return -ENOMEM; cd = kzalloc(sizeof(*cd), GFP_KERNEL); @@ -564,7 +564,7 @@ static int chsc_ioctl_info_sch_cu(void __user *user_cud) u8 data[PAGE_SIZE - 20]; } __attribute__ ((packed)) *sscud_area; - sscud_area = (void *)get_zeroed_page(GFP_KERNEL | GFP_DMA); + sscud_area = (void *)get_zeroed_page(GFP_KERNEL); if (!sscud_area) return -ENOMEM; cud = kzalloc(sizeof(*cud), GFP_KERNEL); @@ -626,7 +626,7 @@ static int chsc_ioctl_conf_info(void __user *user_ci) u8 data[PAGE_SIZE - 20]; } __attribute__ ((packed)) *sci_area; - sci_area = (void *)get_zeroed_page(GFP_KERNEL | GFP_DMA); + sci_area = (void *)get_zeroed_page(GFP_KERNEL); if (!sci_area) return -ENOMEM; ci = kzalloc(sizeof(*ci), GFP_KERNEL); @@ -697,7 +697,7 @@ static int chsc_ioctl_conf_comp_list(void __user *user_ccl) u32 res; } __attribute__ ((packed)) *cssids_parm; - sccl_area = (void *)get_zeroed_page(GFP_KERNEL | GFP_DMA); + sccl_area = (void *)get_zeroed_page(GFP_KERNEL); if (!sccl_area) return -ENOMEM; ccl = kzalloc(sizeof(*ccl), GFP_KERNEL); @@ -757,7 +757,7 @@ static int chsc_ioctl_chpd(void __user *user_chpd) int ret; chpd = kzalloc(sizeof(*chpd), GFP_KERNEL); - scpd_area = (void *)get_zeroed_page(GFP_KERNEL | GFP_DMA); + scpd_area = (void *)get_zeroed_page(GFP_KERNEL); if (!scpd_area || !chpd) { ret = -ENOMEM; goto out_free; @@ -797,7 +797,7 @@ static int chsc_ioctl_dcal(void __user *user_dcal) u8 data[PAGE_SIZE - 36]; } __attribute__ ((packed)) *sdcal_area; - sdcal_area = (void *)get_zeroed_page(GFP_KERNEL | GFP_DMA); + sdcal_area = (void *)get_zeroed_page(GFP_KERNEL); if (!sdcal_area) return -ENOMEM; dcal = kzalloc(sizeof(*dcal), GFP_KERNEL); diff --git a/drivers/s390/cio/cmf.c b/drivers/s390/cio/cmf.c index 5584aa46c94e..f80dc18e2a76 100644 --- a/drivers/s390/cio/cmf.c +++ b/drivers/s390/cio/cmf.c @@ -169,7 +169,8 @@ static inline void cmf_activate(void *area, unsigned int onoff) " lgr 2,%[mbo]\n" " schm\n" : - : [r1] "d" ((unsigned long)onoff), [mbo] "d" (area) + : [r1] "d" ((unsigned long)onoff), + [mbo] "d" (virt_to_phys(area)) : "1", "2"); } @@ -501,8 +502,7 @@ static int alloc_cmb(struct ccw_device *cdev) WARN_ON(!list_empty(&cmb_area.list)); spin_unlock(&cmb_area.lock); - mem = (void*)__get_free_pages(GFP_KERNEL | GFP_DMA, - get_order(size)); + mem = (void *)__get_free_pages(GFP_KERNEL, get_order(size)); spin_lock(&cmb_area.lock); if (cmb_area.mem) { diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c index 28a88ed2c3aa..094431a62ad5 100644 --- a/drivers/s390/cio/css.c +++ b/drivers/s390/cio/css.c @@ -39,7 +39,7 @@ int max_ssid; #define MAX_CSS_IDX 0 struct channel_subsystem *channel_subsystems[MAX_CSS_IDX + 1]; -static struct bus_type css_bus_type; +static const struct bus_type css_bus_type; int for_each_subchannel(int(*fn)(struct subchannel_id, void *), void *data) @@ -1409,7 +1409,7 @@ static int css_uevent(const struct device *dev, struct kobj_uevent_env *env) return ret; } -static struct bus_type css_bus_type = { +static const struct bus_type css_bus_type = { .name = "css", .match = css_bus_match, .probe = css_probe, diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c index 0cfb179e1bcb..f95d12345d98 100644 --- a/drivers/s390/cio/device.c +++ b/drivers/s390/cio/device.c @@ -49,7 +49,7 @@ static const unsigned long recovery_delay[] = { 3, 30, 300 }; static atomic_t ccw_device_init_count = ATOMIC_INIT(0); static DECLARE_WAIT_QUEUE_HEAD(ccw_device_init_wq); -static struct bus_type ccw_bus_type; +static const struct bus_type ccw_bus_type; /******************* bus type handling ***********************/ @@ -1776,7 +1776,7 @@ static void ccw_device_shutdown(struct device *dev) __disable_cmf(cdev); } -static struct bus_type ccw_bus_type = { +static const struct bus_type ccw_bus_type = { .name = "ccw", .match = ccw_bus_match, .uevent = ccw_uevent, diff --git a/drivers/s390/cio/scm.c b/drivers/s390/cio/scm.c index 6b21ba68c1fe..c7894d61306d 100644 --- a/drivers/s390/cio/scm.c +++ b/drivers/s390/cio/scm.c @@ -42,7 +42,7 @@ static int scmdev_uevent(const struct device *dev, struct kobj_uevent_env *env) return add_uevent_var(env, "MODALIAS=scm:scmdev"); } -static struct bus_type scm_bus_type = { +static const struct bus_type scm_bus_type = { .name = "scm", .probe = scmdev_probe, .remove = scmdev_remove, @@ -228,7 +228,7 @@ int scm_update_information(void) size_t num; int ret; - scm_info = (void *)__get_free_page(GFP_KERNEL | GFP_DMA); + scm_info = (void *)__get_free_page(GFP_KERNEL); if (!scm_info) return -ENOMEM; diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index f46dd6abacd7..cce0bafd4c92 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -38,6 +38,7 @@ #include <linux/debugfs.h> #include <linux/ctype.h> #include <linux/module.h> +#include <asm/uv.h> #include "ap_bus.h" #include "ap_debug.h" @@ -83,14 +84,11 @@ EXPORT_SYMBOL(ap_perms); DEFINE_MUTEX(ap_perms_mutex); EXPORT_SYMBOL(ap_perms_mutex); -/* # of bus scans since init */ -static atomic64_t ap_scan_bus_count; - /* # of bindings complete since init */ static atomic64_t ap_bindings_complete_count = ATOMIC64_INIT(0); -/* completion for initial APQN bindings complete */ -static DECLARE_COMPLETION(ap_init_apqn_bindings_complete); +/* completion for APQN bindings complete */ +static DECLARE_COMPLETION(ap_apqn_bindings_complete); static struct ap_config_info *ap_qci_info; static struct ap_config_info *ap_qci_info_old; @@ -101,12 +99,16 @@ static struct ap_config_info *ap_qci_info_old; debug_info_t *ap_dbf_info; /* - * Workqueue timer for bus rescan. + * AP bus rescan related things. */ -static struct timer_list ap_config_timer; -static int ap_config_time = AP_CONFIG_TIME; -static void ap_scan_bus(struct work_struct *); -static DECLARE_WORK(ap_scan_work, ap_scan_bus); +static bool ap_scan_bus(void); +static bool ap_scan_bus_result; /* result of last ap_scan_bus() */ +static DEFINE_MUTEX(ap_scan_bus_mutex); /* mutex ap_scan_bus() invocations */ +static atomic64_t ap_scan_bus_count; /* counter ap_scan_bus() invocations */ +static int ap_scan_bus_time = AP_CONFIG_TIME; +static struct timer_list ap_scan_bus_timer; +static void ap_scan_bus_wq_callback(struct work_struct *); +static DECLARE_WORK(ap_scan_bus_work, ap_scan_bus_wq_callback); /* * Tasklet & timer for AP request polling and interrupts @@ -135,7 +137,7 @@ static int ap_max_domain_id = 15; /* Maximum adapter id, if not given via qci */ static int ap_max_adapter_id = 63; -static struct bus_type ap_bus_type; +static const struct bus_type ap_bus_type; /* Adapter interrupt definitions */ static void ap_interrupt_handler(struct airq_struct *airq, @@ -753,7 +755,7 @@ static void ap_calc_bound_apqns(unsigned int *apqns, unsigned int *bound) } /* - * After initial ap bus scan do check if all existing APQNs are + * After ap bus scan do check if all existing APQNs are * bound to device drivers. */ static void ap_check_bindings_complete(void) @@ -763,9 +765,9 @@ static void ap_check_bindings_complete(void) if (atomic64_read(&ap_scan_bus_count) >= 1) { ap_calc_bound_apqns(&apqns, &bound); if (bound == apqns) { - if (!completion_done(&ap_init_apqn_bindings_complete)) { - complete_all(&ap_init_apqn_bindings_complete); - AP_DBF_INFO("%s complete\n", __func__); + if (!completion_done(&ap_apqn_bindings_complete)) { + complete_all(&ap_apqn_bindings_complete); + pr_debug("%s all apqn bindings complete\n", __func__); } ap_send_bindings_complete_uevent(); } @@ -782,27 +784,29 @@ static void ap_check_bindings_complete(void) * -ETIME is returned. On failures negative return values are * returned to the caller. */ -int ap_wait_init_apqn_bindings_complete(unsigned long timeout) +int ap_wait_apqn_bindings_complete(unsigned long timeout) { + int rc = 0; long l; - if (completion_done(&ap_init_apqn_bindings_complete)) + if (completion_done(&ap_apqn_bindings_complete)) return 0; if (timeout) l = wait_for_completion_interruptible_timeout( - &ap_init_apqn_bindings_complete, timeout); + &ap_apqn_bindings_complete, timeout); else l = wait_for_completion_interruptible( - &ap_init_apqn_bindings_complete); + &ap_apqn_bindings_complete); if (l < 0) - return l == -ERESTARTSYS ? -EINTR : l; + rc = l == -ERESTARTSYS ? -EINTR : l; else if (l == 0 && timeout) - return -ETIME; + rc = -ETIME; - return 0; + pr_debug("%s rc=%d\n", __func__, rc); + return rc; } -EXPORT_SYMBOL(ap_wait_init_apqn_bindings_complete); +EXPORT_SYMBOL(ap_wait_apqn_bindings_complete); static int __ap_queue_devices_with_id_unregister(struct device *dev, void *data) { @@ -826,8 +830,8 @@ static int __ap_revise_reserved(struct device *dev, void *dummy) drvres = to_ap_drv(dev->driver)->flags & AP_DRIVER_FLAG_DEFAULT; if (!!devres != !!drvres) { - AP_DBF_DBG("%s reprobing queue=%02x.%04x\n", - __func__, card, queue); + pr_debug("%s reprobing queue=%02x.%04x\n", + __func__, card, queue); rc = device_reprobe(dev); if (rc) AP_DBF_WARN("%s reprobing queue=%02x.%04x failed\n", @@ -939,8 +943,6 @@ static int ap_device_probe(struct device *dev) if (is_queue_dev(dev)) hash_del(&to_ap_queue(dev)->hnode); spin_unlock_bh(&ap_queues_lock); - } else { - ap_check_bindings_complete(); } out: @@ -1012,16 +1014,47 @@ void ap_driver_unregister(struct ap_driver *ap_drv) } EXPORT_SYMBOL(ap_driver_unregister); -void ap_bus_force_rescan(void) +/* + * Enforce a synchronous AP bus rescan. + * Returns true if the bus scan finds a change in the AP configuration + * and AP devices have been added or deleted when this function returns. + */ +bool ap_bus_force_rescan(void) { + unsigned long scan_counter = atomic64_read(&ap_scan_bus_count); + bool rc = false; + + pr_debug(">%s scan counter=%lu\n", __func__, scan_counter); + /* Only trigger AP bus scans after the initial scan is done */ - if (atomic64_read(&ap_scan_bus_count) <= 0) - return; + if (scan_counter <= 0) + goto out; + + /* Try to acquire the AP scan bus mutex */ + if (mutex_trylock(&ap_scan_bus_mutex)) { + /* mutex acquired, run the AP bus scan */ + ap_scan_bus_result = ap_scan_bus(); + rc = ap_scan_bus_result; + mutex_unlock(&ap_scan_bus_mutex); + goto out; + } + + /* + * Mutex acquire failed. So there is currently another task + * already running the AP bus scan. Then let's simple wait + * for the lock which means the other task has finished and + * stored the result in ap_scan_bus_result. + */ + if (mutex_lock_interruptible(&ap_scan_bus_mutex)) { + /* some error occurred, ignore and go out */ + goto out; + } + rc = ap_scan_bus_result; + mutex_unlock(&ap_scan_bus_mutex); - /* processing a asynchronous bus rescan */ - del_timer(&ap_config_timer); - queue_work(system_long_wq, &ap_scan_work); - flush_work(&ap_scan_work); +out: + pr_debug("%s rc=%d\n", __func__, rc); + return rc; } EXPORT_SYMBOL(ap_bus_force_rescan); @@ -1030,7 +1063,7 @@ EXPORT_SYMBOL(ap_bus_force_rescan); */ void ap_bus_cfg_chg(void) { - AP_DBF_DBG("%s config change, forcing bus rescan\n", __func__); + pr_debug("%s config change, forcing bus rescan\n", __func__); ap_bus_force_rescan(); } @@ -1250,7 +1283,7 @@ static BUS_ATTR_RO(ap_interrupts); static ssize_t config_time_show(const struct bus_type *bus, char *buf) { - return sysfs_emit(buf, "%d\n", ap_config_time); + return sysfs_emit(buf, "%d\n", ap_scan_bus_time); } static ssize_t config_time_store(const struct bus_type *bus, @@ -1260,8 +1293,8 @@ static ssize_t config_time_store(const struct bus_type *bus, if (sscanf(buf, "%d\n", &time) != 1 || time < 5 || time > 120) return -EINVAL; - ap_config_time = time; - mod_timer(&ap_config_timer, jiffies + ap_config_time * HZ); + ap_scan_bus_time = time; + mod_timer(&ap_scan_bus_timer, jiffies + ap_scan_bus_time * HZ); return count; } @@ -1603,7 +1636,7 @@ static struct attribute *ap_bus_attrs[] = { }; ATTRIBUTE_GROUPS(ap_bus); -static struct bus_type ap_bus_type = { +static const struct bus_type ap_bus_type = { .name = "ap", .bus_groups = ap_bus_groups, .match = &ap_bus_match, @@ -1888,8 +1921,8 @@ static inline void ap_scan_domains(struct ap_card *ac) aq->last_err_rc = AP_RESPONSE_CHECKSTOPPED; } spin_unlock_bh(&aq->lock); - AP_DBF_DBG("%s(%d,%d) queue dev checkstop on\n", - __func__, ac->id, dom); + pr_debug("%s(%d,%d) queue dev checkstop on\n", + __func__, ac->id, dom); /* 'receive' pending messages with -EAGAIN */ ap_flush_queue(aq); goto put_dev_and_continue; @@ -1899,8 +1932,8 @@ static inline void ap_scan_domains(struct ap_card *ac) if (aq->dev_state > AP_DEV_STATE_UNINITIATED) _ap_queue_init_state(aq); spin_unlock_bh(&aq->lock); - AP_DBF_DBG("%s(%d,%d) queue dev checkstop off\n", - __func__, ac->id, dom); + pr_debug("%s(%d,%d) queue dev checkstop off\n", + __func__, ac->id, dom); goto put_dev_and_continue; } /* config state change */ @@ -1912,8 +1945,8 @@ static inline void ap_scan_domains(struct ap_card *ac) aq->last_err_rc = AP_RESPONSE_DECONFIGURED; } spin_unlock_bh(&aq->lock); - AP_DBF_DBG("%s(%d,%d) queue dev config off\n", - __func__, ac->id, dom); + pr_debug("%s(%d,%d) queue dev config off\n", + __func__, ac->id, dom); ap_send_config_uevent(&aq->ap_dev, aq->config); /* 'receive' pending messages with -EAGAIN */ ap_flush_queue(aq); @@ -1924,8 +1957,8 @@ static inline void ap_scan_domains(struct ap_card *ac) if (aq->dev_state > AP_DEV_STATE_UNINITIATED) _ap_queue_init_state(aq); spin_unlock_bh(&aq->lock); - AP_DBF_DBG("%s(%d,%d) queue dev config on\n", - __func__, ac->id, dom); + pr_debug("%s(%d,%d) queue dev config on\n", + __func__, ac->id, dom); ap_send_config_uevent(&aq->ap_dev, aq->config); goto put_dev_and_continue; } @@ -1997,8 +2030,8 @@ static inline void ap_scan_adapter(int ap) ap_scan_rm_card_dev_and_queue_devs(ac); put_device(dev); } else { - AP_DBF_DBG("%s(%d) no type info (no APQN found), ignored\n", - __func__, ap); + pr_debug("%s(%d) no type info (no APQN found), ignored\n", + __func__, ap); } return; } @@ -2010,8 +2043,8 @@ static inline void ap_scan_adapter(int ap) ap_scan_rm_card_dev_and_queue_devs(ac); put_device(dev); } else { - AP_DBF_DBG("%s(%d) no valid type (0) info, ignored\n", - __func__, ap); + pr_debug("%s(%d) no valid type (0) info, ignored\n", + __func__, ap); } return; } @@ -2135,23 +2168,80 @@ static bool ap_get_configuration(void) sizeof(struct ap_config_info)) != 0; } +/* + * ap_config_has_new_aps - Check current against old qci info if + * new adapters have appeared. Returns true if at least one new + * adapter in the apm mask is showing up. Existing adapters or + * receding adapters are not counted. + */ +static bool ap_config_has_new_aps(void) +{ + + unsigned long m[BITS_TO_LONGS(AP_DEVICES)]; + + if (!ap_qci_info) + return false; + + bitmap_andnot(m, (unsigned long *)ap_qci_info->apm, + (unsigned long *)ap_qci_info_old->apm, AP_DEVICES); + if (!bitmap_empty(m, AP_DEVICES)) + return true; + + return false; +} + +/* + * ap_config_has_new_doms - Check current against old qci info if + * new (usage) domains have appeared. Returns true if at least one + * new domain in the aqm mask is showing up. Existing domains or + * receding domains are not counted. + */ +static bool ap_config_has_new_doms(void) +{ + unsigned long m[BITS_TO_LONGS(AP_DOMAINS)]; + + if (!ap_qci_info) + return false; + + bitmap_andnot(m, (unsigned long *)ap_qci_info->aqm, + (unsigned long *)ap_qci_info_old->aqm, AP_DOMAINS); + if (!bitmap_empty(m, AP_DOMAINS)) + return true; + + return false; +} + /** * ap_scan_bus(): Scan the AP bus for new devices - * Runs periodically, workqueue timer (ap_config_time) - * @unused: Unused pointer. + * Always run under mutex ap_scan_bus_mutex protection + * which needs to get locked/unlocked by the caller! + * Returns true if any config change has been detected + * during the scan, otherwise false. */ -static void ap_scan_bus(struct work_struct *unused) +static bool ap_scan_bus(void) { - int ap, config_changed = 0; + bool config_changed; + int ap; + + pr_debug(">%s\n", __func__); - /* config change notify */ + /* (re-)fetch configuration via QCI */ config_changed = ap_get_configuration(); - if (config_changed) + if (config_changed) { + if (ap_config_has_new_aps() || ap_config_has_new_doms()) { + /* + * Appearance of new adapters and/or domains need to + * build new ap devices which need to get bound to an + * device driver. Thus reset the APQN bindings complete + * completion. + */ + reinit_completion(&ap_apqn_bindings_complete); + } + /* post a config change notify */ notify_config_changed(); + } ap_select_domain(); - AP_DBF_DBG("%s running\n", __func__); - /* loop over all possible adapters */ for (ap = 0; ap <= ap_max_adapter_id; ap++) ap_scan_adapter(ap); @@ -2174,23 +2264,56 @@ static void ap_scan_bus(struct work_struct *unused) } if (atomic64_inc_return(&ap_scan_bus_count) == 1) { - AP_DBF_DBG("%s init scan complete\n", __func__); + pr_debug("%s init scan complete\n", __func__); ap_send_init_scan_done_uevent(); - ap_check_bindings_complete(); } - mod_timer(&ap_config_timer, jiffies + ap_config_time * HZ); + ap_check_bindings_complete(); + + mod_timer(&ap_scan_bus_timer, jiffies + ap_scan_bus_time * HZ); + + pr_debug("<%s config_changed=%d\n", __func__, config_changed); + + return config_changed; } -static void ap_config_timeout(struct timer_list *unused) +/* + * Callback for the ap_scan_bus_timer + * Runs periodically, workqueue timer (ap_scan_bus_time) + */ +static void ap_scan_bus_timer_callback(struct timer_list *unused) { - queue_work(system_long_wq, &ap_scan_work); + /* + * schedule work into the system long wq which when + * the work is finally executed, calls the AP bus scan. + */ + queue_work(system_long_wq, &ap_scan_bus_work); +} + +/* + * Callback for the ap_scan_bus_work + */ +static void ap_scan_bus_wq_callback(struct work_struct *unused) +{ + /* + * Try to invoke an ap_scan_bus(). If the mutex acquisition + * fails there is currently another task already running the + * AP scan bus and there is no need to wait and re-trigger the + * scan again. Please note at the end of the scan bus function + * the AP scan bus timer is re-armed which triggers then the + * ap_scan_bus_timer_callback which enqueues a work into the + * system_long_wq which invokes this function here again. + */ + if (mutex_trylock(&ap_scan_bus_mutex)) { + ap_scan_bus_result = ap_scan_bus(); + mutex_unlock(&ap_scan_bus_mutex); + } } static int __init ap_debug_init(void) { ap_dbf_info = debug_register("ap", 2, 1, - DBF_MAX_SPRINTF_ARGS * sizeof(long)); + AP_DBF_MAX_SPRINTF_ARGS * sizeof(long)); debug_register_view(ap_dbf_info, &debug_sprintf_view); debug_set_level(ap_dbf_info, DBF_ERR); @@ -2274,7 +2397,7 @@ static int __init ap_module_init(void) ap_root_device->bus = &ap_bus_type; /* Setup the AP bus rescan timer. */ - timer_setup(&ap_config_timer, ap_config_timeout, 0); + timer_setup(&ap_scan_bus_timer, ap_scan_bus_timer_callback, 0); /* * Setup the high resolution poll timer. @@ -2292,7 +2415,7 @@ static int __init ap_module_init(void) goto out_work; } - queue_work(system_long_wq, &ap_scan_work); + queue_work(system_long_wq, &ap_scan_bus_work); return 0; diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h index 98814839ef30..59c7ed49aa02 100644 --- a/drivers/s390/crypto/ap_bus.h +++ b/drivers/s390/crypto/ap_bus.h @@ -266,7 +266,7 @@ int ap_sb_available(void); bool ap_is_se_guest(void); void ap_wait(enum ap_sm_wait wait); void ap_request_timeout(struct timer_list *t); -void ap_bus_force_rescan(void); +bool ap_bus_force_rescan(void); int ap_test_config_usage_domain(unsigned int domain); int ap_test_config_ctrl_domain(unsigned int domain); @@ -352,8 +352,12 @@ int ap_parse_mask_str(const char *str, * the return value is 0. If the timeout (in jiffies) hits instead * -ETIME is returned. On failures negative return values are * returned to the caller. + * It may be that the AP bus scan finds new devices. Then the + * condition that all APQNs are bound to their device drivers + * is reset to false and this call again blocks until either all + * APQNs are bound to a device driver or the timeout hits again. */ -int ap_wait_init_apqn_bindings_complete(unsigned long timeout); +int ap_wait_apqn_bindings_complete(unsigned long timeout); void ap_send_config_uevent(struct ap_device *ap_dev, bool cfg); void ap_send_online_uevent(struct ap_device *ap_dev, int online); diff --git a/drivers/s390/crypto/ap_debug.h b/drivers/s390/crypto/ap_debug.h index c083ce88a9a6..2f66271b8564 100644 --- a/drivers/s390/crypto/ap_debug.h +++ b/drivers/s390/crypto/ap_debug.h @@ -16,7 +16,7 @@ #define RC2ERR(rc) ((rc) ? DBF_ERR : DBF_INFO) #define RC2WARN(rc) ((rc) ? DBF_WARN : DBF_INFO) -#define DBF_MAX_SPRINTF_ARGS 6 +#define AP_DBF_MAX_SPRINTF_ARGS 6 #define AP_DBF(...) \ debug_sprintf_event(ap_dbf_info, ##__VA_ARGS__) @@ -26,8 +26,6 @@ debug_sprintf_event(ap_dbf_info, DBF_WARN, ##__VA_ARGS__) #define AP_DBF_INFO(...) \ debug_sprintf_event(ap_dbf_info, DBF_INFO, ##__VA_ARGS__) -#define AP_DBF_DBG(...) \ - debug_sprintf_event(ap_dbf_info, DBF_DEBUG, ##__VA_ARGS__) extern debug_info_t *ap_dbf_info; diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c index 682595443145..6e4e8d324a6d 100644 --- a/drivers/s390/crypto/ap_queue.c +++ b/drivers/s390/crypto/ap_queue.c @@ -136,6 +136,8 @@ static struct ap_queue_status ap_sm_recv(struct ap_queue *aq) switch (status.response_code) { case AP_RESPONSE_NORMAL: + print_hex_dump_debug("aprpl: ", DUMP_PREFIX_ADDRESS, 16, 1, + aq->reply->msg, aq->reply->len, false); aq->queue_count = max_t(int, 0, aq->queue_count - 1); if (!status.queue_empty && !aq->queue_count) aq->queue_count++; @@ -169,6 +171,9 @@ static struct ap_queue_status ap_sm_recv(struct ap_queue *aq) aq->queue_count = 0; list_splice_init(&aq->pendingq, &aq->requestq); aq->requestq_count += aq->pendingq_count; + pr_debug("%s queue 0x%02x.%04x rescheduled %d reqs (new req %d)\n", + __func__, AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid), + aq->pendingq_count, aq->requestq_count); aq->pendingq_count = 0; break; default: @@ -243,6 +248,8 @@ static enum ap_sm_wait ap_sm_write(struct ap_queue *aq) /* Start the next request on the queue. */ ap_msg = list_entry(aq->requestq.next, struct ap_message, list); + print_hex_dump_debug("apreq: ", DUMP_PREFIX_ADDRESS, 16, 1, + ap_msg->msg, ap_msg->len, false); status = __ap_send(qid, ap_msg->psmid, ap_msg->msg, ap_msg->len, ap_msg->flags & AP_MSG_FLAG_SPECIAL); @@ -446,9 +453,9 @@ static enum ap_sm_wait ap_sm_assoc_wait(struct ap_queue *aq) case AP_BS_Q_USABLE: /* association is through */ aq->sm_state = AP_SM_STATE_IDLE; - AP_DBF_DBG("%s queue 0x%02x.%04x associated with %u\n", - __func__, AP_QID_CARD(aq->qid), - AP_QID_QUEUE(aq->qid), aq->assoc_idx); + pr_debug("%s queue 0x%02x.%04x associated with %u\n", + __func__, AP_QID_CARD(aq->qid), + AP_QID_QUEUE(aq->qid), aq->assoc_idx); return AP_SM_WAIT_NONE; case AP_BS_Q_USABLE_NO_SECURE_KEY: /* association still pending */ @@ -690,9 +697,9 @@ static ssize_t ap_functions_show(struct device *dev, status = ap_test_queue(aq->qid, 1, &hwinfo); if (status.response_code > AP_RESPONSE_BUSY) { - AP_DBF_DBG("%s RC 0x%02x on tapq(0x%02x.%04x)\n", - __func__, status.response_code, - AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid)); + pr_debug("%s RC 0x%02x on tapq(0x%02x.%04x)\n", + __func__, status.response_code, + AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid)); return -EIO; } @@ -846,9 +853,9 @@ static ssize_t se_bind_show(struct device *dev, status = ap_test_queue(aq->qid, 1, &hwinfo); if (status.response_code > AP_RESPONSE_BUSY) { - AP_DBF_DBG("%s RC 0x%02x on tapq(0x%02x.%04x)\n", - __func__, status.response_code, - AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid)); + pr_debug("%s RC 0x%02x on tapq(0x%02x.%04x)\n", + __func__, status.response_code, + AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid)); return -EIO; } @@ -974,9 +981,9 @@ static ssize_t se_associate_show(struct device *dev, status = ap_test_queue(aq->qid, 1, &hwinfo); if (status.response_code > AP_RESPONSE_BUSY) { - AP_DBF_DBG("%s RC 0x%02x on tapq(0x%02x.%04x)\n", - __func__, status.response_code, - AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid)); + pr_debug("%s RC 0x%02x on tapq(0x%02x.%04x)\n", + __func__, status.response_code, + AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid)); return -EIO; } diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c index 6cfb6b2340c9..dccf664a3d95 100644 --- a/drivers/s390/crypto/pkey_api.c +++ b/drivers/s390/crypto/pkey_api.c @@ -42,24 +42,23 @@ MODULE_DESCRIPTION("s390 protected key interface"); * debug feature data and functions */ -static debug_info_t *debug_info; +static debug_info_t *pkey_dbf_info; -#define DEBUG_DBG(...) debug_sprintf_event(debug_info, 6, ##__VA_ARGS__) -#define DEBUG_INFO(...) debug_sprintf_event(debug_info, 5, ##__VA_ARGS__) -#define DEBUG_WARN(...) debug_sprintf_event(debug_info, 4, ##__VA_ARGS__) -#define DEBUG_ERR(...) debug_sprintf_event(debug_info, 3, ##__VA_ARGS__) +#define PKEY_DBF_INFO(...) debug_sprintf_event(pkey_dbf_info, 5, ##__VA_ARGS__) +#define PKEY_DBF_WARN(...) debug_sprintf_event(pkey_dbf_info, 4, ##__VA_ARGS__) +#define PKEY_DBF_ERR(...) debug_sprintf_event(pkey_dbf_info, 3, ##__VA_ARGS__) static void __init pkey_debug_init(void) { /* 5 arguments per dbf entry (including the format string ptr) */ - debug_info = debug_register("pkey", 1, 1, 5 * sizeof(long)); - debug_register_view(debug_info, &debug_sprintf_view); - debug_set_level(debug_info, 3); + pkey_dbf_info = debug_register("pkey", 1, 1, 5 * sizeof(long)); + debug_register_view(pkey_dbf_info, &debug_sprintf_view); + debug_set_level(pkey_dbf_info, 3); } static void __exit pkey_debug_exit(void) { - debug_unregister(debug_info); + debug_unregister(pkey_dbf_info); } /* inside view of a protected key token (only type 0x00 version 0x01) */ @@ -163,14 +162,14 @@ static int pkey_clr2protkey(u32 keytype, const u8 *clrkey, fc = CPACF_PCKMO_ENC_ECC_ED448_KEY; break; default: - DEBUG_ERR("%s unknown/unsupported keytype %u\n", - __func__, keytype); + PKEY_DBF_ERR("%s unknown/unsupported keytype %u\n", + __func__, keytype); return -EINVAL; } if (*protkeylen < keysize + AES_WK_VP_SIZE) { - DEBUG_ERR("%s prot key buffer size too small: %u < %d\n", - __func__, *protkeylen, keysize + AES_WK_VP_SIZE); + PKEY_DBF_ERR("%s prot key buffer size too small: %u < %d\n", + __func__, *protkeylen, keysize + AES_WK_VP_SIZE); return -EINVAL; } @@ -182,7 +181,7 @@ static int pkey_clr2protkey(u32 keytype, const u8 *clrkey, } /* check for the pckmo subfunction we need now */ if (!cpacf_test_func(&pckmo_functions, fc)) { - DEBUG_ERR("%s pckmo functions not available\n", __func__); + PKEY_DBF_ERR("%s pckmo functions not available\n", __func__); return -ENODEV; } @@ -244,7 +243,7 @@ static int pkey_skey2pkey(const u8 *key, u8 *protkey, } if (rc) - DEBUG_DBG("%s failed rc=%d\n", __func__, rc); + pr_debug("%s failed rc=%d\n", __func__, rc); return rc; } @@ -283,7 +282,7 @@ static int pkey_clr2ep11key(const u8 *clrkey, size_t clrkeylen, out: kfree(apqns); if (rc) - DEBUG_DBG("%s failed rc=%d\n", __func__, rc); + pr_debug("%s failed rc=%d\n", __func__, rc); return rc; } @@ -294,33 +293,36 @@ static int pkey_ep11key2pkey(const u8 *key, size_t keylen, u8 *protkey, u32 *protkeylen, u32 *protkeytype) { u32 nr_apqns, *apqns = NULL; + int i, j, rc = -ENODEV; u16 card, dom; - int i, rc; zcrypt_wait_api_operational(); - /* build a list of apqns suitable for this key */ - rc = ep11_findcard2(&apqns, &nr_apqns, 0xFFFF, 0xFFFF, - ZCRYPT_CEX7, - ap_is_se_guest() ? EP11_API_V6 : EP11_API_V4, - ep11_kb_wkvp(key, keylen)); - if (rc) - goto out; + /* try two times in case of failure */ + for (i = 0; i < 2 && rc; i++) { - /* go through the list of apqns and try to derive an pkey */ - for (rc = -ENODEV, i = 0; i < nr_apqns; i++) { - card = apqns[i] >> 16; - dom = apqns[i] & 0xFFFF; - rc = ep11_kblob2protkey(card, dom, key, keylen, - protkey, protkeylen, protkeytype); - if (rc == 0) - break; + /* build a list of apqns suitable for this key */ + rc = ep11_findcard2(&apqns, &nr_apqns, 0xFFFF, 0xFFFF, + ZCRYPT_CEX7, + ap_is_se_guest() ? EP11_API_V6 : EP11_API_V4, + ep11_kb_wkvp(key, keylen)); + if (rc) + continue; /* retry findcard on failure */ + + /* go through the list of apqns and try to derive an pkey */ + for (rc = -ENODEV, j = 0; j < nr_apqns && rc; j++) { + card = apqns[j] >> 16; + dom = apqns[j] & 0xFFFF; + rc = ep11_kblob2protkey(card, dom, key, keylen, + protkey, protkeylen, protkeytype); + } + + kfree(apqns); } -out: - kfree(apqns); if (rc) - DEBUG_DBG("%s failed rc=%d\n", __func__, rc); + pr_debug("%s failed rc=%d\n", __func__, rc); + return rc; } @@ -336,7 +338,7 @@ static int pkey_verifykey(const struct pkey_seckey *seckey, int rc; /* check the secure key for valid AES secure key */ - rc = cca_check_secaeskeytoken(debug_info, 3, (u8 *)seckey, 0); + rc = cca_check_secaeskeytoken(pkey_dbf_info, 3, (u8 *)seckey, 0); if (rc) goto out; if (pattributes) @@ -351,7 +353,7 @@ static int pkey_verifykey(const struct pkey_seckey *seckey, if (rc > 0) { /* key mkvp matches to old master key mkvp */ - DEBUG_DBG("%s secure key has old mkvp\n", __func__); + pr_debug("%s secure key has old mkvp\n", __func__); if (pattributes) *pattributes |= PKEY_VERIFY_ATTR_OLD_MKVP; rc = 0; @@ -363,7 +365,7 @@ static int pkey_verifykey(const struct pkey_seckey *seckey, *pdomain = domain; out: - DEBUG_DBG("%s rc=%d\n", __func__, rc); + pr_debug("%s rc=%d\n", __func__, rc); return rc; } @@ -379,8 +381,8 @@ static int pkey_genprotkey(u32 keytype, u8 *protkey, keysize = pkey_keytype_aes_to_size(keytype); if (!keysize) { - DEBUG_ERR("%s unknown/unsupported keytype %d\n", __func__, - keytype); + PKEY_DBF_ERR("%s unknown/unsupported keytype %d\n", __func__, + keytype); return -EINVAL; } @@ -428,13 +430,13 @@ static int pkey_verifyprotkey(const u8 *protkey, u32 protkeylen, fc = CPACF_KMC_PAES_256; break; default: - DEBUG_ERR("%s unknown/unsupported keytype %u\n", __func__, - protkeytype); + PKEY_DBF_ERR("%s unknown/unsupported keytype %u\n", __func__, + protkeytype); return -EINVAL; } if (protkeylen != pkeylen) { - DEBUG_ERR("%s invalid protected key size %u for keytype %u\n", - __func__, protkeylen, protkeytype); + PKEY_DBF_ERR("%s invalid protected key size %u for keytype %u\n", + __func__, protkeylen, protkeytype); return -EINVAL; } @@ -446,7 +448,7 @@ static int pkey_verifyprotkey(const u8 *protkey, u32 protkeylen, k = cpacf_kmc(fc | CPACF_ENCRYPT, ¶m, null_msg, dest_buf, sizeof(null_msg)); if (k != sizeof(null_msg)) { - DEBUG_ERR("%s protected key is not valid\n", __func__); + PKEY_DBF_ERR("%s protected key is not valid\n", __func__); return -EKEYREJECTED; } @@ -464,13 +466,13 @@ static int nonccatokaes2pkey(const struct clearkeytoken *t, keysize = pkey_keytype_aes_to_size(t->keytype); if (!keysize) { - DEBUG_ERR("%s unknown/unsupported keytype %u\n", - __func__, t->keytype); + PKEY_DBF_ERR("%s unknown/unsupported keytype %u\n", + __func__, t->keytype); return -EINVAL; } if (t->len != keysize) { - DEBUG_ERR("%s non clear key aes token: invalid key len %u\n", - __func__, t->len); + PKEY_DBF_ERR("%s non clear key aes token: invalid key len %u\n", + __func__, t->len); return -EINVAL; } @@ -505,7 +507,7 @@ try_via_ep11: goto out; failure: - DEBUG_ERR("%s unable to build protected key from clear", __func__); + PKEY_DBF_ERR("%s unable to build protected key from clear", __func__); out: kfree(tmpbuf); @@ -536,14 +538,14 @@ static int nonccatokecc2pkey(const struct clearkeytoken *t, keylen = 64; break; default: - DEBUG_ERR("%s unknown/unsupported keytype %u\n", - __func__, t->keytype); + PKEY_DBF_ERR("%s unknown/unsupported keytype %u\n", + __func__, t->keytype); return -EINVAL; } if (t->len != keylen) { - DEBUG_ERR("%s non clear key ecc token: invalid key len %u\n", - __func__, t->len); + PKEY_DBF_ERR("%s non clear key ecc token: invalid key len %u\n", + __func__, t->len); return -EINVAL; } @@ -551,8 +553,8 @@ static int nonccatokecc2pkey(const struct clearkeytoken *t, rc = pkey_clr2protkey(t->keytype, t->clearkey, protkey, protkeylen, protkeytype); if (rc) { - DEBUG_ERR("%s unable to build protected key from clear", - __func__); + PKEY_DBF_ERR("%s unable to build protected key from clear", + __func__); } return rc; @@ -604,15 +606,15 @@ static int pkey_nonccatok2pkey(const u8 *key, u32 keylen, protkeylen, protkeytype); break; default: - DEBUG_ERR("%s unknown/unsupported non cca clear key type %u\n", - __func__, t->keytype); + PKEY_DBF_ERR("%s unknown/unsupported non cca clear key type %u\n", + __func__, t->keytype); return -EINVAL; } break; } case TOKVER_EP11_AES: { /* check ep11 key for exportable as protected key */ - rc = ep11_check_aes_key(debug_info, 3, key, keylen, 1); + rc = ep11_check_aes_key(pkey_dbf_info, 3, key, keylen, 1); if (rc) goto out; rc = pkey_ep11key2pkey(key, keylen, @@ -621,15 +623,16 @@ static int pkey_nonccatok2pkey(const u8 *key, u32 keylen, } case TOKVER_EP11_AES_WITH_HEADER: /* check ep11 key with header for exportable as protected key */ - rc = ep11_check_aes_key_with_hdr(debug_info, 3, key, keylen, 1); + rc = ep11_check_aes_key_with_hdr(pkey_dbf_info, + 3, key, keylen, 1); if (rc) goto out; rc = pkey_ep11key2pkey(key, keylen, protkey, protkeylen, protkeytype); break; default: - DEBUG_ERR("%s unknown/unsupported non-CCA token version %d\n", - __func__, hdr->version); + PKEY_DBF_ERR("%s unknown/unsupported non-CCA token version %d\n", + __func__, hdr->version); } out: @@ -654,8 +657,8 @@ static int pkey_ccainttok2pkey(const u8 *key, u32 keylen, return -EINVAL; break; default: - DEBUG_ERR("%s unknown/unsupported CCA internal token version %d\n", - __func__, hdr->version); + PKEY_DBF_ERR("%s unknown/unsupported CCA internal token version %d\n", + __func__, hdr->version); return -EINVAL; } @@ -672,7 +675,7 @@ int pkey_keyblob2pkey(const u8 *key, u32 keylen, int rc; if (keylen < sizeof(struct keytoken_header)) { - DEBUG_ERR("%s invalid keylen %d\n", __func__, keylen); + PKEY_DBF_ERR("%s invalid keylen %d\n", __func__, keylen); return -EINVAL; } @@ -686,12 +689,12 @@ int pkey_keyblob2pkey(const u8 *key, u32 keylen, protkey, protkeylen, protkeytype); break; default: - DEBUG_ERR("%s unknown/unsupported blob type %d\n", - __func__, hdr->type); + PKEY_DBF_ERR("%s unknown/unsupported blob type %d\n", + __func__, hdr->type); return -EINVAL; } - DEBUG_DBG("%s rc=%d\n", __func__, rc); + pr_debug("%s rc=%d\n", __func__, rc); return rc; } EXPORT_SYMBOL(pkey_keyblob2pkey); @@ -839,7 +842,7 @@ static int pkey_verifykey2(const u8 *key, size_t keylen, hdr->version == TOKVER_CCA_AES) { struct secaeskeytoken *t = (struct secaeskeytoken *)key; - rc = cca_check_secaeskeytoken(debug_info, 3, key, 0); + rc = cca_check_secaeskeytoken(pkey_dbf_info, 3, key, 0); if (rc) goto out; if (ktype) @@ -869,7 +872,7 @@ static int pkey_verifykey2(const u8 *key, size_t keylen, hdr->version == TOKVER_CCA_VLSC) { struct cipherkeytoken *t = (struct cipherkeytoken *)key; - rc = cca_check_secaescipherkey(debug_info, 3, key, 0, 1); + rc = cca_check_secaescipherkey(pkey_dbf_info, 3, key, 0, 1); if (rc) goto out; if (ktype) @@ -907,7 +910,7 @@ static int pkey_verifykey2(const u8 *key, size_t keylen, struct ep11keyblob *kb = (struct ep11keyblob *)key; int api; - rc = ep11_check_aes_key(debug_info, 3, key, keylen, 1); + rc = ep11_check_aes_key(pkey_dbf_info, 3, key, keylen, 1); if (rc) goto out; if (ktype) @@ -933,8 +936,8 @@ static int pkey_verifykey2(const u8 *key, size_t keylen, struct ep11kblob_header *kh = (struct ep11kblob_header *)key; int api; - rc = ep11_check_aes_key_with_hdr(debug_info, 3, - key, keylen, 1); + rc = ep11_check_aes_key_with_hdr(pkey_dbf_info, + 3, key, keylen, 1); if (rc) goto out; if (ktype) @@ -981,25 +984,27 @@ static int pkey_keyblob2pkey2(const struct pkey_apqn *apqns, size_t nr_apqns, if (hdr->version == TOKVER_CCA_AES) { if (keylen != sizeof(struct secaeskeytoken)) return -EINVAL; - if (cca_check_secaeskeytoken(debug_info, 3, key, 0)) + if (cca_check_secaeskeytoken(pkey_dbf_info, 3, key, 0)) return -EINVAL; } else if (hdr->version == TOKVER_CCA_VLSC) { if (keylen < hdr->len || keylen > MAXCCAVLSCTOKENSIZE) return -EINVAL; - if (cca_check_secaescipherkey(debug_info, 3, key, 0, 1)) + if (cca_check_secaescipherkey(pkey_dbf_info, + 3, key, 0, 1)) return -EINVAL; } else { - DEBUG_ERR("%s unknown CCA internal token version %d\n", - __func__, hdr->version); + PKEY_DBF_ERR("%s unknown CCA internal token version %d\n", + __func__, hdr->version); return -EINVAL; } } else if (hdr->type == TOKTYPE_NON_CCA) { if (hdr->version == TOKVER_EP11_AES) { - if (ep11_check_aes_key(debug_info, 3, key, keylen, 1)) + if (ep11_check_aes_key(pkey_dbf_info, + 3, key, keylen, 1)) return -EINVAL; } else if (hdr->version == TOKVER_EP11_AES_WITH_HEADER) { - if (ep11_check_aes_key_with_hdr(debug_info, 3, - key, keylen, 1)) + if (ep11_check_aes_key_with_hdr(pkey_dbf_info, + 3, key, keylen, 1)) return -EINVAL; } else { return pkey_nonccatok2pkey(key, keylen, @@ -1007,8 +1012,8 @@ static int pkey_keyblob2pkey2(const struct pkey_apqn *apqns, size_t nr_apqns, protkeytype); } } else { - DEBUG_ERR("%s unknown/unsupported blob type %d\n", - __func__, hdr->type); + PKEY_DBF_ERR("%s unknown/unsupported blob type %d\n", + __func__, hdr->type); return -EINVAL; } @@ -1234,50 +1239,53 @@ static int pkey_keyblob2pkey3(const struct pkey_apqn *apqns, size_t nr_apqns, hdr->version == TOKVER_EP11_AES_WITH_HEADER && is_ep11_keyblob(key + sizeof(struct ep11kblob_header))) { /* EP11 AES key blob with header */ - if (ep11_check_aes_key_with_hdr(debug_info, 3, key, keylen, 1)) + if (ep11_check_aes_key_with_hdr(pkey_dbf_info, + 3, key, keylen, 1)) return -EINVAL; } else if (hdr->type == TOKTYPE_NON_CCA && hdr->version == TOKVER_EP11_ECC_WITH_HEADER && is_ep11_keyblob(key + sizeof(struct ep11kblob_header))) { /* EP11 ECC key blob with header */ - if (ep11_check_ecc_key_with_hdr(debug_info, 3, key, keylen, 1)) + if (ep11_check_ecc_key_with_hdr(pkey_dbf_info, + 3, key, keylen, 1)) return -EINVAL; } else if (hdr->type == TOKTYPE_NON_CCA && hdr->version == TOKVER_EP11_AES && is_ep11_keyblob(key)) { /* EP11 AES key blob with header in session field */ - if (ep11_check_aes_key(debug_info, 3, key, keylen, 1)) + if (ep11_check_aes_key(pkey_dbf_info, 3, key, keylen, 1)) return -EINVAL; } else if (hdr->type == TOKTYPE_CCA_INTERNAL) { if (hdr->version == TOKVER_CCA_AES) { /* CCA AES data key */ if (keylen != sizeof(struct secaeskeytoken)) return -EINVAL; - if (cca_check_secaeskeytoken(debug_info, 3, key, 0)) + if (cca_check_secaeskeytoken(pkey_dbf_info, 3, key, 0)) return -EINVAL; } else if (hdr->version == TOKVER_CCA_VLSC) { /* CCA AES cipher key */ if (keylen < hdr->len || keylen > MAXCCAVLSCTOKENSIZE) return -EINVAL; - if (cca_check_secaescipherkey(debug_info, 3, key, 0, 1)) + if (cca_check_secaescipherkey(pkey_dbf_info, + 3, key, 0, 1)) return -EINVAL; } else { - DEBUG_ERR("%s unknown CCA internal token version %d\n", - __func__, hdr->version); + PKEY_DBF_ERR("%s unknown CCA internal token version %d\n", + __func__, hdr->version); return -EINVAL; } } else if (hdr->type == TOKTYPE_CCA_INTERNAL_PKA) { /* CCA ECC (private) key */ if (keylen < sizeof(struct eccprivkeytoken)) return -EINVAL; - if (cca_check_sececckeytoken(debug_info, 3, key, keylen, 1)) + if (cca_check_sececckeytoken(pkey_dbf_info, 3, key, keylen, 1)) return -EINVAL; } else if (hdr->type == TOKTYPE_NON_CCA) { return pkey_nonccatok2pkey(key, keylen, protkey, protkeylen, protkeytype); } else { - DEBUG_ERR("%s unknown/unsupported blob type %d\n", - __func__, hdr->type); + PKEY_DBF_ERR("%s unknown/unsupported blob type %d\n", + __func__, hdr->type); return -EINVAL; } @@ -1350,7 +1358,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, return -EFAULT; rc = cca_genseckey(kgs.cardnr, kgs.domain, kgs.keytype, kgs.seckey.seckey); - DEBUG_DBG("%s cca_genseckey()=%d\n", __func__, rc); + pr_debug("%s cca_genseckey()=%d\n", __func__, rc); if (rc) break; if (copy_to_user(ugs, &kgs, sizeof(kgs))) @@ -1365,7 +1373,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, return -EFAULT; rc = cca_clr2seckey(kcs.cardnr, kcs.domain, kcs.keytype, kcs.clrkey.clrkey, kcs.seckey.seckey); - DEBUG_DBG("%s cca_clr2seckey()=%d\n", __func__, rc); + pr_debug("%s cca_clr2seckey()=%d\n", __func__, rc); if (rc) break; if (copy_to_user(ucs, &kcs, sizeof(kcs))) @@ -1383,7 +1391,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, rc = cca_sec2protkey(ksp.cardnr, ksp.domain, ksp.seckey.seckey, ksp.protkey.protkey, &ksp.protkey.len, &ksp.protkey.type); - DEBUG_DBG("%s cca_sec2protkey()=%d\n", __func__, rc); + pr_debug("%s cca_sec2protkey()=%d\n", __func__, rc); if (rc) break; if (copy_to_user(usp, &ksp, sizeof(ksp))) @@ -1400,7 +1408,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, rc = pkey_clr2protkey(kcp.keytype, kcp.clrkey.clrkey, kcp.protkey.protkey, &kcp.protkey.len, &kcp.protkey.type); - DEBUG_DBG("%s pkey_clr2protkey()=%d\n", __func__, rc); + pr_debug("%s pkey_clr2protkey()=%d\n", __func__, rc); if (rc) break; if (copy_to_user(ucp, &kcp, sizeof(kcp))) @@ -1416,7 +1424,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, return -EFAULT; rc = cca_findcard(kfc.seckey.seckey, &kfc.cardnr, &kfc.domain, 1); - DEBUG_DBG("%s cca_findcard()=%d\n", __func__, rc); + pr_debug("%s cca_findcard()=%d\n", __func__, rc); if (rc < 0) break; if (copy_to_user(ufc, &kfc, sizeof(kfc))) @@ -1432,7 +1440,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, ksp.protkey.len = sizeof(ksp.protkey.protkey); rc = pkey_skey2pkey(ksp.seckey.seckey, ksp.protkey.protkey, &ksp.protkey.len, &ksp.protkey.type); - DEBUG_DBG("%s pkey_skey2pkey()=%d\n", __func__, rc); + pr_debug("%s pkey_skey2pkey()=%d\n", __func__, rc); if (rc) break; if (copy_to_user(usp, &ksp, sizeof(ksp))) @@ -1447,7 +1455,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, return -EFAULT; rc = pkey_verifykey(&kvk.seckey, &kvk.cardnr, &kvk.domain, &kvk.keysize, &kvk.attributes); - DEBUG_DBG("%s pkey_verifykey()=%d\n", __func__, rc); + pr_debug("%s pkey_verifykey()=%d\n", __func__, rc); if (rc) break; if (copy_to_user(uvk, &kvk, sizeof(kvk))) @@ -1463,7 +1471,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, kgp.protkey.len = sizeof(kgp.protkey.protkey); rc = pkey_genprotkey(kgp.keytype, kgp.protkey.protkey, &kgp.protkey.len, &kgp.protkey.type); - DEBUG_DBG("%s pkey_genprotkey()=%d\n", __func__, rc); + pr_debug("%s pkey_genprotkey()=%d\n", __func__, rc); if (rc) break; if (copy_to_user(ugp, &kgp, sizeof(kgp))) @@ -1478,7 +1486,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, return -EFAULT; rc = pkey_verifyprotkey(kvp.protkey.protkey, kvp.protkey.len, kvp.protkey.type); - DEBUG_DBG("%s pkey_verifyprotkey()=%d\n", __func__, rc); + pr_debug("%s pkey_verifyprotkey()=%d\n", __func__, rc); break; } case PKEY_KBLOB2PROTK: { @@ -1494,7 +1502,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, ktp.protkey.len = sizeof(ktp.protkey.protkey); rc = pkey_keyblob2pkey(kkey, ktp.keylen, ktp.protkey.protkey, &ktp.protkey.len, &ktp.protkey.type); - DEBUG_DBG("%s pkey_keyblob2pkey()=%d\n", __func__, rc); + pr_debug("%s pkey_keyblob2pkey()=%d\n", __func__, rc); memzero_explicit(kkey, ktp.keylen); kfree(kkey); if (rc) @@ -1523,7 +1531,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, rc = pkey_genseckey2(apqns, kgs.apqn_entries, kgs.type, kgs.size, kgs.keygenflags, kkey, &klen); - DEBUG_DBG("%s pkey_genseckey2()=%d\n", __func__, rc); + pr_debug("%s pkey_genseckey2()=%d\n", __func__, rc); kfree(apqns); if (rc) { kfree(kkey); @@ -1565,7 +1573,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, rc = pkey_clr2seckey2(apqns, kcs.apqn_entries, kcs.type, kcs.size, kcs.keygenflags, kcs.clrkey.clrkey, kkey, &klen); - DEBUG_DBG("%s pkey_clr2seckey2()=%d\n", __func__, rc); + pr_debug("%s pkey_clr2seckey2()=%d\n", __func__, rc); kfree(apqns); if (rc) { kfree(kkey); @@ -1601,7 +1609,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, rc = pkey_verifykey2(kkey, kvk.keylen, &kvk.cardnr, &kvk.domain, &kvk.type, &kvk.size, &kvk.flags); - DEBUG_DBG("%s pkey_verifykey2()=%d\n", __func__, rc); + pr_debug("%s pkey_verifykey2()=%d\n", __func__, rc); kfree(kkey); if (rc) break; @@ -1630,7 +1638,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, kkey, ktp.keylen, ktp.protkey.protkey, &ktp.protkey.len, &ktp.protkey.type); - DEBUG_DBG("%s pkey_keyblob2pkey2()=%d\n", __func__, rc); + pr_debug("%s pkey_keyblob2pkey2()=%d\n", __func__, rc); kfree(apqns); memzero_explicit(kkey, ktp.keylen); kfree(kkey); @@ -1664,7 +1672,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, } rc = pkey_apqns4key(kkey, kak.keylen, kak.flags, apqns, &nr_apqns); - DEBUG_DBG("%s pkey_apqns4key()=%d\n", __func__, rc); + pr_debug("%s pkey_apqns4key()=%d\n", __func__, rc); kfree(kkey); if (rc && rc != -ENOSPC) { kfree(apqns); @@ -1707,7 +1715,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, } rc = pkey_apqns4keytype(kat.type, kat.cur_mkvp, kat.alt_mkvp, kat.flags, apqns, &nr_apqns); - DEBUG_DBG("%s pkey_apqns4keytype()=%d\n", __func__, rc); + pr_debug("%s pkey_apqns4keytype()=%d\n", __func__, rc); if (rc && rc != -ENOSPC) { kfree(apqns); break; @@ -1757,7 +1765,7 @@ static long pkey_unlocked_ioctl(struct file *filp, unsigned int cmd, rc = pkey_keyblob2pkey3(apqns, ktp.apqn_entries, kkey, ktp.keylen, protkey, &protkeylen, &ktp.pkeytype); - DEBUG_DBG("%s pkey_keyblob2pkey3()=%d\n", __func__, rc); + pr_debug("%s pkey_keyblob2pkey3()=%d\n", __func__, rc); kfree(apqns); memzero_explicit(kkey, ktp.keylen); kfree(kkey); diff --git a/drivers/s390/crypto/vfio_ap_drv.c b/drivers/s390/crypto/vfio_ap_drv.c index a5ab03e42ff1..4aeb3e1213c7 100644 --- a/drivers/s390/crypto/vfio_ap_drv.c +++ b/drivers/s390/crypto/vfio_ap_drv.c @@ -60,7 +60,7 @@ static void vfio_ap_matrix_dev_release(struct device *dev) kfree(matrix_dev); } -static struct bus_type matrix_bus = { +static const struct bus_type matrix_bus = { .name = "matrix", }; diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c index 983b3b16196c..fc169bc61593 100644 --- a/drivers/s390/crypto/vfio_ap_ops.c +++ b/drivers/s390/crypto/vfio_ap_ops.c @@ -659,6 +659,21 @@ static bool vfio_ap_mdev_filter_cdoms(struct ap_matrix_mdev *matrix_mdev) AP_DOMAINS); } +static bool _queue_passable(struct vfio_ap_queue *q) +{ + if (!q) + return false; + + switch (q->reset_status.response_code) { + case AP_RESPONSE_NORMAL: + case AP_RESPONSE_DECONFIGURED: + case AP_RESPONSE_CHECKSTOPPED: + return true; + default: + return false; + } +} + /* * vfio_ap_mdev_filter_matrix - filter the APQNs assigned to the matrix mdev * to ensure no queue devices are passed through to @@ -687,7 +702,6 @@ static bool vfio_ap_mdev_filter_matrix(struct ap_matrix_mdev *matrix_mdev, unsigned long apid, apqi, apqn; DECLARE_BITMAP(prev_shadow_apm, AP_DEVICES); DECLARE_BITMAP(prev_shadow_aqm, AP_DOMAINS); - struct vfio_ap_queue *q; bitmap_copy(prev_shadow_apm, matrix_mdev->shadow_apcb.apm, AP_DEVICES); bitmap_copy(prev_shadow_aqm, matrix_mdev->shadow_apcb.aqm, AP_DOMAINS); @@ -716,8 +730,7 @@ static bool vfio_ap_mdev_filter_matrix(struct ap_matrix_mdev *matrix_mdev, * hardware device. */ apqn = AP_MKQID(apid, apqi); - q = vfio_ap_mdev_get_queue(matrix_mdev, apqn); - if (!q || q->reset_status.response_code) { + if (!_queue_passable(vfio_ap_mdev_get_queue(matrix_mdev, apqn))) { clear_bit_inv(apid, matrix_mdev->shadow_apcb.apm); /* @@ -1691,6 +1704,7 @@ static int apq_status_check(int apqn, struct ap_queue_status *status) switch (status->response_code) { case AP_RESPONSE_NORMAL: case AP_RESPONSE_DECONFIGURED: + case AP_RESPONSE_CHECKSTOPPED: return 0; case AP_RESPONSE_RESET_IN_PROGRESS: case AP_RESPONSE_BUSY: @@ -1747,14 +1761,6 @@ static void apq_reset_check(struct work_struct *reset_work) memcpy(&q->reset_status, &status, sizeof(status)); continue; } - /* - * When an AP adapter is deconfigured, the - * associated queues are reset, so let's set the - * status response code to 0 so the queue may be - * passed through (i.e., not filtered) - */ - if (status.response_code == AP_RESPONSE_DECONFIGURED) - q->reset_status.response_code = 0; if (q->saved_isc != VFIO_AP_ISC_INVALID) vfio_ap_free_aqic_resources(q); break; @@ -1781,12 +1787,7 @@ static void vfio_ap_mdev_reset_queue(struct vfio_ap_queue *q) queue_work(system_long_wq, &q->reset_work); break; case AP_RESPONSE_DECONFIGURED: - /* - * When an AP adapter is deconfigured, the associated - * queues are reset, so let's set the status response code to 0 - * so the queue may be passed through (i.e., not filtered). - */ - q->reset_status.response_code = 0; + case AP_RESPONSE_CHECKSTOPPED: vfio_ap_free_aqic_resources(q); break; default: diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c index 74200f54dfff..02c503f16bc2 100644 --- a/drivers/s390/crypto/zcrypt_api.c +++ b/drivers/s390/crypto/zcrypt_api.c @@ -12,6 +12,9 @@ * Multiple device nodes: Harald Freudenberger <freude@linux.ibm.com> */ +#define KMSG_COMPONENT "zcrypt" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + #include <linux/module.h> #include <linux/init.h> #include <linux/interrupt.h> @@ -57,10 +60,6 @@ DEFINE_SPINLOCK(zcrypt_list_lock); LIST_HEAD(zcrypt_card_list); static atomic_t zcrypt_open_count = ATOMIC_INIT(0); -static atomic_t zcrypt_rescan_count = ATOMIC_INIT(0); - -atomic_t zcrypt_rescan_req = ATOMIC_INIT(0); -EXPORT_SYMBOL(zcrypt_rescan_req); static LIST_HEAD(zcrypt_ops_list); @@ -69,20 +68,15 @@ debug_info_t *zcrypt_dbf_info; /* * Process a rescan of the transport layer. - * - * Returns 1, if the rescan has been processed, otherwise 0. + * Runs a synchronous AP bus rescan. + * Returns true if something has changed (for example the + * bus scan has found and build up new devices) and it is + * worth to do a retry. Otherwise false is returned meaning + * no changes on the AP bus level. */ -static inline int zcrypt_process_rescan(void) -{ - if (atomic_read(&zcrypt_rescan_req)) { - atomic_set(&zcrypt_rescan_req, 0); - atomic_inc(&zcrypt_rescan_count); - ap_bus_force_rescan(); - ZCRYPT_DBF_INFO("%s rescan count=%07d\n", __func__, - atomic_inc_return(&zcrypt_rescan_count)); - return 1; - } - return 0; +static inline bool zcrypt_process_rescan(void) +{ + return ap_bus_force_rescan(); } void zcrypt_msgtype_register(struct zcrypt_ops *zops) @@ -715,8 +709,7 @@ static long zcrypt_rsa_modexpo(struct ap_perms *perms, spin_unlock(&zcrypt_list_lock); if (!pref_zq) { - ZCRYPT_DBF_DBG("%s no matching queue found => ENODEV\n", - __func__); + pr_debug("%s no matching queue found => ENODEV\n", __func__); rc = -ENODEV; goto out; } @@ -820,8 +813,7 @@ static long zcrypt_rsa_crt(struct ap_perms *perms, spin_unlock(&zcrypt_list_lock); if (!pref_zq) { - ZCRYPT_DBF_DBG("%s no matching queue found => ENODEV\n", - __func__); + pr_debug("%s no matching queue found => ENODEV\n", __func__); rc = -ENODEV; goto out; } @@ -865,6 +857,8 @@ static long _zcrypt_send_cprb(bool userspace, struct ap_perms *perms, rc = prep_cca_ap_msg(userspace, xcrb, &ap_msg, &func_code, &domain); if (rc) goto out; + print_hex_dump_debug("ccareq: ", DUMP_PREFIX_ADDRESS, 16, 1, + ap_msg.msg, ap_msg.len, false); tdom = *domain; if (perms != &ap_perms && tdom < AP_DOMAINS) { @@ -940,8 +934,8 @@ static long _zcrypt_send_cprb(bool userspace, struct ap_perms *perms, spin_unlock(&zcrypt_list_lock); if (!pref_zq) { - ZCRYPT_DBF_DBG("%s no match for address %02x.%04x => ENODEV\n", - __func__, xcrb->user_defined, *domain); + pr_debug("%s no match for address %02x.%04x => ENODEV\n", + __func__, xcrb->user_defined, *domain); rc = -ENODEV; goto out; } @@ -952,6 +946,10 @@ static long _zcrypt_send_cprb(bool userspace, struct ap_perms *perms, *domain = AP_QID_QUEUE(qid); rc = pref_zq->ops->send_cprb(userspace, pref_zq, xcrb, &ap_msg); + if (!rc) { + print_hex_dump_debug("ccarpl: ", DUMP_PREFIX_ADDRESS, 16, 1, + ap_msg.msg, ap_msg.len, false); + } spin_lock(&zcrypt_list_lock); zcrypt_drop_queue(pref_zc, pref_zq, mod, wgt); @@ -970,7 +968,26 @@ out: long zcrypt_send_cprb(struct ica_xcRB *xcrb) { - return _zcrypt_send_cprb(false, &ap_perms, NULL, xcrb); + struct zcrypt_track tr; + int rc; + + memset(&tr, 0, sizeof(tr)); + + do { + rc = _zcrypt_send_cprb(false, &ap_perms, &tr, xcrb); + } while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX); + + /* on ENODEV failure: retry once again after a requested rescan */ + if (rc == -ENODEV && zcrypt_process_rescan()) + do { + rc = _zcrypt_send_cprb(false, &ap_perms, &tr, xcrb); + } while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX); + if (rc == -EAGAIN && tr.again_counter >= TRACK_AGAIN_MAX) + rc = -EIO; + if (rc) + pr_debug("%s rc=%d\n", __func__, rc); + + return rc; } EXPORT_SYMBOL(zcrypt_send_cprb); @@ -1045,6 +1062,8 @@ static long _zcrypt_send_ep11_cprb(bool userspace, struct ap_perms *perms, rc = prep_ep11_ap_msg(userspace, xcrb, &ap_msg, &func_code, &domain); if (rc) goto out_free; + print_hex_dump_debug("ep11req: ", DUMP_PREFIX_ADDRESS, 16, 1, + ap_msg.msg, ap_msg.len, false); if (perms != &ap_perms && domain < AUTOSEL_DOM) { if (ap_msg.flags & AP_MSG_FLAG_ADMIN) { @@ -1113,15 +1132,15 @@ static long _zcrypt_send_ep11_cprb(bool userspace, struct ap_perms *perms, if (!pref_zq) { if (targets && target_num == 1) { - ZCRYPT_DBF_DBG("%s no match for address %02x.%04x => ENODEV\n", - __func__, (int)targets->ap_id, - (int)targets->dom_id); + pr_debug("%s no match for address %02x.%04x => ENODEV\n", + __func__, (int)targets->ap_id, + (int)targets->dom_id); } else if (targets) { - ZCRYPT_DBF_DBG("%s no match for %d target addrs => ENODEV\n", - __func__, (int)target_num); + pr_debug("%s no match for %d target addrs => ENODEV\n", + __func__, (int)target_num); } else { - ZCRYPT_DBF_DBG("%s no match for address ff.ffff => ENODEV\n", - __func__); + pr_debug("%s no match for address ff.ffff => ENODEV\n", + __func__); } rc = -ENODEV; goto out_free; @@ -1129,6 +1148,10 @@ static long _zcrypt_send_ep11_cprb(bool userspace, struct ap_perms *perms, qid = pref_zq->queue->qid; rc = pref_zq->ops->send_ep11_cprb(userspace, pref_zq, xcrb, &ap_msg); + if (!rc) { + print_hex_dump_debug("ep11rpl: ", DUMP_PREFIX_ADDRESS, 16, 1, + ap_msg.msg, ap_msg.len, false); + } spin_lock(&zcrypt_list_lock); zcrypt_drop_queue(pref_zc, pref_zq, mod, wgt); @@ -1149,7 +1172,26 @@ out: long zcrypt_send_ep11_cprb(struct ep11_urb *xcrb) { - return _zcrypt_send_ep11_cprb(false, &ap_perms, NULL, xcrb); + struct zcrypt_track tr; + int rc; + + memset(&tr, 0, sizeof(tr)); + + do { + rc = _zcrypt_send_ep11_cprb(false, &ap_perms, &tr, xcrb); + } while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX); + + /* on ENODEV failure: retry once again after a requested rescan */ + if (rc == -ENODEV && zcrypt_process_rescan()) + do { + rc = _zcrypt_send_ep11_cprb(false, &ap_perms, &tr, xcrb); + } while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX); + if (rc == -EAGAIN && tr.again_counter >= TRACK_AGAIN_MAX) + rc = -EIO; + if (rc) + pr_debug("%s rc=%d\n", __func__, rc); + + return rc; } EXPORT_SYMBOL(zcrypt_send_ep11_cprb); @@ -1199,8 +1241,7 @@ static long zcrypt_rng(char *buffer) spin_unlock(&zcrypt_list_lock); if (!pref_zq) { - ZCRYPT_DBF_DBG("%s no matching queue found => ENODEV\n", - __func__); + pr_debug("%s no matching queue found => ENODEV\n", __func__); rc = -ENODEV; goto out; } @@ -1431,20 +1472,17 @@ static int icarsamodexpo_ioctl(struct ap_perms *perms, unsigned long arg) do { rc = zcrypt_rsa_modexpo(perms, &tr, &mex); - if (rc == -EAGAIN) - tr.again_counter++; - } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); - /* on failure: retry once again after a requested rescan */ - if ((rc == -ENODEV) && (zcrypt_process_rescan())) + } while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX); + + /* on ENODEV failure: retry once again after a requested rescan */ + if (rc == -ENODEV && zcrypt_process_rescan()) do { rc = zcrypt_rsa_modexpo(perms, &tr, &mex); - if (rc == -EAGAIN) - tr.again_counter++; - } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); + } while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX); if (rc == -EAGAIN && tr.again_counter >= TRACK_AGAIN_MAX) rc = -EIO; if (rc) { - ZCRYPT_DBF_DBG("ioctl ICARSAMODEXPO rc=%d\n", rc); + pr_debug("ioctl ICARSAMODEXPO rc=%d\n", rc); return rc; } return put_user(mex.outputdatalength, &umex->outputdatalength); @@ -1463,20 +1501,17 @@ static int icarsacrt_ioctl(struct ap_perms *perms, unsigned long arg) do { rc = zcrypt_rsa_crt(perms, &tr, &crt); - if (rc == -EAGAIN) - tr.again_counter++; - } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); - /* on failure: retry once again after a requested rescan */ - if ((rc == -ENODEV) && (zcrypt_process_rescan())) + } while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX); + + /* on ENODEV failure: retry once again after a requested rescan */ + if (rc == -ENODEV && zcrypt_process_rescan()) do { rc = zcrypt_rsa_crt(perms, &tr, &crt); - if (rc == -EAGAIN) - tr.again_counter++; - } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); + } while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX); if (rc == -EAGAIN && tr.again_counter >= TRACK_AGAIN_MAX) rc = -EIO; if (rc) { - ZCRYPT_DBF_DBG("ioctl ICARSACRT rc=%d\n", rc); + pr_debug("ioctl ICARSACRT rc=%d\n", rc); return rc; } return put_user(crt.outputdatalength, &ucrt->outputdatalength); @@ -1495,21 +1530,18 @@ static int zsecsendcprb_ioctl(struct ap_perms *perms, unsigned long arg) do { rc = _zcrypt_send_cprb(true, perms, &tr, &xcrb); - if (rc == -EAGAIN) - tr.again_counter++; - } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); - /* on failure: retry once again after a requested rescan */ - if ((rc == -ENODEV) && (zcrypt_process_rescan())) + } while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX); + + /* on ENODEV failure: retry once again after a requested rescan */ + if (rc == -ENODEV && zcrypt_process_rescan()) do { rc = _zcrypt_send_cprb(true, perms, &tr, &xcrb); - if (rc == -EAGAIN) - tr.again_counter++; - } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); + } while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX); if (rc == -EAGAIN && tr.again_counter >= TRACK_AGAIN_MAX) rc = -EIO; if (rc) - ZCRYPT_DBF_DBG("ioctl ZSENDCPRB rc=%d status=0x%x\n", - rc, xcrb.status); + pr_debug("ioctl ZSENDCPRB rc=%d status=0x%x\n", + rc, xcrb.status); if (copy_to_user(uxcrb, &xcrb, sizeof(xcrb))) return -EFAULT; return rc; @@ -1528,20 +1560,17 @@ static int zsendep11cprb_ioctl(struct ap_perms *perms, unsigned long arg) do { rc = _zcrypt_send_ep11_cprb(true, perms, &tr, &xcrb); - if (rc == -EAGAIN) - tr.again_counter++; - } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); - /* on failure: retry once again after a requested rescan */ - if ((rc == -ENODEV) && (zcrypt_process_rescan())) + } while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX); + + /* on ENODEV failure: retry once again after a requested rescan */ + if (rc == -ENODEV && zcrypt_process_rescan()) do { rc = _zcrypt_send_ep11_cprb(true, perms, &tr, &xcrb); - if (rc == -EAGAIN) - tr.again_counter++; - } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); + } while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX); if (rc == -EAGAIN && tr.again_counter >= TRACK_AGAIN_MAX) rc = -EIO; if (rc) - ZCRYPT_DBF_DBG("ioctl ZSENDEP11CPRB rc=%d\n", rc); + pr_debug("ioctl ZSENDEP11CPRB rc=%d\n", rc); if (copy_to_user(uxcrb, &xcrb, sizeof(xcrb))) return -EFAULT; return rc; @@ -1670,7 +1699,7 @@ static long zcrypt_unlocked_ioctl(struct file *filp, unsigned int cmd, } /* unknown ioctl number */ default: - ZCRYPT_DBF_DBG("unknown ioctl 0x%08x\n", cmd); + pr_debug("unknown ioctl 0x%08x\n", cmd); return -ENOIOCTLCMD; } } @@ -1708,16 +1737,13 @@ static long trans_modexpo32(struct ap_perms *perms, struct file *filp, mex64.n_modulus = compat_ptr(mex32.n_modulus); do { rc = zcrypt_rsa_modexpo(perms, &tr, &mex64); - if (rc == -EAGAIN) - tr.again_counter++; - } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); - /* on failure: retry once again after a requested rescan */ - if ((rc == -ENODEV) && (zcrypt_process_rescan())) + } while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX); + + /* on ENODEV failure: retry once again after a requested rescan */ + if (rc == -ENODEV && zcrypt_process_rescan()) do { rc = zcrypt_rsa_modexpo(perms, &tr, &mex64); - if (rc == -EAGAIN) - tr.again_counter++; - } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); + } while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX); if (rc == -EAGAIN && tr.again_counter >= TRACK_AGAIN_MAX) rc = -EIO; if (rc) @@ -1761,16 +1787,13 @@ static long trans_modexpo_crt32(struct ap_perms *perms, struct file *filp, crt64.u_mult_inv = compat_ptr(crt32.u_mult_inv); do { rc = zcrypt_rsa_crt(perms, &tr, &crt64); - if (rc == -EAGAIN) - tr.again_counter++; - } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); - /* on failure: retry once again after a requested rescan */ - if ((rc == -ENODEV) && (zcrypt_process_rescan())) + } while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX); + + /* on ENODEV failure: retry once again after a requested rescan */ + if (rc == -ENODEV && zcrypt_process_rescan()) do { rc = zcrypt_rsa_crt(perms, &tr, &crt64); - if (rc == -EAGAIN) - tr.again_counter++; - } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); + } while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX); if (rc == -EAGAIN && tr.again_counter >= TRACK_AGAIN_MAX) rc = -EIO; if (rc) @@ -1833,16 +1856,13 @@ static long trans_xcrb32(struct ap_perms *perms, struct file *filp, xcrb64.status = xcrb32.status; do { rc = _zcrypt_send_cprb(true, perms, &tr, &xcrb64); - if (rc == -EAGAIN) - tr.again_counter++; - } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); - /* on failure: retry once again after a requested rescan */ - if ((rc == -ENODEV) && (zcrypt_process_rescan())) + } while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX); + + /* on ENODEV failure: retry once again after a requested rescan */ + if (rc == -ENODEV && zcrypt_process_rescan()) do { rc = _zcrypt_send_cprb(true, perms, &tr, &xcrb64); - if (rc == -EAGAIN) - tr.again_counter++; - } while (rc == -EAGAIN && tr.again_counter < TRACK_AGAIN_MAX); + } while (rc == -EAGAIN && ++tr.again_counter < TRACK_AGAIN_MAX); if (rc == -EAGAIN && tr.again_counter >= TRACK_AGAIN_MAX) rc = -EIO; xcrb32.reply_control_blk_length = xcrb64.reply_control_blk_length; @@ -1914,8 +1934,8 @@ static int zcrypt_rng_data_read(struct hwrng *rng, u32 *data) */ if (zcrypt_rng_buffer_index == 0) { rc = zcrypt_rng((char *)zcrypt_rng_buffer); - /* on failure: retry once again after a requested rescan */ - if ((rc == -ENODEV) && (zcrypt_process_rescan())) + /* on ENODEV failure: retry once again after an AP bus rescan */ + if (rc == -ENODEV && zcrypt_process_rescan()) rc = zcrypt_rng((char *)zcrypt_rng_buffer); if (rc < 0) return -EIO; @@ -1977,7 +1997,7 @@ void zcrypt_rng_device_remove(void) * an asynchronous job. This function waits until these initial jobs * are done and so the zcrypt api should be ready to serve crypto * requests - if there are resources available. The function uses an - * internal timeout of 60s. The very first caller will either wait for + * internal timeout of 30s. The very first caller will either wait for * ap bus bindings complete or the timeout happens. This state will be * remembered for further callers which will only be blocked until a * decision is made (timeout or bindings complete). @@ -1996,8 +2016,8 @@ int zcrypt_wait_api_operational(void) switch (zcrypt_wait_api_state) { case 0: /* initial state, invoke wait for the ap bus complete */ - rc = ap_wait_init_apqn_bindings_complete( - msecs_to_jiffies(60 * 1000)); + rc = ap_wait_apqn_bindings_complete( + msecs_to_jiffies(ZCRYPT_WAIT_BINDINGS_COMPLETE_MS)); switch (rc) { case 0: /* ap bus bindings are complete */ @@ -2014,8 +2034,8 @@ int zcrypt_wait_api_operational(void) break; default: /* other failure */ - ZCRYPT_DBF_DBG("%s ap_wait_init_apqn_bindings_complete()=%d\n", - __func__, rc); + pr_debug("%s ap_wait_init_apqn_bindings_complete()=%d\n", + __func__, rc); break; } break; @@ -2038,7 +2058,7 @@ EXPORT_SYMBOL(zcrypt_wait_api_operational); int __init zcrypt_debug_init(void) { zcrypt_dbf_info = debug_register("zcrypt", 2, 1, - DBF_MAX_SPRINTF_ARGS * sizeof(long)); + ZCRYPT_DBF_MAX_SPRINTF_ARGS * sizeof(long)); debug_register_view(zcrypt_dbf_info, &debug_sprintf_view); debug_set_level(zcrypt_dbf_info, DBF_ERR); diff --git a/drivers/s390/crypto/zcrypt_api.h b/drivers/s390/crypto/zcrypt_api.h index de659954c8f7..4ed481df57ca 100644 --- a/drivers/s390/crypto/zcrypt_api.h +++ b/drivers/s390/crypto/zcrypt_api.h @@ -38,6 +38,15 @@ */ #define ZCRYPT_RNG_BUFFER_SIZE 4096 +/** + * The zcrypt_wait_api_operational() function waits this + * amount in milliseconds for ap_wait_aqpn_bindings_complete(). + * Also on a cprb send failure with ENODEV the send functions + * trigger an ap bus rescan and wait this time in milliseconds + * for ap_wait_aqpn_bindings_complete() before resending. + */ +#define ZCRYPT_WAIT_BINDINGS_COMPLETE_MS 30000 + /* * Identifier for Crypto Request Performance Index */ diff --git a/drivers/s390/crypto/zcrypt_ccamisc.c b/drivers/s390/crypto/zcrypt_ccamisc.c index 263fe182648b..0a3a678ffc7e 100644 --- a/drivers/s390/crypto/zcrypt_ccamisc.c +++ b/drivers/s390/crypto/zcrypt_ccamisc.c @@ -23,11 +23,6 @@ #include "zcrypt_msgtype6.h" #include "zcrypt_ccamisc.h" -#define DEBUG_DBG(...) ZCRYPT_DBF(DBF_DEBUG, ##__VA_ARGS__) -#define DEBUG_INFO(...) ZCRYPT_DBF(DBF_INFO, ##__VA_ARGS__) -#define DEBUG_WARN(...) ZCRYPT_DBF(DBF_WARN, ##__VA_ARGS__) -#define DEBUG_ERR(...) ZCRYPT_DBF(DBF_ERR, ##__VA_ARGS__) - /* Size of parameter block used for all cca requests/replies */ #define PARMBSIZE 512 @@ -367,8 +362,8 @@ int cca_genseckey(u16 cardnr, u16 domain, memcpy(preqparm->lv1.key_length, "KEYLN32 ", 8); break; default: - DEBUG_ERR("%s unknown/unsupported keybitsize %d\n", - __func__, keybitsize); + ZCRYPT_DBF_ERR("%s unknown/unsupported keybitsize %d\n", + __func__, keybitsize); rc = -EINVAL; goto out; } @@ -386,15 +381,15 @@ int cca_genseckey(u16 cardnr, u16 domain, /* forward xcrb with request CPRB and reply CPRB to zcrypt dd */ rc = zcrypt_send_cprb(&xcrb); if (rc) { - DEBUG_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, errno %d\n", - __func__, (int)cardnr, (int)domain, rc); + ZCRYPT_DBF_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, errno %d\n", + __func__, (int)cardnr, (int)domain, rc); goto out; } /* check response returncode and reasoncode */ if (prepcblk->ccp_rtcode != 0) { - DEBUG_ERR("%s secure key generate failure, card response %d/%d\n", - __func__, + ZCRYPT_DBF_ERR("%s secure key generate failure, card response %d/%d\n", + __func__, (int)prepcblk->ccp_rtcode, (int)prepcblk->ccp_rscode); rc = -EIO; @@ -411,8 +406,8 @@ int cca_genseckey(u16 cardnr, u16 domain, - sizeof(prepparm->lv3.keyblock.toklen) - sizeof(prepparm->lv3.keyblock.tokattr); if (seckeysize != SECKEYBLOBSIZE) { - DEBUG_ERR("%s secure token size mismatch %d != %d bytes\n", - __func__, seckeysize, SECKEYBLOBSIZE); + ZCRYPT_DBF_ERR("%s secure token size mismatch %d != %d bytes\n", + __func__, seckeysize, SECKEYBLOBSIZE); rc = -EIO; goto out; } @@ -505,8 +500,8 @@ int cca_clr2seckey(u16 cardnr, u16 domain, u32 keybitsize, keysize = 32; break; default: - DEBUG_ERR("%s unknown/unsupported keybitsize %d\n", - __func__, keybitsize); + ZCRYPT_DBF_ERR("%s unknown/unsupported keybitsize %d\n", + __func__, keybitsize); rc = -EINVAL; goto out; } @@ -524,17 +519,17 @@ int cca_clr2seckey(u16 cardnr, u16 domain, u32 keybitsize, /* forward xcrb with request CPRB and reply CPRB to zcrypt dd */ rc = zcrypt_send_cprb(&xcrb); if (rc) { - DEBUG_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", - __func__, (int)cardnr, (int)domain, rc); + ZCRYPT_DBF_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", + __func__, (int)cardnr, (int)domain, rc); goto out; } /* check response returncode and reasoncode */ if (prepcblk->ccp_rtcode != 0) { - DEBUG_ERR("%s clear key import failure, card response %d/%d\n", - __func__, - (int)prepcblk->ccp_rtcode, - (int)prepcblk->ccp_rscode); + ZCRYPT_DBF_ERR("%s clear key import failure, card response %d/%d\n", + __func__, + (int)prepcblk->ccp_rtcode, + (int)prepcblk->ccp_rscode); rc = -EIO; goto out; } @@ -549,8 +544,8 @@ int cca_clr2seckey(u16 cardnr, u16 domain, u32 keybitsize, - sizeof(prepparm->lv3.keyblock.toklen) - sizeof(prepparm->lv3.keyblock.tokattr); if (seckeysize != SECKEYBLOBSIZE) { - DEBUG_ERR("%s secure token size mismatch %d != %d bytes\n", - __func__, seckeysize, SECKEYBLOBSIZE); + ZCRYPT_DBF_ERR("%s secure token size mismatch %d != %d bytes\n", + __func__, seckeysize, SECKEYBLOBSIZE); rc = -EIO; goto out; } @@ -651,17 +646,17 @@ int cca_sec2protkey(u16 cardnr, u16 domain, /* forward xcrb with request CPRB and reply CPRB to zcrypt dd */ rc = zcrypt_send_cprb(&xcrb); if (rc) { - DEBUG_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", - __func__, (int)cardnr, (int)domain, rc); + ZCRYPT_DBF_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", + __func__, (int)cardnr, (int)domain, rc); goto out; } /* check response returncode and reasoncode */ if (prepcblk->ccp_rtcode != 0) { - DEBUG_ERR("%s unwrap secure key failure, card response %d/%d\n", - __func__, - (int)prepcblk->ccp_rtcode, - (int)prepcblk->ccp_rscode); + ZCRYPT_DBF_ERR("%s unwrap secure key failure, card response %d/%d\n", + __func__, + (int)prepcblk->ccp_rtcode, + (int)prepcblk->ccp_rscode); if (prepcblk->ccp_rtcode == 8 && prepcblk->ccp_rscode == 2290) rc = -EAGAIN; else @@ -669,10 +664,10 @@ int cca_sec2protkey(u16 cardnr, u16 domain, goto out; } if (prepcblk->ccp_rscode != 0) { - DEBUG_WARN("%s unwrap secure key warning, card response %d/%d\n", - __func__, - (int)prepcblk->ccp_rtcode, - (int)prepcblk->ccp_rscode); + ZCRYPT_DBF_WARN("%s unwrap secure key warning, card response %d/%d\n", + __func__, + (int)prepcblk->ccp_rtcode, + (int)prepcblk->ccp_rscode); } /* process response cprb param block */ @@ -683,8 +678,8 @@ int cca_sec2protkey(u16 cardnr, u16 domain, /* check the returned keyblock */ if (prepparm->lv3.ckb.version != 0x01 && prepparm->lv3.ckb.version != 0x02) { - DEBUG_ERR("%s reply param keyblock version mismatch 0x%02x\n", - __func__, (int)prepparm->lv3.ckb.version); + ZCRYPT_DBF_ERR("%s reply param keyblock version mismatch 0x%02x\n", + __func__, (int)prepparm->lv3.ckb.version); rc = -EIO; goto out; } @@ -707,8 +702,8 @@ int cca_sec2protkey(u16 cardnr, u16 domain, *protkeytype = PKEY_KEYTYPE_AES_256; break; default: - DEBUG_ERR("%s unknown/unsupported keylen %d\n", - __func__, prepparm->lv3.ckb.len); + ZCRYPT_DBF_ERR("%s unknown/unsupported keylen %d\n", + __func__, prepparm->lv3.ckb.len); rc = -EIO; goto out; } @@ -840,9 +835,8 @@ int cca_gencipherkey(u16 cardnr, u16 domain, u32 keybitsize, u32 keygenflags, case 256: break; default: - DEBUG_ERR( - "%s unknown/unsupported keybitsize %d\n", - __func__, keybitsize); + ZCRYPT_DBF_ERR("%s unknown/unsupported keybitsize %d\n", + __func__, keybitsize); rc = -EINVAL; goto out; } @@ -880,19 +874,17 @@ int cca_gencipherkey(u16 cardnr, u16 domain, u32 keybitsize, u32 keygenflags, /* forward xcrb with request CPRB and reply CPRB to zcrypt dd */ rc = zcrypt_send_cprb(&xcrb); if (rc) { - DEBUG_ERR( - "%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", - __func__, (int)cardnr, (int)domain, rc); + ZCRYPT_DBF_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", + __func__, (int)cardnr, (int)domain, rc); goto out; } /* check response returncode and reasoncode */ if (prepcblk->ccp_rtcode != 0) { - DEBUG_ERR( - "%s cipher key generate failure, card response %d/%d\n", - __func__, - (int)prepcblk->ccp_rtcode, - (int)prepcblk->ccp_rscode); + ZCRYPT_DBF_ERR("%s cipher key generate failure, card response %d/%d\n", + __func__, + (int)prepcblk->ccp_rtcode, + (int)prepcblk->ccp_rscode); rc = -EIO; goto out; } @@ -905,8 +897,8 @@ int cca_gencipherkey(u16 cardnr, u16 domain, u32 keybitsize, u32 keygenflags, /* do some plausibility checks on the key block */ if (prepparm->kb.len < 120 + 5 * sizeof(uint16_t) || prepparm->kb.len > 136 + 5 * sizeof(uint16_t)) { - DEBUG_ERR("%s reply with invalid or unknown key block\n", - __func__); + ZCRYPT_DBF_ERR("%s reply with invalid or unknown key block\n", + __func__); rc = -EIO; goto out; } @@ -1048,19 +1040,17 @@ static int _ip_cprb_helper(u16 cardnr, u16 domain, /* forward xcrb with request CPRB and reply CPRB to zcrypt dd */ rc = zcrypt_send_cprb(&xcrb); if (rc) { - DEBUG_ERR( - "%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", - __func__, (int)cardnr, (int)domain, rc); + ZCRYPT_DBF_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", + __func__, (int)cardnr, (int)domain, rc); goto out; } /* check response returncode and reasoncode */ if (prepcblk->ccp_rtcode != 0) { - DEBUG_ERR( - "%s CSNBKPI2 failure, card response %d/%d\n", - __func__, - (int)prepcblk->ccp_rtcode, - (int)prepcblk->ccp_rscode); + ZCRYPT_DBF_ERR("%s CSNBKPI2 failure, card response %d/%d\n", + __func__, + (int)prepcblk->ccp_rtcode, + (int)prepcblk->ccp_rscode); rc = -EIO; goto out; } @@ -1073,8 +1063,8 @@ static int _ip_cprb_helper(u16 cardnr, u16 domain, /* do some plausibility checks on the key block */ if (prepparm->kb.len < 120 + 3 * sizeof(uint16_t) || prepparm->kb.len > 136 + 3 * sizeof(uint16_t)) { - DEBUG_ERR("%s reply with invalid or unknown key block\n", - __func__); + ZCRYPT_DBF_ERR("%s reply with invalid or unknown key block\n", + __func__); rc = -EIO; goto out; } @@ -1132,33 +1122,29 @@ int cca_clr2cipherkey(u16 card, u16 dom, u32 keybitsize, u32 keygenflags, rc = _ip_cprb_helper(card, dom, "AES ", "FIRST ", "MIN3PART", exorbuf, keybitsize, token, &tokensize); if (rc) { - DEBUG_ERR( - "%s clear key import 1/4 with CSNBKPI2 failed, rc=%d\n", - __func__, rc); + ZCRYPT_DBF_ERR("%s clear key import 1/4 with CSNBKPI2 failed, rc=%d\n", + __func__, rc); goto out; } rc = _ip_cprb_helper(card, dom, "AES ", "ADD-PART", NULL, clrkey, keybitsize, token, &tokensize); if (rc) { - DEBUG_ERR( - "%s clear key import 2/4 with CSNBKPI2 failed, rc=%d\n", - __func__, rc); + ZCRYPT_DBF_ERR("%s clear key import 2/4 with CSNBKPI2 failed, rc=%d\n", + __func__, rc); goto out; } rc = _ip_cprb_helper(card, dom, "AES ", "ADD-PART", NULL, exorbuf, keybitsize, token, &tokensize); if (rc) { - DEBUG_ERR( - "%s clear key import 3/4 with CSNBKPI2 failed, rc=%d\n", - __func__, rc); + ZCRYPT_DBF_ERR("%s clear key import 3/4 with CSNBKPI2 failed, rc=%d\n", + __func__, rc); goto out; } rc = _ip_cprb_helper(card, dom, "AES ", "COMPLETE", NULL, NULL, keybitsize, token, &tokensize); if (rc) { - DEBUG_ERR( - "%s clear key import 4/4 with CSNBKPI2 failed, rc=%d\n", - __func__, rc); + ZCRYPT_DBF_ERR("%s clear key import 4/4 with CSNBKPI2 failed, rc=%d\n", + __func__, rc); goto out; } @@ -1265,19 +1251,17 @@ int cca_cipher2protkey(u16 cardnr, u16 domain, const u8 *ckey, /* forward xcrb with request CPRB and reply CPRB to zcrypt dd */ rc = zcrypt_send_cprb(&xcrb); if (rc) { - DEBUG_ERR( - "%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", - __func__, (int)cardnr, (int)domain, rc); + ZCRYPT_DBF_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", + __func__, (int)cardnr, (int)domain, rc); goto out; } /* check response returncode and reasoncode */ if (prepcblk->ccp_rtcode != 0) { - DEBUG_ERR( - "%s unwrap secure key failure, card response %d/%d\n", - __func__, - (int)prepcblk->ccp_rtcode, - (int)prepcblk->ccp_rscode); + ZCRYPT_DBF_ERR("%s unwrap secure key failure, card response %d/%d\n", + __func__, + (int)prepcblk->ccp_rtcode, + (int)prepcblk->ccp_rscode); if (prepcblk->ccp_rtcode == 8 && prepcblk->ccp_rscode == 2290) rc = -EAGAIN; else @@ -1285,11 +1269,10 @@ int cca_cipher2protkey(u16 cardnr, u16 domain, const u8 *ckey, goto out; } if (prepcblk->ccp_rscode != 0) { - DEBUG_WARN( - "%s unwrap secure key warning, card response %d/%d\n", - __func__, - (int)prepcblk->ccp_rtcode, - (int)prepcblk->ccp_rscode); + ZCRYPT_DBF_WARN("%s unwrap secure key warning, card response %d/%d\n", + __func__, + (int)prepcblk->ccp_rtcode, + (int)prepcblk->ccp_rscode); } /* process response cprb param block */ @@ -1300,15 +1283,14 @@ int cca_cipher2protkey(u16 cardnr, u16 domain, const u8 *ckey, /* check the returned keyblock */ if (prepparm->vud.ckb.version != 0x01 && prepparm->vud.ckb.version != 0x02) { - DEBUG_ERR("%s reply param keyblock version mismatch 0x%02x\n", - __func__, (int)prepparm->vud.ckb.version); + ZCRYPT_DBF_ERR("%s reply param keyblock version mismatch 0x%02x\n", + __func__, (int)prepparm->vud.ckb.version); rc = -EIO; goto out; } if (prepparm->vud.ckb.algo != 0x02) { - DEBUG_ERR( - "%s reply param keyblock algo mismatch 0x%02x != 0x02\n", - __func__, (int)prepparm->vud.ckb.algo); + ZCRYPT_DBF_ERR("%s reply param keyblock algo mismatch 0x%02x != 0x02\n", + __func__, (int)prepparm->vud.ckb.algo); rc = -EIO; goto out; } @@ -1331,8 +1313,8 @@ int cca_cipher2protkey(u16 cardnr, u16 domain, const u8 *ckey, *protkeytype = PKEY_KEYTYPE_AES_256; break; default: - DEBUG_ERR("%s unknown/unsupported keylen %d\n", - __func__, prepparm->vud.ckb.keylen); + ZCRYPT_DBF_ERR("%s unknown/unsupported keylen %d\n", + __func__, prepparm->vud.ckb.keylen); rc = -EIO; goto out; } @@ -1432,19 +1414,17 @@ int cca_ecc2protkey(u16 cardnr, u16 domain, const u8 *key, /* forward xcrb with request CPRB and reply CPRB to zcrypt dd */ rc = zcrypt_send_cprb(&xcrb); if (rc) { - DEBUG_ERR( - "%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", - __func__, (int)cardnr, (int)domain, rc); + ZCRYPT_DBF_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", + __func__, (int)cardnr, (int)domain, rc); goto out; } /* check response returncode and reasoncode */ if (prepcblk->ccp_rtcode != 0) { - DEBUG_ERR( - "%s unwrap secure key failure, card response %d/%d\n", - __func__, - (int)prepcblk->ccp_rtcode, - (int)prepcblk->ccp_rscode); + ZCRYPT_DBF_ERR("%s unwrap secure key failure, card response %d/%d\n", + __func__, + (int)prepcblk->ccp_rtcode, + (int)prepcblk->ccp_rscode); if (prepcblk->ccp_rtcode == 8 && prepcblk->ccp_rscode == 2290) rc = -EAGAIN; else @@ -1452,11 +1432,10 @@ int cca_ecc2protkey(u16 cardnr, u16 domain, const u8 *key, goto out; } if (prepcblk->ccp_rscode != 0) { - DEBUG_WARN( - "%s unwrap secure key warning, card response %d/%d\n", - __func__, - (int)prepcblk->ccp_rtcode, - (int)prepcblk->ccp_rscode); + ZCRYPT_DBF_WARN("%s unwrap secure key warning, card response %d/%d\n", + __func__, + (int)prepcblk->ccp_rtcode, + (int)prepcblk->ccp_rscode); } /* process response cprb param block */ @@ -1466,23 +1445,22 @@ int cca_ecc2protkey(u16 cardnr, u16 domain, const u8 *key, /* check the returned keyblock */ if (prepparm->vud.ckb.version != 0x02) { - DEBUG_ERR("%s reply param keyblock version mismatch 0x%02x != 0x02\n", - __func__, (int)prepparm->vud.ckb.version); + ZCRYPT_DBF_ERR("%s reply param keyblock version mismatch 0x%02x != 0x02\n", + __func__, (int)prepparm->vud.ckb.version); rc = -EIO; goto out; } if (prepparm->vud.ckb.algo != 0x81) { - DEBUG_ERR( - "%s reply param keyblock algo mismatch 0x%02x != 0x81\n", - __func__, (int)prepparm->vud.ckb.algo); + ZCRYPT_DBF_ERR("%s reply param keyblock algo mismatch 0x%02x != 0x81\n", + __func__, (int)prepparm->vud.ckb.algo); rc = -EIO; goto out; } /* copy the translated protected key */ if (prepparm->vud.ckb.keylen > *protkeylen) { - DEBUG_ERR("%s prot keylen mismatch %d > buffersize %u\n", - __func__, prepparm->vud.ckb.keylen, *protkeylen); + ZCRYPT_DBF_ERR("%s prot keylen mismatch %d > buffersize %u\n", + __func__, prepparm->vud.ckb.keylen, *protkeylen); rc = -EIO; goto out; } @@ -1550,17 +1528,17 @@ int cca_query_crypto_facility(u16 cardnr, u16 domain, /* forward xcrb with request CPRB and reply CPRB to zcrypt dd */ rc = zcrypt_send_cprb(&xcrb); if (rc) { - DEBUG_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", - __func__, (int)cardnr, (int)domain, rc); + ZCRYPT_DBF_ERR("%s zcrypt_send_cprb (cardnr=%d domain=%d) failed, rc=%d\n", + __func__, (int)cardnr, (int)domain, rc); goto out; } /* check response returncode and reasoncode */ if (prepcblk->ccp_rtcode != 0) { - DEBUG_ERR("%s unwrap secure key failure, card response %d/%d\n", - __func__, - (int)prepcblk->ccp_rtcode, - (int)prepcblk->ccp_rscode); + ZCRYPT_DBF_ERR("%s unwrap secure key failure, card response %d/%d\n", + __func__, + (int)prepcblk->ccp_rtcode, + (int)prepcblk->ccp_rscode); rc = -EIO; goto out; } diff --git a/drivers/s390/crypto/zcrypt_debug.h b/drivers/s390/crypto/zcrypt_debug.h index 5cf88aabd64b..9a208dc4c200 100644 --- a/drivers/s390/crypto/zcrypt_debug.h +++ b/drivers/s390/crypto/zcrypt_debug.h @@ -17,7 +17,7 @@ #define RC2ERR(rc) ((rc) ? DBF_ERR : DBF_INFO) #define RC2WARN(rc) ((rc) ? DBF_WARN : DBF_INFO) -#define DBF_MAX_SPRINTF_ARGS 6 +#define ZCRYPT_DBF_MAX_SPRINTF_ARGS 6 #define ZCRYPT_DBF(...) \ debug_sprintf_event(zcrypt_dbf_info, ##__VA_ARGS__) @@ -27,8 +27,6 @@ debug_sprintf_event(zcrypt_dbf_info, DBF_WARN, ##__VA_ARGS__) #define ZCRYPT_DBF_INFO(...) \ debug_sprintf_event(zcrypt_dbf_info, DBF_INFO, ##__VA_ARGS__) -#define ZCRYPT_DBF_DBG(...) \ - debug_sprintf_event(zcrypt_dbf_info, DBF_DEBUG, ##__VA_ARGS__) extern debug_info_t *zcrypt_dbf_info; diff --git a/drivers/s390/crypto/zcrypt_ep11misc.c b/drivers/s390/crypto/zcrypt_ep11misc.c index 0a877f9792c2..eb7f5489ccf9 100644 --- a/drivers/s390/crypto/zcrypt_ep11misc.c +++ b/drivers/s390/crypto/zcrypt_ep11misc.c @@ -24,11 +24,6 @@ #include "zcrypt_ep11misc.h" #include "zcrypt_ccamisc.h" -#define DEBUG_DBG(...) ZCRYPT_DBF(DBF_DEBUG, ##__VA_ARGS__) -#define DEBUG_INFO(...) ZCRYPT_DBF(DBF_INFO, ##__VA_ARGS__) -#define DEBUG_WARN(...) ZCRYPT_DBF(DBF_WARN, ##__VA_ARGS__) -#define DEBUG_ERR(...) ZCRYPT_DBF(DBF_ERR, ##__VA_ARGS__) - #define EP11_PINBLOB_V1_BYTES 56 /* default iv used here */ @@ -510,7 +505,7 @@ static int check_reply_pl(const u8 *pl, const char *func) /* start tag */ if (*pl++ != 0x30) { - DEBUG_ERR("%s reply start tag mismatch\n", func); + ZCRYPT_DBF_ERR("%s reply start tag mismatch\n", func); return -EIO; } @@ -527,40 +522,41 @@ static int check_reply_pl(const u8 *pl, const char *func) len = *((u16 *)pl); pl += 2; } else { - DEBUG_ERR("%s reply start tag lenfmt mismatch 0x%02hhx\n", - func, *pl); + ZCRYPT_DBF_ERR("%s reply start tag lenfmt mismatch 0x%02hhx\n", + func, *pl); return -EIO; } /* len should cover at least 3 fields with 32 bit value each */ if (len < 3 * 6) { - DEBUG_ERR("%s reply length %d too small\n", func, len); + ZCRYPT_DBF_ERR("%s reply length %d too small\n", func, len); return -EIO; } /* function tag, length and value */ if (pl[0] != 0x04 || pl[1] != 0x04) { - DEBUG_ERR("%s function tag or length mismatch\n", func); + ZCRYPT_DBF_ERR("%s function tag or length mismatch\n", func); return -EIO; } pl += 6; /* dom tag, length and value */ if (pl[0] != 0x04 || pl[1] != 0x04) { - DEBUG_ERR("%s dom tag or length mismatch\n", func); + ZCRYPT_DBF_ERR("%s dom tag or length mismatch\n", func); return -EIO; } pl += 6; /* return value tag, length and value */ if (pl[0] != 0x04 || pl[1] != 0x04) { - DEBUG_ERR("%s return value tag or length mismatch\n", func); + ZCRYPT_DBF_ERR("%s return value tag or length mismatch\n", + func); return -EIO; } pl += 2; ret = *((u32 *)pl); if (ret != 0) { - DEBUG_ERR("%s return value 0x%04x != 0\n", func, ret); + ZCRYPT_DBF_ERR("%s return value 0x%04x != 0\n", func, ret); return -EIO; } @@ -626,9 +622,8 @@ static int ep11_query_info(u16 cardnr, u16 domain, u32 query_type, rc = zcrypt_send_ep11_cprb(urb); if (rc) { - DEBUG_ERR( - "%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n", - __func__, (int)cardnr, (int)domain, rc); + ZCRYPT_DBF_ERR("%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n", + __func__, (int)cardnr, (int)domain, rc); goto out; } @@ -636,13 +631,13 @@ static int ep11_query_info(u16 cardnr, u16 domain, u32 query_type, if (rc) goto out; if (rep_pl->data_tag != 0x04 || rep_pl->data_lenfmt != 0x82) { - DEBUG_ERR("%s unknown reply data format\n", __func__); + ZCRYPT_DBF_ERR("%s unknown reply data format\n", __func__); rc = -EIO; goto out; } if (rep_pl->data_len > buflen) { - DEBUG_ERR("%s mismatch between reply data len and buffer len\n", - __func__); + ZCRYPT_DBF_ERR("%s mismatch between reply data len and buffer len\n", + __func__); rc = -ENOSPC; goto out; } @@ -816,9 +811,8 @@ static int _ep11_genaeskey(u16 card, u16 domain, case 256: break; default: - DEBUG_ERR( - "%s unknown/unsupported keybitsize %d\n", - __func__, keybitsize); + ZCRYPT_DBF_ERR("%s unknown/unsupported keybitsize %d\n", + __func__, keybitsize); rc = -EINVAL; goto out; } @@ -878,9 +872,8 @@ static int _ep11_genaeskey(u16 card, u16 domain, rc = zcrypt_send_ep11_cprb(urb); if (rc) { - DEBUG_ERR( - "%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n", - __func__, (int)card, (int)domain, rc); + ZCRYPT_DBF_ERR("%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n", + __func__, (int)card, (int)domain, rc); goto out; } @@ -888,13 +881,13 @@ static int _ep11_genaeskey(u16 card, u16 domain, if (rc) goto out; if (rep_pl->data_tag != 0x04 || rep_pl->data_lenfmt != 0x82) { - DEBUG_ERR("%s unknown reply data format\n", __func__); + ZCRYPT_DBF_ERR("%s unknown reply data format\n", __func__); rc = -EIO; goto out; } if (rep_pl->data_len > *keybufsize) { - DEBUG_ERR("%s mismatch reply data len / key buffer len\n", - __func__); + ZCRYPT_DBF_ERR("%s mismatch reply data len / key buffer len\n", + __func__); rc = -ENOSPC; goto out; } @@ -1030,9 +1023,8 @@ static int ep11_cryptsingle(u16 card, u16 domain, rc = zcrypt_send_ep11_cprb(urb); if (rc) { - DEBUG_ERR( - "%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n", - __func__, (int)card, (int)domain, rc); + ZCRYPT_DBF_ERR("%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n", + __func__, (int)card, (int)domain, rc); goto out; } @@ -1040,7 +1032,7 @@ static int ep11_cryptsingle(u16 card, u16 domain, if (rc) goto out; if (rep_pl->data_tag != 0x04) { - DEBUG_ERR("%s unknown reply data format\n", __func__); + ZCRYPT_DBF_ERR("%s unknown reply data format\n", __func__); rc = -EIO; goto out; } @@ -1053,14 +1045,14 @@ static int ep11_cryptsingle(u16 card, u16 domain, n = *((u16 *)p); p += 2; } else { - DEBUG_ERR("%s unknown reply data length format 0x%02hhx\n", - __func__, rep_pl->data_lenfmt); + ZCRYPT_DBF_ERR("%s unknown reply data length format 0x%02hhx\n", + __func__, rep_pl->data_lenfmt); rc = -EIO; goto out; } if (n > *outbufsize) { - DEBUG_ERR("%s mismatch reply data len %d / output buffer %zu\n", - __func__, n, *outbufsize); + ZCRYPT_DBF_ERR("%s mismatch reply data len %d / output buffer %zu\n", + __func__, n, *outbufsize); rc = -ENOSPC; goto out; } @@ -1188,9 +1180,8 @@ static int _ep11_unwrapkey(u16 card, u16 domain, rc = zcrypt_send_ep11_cprb(urb); if (rc) { - DEBUG_ERR( - "%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n", - __func__, (int)card, (int)domain, rc); + ZCRYPT_DBF_ERR("%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n", + __func__, (int)card, (int)domain, rc); goto out; } @@ -1198,13 +1189,13 @@ static int _ep11_unwrapkey(u16 card, u16 domain, if (rc) goto out; if (rep_pl->data_tag != 0x04 || rep_pl->data_lenfmt != 0x82) { - DEBUG_ERR("%s unknown reply data format\n", __func__); + ZCRYPT_DBF_ERR("%s unknown reply data format\n", __func__); rc = -EIO; goto out; } if (rep_pl->data_len > *keybufsize) { - DEBUG_ERR("%s mismatch reply data len / key buffer len\n", - __func__); + ZCRYPT_DBF_ERR("%s mismatch reply data len / key buffer len\n", + __func__); rc = -ENOSPC; goto out; } @@ -1343,9 +1334,8 @@ static int _ep11_wrapkey(u16 card, u16 domain, rc = zcrypt_send_ep11_cprb(urb); if (rc) { - DEBUG_ERR( - "%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n", - __func__, (int)card, (int)domain, rc); + ZCRYPT_DBF_ERR("%s zcrypt_send_ep11_cprb(card=%d dom=%d) failed, rc=%d\n", + __func__, (int)card, (int)domain, rc); goto out; } @@ -1353,13 +1343,13 @@ static int _ep11_wrapkey(u16 card, u16 domain, if (rc) goto out; if (rep_pl->data_tag != 0x04 || rep_pl->data_lenfmt != 0x82) { - DEBUG_ERR("%s unknown reply data format\n", __func__); + ZCRYPT_DBF_ERR("%s unknown reply data format\n", __func__); rc = -EIO; goto out; } if (rep_pl->data_len > *datasize) { - DEBUG_ERR("%s mismatch reply data len / data buffer len\n", - __func__); + ZCRYPT_DBF_ERR("%s mismatch reply data len / data buffer len\n", + __func__); rc = -ENOSPC; goto out; } @@ -1386,9 +1376,8 @@ int ep11_clr2keyblob(u16 card, u16 domain, u32 keybitsize, u32 keygenflags, if (keybitsize == 128 || keybitsize == 192 || keybitsize == 256) { clrkeylen = keybitsize / 8; } else { - DEBUG_ERR( - "%s unknown/unsupported keybitsize %d\n", - __func__, keybitsize); + ZCRYPT_DBF_ERR("%s unknown/unsupported keybitsize %d\n", + __func__, keybitsize); return -EINVAL; } @@ -1405,9 +1394,8 @@ int ep11_clr2keyblob(u16 card, u16 domain, u32 keybitsize, u32 keygenflags, 0x00006c00, /* EN/DECRYPT, WRAP/UNWRAP */ kek, &keklen); if (rc) { - DEBUG_ERR( - "%s generate kek key failed, rc=%d\n", - __func__, rc); + ZCRYPT_DBF_ERR("%s generate kek key failed, rc=%d\n", + __func__, rc); goto out; } @@ -1415,9 +1403,8 @@ int ep11_clr2keyblob(u16 card, u16 domain, u32 keybitsize, u32 keygenflags, rc = ep11_cryptsingle(card, domain, 0, 0, def_iv, kek, keklen, clrkey, clrkeylen, encbuf, &encbuflen); if (rc) { - DEBUG_ERR( - "%s encrypting key value with kek key failed, rc=%d\n", - __func__, rc); + ZCRYPT_DBF_ERR("%s encrypting key value with kek key failed, rc=%d\n", + __func__, rc); goto out; } @@ -1426,9 +1413,8 @@ int ep11_clr2keyblob(u16 card, u16 domain, u32 keybitsize, u32 keygenflags, encbuf, encbuflen, 0, def_iv, keybitsize, 0, keybuf, keybufsize, keytype); if (rc) { - DEBUG_ERR( - "%s importing key value as new key failed,, rc=%d\n", - __func__, rc); + ZCRYPT_DBF_ERR("%s importing key value as new key failed,, rc=%d\n", + __func__, rc); goto out; } @@ -1476,17 +1462,16 @@ int ep11_kblob2protkey(u16 card, u16 dom, rc = _ep11_wrapkey(card, dom, (u8 *)key, keylen, 0, def_iv, wkbuf, &wkbuflen); if (rc) { - DEBUG_ERR( - "%s rewrapping ep11 key to pkey failed, rc=%d\n", - __func__, rc); + ZCRYPT_DBF_ERR("%s rewrapping ep11 key to pkey failed, rc=%d\n", + __func__, rc); goto out; } wki = (struct wk_info *)wkbuf; /* check struct version and pkey type */ if (wki->version != 1 || wki->pkeytype < 1 || wki->pkeytype > 5) { - DEBUG_ERR("%s wk info version %d or pkeytype %d mismatch.\n", - __func__, (int)wki->version, (int)wki->pkeytype); + ZCRYPT_DBF_ERR("%s wk info version %d or pkeytype %d mismatch.\n", + __func__, (int)wki->version, (int)wki->pkeytype); rc = -EIO; goto out; } @@ -1511,8 +1496,8 @@ int ep11_kblob2protkey(u16 card, u16 dom, *protkeytype = PKEY_KEYTYPE_AES_256; break; default: - DEBUG_ERR("%s unknown/unsupported AES pkeysize %d\n", - __func__, (int)wki->pkeysize); + ZCRYPT_DBF_ERR("%s unknown/unsupported AES pkeysize %d\n", + __func__, (int)wki->pkeysize); rc = -EIO; goto out; } @@ -1525,16 +1510,16 @@ int ep11_kblob2protkey(u16 card, u16 dom, break; case 2: /* TDES */ default: - DEBUG_ERR("%s unknown/unsupported key type %d\n", - __func__, (int)wki->pkeytype); + ZCRYPT_DBF_ERR("%s unknown/unsupported key type %d\n", + __func__, (int)wki->pkeytype); rc = -EIO; goto out; } /* copy the translated protected key */ if (wki->pkeysize > *protkeylen) { - DEBUG_ERR("%s wk info pkeysize %llu > protkeysize %u\n", - __func__, wki->pkeysize, *protkeylen); + ZCRYPT_DBF_ERR("%s wk info pkeysize %llu > protkeysize %u\n", + __func__, wki->pkeysize, *protkeylen); rc = -EINVAL; goto out; } diff --git a/drivers/s390/crypto/zcrypt_error.h b/drivers/s390/crypto/zcrypt_error.h index a44fcfcec938..46e27b43a8af 100644 --- a/drivers/s390/crypto/zcrypt_error.h +++ b/drivers/s390/crypto/zcrypt_error.h @@ -119,10 +119,9 @@ static inline int convert_error(struct zcrypt_queue *zq, case REP82_ERROR_MESSAGE_TYPE: /* 0x20 */ case REP82_ERROR_TRANSPORT_FAIL: /* 0x90 */ /* - * Msg to wrong type or card/infrastructure failure. - * Trigger rescan of the ap bus, trigger retry request. + * Msg to wrong type or card/infrastructure failure. Return + * EAGAIN, the upper layer may do a retry on the request. */ - atomic_set(&zcrypt_rescan_req, 1); /* For type 86 response show the apfs value (failure reason) */ if (ehdr->reply_code == REP82_ERROR_TRANSPORT_FAIL && ehdr->type == TYPE86_RSP_CODE) { diff --git a/drivers/s390/crypto/zcrypt_msgtype50.c b/drivers/s390/crypto/zcrypt_msgtype50.c index 2e155de8abe5..3b39cb8f926d 100644 --- a/drivers/s390/crypto/zcrypt_msgtype50.c +++ b/drivers/s390/crypto/zcrypt_msgtype50.c @@ -427,7 +427,7 @@ static void zcrypt_msgtype50_receive(struct ap_queue *aq, len = t80h->len; if (len > reply->bufsize || len > msg->bufsize || len != reply->len) { - ZCRYPT_DBF_DBG("%s len mismatch => EMSGSIZE\n", __func__); + pr_debug("%s len mismatch => EMSGSIZE\n", __func__); msg->rc = -EMSGSIZE; goto out; } @@ -487,9 +487,9 @@ static long zcrypt_msgtype50_modexpo(struct zcrypt_queue *zq, out: ap_msg->private = NULL; if (rc) - ZCRYPT_DBF_DBG("%s send me cprb at dev=%02x.%04x rc=%d\n", - __func__, AP_QID_CARD(zq->queue->qid), - AP_QID_QUEUE(zq->queue->qid), rc); + pr_debug("%s send me cprb at dev=%02x.%04x rc=%d\n", + __func__, AP_QID_CARD(zq->queue->qid), + AP_QID_QUEUE(zq->queue->qid), rc); return rc; } @@ -537,9 +537,9 @@ static long zcrypt_msgtype50_modexpo_crt(struct zcrypt_queue *zq, out: ap_msg->private = NULL; if (rc) - ZCRYPT_DBF_DBG("%s send crt cprb at dev=%02x.%04x rc=%d\n", - __func__, AP_QID_CARD(zq->queue->qid), - AP_QID_QUEUE(zq->queue->qid), rc); + pr_debug("%s send crt cprb at dev=%02x.%04x rc=%d\n", + __func__, AP_QID_CARD(zq->queue->qid), + AP_QID_QUEUE(zq->queue->qid), rc); return rc; } diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c index 3c53abbdc342..215f257d2360 100644 --- a/drivers/s390/crypto/zcrypt_msgtype6.c +++ b/drivers/s390/crypto/zcrypt_msgtype6.c @@ -437,9 +437,9 @@ static int xcrb_msg_to_type6cprb_msgx(bool userspace, struct ap_message *ap_msg, ap_msg->flags |= AP_MSG_FLAG_ADMIN; break; default: - ZCRYPT_DBF_DBG("%s unknown CPRB minor version '%c%c'\n", - __func__, msg->cprbx.func_id[0], - msg->cprbx.func_id[1]); + pr_debug("%s unknown CPRB minor version '%c%c'\n", + __func__, msg->cprbx.func_id[0], + msg->cprbx.func_id[1]); } /* copy data block */ @@ -629,9 +629,9 @@ static int convert_type86_xcrb(bool userspace, struct zcrypt_queue *zq, /* Copy CPRB to user */ if (xcrb->reply_control_blk_length < msg->fmt2.count1) { - ZCRYPT_DBF_DBG("%s reply_control_blk_length %u < required %u => EMSGSIZE\n", - __func__, xcrb->reply_control_blk_length, - msg->fmt2.count1); + pr_debug("%s reply_control_blk_length %u < required %u => EMSGSIZE\n", + __func__, xcrb->reply_control_blk_length, + msg->fmt2.count1); return -EMSGSIZE; } if (z_copy_to_user(userspace, xcrb->reply_control_blk_addr, @@ -642,9 +642,9 @@ static int convert_type86_xcrb(bool userspace, struct zcrypt_queue *zq, /* Copy data buffer to user */ if (msg->fmt2.count2) { if (xcrb->reply_data_length < msg->fmt2.count2) { - ZCRYPT_DBF_DBG("%s reply_data_length %u < required %u => EMSGSIZE\n", - __func__, xcrb->reply_data_length, - msg->fmt2.count2); + pr_debug("%s reply_data_length %u < required %u => EMSGSIZE\n", + __func__, xcrb->reply_data_length, + msg->fmt2.count2); return -EMSGSIZE; } if (z_copy_to_user(userspace, xcrb->reply_data_addr, @@ -673,9 +673,9 @@ static int convert_type86_ep11_xcrb(bool userspace, struct zcrypt_queue *zq, char *data = reply->msg; if (xcrb->resp_len < msg->fmt2.count1) { - ZCRYPT_DBF_DBG("%s resp_len %u < required %u => EMSGSIZE\n", - __func__, (unsigned int)xcrb->resp_len, - msg->fmt2.count1); + pr_debug("%s resp_len %u < required %u => EMSGSIZE\n", + __func__, (unsigned int)xcrb->resp_len, + msg->fmt2.count1); return -EMSGSIZE; } @@ -875,7 +875,8 @@ static void zcrypt_msgtype6_receive(struct ap_queue *aq, len = sizeof(struct type86x_reply) + t86r->length; if (len > reply->bufsize || len > msg->bufsize || len != reply->len) { - ZCRYPT_DBF_DBG("%s len mismatch => EMSGSIZE\n", __func__); + pr_debug("%s len mismatch => EMSGSIZE\n", + __func__); msg->rc = -EMSGSIZE; goto out; } @@ -889,7 +890,8 @@ static void zcrypt_msgtype6_receive(struct ap_queue *aq, len = t86r->fmt2.offset1 + t86r->fmt2.count1; if (len > reply->bufsize || len > msg->bufsize || len != reply->len) { - ZCRYPT_DBF_DBG("%s len mismatch => EMSGSIZE\n", __func__); + pr_debug("%s len mismatch => EMSGSIZE\n", + __func__); msg->rc = -EMSGSIZE; goto out; } @@ -939,7 +941,8 @@ static void zcrypt_msgtype6_receive_ep11(struct ap_queue *aq, len = t86r->fmt2.offset1 + t86r->fmt2.count1; if (len > reply->bufsize || len > msg->bufsize || len != reply->len) { - ZCRYPT_DBF_DBG("%s len mismatch => EMSGSIZE\n", __func__); + pr_debug("%s len mismatch => EMSGSIZE\n", + __func__); msg->rc = -EMSGSIZE; goto out; } @@ -1151,9 +1154,9 @@ static long zcrypt_msgtype6_send_cprb(bool userspace, struct zcrypt_queue *zq, out: if (rc) - ZCRYPT_DBF_DBG("%s send cprb at dev=%02x.%04x rc=%d\n", - __func__, AP_QID_CARD(zq->queue->qid), - AP_QID_QUEUE(zq->queue->qid), rc); + pr_debug("%s send cprb at dev=%02x.%04x rc=%d\n", + __func__, AP_QID_CARD(zq->queue->qid), + AP_QID_QUEUE(zq->queue->qid), rc); return rc; } @@ -1274,9 +1277,9 @@ static long zcrypt_msgtype6_send_ep11_cprb(bool userspace, struct zcrypt_queue * out: if (rc) - ZCRYPT_DBF_DBG("%s send cprb at dev=%02x.%04x rc=%d\n", - __func__, AP_QID_CARD(zq->queue->qid), - AP_QID_QUEUE(zq->queue->qid), rc); + pr_debug("%s send cprb at dev=%02x.%04x rc=%d\n", + __func__, AP_QID_CARD(zq->queue->qid), + AP_QID_QUEUE(zq->queue->qid), rc); return rc; } diff --git a/drivers/zorro/zorro-driver.c b/drivers/zorro/zorro-driver.c index 025edfccedcf..f49d19977e82 100644 --- a/drivers/zorro/zorro-driver.c +++ b/drivers/zorro/zorro-driver.c @@ -150,7 +150,7 @@ static int zorro_uevent(const struct device *dev, struct kobj_uevent_env *env) return 0; } -struct bus_type zorro_bus_type = { +const struct bus_type zorro_bus_type = { .name = "zorro", .dev_name = "zorro", .dev_groups = zorro_device_attribute_groups, diff --git a/drivers/zorro/zorro.h b/drivers/zorro/zorro.h index f84df9fb4c20..df44e35203fd 100644 --- a/drivers/zorro/zorro.h +++ b/drivers/zorro/zorro.h @@ -4,7 +4,7 @@ * Zorro bus */ -extern struct bus_type zorro_bus_type; +extern const struct bus_type zorro_bus_type; #ifdef CONFIG_ZORRO_NAMES diff --git a/include/linux/amd-iommu.h b/include/linux/amd-iommu.h index dc7ed2f46886..2b90c48a6a87 100644 --- a/include/linux/amd-iommu.h +++ b/include/linux/amd-iommu.h @@ -85,8 +85,10 @@ int amd_iommu_pc_get_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, u8 fxn, u64 *value); struct amd_iommu *get_amd_iommu(unsigned int idx); -#ifdef CONFIG_AMD_MEM_ENCRYPT -int amd_iommu_snp_enable(void); +#ifdef CONFIG_KVM_AMD_SEV +int amd_iommu_snp_disable(void); +#else +static inline int amd_iommu_snp_disable(void) { return 0; } #endif #endif /* _ASM_X86_AMD_IOMMU_H */ diff --git a/include/linux/atomic/atomic-arch-fallback.h b/include/linux/atomic/atomic-arch-fallback.h index 5e95faa959c4..956bcba5dbf2 100644 --- a/include/linux/atomic/atomic-arch-fallback.h +++ b/include/linux/atomic/atomic-arch-fallback.h @@ -2005,6 +2005,7 @@ raw_atomic_xchg_relaxed(atomic_t *v, int new) * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_cmpxchg() elsewhere. * @@ -2033,6 +2034,7 @@ raw_atomic_cmpxchg(atomic_t *v, int old, int new) * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_cmpxchg_acquire() elsewhere. * @@ -2061,6 +2063,7 @@ raw_atomic_cmpxchg_acquire(atomic_t *v, int old, int new) * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_cmpxchg_release() elsewhere. * @@ -2088,6 +2091,7 @@ raw_atomic_cmpxchg_release(atomic_t *v, int old, int new) * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_cmpxchg_relaxed() elsewhere. * @@ -2112,7 +2116,8 @@ raw_atomic_cmpxchg_relaxed(atomic_t *v, int old, int new) * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_try_cmpxchg() elsewhere. * @@ -2145,7 +2150,8 @@ raw_atomic_try_cmpxchg(atomic_t *v, int *old, int new) * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_try_cmpxchg_acquire() elsewhere. * @@ -2178,7 +2184,8 @@ raw_atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_try_cmpxchg_release() elsewhere. * @@ -2210,7 +2217,8 @@ raw_atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_try_cmpxchg_relaxed() elsewhere. * @@ -2403,6 +2411,7 @@ raw_atomic_add_negative_relaxed(int i, atomic_t *v) * @u: int value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_fetch_add_unless() elsewhere. * @@ -2432,6 +2441,7 @@ raw_atomic_fetch_add_unless(atomic_t *v, int a, int u) * @u: int value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_add_unless() elsewhere. * @@ -2452,6 +2462,7 @@ raw_atomic_add_unless(atomic_t *v, int a, int u) * @v: pointer to atomic_t * * If (@v != 0), atomically updates @v to (@v + 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_inc_not_zero() elsewhere. * @@ -2472,6 +2483,7 @@ raw_atomic_inc_not_zero(atomic_t *v) * @v: pointer to atomic_t * * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_inc_unless_negative() elsewhere. * @@ -2499,6 +2511,7 @@ raw_atomic_inc_unless_negative(atomic_t *v) * @v: pointer to atomic_t * * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_dec_unless_positive() elsewhere. * @@ -2526,6 +2539,7 @@ raw_atomic_dec_unless_positive(atomic_t *v) * @v: pointer to atomic_t * * If (@v > 0), atomically updates @v to (@v - 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_dec_if_positive() elsewhere. * @@ -4117,6 +4131,7 @@ raw_atomic64_xchg_relaxed(atomic64_t *v, s64 new) * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_cmpxchg() elsewhere. * @@ -4145,6 +4160,7 @@ raw_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_cmpxchg_acquire() elsewhere. * @@ -4173,6 +4189,7 @@ raw_atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new) * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_cmpxchg_release() elsewhere. * @@ -4200,6 +4217,7 @@ raw_atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new) * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_cmpxchg_relaxed() elsewhere. * @@ -4224,7 +4242,8 @@ raw_atomic64_cmpxchg_relaxed(atomic64_t *v, s64 old, s64 new) * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_try_cmpxchg() elsewhere. * @@ -4257,7 +4276,8 @@ raw_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_try_cmpxchg_acquire() elsewhere. * @@ -4290,7 +4310,8 @@ raw_atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_try_cmpxchg_release() elsewhere. * @@ -4322,7 +4343,8 @@ raw_atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_try_cmpxchg_relaxed() elsewhere. * @@ -4515,6 +4537,7 @@ raw_atomic64_add_negative_relaxed(s64 i, atomic64_t *v) * @u: s64 value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_fetch_add_unless() elsewhere. * @@ -4544,6 +4567,7 @@ raw_atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) * @u: s64 value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_add_unless() elsewhere. * @@ -4564,6 +4588,7 @@ raw_atomic64_add_unless(atomic64_t *v, s64 a, s64 u) * @v: pointer to atomic64_t * * If (@v != 0), atomically updates @v to (@v + 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_inc_not_zero() elsewhere. * @@ -4584,6 +4609,7 @@ raw_atomic64_inc_not_zero(atomic64_t *v) * @v: pointer to atomic64_t * * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_inc_unless_negative() elsewhere. * @@ -4611,6 +4637,7 @@ raw_atomic64_inc_unless_negative(atomic64_t *v) * @v: pointer to atomic64_t * * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_dec_unless_positive() elsewhere. * @@ -4638,6 +4665,7 @@ raw_atomic64_dec_unless_positive(atomic64_t *v) * @v: pointer to atomic64_t * * If (@v > 0), atomically updates @v to (@v - 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic64_dec_if_positive() elsewhere. * @@ -4662,4 +4690,4 @@ raw_atomic64_dec_if_positive(atomic64_t *v) } #endif /* _LINUX_ATOMIC_FALLBACK_H */ -// eec048affea735b8464f58e6d96992101f8f85f1 +// 14850c0b0db20c62fdc78ccd1d42b98b88d76331 diff --git a/include/linux/atomic/atomic-instrumented.h b/include/linux/atomic/atomic-instrumented.h index 54d7bbe0aeaa..debd487fe971 100644 --- a/include/linux/atomic/atomic-instrumented.h +++ b/include/linux/atomic/atomic-instrumented.h @@ -1182,6 +1182,7 @@ atomic_xchg_relaxed(atomic_t *v, int new) * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_cmpxchg() there. * @@ -1202,6 +1203,7 @@ atomic_cmpxchg(atomic_t *v, int old, int new) * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_cmpxchg_acquire() there. * @@ -1221,6 +1223,7 @@ atomic_cmpxchg_acquire(atomic_t *v, int old, int new) * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_cmpxchg_release() there. * @@ -1241,6 +1244,7 @@ atomic_cmpxchg_release(atomic_t *v, int old, int new) * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_cmpxchg_relaxed() there. * @@ -1260,7 +1264,8 @@ atomic_cmpxchg_relaxed(atomic_t *v, int old, int new) * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_try_cmpxchg() there. * @@ -1282,7 +1287,8 @@ atomic_try_cmpxchg(atomic_t *v, int *old, int new) * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_try_cmpxchg_acquire() there. * @@ -1303,7 +1309,8 @@ atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_try_cmpxchg_release() there. * @@ -1325,7 +1332,8 @@ atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) * @new: int value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_try_cmpxchg_relaxed() there. * @@ -1475,6 +1483,7 @@ atomic_add_negative_relaxed(int i, atomic_t *v) * @u: int value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_fetch_add_unless() there. * @@ -1495,6 +1504,7 @@ atomic_fetch_add_unless(atomic_t *v, int a, int u) * @u: int value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_add_unless() there. * @@ -1513,6 +1523,7 @@ atomic_add_unless(atomic_t *v, int a, int u) * @v: pointer to atomic_t * * If (@v != 0), atomically updates @v to (@v + 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_inc_not_zero() there. * @@ -1531,6 +1542,7 @@ atomic_inc_not_zero(atomic_t *v) * @v: pointer to atomic_t * * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_inc_unless_negative() there. * @@ -1549,6 +1561,7 @@ atomic_inc_unless_negative(atomic_t *v) * @v: pointer to atomic_t * * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_dec_unless_positive() there. * @@ -1567,6 +1580,7 @@ atomic_dec_unless_positive(atomic_t *v) * @v: pointer to atomic_t * * If (@v > 0), atomically updates @v to (@v - 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_dec_if_positive() there. * @@ -2746,6 +2760,7 @@ atomic64_xchg_relaxed(atomic64_t *v, s64 new) * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_cmpxchg() there. * @@ -2766,6 +2781,7 @@ atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_cmpxchg_acquire() there. * @@ -2785,6 +2801,7 @@ atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new) * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_cmpxchg_release() there. * @@ -2805,6 +2822,7 @@ atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new) * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_cmpxchg_relaxed() there. * @@ -2824,7 +2842,8 @@ atomic64_cmpxchg_relaxed(atomic64_t *v, s64 old, s64 new) * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_try_cmpxchg() there. * @@ -2846,7 +2865,8 @@ atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_try_cmpxchg_acquire() there. * @@ -2867,7 +2887,8 @@ atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_try_cmpxchg_release() there. * @@ -2889,7 +2910,8 @@ atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) * @new: s64 value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_try_cmpxchg_relaxed() there. * @@ -3039,6 +3061,7 @@ atomic64_add_negative_relaxed(s64 i, atomic64_t *v) * @u: s64 value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_fetch_add_unless() there. * @@ -3059,6 +3082,7 @@ atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) * @u: s64 value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_add_unless() there. * @@ -3077,6 +3101,7 @@ atomic64_add_unless(atomic64_t *v, s64 a, s64 u) * @v: pointer to atomic64_t * * If (@v != 0), atomically updates @v to (@v + 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_inc_not_zero() there. * @@ -3095,6 +3120,7 @@ atomic64_inc_not_zero(atomic64_t *v) * @v: pointer to atomic64_t * * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_inc_unless_negative() there. * @@ -3113,6 +3139,7 @@ atomic64_inc_unless_negative(atomic64_t *v) * @v: pointer to atomic64_t * * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_dec_unless_positive() there. * @@ -3131,6 +3158,7 @@ atomic64_dec_unless_positive(atomic64_t *v) * @v: pointer to atomic64_t * * If (@v > 0), atomically updates @v to (@v - 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic64_dec_if_positive() there. * @@ -4310,6 +4338,7 @@ atomic_long_xchg_relaxed(atomic_long_t *v, long new) * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_cmpxchg() there. * @@ -4330,6 +4359,7 @@ atomic_long_cmpxchg(atomic_long_t *v, long old, long new) * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_cmpxchg_acquire() there. * @@ -4349,6 +4379,7 @@ atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new) * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_cmpxchg_release() there. * @@ -4369,6 +4400,7 @@ atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new) * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_cmpxchg_relaxed() there. * @@ -4388,7 +4420,8 @@ atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new) * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_try_cmpxchg() there. * @@ -4410,7 +4443,8 @@ atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new) * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_try_cmpxchg_acquire() there. * @@ -4431,7 +4465,8 @@ atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new) * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_try_cmpxchg_release() there. * @@ -4453,7 +4488,8 @@ atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new) * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_try_cmpxchg_relaxed() there. * @@ -4603,6 +4639,7 @@ atomic_long_add_negative_relaxed(long i, atomic_long_t *v) * @u: long value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_fetch_add_unless() there. * @@ -4623,6 +4660,7 @@ atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u) * @u: long value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_add_unless() there. * @@ -4641,6 +4679,7 @@ atomic_long_add_unless(atomic_long_t *v, long a, long u) * @v: pointer to atomic_long_t * * If (@v != 0), atomically updates @v to (@v + 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_inc_not_zero() there. * @@ -4659,6 +4698,7 @@ atomic_long_inc_not_zero(atomic_long_t *v) * @v: pointer to atomic_long_t * * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_inc_unless_negative() there. * @@ -4677,6 +4717,7 @@ atomic_long_inc_unless_negative(atomic_long_t *v) * @v: pointer to atomic_long_t * * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_dec_unless_positive() there. * @@ -4695,6 +4736,7 @@ atomic_long_dec_unless_positive(atomic_long_t *v) * @v: pointer to atomic_long_t * * If (@v > 0), atomically updates @v to (@v - 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Unsafe to use in noinstr code; use raw_atomic_long_dec_if_positive() there. * @@ -5008,4 +5050,4 @@ atomic_long_dec_if_positive(atomic_long_t *v) #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */ -// 2cc4bc990fef44d3836ec108f11b610f3f438184 +// ce5b65e0f1f8a276268b667194581d24bed219d4 diff --git a/include/linux/atomic/atomic-long.h b/include/linux/atomic/atomic-long.h index c82947170ddc..3ef844b3ab8a 100644 --- a/include/linux/atomic/atomic-long.h +++ b/include/linux/atomic/atomic-long.h @@ -1352,6 +1352,7 @@ raw_atomic_long_xchg_relaxed(atomic_long_t *v, long new) * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_cmpxchg() elsewhere. * @@ -1374,6 +1375,7 @@ raw_atomic_long_cmpxchg(atomic_long_t *v, long old, long new) * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_cmpxchg_acquire() elsewhere. * @@ -1396,6 +1398,7 @@ raw_atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new) * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_cmpxchg_release() elsewhere. * @@ -1418,6 +1421,7 @@ raw_atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new) * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_cmpxchg_relaxed() elsewhere. * @@ -1440,7 +1444,8 @@ raw_atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new) * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with full ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_try_cmpxchg() elsewhere. * @@ -1463,7 +1468,8 @@ raw_atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new) * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with acquire ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_try_cmpxchg_acquire() elsewhere. * @@ -1486,7 +1492,8 @@ raw_atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new) * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with release ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_try_cmpxchg_release() elsewhere. * @@ -1509,7 +1516,8 @@ raw_atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new) * @new: long value to assign * * If (@v == @old), atomically updates @v to @new with relaxed ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_try_cmpxchg_relaxed() elsewhere. * @@ -1677,6 +1685,7 @@ raw_atomic_long_add_negative_relaxed(long i, atomic_long_t *v) * @u: long value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_fetch_add_unless() elsewhere. * @@ -1699,6 +1708,7 @@ raw_atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u) * @u: long value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_add_unless() elsewhere. * @@ -1719,6 +1729,7 @@ raw_atomic_long_add_unless(atomic_long_t *v, long a, long u) * @v: pointer to atomic_long_t * * If (@v != 0), atomically updates @v to (@v + 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_inc_not_zero() elsewhere. * @@ -1739,6 +1750,7 @@ raw_atomic_long_inc_not_zero(atomic_long_t *v) * @v: pointer to atomic_long_t * * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_inc_unless_negative() elsewhere. * @@ -1759,6 +1771,7 @@ raw_atomic_long_inc_unless_negative(atomic_long_t *v) * @v: pointer to atomic_long_t * * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_dec_unless_positive() elsewhere. * @@ -1779,6 +1792,7 @@ raw_atomic_long_dec_unless_positive(atomic_long_t *v) * @v: pointer to atomic_long_t * * If (@v > 0), atomically updates @v to (@v - 1) with full ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * Safe to use in noinstr code; prefer atomic_long_dec_if_positive() elsewhere. * @@ -1795,4 +1809,4 @@ raw_atomic_long_dec_if_positive(atomic_long_t *v) } #endif /* _LINUX_ATOMIC_LONG_H */ -// 4ef23f98c73cff96d239896175fd26b10b88899e +// 1c4a26fc77f345342953770ebe3c4d08e7ce2f9a diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 75bd1692d2e3..aff92b1d284f 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -35,7 +35,7 @@ (typeof(ptr)) (__ptr + (off)); \ }) -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE #define __noretpoline __attribute__((__indirect_branch__("keep"))) #endif diff --git a/include/linux/compiler.h b/include/linux/compiler.h index bb1339c7057b..cdcdaa48b4d2 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -209,7 +209,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, */ #define ___ADDRESSABLE(sym, __attrs) \ static void * __used __attrs \ - __UNIQUE_ID(__PASTE(__addressable_,sym)) = (void *)&sym; + __UNIQUE_ID(__PASTE(__addressable_,sym)) = (void *)(uintptr_t)&sym; #define __ADDRESSABLE(sym) \ ___ADDRESSABLE(sym, __section(".discard.addressable")) diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index 289810685fc5..8bdf6e0918c1 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -334,6 +334,18 @@ #define __section(section) __attribute__((__section__(section))) /* + * Optional: only supported since gcc >= 12 + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-uninitialized-variable-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#uninitialized + */ +#if __has_attribute(__uninitialized__) +# define __uninitialized __attribute__((__uninitialized__)) +#else +# define __uninitialized +#endif + +/* * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-unused-function-attribute * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Type-Attributes.html#index-unused-type-attribute * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-unused-variable-attribute diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 61a0ddf2bef6..ae5a20cf2f9c 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -75,6 +75,8 @@ extern ssize_t cpu_show_spec_rstack_overflow(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t cpu_show_gds(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_reg_file_data_sampling(struct device *dev, + struct device_attribute *attr, char *buf); extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, @@ -196,6 +198,8 @@ void arch_cpu_idle(void); void arch_cpu_idle_prepare(void); void arch_cpu_idle_enter(void); void arch_cpu_idle_exit(void); +void arch_tick_broadcast_enter(void); +void arch_tick_broadcast_exit(void); void __noreturn arch_cpu_idle_dead(void); #ifdef CONFIG_ARCH_HAS_CPU_FINALIZE_INIT diff --git a/include/linux/indirect_call_wrapper.h b/include/linux/indirect_call_wrapper.h index adb83a42a6b9..35227d47cfc9 100644 --- a/include/linux/indirect_call_wrapper.h +++ b/include/linux/indirect_call_wrapper.h @@ -2,7 +2,7 @@ #ifndef _LINUX_INDIRECT_CALL_WRAPPER_H #define _LINUX_INDIRECT_CALL_WRAPPER_H -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE /* * INDIRECT_CALL_$NR - wrapper for indirect calls with $NR known builtin diff --git a/include/linux/module.h b/include/linux/module.h index 452500431077..932fabe2965a 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -888,7 +888,7 @@ static inline void module_bug_finalize(const Elf_Ehdr *hdr, static inline void module_bug_cleanup(struct module *mod) {} #endif /* CONFIG_GENERIC_BUG */ -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE extern bool retpoline_module_ok(bool has_retpoline); #else static inline bool retpoline_module_ok(bool has_retpoline) diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 7e208d46ba5b..67edc4ca2bee 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -32,11 +32,9 @@ # define __DEP_MAP_MUTEX_INITIALIZER(lockname) #endif -#ifndef CONFIG_PREEMPT_RT - #ifdef CONFIG_DEBUG_MUTEXES -#define __DEBUG_MUTEX_INITIALIZER(lockname) \ +# define __DEBUG_MUTEX_INITIALIZER(lockname) \ , .magic = &lockname extern void mutex_destroy(struct mutex *lock); @@ -49,6 +47,7 @@ static inline void mutex_destroy(struct mutex *lock) {} #endif +#ifndef CONFIG_PREEMPT_RT /** * mutex_init - initialize the mutex * @mutex: the mutex to be initialized @@ -101,9 +100,6 @@ extern bool mutex_is_locked(struct mutex *lock); extern void __mutex_rt_init(struct mutex *lock, const char *name, struct lock_class_key *key); -extern int mutex_trylock(struct mutex *lock); - -static inline void mutex_destroy(struct mutex *lock) { } #define mutex_is_locked(l) rt_mutex_base_is_locked(&(l)->rtmutex) diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 33212e93f4a6..b3b8d3dab52d 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -131,7 +131,7 @@ */ .macro VALIDATE_UNRET_BEGIN #if defined(CONFIG_NOINSTR_VALIDATION) && \ - (defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO)) + (defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO)) .Lhere_\@: .pushsection .discard.validate_unret .long .Lhere_\@ - . diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h index 7fd17e82bab4..3705c2044fc0 100644 --- a/include/linux/psp-sev.h +++ b/include/linux/psp-sev.h @@ -78,6 +78,36 @@ enum sev_cmd { SEV_CMD_DBG_DECRYPT = 0x060, SEV_CMD_DBG_ENCRYPT = 0x061, + /* SNP specific commands */ + SEV_CMD_SNP_INIT = 0x081, + SEV_CMD_SNP_SHUTDOWN = 0x082, + SEV_CMD_SNP_PLATFORM_STATUS = 0x083, + SEV_CMD_SNP_DF_FLUSH = 0x084, + SEV_CMD_SNP_INIT_EX = 0x085, + SEV_CMD_SNP_SHUTDOWN_EX = 0x086, + SEV_CMD_SNP_DECOMMISSION = 0x090, + SEV_CMD_SNP_ACTIVATE = 0x091, + SEV_CMD_SNP_GUEST_STATUS = 0x092, + SEV_CMD_SNP_GCTX_CREATE = 0x093, + SEV_CMD_SNP_GUEST_REQUEST = 0x094, + SEV_CMD_SNP_ACTIVATE_EX = 0x095, + SEV_CMD_SNP_LAUNCH_START = 0x0A0, + SEV_CMD_SNP_LAUNCH_UPDATE = 0x0A1, + SEV_CMD_SNP_LAUNCH_FINISH = 0x0A2, + SEV_CMD_SNP_DBG_DECRYPT = 0x0B0, + SEV_CMD_SNP_DBG_ENCRYPT = 0x0B1, + SEV_CMD_SNP_PAGE_SWAP_OUT = 0x0C0, + SEV_CMD_SNP_PAGE_SWAP_IN = 0x0C1, + SEV_CMD_SNP_PAGE_MOVE = 0x0C2, + SEV_CMD_SNP_PAGE_MD_INIT = 0x0C3, + SEV_CMD_SNP_PAGE_SET_STATE = 0x0C6, + SEV_CMD_SNP_PAGE_RECLAIM = 0x0C7, + SEV_CMD_SNP_PAGE_UNSMASH = 0x0C8, + SEV_CMD_SNP_CONFIG = 0x0C9, + SEV_CMD_SNP_DOWNLOAD_FIRMWARE_EX = 0x0CA, + SEV_CMD_SNP_COMMIT = 0x0CB, + SEV_CMD_SNP_VLEK_LOAD = 0x0CD, + SEV_CMD_MAX, }; @@ -523,12 +553,269 @@ struct sev_data_attestation_report { u32 len; /* In/Out */ } __packed; +/** + * struct sev_data_snp_download_firmware - SNP_DOWNLOAD_FIRMWARE command params + * + * @address: physical address of firmware image + * @len: length of the firmware image + */ +struct sev_data_snp_download_firmware { + u64 address; /* In */ + u32 len; /* In */ +} __packed; + +/** + * struct sev_data_snp_activate - SNP_ACTIVATE command params + * + * @gctx_paddr: system physical address guest context page + * @asid: ASID to bind to the guest + */ +struct sev_data_snp_activate { + u64 gctx_paddr; /* In */ + u32 asid; /* In */ +} __packed; + +/** + * struct sev_data_snp_addr - generic SNP command params + * + * @address: physical address of generic data param + */ +struct sev_data_snp_addr { + u64 address; /* In/Out */ +} __packed; + +/** + * struct sev_data_snp_launch_start - SNP_LAUNCH_START command params + * + * @gctx_paddr: system physical address of guest context page + * @policy: guest policy + * @ma_gctx_paddr: system physical address of migration agent + * @ma_en: the guest is associated with a migration agent + * @imi_en: launch flow is launching an IMI (Incoming Migration Image) for the + * purpose of guest-assisted migration. + * @rsvd: reserved + * @gosvw: guest OS-visible workarounds, as defined by hypervisor + */ +struct sev_data_snp_launch_start { + u64 gctx_paddr; /* In */ + u64 policy; /* In */ + u64 ma_gctx_paddr; /* In */ + u32 ma_en:1; /* In */ + u32 imi_en:1; /* In */ + u32 rsvd:30; + u8 gosvw[16]; /* In */ +} __packed; + +/* SNP support page type */ +enum { + SNP_PAGE_TYPE_NORMAL = 0x1, + SNP_PAGE_TYPE_VMSA = 0x2, + SNP_PAGE_TYPE_ZERO = 0x3, + SNP_PAGE_TYPE_UNMEASURED = 0x4, + SNP_PAGE_TYPE_SECRET = 0x5, + SNP_PAGE_TYPE_CPUID = 0x6, + + SNP_PAGE_TYPE_MAX +}; + +/** + * struct sev_data_snp_launch_update - SNP_LAUNCH_UPDATE command params + * + * @gctx_paddr: system physical address of guest context page + * @page_size: page size 0 indicates 4K and 1 indicates 2MB page + * @page_type: encoded page type + * @imi_page: indicates that this page is part of the IMI (Incoming Migration + * Image) of the guest + * @rsvd: reserved + * @rsvd2: reserved + * @address: system physical address of destination page to encrypt + * @rsvd3: reserved + * @vmpl1_perms: VMPL permission mask for VMPL1 + * @vmpl2_perms: VMPL permission mask for VMPL2 + * @vmpl3_perms: VMPL permission mask for VMPL3 + * @rsvd4: reserved + */ +struct sev_data_snp_launch_update { + u64 gctx_paddr; /* In */ + u32 page_size:1; /* In */ + u32 page_type:3; /* In */ + u32 imi_page:1; /* In */ + u32 rsvd:27; + u32 rsvd2; + u64 address; /* In */ + u32 rsvd3:8; + u32 vmpl1_perms:8; /* In */ + u32 vmpl2_perms:8; /* In */ + u32 vmpl3_perms:8; /* In */ + u32 rsvd4; +} __packed; + +/** + * struct sev_data_snp_launch_finish - SNP_LAUNCH_FINISH command params + * + * @gctx_paddr: system physical address of guest context page + * @id_block_paddr: system physical address of ID block + * @id_auth_paddr: system physical address of ID block authentication structure + * @id_block_en: indicates whether ID block is present + * @auth_key_en: indicates whether author key is present in authentication structure + * @rsvd: reserved + * @host_data: host-supplied data for guest, not interpreted by firmware + */ +struct sev_data_snp_launch_finish { + u64 gctx_paddr; + u64 id_block_paddr; + u64 id_auth_paddr; + u8 id_block_en:1; + u8 auth_key_en:1; + u64 rsvd:62; + u8 host_data[32]; +} __packed; + +/** + * struct sev_data_snp_guest_status - SNP_GUEST_STATUS command params + * + * @gctx_paddr: system physical address of guest context page + * @address: system physical address of guest status page + */ +struct sev_data_snp_guest_status { + u64 gctx_paddr; + u64 address; +} __packed; + +/** + * struct sev_data_snp_page_reclaim - SNP_PAGE_RECLAIM command params + * + * @paddr: system physical address of page to be claimed. The 0th bit in the + * address indicates the page size. 0h indicates 4KB and 1h indicates + * 2MB page. + */ +struct sev_data_snp_page_reclaim { + u64 paddr; +} __packed; + +/** + * struct sev_data_snp_page_unsmash - SNP_PAGE_UNSMASH command params + * + * @paddr: system physical address of page to be unsmashed. The 0th bit in the + * address indicates the page size. 0h indicates 4 KB and 1h indicates + * 2 MB page. + */ +struct sev_data_snp_page_unsmash { + u64 paddr; +} __packed; + +/** + * struct sev_data_snp_dbg - DBG_ENCRYPT/DBG_DECRYPT command parameters + * + * @gctx_paddr: system physical address of guest context page + * @src_addr: source address of data to operate on + * @dst_addr: destination address of data to operate on + */ +struct sev_data_snp_dbg { + u64 gctx_paddr; /* In */ + u64 src_addr; /* In */ + u64 dst_addr; /* In */ +} __packed; + +/** + * struct sev_data_snp_guest_request - SNP_GUEST_REQUEST command params + * + * @gctx_paddr: system physical address of guest context page + * @req_paddr: system physical address of request page + * @res_paddr: system physical address of response page + */ +struct sev_data_snp_guest_request { + u64 gctx_paddr; /* In */ + u64 req_paddr; /* In */ + u64 res_paddr; /* In */ +} __packed; + +/** + * struct sev_data_snp_init_ex - SNP_INIT_EX structure + * + * @init_rmp: indicate that the RMP should be initialized. + * @list_paddr_en: indicate that list_paddr is valid + * @rsvd: reserved + * @rsvd1: reserved + * @list_paddr: system physical address of range list + * @rsvd2: reserved + */ +struct sev_data_snp_init_ex { + u32 init_rmp:1; + u32 list_paddr_en:1; + u32 rsvd:30; + u32 rsvd1; + u64 list_paddr; + u8 rsvd2[48]; +} __packed; + +/** + * struct sev_data_range - RANGE structure + * + * @base: system physical address of first byte of range + * @page_count: number of 4KB pages in this range + * @rsvd: reserved + */ +struct sev_data_range { + u64 base; + u32 page_count; + u32 rsvd; +} __packed; + +/** + * struct sev_data_range_list - RANGE_LIST structure + * + * @num_elements: number of elements in RANGE_ARRAY + * @rsvd: reserved + * @ranges: array of num_elements of type RANGE + */ +struct sev_data_range_list { + u32 num_elements; + u32 rsvd; + struct sev_data_range ranges[]; +} __packed; + +/** + * struct sev_data_snp_shutdown_ex - SNP_SHUTDOWN_EX structure + * + * @len: length of the command buffer read by the PSP + * @iommu_snp_shutdown: Disable enforcement of SNP in the IOMMU + * @rsvd1: reserved + */ +struct sev_data_snp_shutdown_ex { + u32 len; + u32 iommu_snp_shutdown:1; + u32 rsvd1:31; +} __packed; + +/** + * struct sev_platform_init_args + * + * @error: SEV firmware error code + * @probe: True if this is being called as part of CCP module probe, which + * will defer SEV_INIT/SEV_INIT_EX firmware initialization until needed + * unless psp_init_on_probe module param is set + */ +struct sev_platform_init_args { + int error; + bool probe; +}; + +/** + * struct sev_data_snp_commit - SNP_COMMIT structure + * + * @len: length of the command buffer read by the PSP + */ +struct sev_data_snp_commit { + u32 len; +} __packed; + #ifdef CONFIG_CRYPTO_DEV_SP_PSP /** * sev_platform_init - perform SEV INIT command * - * @error: SEV command return code + * @args: struct sev_platform_init_args to pass in arguments * * Returns: * 0 if the SEV successfully processed the command @@ -537,7 +824,7 @@ struct sev_data_attestation_report { * -%ETIMEDOUT if the SEV command timed out * -%EIO if the SEV returned a non-zero return code */ -int sev_platform_init(int *error); +int sev_platform_init(struct sev_platform_init_args *args); /** * sev_platform_status - perform SEV PLATFORM_STATUS command @@ -637,14 +924,32 @@ int sev_guest_df_flush(int *error); */ int sev_guest_decommission(struct sev_data_decommission *data, int *error); +/** + * sev_do_cmd - issue an SEV or an SEV-SNP command + * + * @cmd: SEV or SEV-SNP firmware command to issue + * @data: arguments for firmware command + * @psp_ret: SEV command return code + * + * Returns: + * 0 if the SEV device successfully processed the command + * -%ENODEV if the PSP device is not available + * -%ENOTSUPP if PSP device does not support SEV + * -%ETIMEDOUT if the SEV command timed out + * -%EIO if PSP device returned a non-zero return code + */ +int sev_do_cmd(int cmd, void *data, int *psp_ret); + void *psp_copy_user_blob(u64 uaddr, u32 len); +void *snp_alloc_firmware_page(gfp_t mask); +void snp_free_firmware_page(void *addr); #else /* !CONFIG_CRYPTO_DEV_SP_PSP */ static inline int sev_platform_status(struct sev_user_data_status *status, int *error) { return -ENODEV; } -static inline int sev_platform_init(int *error) { return -ENODEV; } +static inline int sev_platform_init(struct sev_platform_init_args *args) { return -ENODEV; } static inline int sev_guest_deactivate(struct sev_data_deactivate *data, int *error) { return -ENODEV; } @@ -653,6 +958,9 @@ static inline int sev_guest_decommission(struct sev_data_decommission *data, int *error) { return -ENODEV; } static inline int +sev_do_cmd(int cmd, void *data, int *psp_ret) { return -ENODEV; } + +static inline int sev_guest_activate(struct sev_data_activate *data, int *error) { return -ENODEV; } static inline int sev_guest_df_flush(int *error) { return -ENODEV; } @@ -662,6 +970,13 @@ sev_issue_cmd_external_user(struct file *filep, unsigned int id, void *data, int static inline void *psp_copy_user_blob(u64 __user uaddr, u32 len) { return ERR_PTR(-EINVAL); } +static inline void *snp_alloc_firmware_page(gfp_t mask) +{ + return NULL; +} + +static inline void snp_free_firmware_page(void *addr) { } + #endif /* CONFIG_CRYPTO_DEV_SP_PSP */ #endif /* __PSP_SEV_H__ */ diff --git a/include/linux/pti.h b/include/linux/pti.h index 1a941efcaa62..1fbf9d6c20ef 100644 --- a/include/linux/pti.h +++ b/include/linux/pti.h @@ -2,7 +2,7 @@ #ifndef _INCLUDE_PTI_H #define _INCLUDE_PTI_H -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION #include <asm/pti.h> #else static inline void pti_init(void) { } diff --git a/include/linux/ras.h b/include/linux/ras.h index 1f4048bf2674..a64182bc72ad 100644 --- a/include/linux/ras.h +++ b/include/linux/ras.h @@ -25,6 +25,7 @@ void log_non_standard_event(const guid_t *sec_type, const guid_t *fru_id, const char *fru_text, const u8 sev, const u8 *err, const u32 len); void log_arm_hw_error(struct cper_sec_proc_arm *err); + #else static inline void log_non_standard_event(const guid_t *sec_type, @@ -35,4 +36,21 @@ static inline void log_arm_hw_error(struct cper_sec_proc_arm *err) { return; } #endif +struct atl_err { + u64 addr; + u64 ipid; + u32 cpu; +}; + +#if IS_ENABLED(CONFIG_AMD_ATL) +void amd_atl_register_decoder(unsigned long (*f)(struct atl_err *)); +void amd_atl_unregister_decoder(void); +void amd_retire_dram_row(struct atl_err *err); +unsigned long amd_convert_umc_mca_addr_to_sys_addr(struct atl_err *err); +#else +static inline void amd_retire_dram_row(struct atl_err *err) { } +static inline unsigned long +amd_convert_umc_mca_addr_to_sys_addr(struct atl_err *err) { return -EINVAL; } +#endif /* CONFIG_AMD_ATL */ + #endif /* __RAS_H__ */ diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index 66942d7fba7f..a365f67131ec 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -6,6 +6,12 @@ #include <linux/list.h> #include <linux/pid.h> +/* CLOSID, RMID value used by the default control group */ +#define RESCTRL_RESERVED_CLOSID 0 +#define RESCTRL_RESERVED_RMID 0 + +#define RESCTRL_PICK_ANY_CPU -1 + #ifdef CONFIG_PROC_CPU_RESCTRL int proc_resctrl_show(struct seq_file *m, @@ -153,7 +159,7 @@ struct resctrl_schema; * @cache_level: Which cache level defines scope of this resource * @cache: Cache allocation related data * @membw: If the component has bandwidth controls, their properties. - * @domains: All domains for this resource + * @domains: RCU list of all domains for this resource * @name: Name to use in "schemata" file. * @data_width: Character width of data when displaying * @default_ctrl: Specifies default cache cbm or memory B/W percent. @@ -219,36 +225,70 @@ u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_domain *d, u32 closid, enum resctrl_conf_type type); int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d); void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d); +void resctrl_online_cpu(unsigned int cpu); +void resctrl_offline_cpu(unsigned int cpu); /** * resctrl_arch_rmid_read() - Read the eventid counter corresponding to rmid * for this resource and domain. * @r: resource that the counter should be read from. * @d: domain that the counter should be read from. + * @closid: closid that matches the rmid. Depending on the architecture, the + * counter may match traffic of both @closid and @rmid, or @rmid + * only. * @rmid: rmid of the counter to read. * @eventid: eventid to read, e.g. L3 occupancy. * @val: result of the counter read in bytes. + * @arch_mon_ctx: An architecture specific value from + * resctrl_arch_mon_ctx_alloc(), for MPAM this identifies + * the hardware monitor allocated for this read request. * - * Call from process context on a CPU that belongs to domain @d. + * Some architectures need to sleep when first programming some of the counters. + * (specifically: arm64's MPAM cache occupancy counters can return 'not ready' + * for a short period of time). Call from a non-migrateable process context on + * a CPU that belongs to domain @d. e.g. use smp_call_on_cpu() or + * schedule_work_on(). This function can be called with interrupts masked, + * e.g. using smp_call_function_any(), but may consistently return an error. * * Return: * 0 on success, or -EIO, -EINVAL etc on error. */ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d, - u32 rmid, enum resctrl_event_id eventid, u64 *val); + u32 closid, u32 rmid, enum resctrl_event_id eventid, + u64 *val, void *arch_mon_ctx); + +/** + * resctrl_arch_rmid_read_context_check() - warn about invalid contexts + * + * When built with CONFIG_DEBUG_ATOMIC_SLEEP generate a warning when + * resctrl_arch_rmid_read() is called with preemption disabled. + * + * The contract with resctrl_arch_rmid_read() is that if interrupts + * are unmasked, it can sleep. This allows NOHZ_FULL systems to use an + * IPI, (and fail if the call needed to sleep), while most of the time + * the work is scheduled, allowing the call to sleep. + */ +static inline void resctrl_arch_rmid_read_context_check(void) +{ + if (!irqs_disabled()) + might_sleep(); +} /** * resctrl_arch_reset_rmid() - Reset any private state associated with rmid * and eventid. * @r: The domain's resource. * @d: The rmid's domain. + * @closid: closid that matches the rmid. Depending on the architecture, the + * counter may match traffic of both @closid and @rmid, or @rmid only. * @rmid: The rmid whose counter values should be reset. * @eventid: The eventid whose counter values should be reset. * * This can be called from any CPU. */ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d, - u32 rmid, enum resctrl_event_id eventid); + u32 closid, u32 rmid, + enum resctrl_event_id eventid); /** * resctrl_arch_reset_rmid_all() - Reset all private state associated with diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h index a8b28647aafc..b04a5d04dee9 100644 --- a/include/linux/sched/sd_flags.h +++ b/include/linux/sched/sd_flags.h @@ -117,13 +117,13 @@ SD_FLAG(SD_SHARE_CPUCAPACITY, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS) SD_FLAG(SD_CLUSTER, SDF_NEEDS_GROUPS) /* - * Domain members share CPU package resources (i.e. caches) + * Domain members share CPU Last Level Caches * * SHARED_CHILD: Set from the base domain up until spanned CPUs no longer share * the same cache(s). * NEEDS_GROUPS: Caches are shared between groups. */ -SD_FLAG(SD_SHARE_PKG_RESOURCES, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS) +SD_FLAG(SD_SHARE_LLC, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS) /* * Only a single load balancing instance diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 11e0e00e0bb9..18572c9ea724 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -38,21 +38,21 @@ extern const struct sd_flag_debug sd_flag_debug[]; #ifdef CONFIG_SCHED_SMT static inline int cpu_smt_flags(void) { - return SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES; + return SD_SHARE_CPUCAPACITY | SD_SHARE_LLC; } #endif #ifdef CONFIG_SCHED_CLUSTER static inline int cpu_cluster_flags(void) { - return SD_CLUSTER | SD_SHARE_PKG_RESOURCES; + return SD_CLUSTER | SD_SHARE_LLC; } #endif #ifdef CONFIG_SCHED_MC static inline int cpu_core_flags(void) { - return SD_SHARE_PKG_RESOURCES; + return SD_SHARE_LLC; } #endif diff --git a/include/linux/smp.h b/include/linux/smp.h index 7398ce99786c..fcd61dfe2af3 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -105,6 +105,12 @@ static inline void on_each_cpu_cond(smp_cond_func_t cond_func, on_each_cpu_cond_mask(cond_func, func, info, wait, cpu_online_mask); } +/* + * Architecture specific boot CPU setup. Defined as empty weak function in + * init/main.c. Architectures can override it. + */ +void smp_prepare_boot_cpu(void); + #ifdef CONFIG_SMP #include <linux/preempt.h> @@ -171,12 +177,6 @@ void generic_smp_call_function_single_interrupt(void); #define generic_smp_call_function_interrupt \ generic_smp_call_function_single_interrupt -/* - * Mark the boot cpu "online" so that it can call console drivers in - * printk() and can access its per-cpu storage. - */ -void smp_prepare_boot_cpu(void); - extern unsigned int setup_max_cpus; extern void __init setup_nr_cpu_ids(void); extern void __init smp_init(void); @@ -203,7 +203,6 @@ static inline void up_smp_call_function(smp_call_func_t func, void *info) (up_smp_call_function(func, info)) static inline void smp_send_reschedule(int cpu) { } -#define smp_prepare_boot_cpu() do {} while (0) #define smp_call_function_many(mask, func, info, wait) \ (up_smp_call_function(func, info)) static inline void call_function_init(void) { } diff --git a/include/linux/tick.h b/include/linux/tick.h index 44fddfa93e18..4924a33700b7 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -12,6 +12,7 @@ #include <linux/cpumask.h> #include <linux/sched.h> #include <linux/rcupdate.h> +#include <linux/static_key.h> #ifdef CONFIG_GENERIC_CLOCKEVENTS extern void __init tick_init(void); @@ -69,6 +70,8 @@ enum tick_broadcast_state { TICK_BROADCAST_ENTER, }; +extern struct static_key_false arch_needs_tick_broadcast; + #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST extern void tick_broadcast_control(enum tick_broadcast_mode mode); #else @@ -164,9 +167,16 @@ static inline u64 get_cpu_idle_time_us(int cpu, u64 *unused) { return -1; } static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; } #endif /* !CONFIG_NO_HZ_COMMON */ +/* + * Mask of CPUs that are nohz_full. + * + * Users should be guarded by CONFIG_NO_HZ_FULL or a tick_nohz_full_cpu() + * check. + */ +extern cpumask_var_t tick_nohz_full_mask; + #ifdef CONFIG_NO_HZ_FULL extern bool tick_nohz_full_running; -extern cpumask_var_t tick_nohz_full_mask; static inline bool tick_nohz_full_enabled(void) { diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index 780a5f6ad4a6..ff27cb2e1662 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -93,7 +93,7 @@ extern const struct nft_set_type nft_set_bitmap_type; extern const struct nft_set_type nft_set_pipapo_type; extern const struct nft_set_type nft_set_pipapo_avx2_type; -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE bool nft_rhash_lookup(const struct net *net, const struct nft_set *set, const u32 *key, const struct nft_set_ext **ext); bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set, diff --git a/include/net/tc_wrapper.h b/include/net/tc_wrapper.h index a608546bcefc..ffe58a02537c 100644 --- a/include/net/tc_wrapper.h +++ b/include/net/tc_wrapper.h @@ -4,7 +4,7 @@ #include <net/pkt_cls.h> -#if IS_ENABLED(CONFIG_RETPOLINE) +#if IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) #include <linux/cpufeature.h> #include <linux/static_key.h> diff --git a/include/uapi/linux/psp-sev.h b/include/uapi/linux/psp-sev.h index b44ba7dcdefc..b7a2c2ee35b7 100644 --- a/include/uapi/linux/psp-sev.h +++ b/include/uapi/linux/psp-sev.h @@ -28,6 +28,9 @@ enum { SEV_PEK_CERT_IMPORT, SEV_GET_ID, /* This command is deprecated, use SEV_GET_ID2 */ SEV_GET_ID2, + SNP_PLATFORM_STATUS, + SNP_COMMIT, + SNP_SET_CONFIG, SEV_MAX, }; @@ -69,6 +72,12 @@ typedef enum { SEV_RET_RESOURCE_LIMIT, SEV_RET_SECURE_DATA_INVALID, SEV_RET_INVALID_KEY = 0x27, + SEV_RET_INVALID_PAGE_SIZE, + SEV_RET_INVALID_PAGE_STATE, + SEV_RET_INVALID_MDATA_ENTRY, + SEV_RET_INVALID_PAGE_OWNER, + SEV_RET_INVALID_PAGE_AEAD_OFLOW, + SEV_RET_RMP_INIT_REQUIRED, SEV_RET_MAX, } sev_ret_code; @@ -156,6 +165,56 @@ struct sev_user_data_get_id2 { } __packed; /** + * struct sev_user_data_snp_status - SNP status + * + * @api_major: API major version + * @api_minor: API minor version + * @state: current platform state + * @is_rmp_initialized: whether RMP is initialized or not + * @rsvd: reserved + * @build_id: firmware build id for the API version + * @mask_chip_id: whether chip id is present in attestation reports or not + * @mask_chip_key: whether attestation reports are signed or not + * @vlek_en: VLEK (Version Loaded Endorsement Key) hashstick is loaded + * @rsvd1: reserved + * @guest_count: the number of guest currently managed by the firmware + * @current_tcb_version: current TCB version + * @reported_tcb_version: reported TCB version + */ +struct sev_user_data_snp_status { + __u8 api_major; /* Out */ + __u8 api_minor; /* Out */ + __u8 state; /* Out */ + __u8 is_rmp_initialized:1; /* Out */ + __u8 rsvd:7; + __u32 build_id; /* Out */ + __u32 mask_chip_id:1; /* Out */ + __u32 mask_chip_key:1; /* Out */ + __u32 vlek_en:1; /* Out */ + __u32 rsvd1:29; + __u32 guest_count; /* Out */ + __u64 current_tcb_version; /* Out */ + __u64 reported_tcb_version; /* Out */ +} __packed; + +/** + * struct sev_user_data_snp_config - system wide configuration value for SNP. + * + * @reported_tcb: the TCB version to report in the guest attestation report. + * @mask_chip_id: whether chip id is present in attestation reports or not + * @mask_chip_key: whether attestation reports are signed or not + * @rsvd: reserved + * @rsvd1: reserved + */ +struct sev_user_data_snp_config { + __u64 reported_tcb ; /* In */ + __u32 mask_chip_id:1; /* In */ + __u32 mask_chip_key:1; /* In */ + __u32 rsvd:30; /* In */ + __u8 rsvd1[52]; +} __packed; + +/** * struct sev_issue_cmd - SEV ioctl parameters * * @cmd: SEV commands to execute diff --git a/init/main.c b/init/main.c index b5bdc1cd7ae9..ac5bc4c3de6d 100644 --- a/init/main.c +++ b/init/main.c @@ -774,6 +774,10 @@ void __init __weak smp_setup_processor_id(void) { } +void __init __weak smp_prepare_boot_cpu(void) +{ +} + # if THREAD_SIZE >= PAGE_SIZE void __init __weak thread_stack_cache_init(void) { diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c index 185bd1c906b0..6083883c4fe0 100644 --- a/kernel/locking/percpu-rwsem.c +++ b/kernel/locking/percpu-rwsem.c @@ -223,9 +223,10 @@ static bool readers_active_check(struct percpu_rw_semaphore *sem) void __sched percpu_down_write(struct percpu_rw_semaphore *sem) { + bool contended = false; + might_sleep(); rwsem_acquire(&sem->dep_map, 0, 0, _RET_IP_); - trace_contention_begin(sem, LCB_F_PERCPU | LCB_F_WRITE); /* Notify readers to take the slow path. */ rcu_sync_enter(&sem->rss); @@ -234,8 +235,11 @@ void __sched percpu_down_write(struct percpu_rw_semaphore *sem) * Try set sem->block; this provides writer-writer exclusion. * Having sem->block set makes new readers block. */ - if (!__percpu_down_write_trylock(sem)) + if (!__percpu_down_write_trylock(sem)) { + trace_contention_begin(sem, LCB_F_PERCPU | LCB_F_WRITE); percpu_rwsem_wait(sem, /* .reader = */ false); + contended = true; + } /* smp_mb() implied by __percpu_down_write_trylock() on success -- D matches A */ @@ -247,7 +251,8 @@ void __sched percpu_down_write(struct percpu_rw_semaphore *sem) /* Wait for all active readers to complete. */ rcuwait_wait_event(&sem->writer, readers_active_check(sem), TASK_UNINTERRUPTIBLE); - trace_contention_end(sem, 0); + if (contended) + trace_contention_end(sem, 0); } EXPORT_SYMBOL_GPL(percpu_down_write); diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h index 6a0184e9c234..ae2b12f68b90 100644 --- a/kernel/locking/qspinlock_paravirt.h +++ b/kernel/locking/qspinlock_paravirt.h @@ -294,8 +294,8 @@ static void pv_wait_node(struct mcs_spinlock *node, struct mcs_spinlock *prev) { struct pv_node *pn = (struct pv_node *)node; struct pv_node *pp = (struct pv_node *)prev; + bool __maybe_unused wait_early; int loop; - bool wait_early; for (;;) { for (wait_early = false, loop = SPIN_THRESHOLD; loop; loop--) { diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 4a10e8c16fd2..88d08eeb8bc0 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -237,12 +237,13 @@ static __always_inline bool rt_mutex_cmpxchg_release(struct rt_mutex_base *lock, */ static __always_inline void mark_rt_mutex_waiters(struct rt_mutex_base *lock) { - unsigned long owner, *p = (unsigned long *) &lock->owner; + unsigned long *p = (unsigned long *) &lock->owner; + unsigned long owner, new; + owner = READ_ONCE(*p); do { - owner = *p; - } while (cmpxchg_relaxed(p, owner, - owner | RT_MUTEX_HAS_WAITERS) != owner); + new = owner | RT_MUTEX_HAS_WAITERS; + } while (!try_cmpxchg_relaxed(p, &owner, new)); /* * The cmpxchg loop above is relaxed to avoid back-to-back ACQUIRE diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index 2340b6d90ec6..c6d17aee4209 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -35,7 +35,7 @@ /* * The least significant 2 bits of the owner value has the following * meanings when set. - * - Bit 0: RWSEM_READER_OWNED - The rwsem is owned by readers + * - Bit 0: RWSEM_READER_OWNED - rwsem may be owned by readers (just a hint) * - Bit 1: RWSEM_NONSPINNABLE - Cannot spin on a reader-owned lock * * When the rwsem is reader-owned and a spinning writer has timed out, @@ -1002,8 +1002,8 @@ rwsem_down_read_slowpath(struct rw_semaphore *sem, long count, unsigned int stat /* * To prevent a constant stream of readers from starving a sleeping - * waiter, don't attempt optimistic lock stealing if the lock is - * currently owned by readers. + * writer, don't attempt optimistic lock stealing if the lock is + * very likely owned by readers. */ if ((atomic_long_read(&sem->owner) & RWSEM_READER_OWNED) && (rcnt > 1) && !(count & RWSEM_WRITER_LOCKED)) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 5f76ec5b0c0c..b35382dbe51d 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1821,7 +1821,6 @@ static void cpu_util_update_eff(struct cgroup_subsys_state *css); #endif #ifdef CONFIG_SYSCTL -#ifdef CONFIG_UCLAMP_TASK #ifdef CONFIG_UCLAMP_TASK_GROUP static void uclamp_update_root_tg(void) { @@ -1927,7 +1926,6 @@ undo: return result; } #endif -#endif static int uclamp_validate(struct task_struct *p, const struct sched_attr *attr) @@ -2096,7 +2094,7 @@ static void __init init_uclamp(void) } } -#else /* CONFIG_UCLAMP_TASK */ +#else /* !CONFIG_UCLAMP_TASK */ static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p) { } static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p) { } static inline int uclamp_validate(struct task_struct *p, diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index c0d0b577fd91..db34050ec3e6 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -7335,7 +7335,7 @@ static int select_idle_core(struct task_struct *p, int core, struct cpumask *cpu if (!available_idle_cpu(cpu)) { idle = false; if (*idle_cpu == -1) { - if (sched_idle_cpu(cpu) && cpumask_test_cpu(cpu, p->cpus_ptr)) { + if (sched_idle_cpu(cpu) && cpumask_test_cpu(cpu, cpus)) { *idle_cpu = cpu; break; } @@ -7343,7 +7343,7 @@ static int select_idle_core(struct task_struct *p, int core, struct cpumask *cpu } break; } - if (*idle_cpu == -1 && cpumask_test_cpu(cpu, p->cpus_ptr)) + if (*idle_cpu == -1 && cpumask_test_cpu(cpu, cpus)) *idle_cpu = cpu; } @@ -7357,13 +7357,19 @@ static int select_idle_core(struct task_struct *p, int core, struct cpumask *cpu /* * Scan the local SMT mask for idle CPUs. */ -static int select_idle_smt(struct task_struct *p, int target) +static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target) { int cpu; for_each_cpu_and(cpu, cpu_smt_mask(target), p->cpus_ptr) { if (cpu == target) continue; + /* + * Check if the CPU is in the LLC scheduling domain of @target. + * Due to isolcpus, there is no guarantee that all the siblings are in the domain. + */ + if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) + continue; if (available_idle_cpu(cpu) || sched_idle_cpu(cpu)) return cpu; } @@ -7387,7 +7393,7 @@ static inline int select_idle_core(struct task_struct *p, int core, struct cpuma return __select_idle_cpu(core, p); } -static inline int select_idle_smt(struct task_struct *p, int target) +static inline int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target) { return -1; } @@ -7637,7 +7643,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target) has_idle_core = test_idle_cores(target); if (!has_idle_core && cpus_share_cache(prev, target)) { - i = select_idle_smt(p, prev); + i = select_idle_smt(p, sd, prev); if ((unsigned int)i < nr_cpumask_bits) return i; } @@ -9330,19 +9336,17 @@ static inline bool cfs_rq_has_blocked(struct cfs_rq *cfs_rq) static inline bool others_have_blocked(struct rq *rq) { - if (READ_ONCE(rq->avg_rt.util_avg)) + if (cpu_util_rt(rq)) return true; - if (READ_ONCE(rq->avg_dl.util_avg)) + if (cpu_util_dl(rq)) return true; if (thermal_load_avg(rq)) return true; -#ifdef CONFIG_HAVE_SCHED_AVG_IRQ - if (READ_ONCE(rq->avg_irq.util_avg)) + if (cpu_util_irq(rq)) return true; -#endif return false; } @@ -9599,8 +9603,8 @@ static unsigned long scale_rt_capacity(int cpu) * avg_thermal.load_avg tracks thermal pressure and the weighted * average uses the actual delta max capacity(load). */ - used = READ_ONCE(rq->avg_rt.util_avg); - used += READ_ONCE(rq->avg_dl.util_avg); + used = cpu_util_rt(rq); + used += cpu_util_dl(rq); used += thermal_load_avg(rq); if (unlikely(used >= max)) @@ -9833,51 +9837,49 @@ group_type group_classify(unsigned int imbalance_pct, */ static bool sched_use_asym_prio(struct sched_domain *sd, int cpu) { + if (!(sd->flags & SD_ASYM_PACKING)) + return false; + if (!sched_smt_active()) return true; return sd->flags & SD_SHARE_CPUCAPACITY || is_core_idle(cpu); } +static inline bool sched_asym(struct sched_domain *sd, int dst_cpu, int src_cpu) +{ + /* + * First check if @dst_cpu can do asym_packing load balance. Only do it + * if it has higher priority than @src_cpu. + */ + return sched_use_asym_prio(sd, dst_cpu) && + sched_asym_prefer(dst_cpu, src_cpu); +} + /** - * sched_asym - Check if the destination CPU can do asym_packing load balance + * sched_group_asym - Check if the destination CPU can do asym_packing balance * @env: The load balancing environment - * @sds: Load-balancing data with statistics of the local group * @sgs: Load-balancing statistics of the candidate busiest group * @group: The candidate busiest group * * @env::dst_cpu can do asym_packing if it has higher priority than the * preferred CPU of @group. * - * SMT is a special case. If we are balancing load between cores, @env::dst_cpu - * can do asym_packing balance only if all its SMT siblings are idle. Also, it - * can only do it if @group is an SMT group and has exactly on busy CPU. Larger - * imbalances in the number of CPUS are dealt with in find_busiest_group(). - * - * If we are balancing load within an SMT core, or at PKG domain level, always - * proceed. - * * Return: true if @env::dst_cpu can do with asym_packing load balance. False * otherwise. */ static inline bool -sched_asym(struct lb_env *env, struct sd_lb_stats *sds, struct sg_lb_stats *sgs, - struct sched_group *group) +sched_group_asym(struct lb_env *env, struct sg_lb_stats *sgs, struct sched_group *group) { - /* Ensure that the whole local core is idle, if applicable. */ - if (!sched_use_asym_prio(env->sd, env->dst_cpu)) - return false; - /* - * CPU priorities does not make sense for SMT cores with more than one + * CPU priorities do not make sense for SMT cores with more than one * busy sibling. */ - if (group->flags & SD_SHARE_CPUCAPACITY) { - if (sgs->group_weight - sgs->idle_cpus != 1) - return false; - } + if ((group->flags & SD_SHARE_CPUCAPACITY) && + (sgs->group_weight - sgs->idle_cpus != 1)) + return false; - return sched_asym_prefer(env->dst_cpu, group->asym_prefer_cpu); + return sched_asym(env->sd, env->dst_cpu, group->asym_prefer_cpu); } /* One group has more than one SMT CPU while the other group does not */ @@ -10031,11 +10033,9 @@ static inline void update_sg_lb_stats(struct lb_env *env, sgs->group_weight = group->group_weight; /* Check if dst CPU is idle and preferred to this group */ - if (!local_group && env->sd->flags & SD_ASYM_PACKING && - env->idle != CPU_NOT_IDLE && sgs->sum_h_nr_running && - sched_asym(env, sds, sgs, group)) { + if (!local_group && env->idle != CPU_NOT_IDLE && sgs->sum_h_nr_running && + sched_group_asym(env, sgs, group)) sgs->group_asym_packing = 1; - } /* Check for loaded SMT group to be balanced to dst CPU */ if (!local_group && smt_balance(env, sgs, group)) @@ -10099,9 +10099,7 @@ static bool update_sd_pick_busiest(struct lb_env *env, switch (sgs->group_type) { case group_overloaded: /* Select the overloaded group with highest avg_load. */ - if (sgs->avg_load <= busiest->avg_load) - return false; - break; + return sgs->avg_load > busiest->avg_load; case group_imbalanced: /* @@ -10112,18 +10110,14 @@ static bool update_sd_pick_busiest(struct lb_env *env, case group_asym_packing: /* Prefer to move from lowest priority CPU's work */ - if (sched_asym_prefer(sg->asym_prefer_cpu, sds->busiest->asym_prefer_cpu)) - return false; - break; + return sched_asym_prefer(sds->busiest->asym_prefer_cpu, sg->asym_prefer_cpu); case group_misfit_task: /* * If we have more than one misfit sg go with the biggest * misfit. */ - if (sgs->group_misfit_task_load < busiest->group_misfit_task_load) - return false; - break; + return sgs->group_misfit_task_load > busiest->group_misfit_task_load; case group_smt_balance: /* @@ -10275,10 +10269,8 @@ static int idle_cpu_without(int cpu, struct task_struct *p) * be computed and tested before calling idle_cpu_without(). */ -#ifdef CONFIG_SMP if (rq->ttwu_pending) return 0; -#endif return 1; } @@ -10671,16 +10663,11 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd update_sg_lb_stats(env, sds, sg, sgs, &sg_status); - if (local_group) - goto next_group; - - - if (update_sd_pick_busiest(env, sds, sg, sgs)) { + if (!local_group && update_sd_pick_busiest(env, sds, sg, sgs)) { sds->busiest = sg; sds->busiest_stat = *sgs; } -next_group: /* Now, start updating sd_lb_stats */ sds->total_load += sgs->group_load; sds->total_capacity += sgs->group_capacity; @@ -10784,7 +10771,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s */ if (local->group_type == group_has_spare) { if ((busiest->group_type > group_fully_busy) && - !(env->sd->flags & SD_SHARE_PKG_RESOURCES)) { + !(env->sd->flags & SD_SHARE_LLC)) { /* * If busiest is overloaded, try to fill spare * capacity. This might end up creating spare capacity @@ -11140,10 +11127,7 @@ static struct rq *find_busiest_queue(struct lb_env *env, * If balancing between cores, let lower priority CPUs help * SMT cores with more than one busy sibling. */ - if ((env->sd->flags & SD_ASYM_PACKING) && - sched_use_asym_prio(env->sd, i) && - sched_asym_prefer(i, env->dst_cpu) && - nr_running == 1) + if (sched_asym(env->sd, i, env->dst_cpu) && nr_running == 1) continue; switch (env->migration_type) { @@ -11239,8 +11223,7 @@ asym_active_balance(struct lb_env *env) * the lower priority @env::dst_cpu help it. Do not follow * CPU priority. */ - return env->idle != CPU_NOT_IDLE && (env->sd->flags & SD_ASYM_PACKING) && - sched_use_asym_prio(env->sd, env->dst_cpu) && + return env->idle != CPU_NOT_IDLE && sched_use_asym_prio(env->sd, env->dst_cpu) && (sched_asym_prefer(env->dst_cpu, env->src_cpu) || !sched_use_asym_prio(env->sd, env->src_cpu)); } @@ -12023,8 +12006,7 @@ static void nohz_balancer_kick(struct rq *rq) * preferred CPU must be idle. */ for_each_cpu_and(i, sched_domain_span(sd), nohz.idle_cpus_mask) { - if (sched_use_asym_prio(sd, i) && - sched_asym_prefer(i, cpu)) { + if (sched_asym(sd, i, cpu)) { flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK; goto unlock; } diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index b15d40cad7ea..6135fbe83d68 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -81,6 +81,25 @@ void __weak arch_cpu_idle(void) cpu_idle_force_poll = 1; } +#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST_IDLE +DEFINE_STATIC_KEY_FALSE(arch_needs_tick_broadcast); + +static inline void cond_tick_broadcast_enter(void) +{ + if (static_branch_unlikely(&arch_needs_tick_broadcast)) + tick_broadcast_enter(); +} + +static inline void cond_tick_broadcast_exit(void) +{ + if (static_branch_unlikely(&arch_needs_tick_broadcast)) + tick_broadcast_exit(); +} +#else +static inline void cond_tick_broadcast_enter(void) { } +static inline void cond_tick_broadcast_exit(void) { } +#endif + /** * default_idle_call - Default CPU idle routine. * @@ -90,6 +109,7 @@ void __cpuidle default_idle_call(void) { instrumentation_begin(); if (!current_clr_polling_and_test()) { + cond_tick_broadcast_enter(); trace_cpu_idle(1, smp_processor_id()); stop_critical_timings(); @@ -99,6 +119,7 @@ void __cpuidle default_idle_call(void) start_critical_timings(); trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id()); + cond_tick_broadcast_exit(); } local_irq_enable(); instrumentation_end(); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index d60841064527..e85c6c76b878 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -3153,7 +3153,7 @@ static inline bool uclamp_rq_is_idle(struct rq *rq) #ifdef CONFIG_HAVE_SCHED_AVG_IRQ static inline unsigned long cpu_util_irq(struct rq *rq) { - return rq->avg_irq.util_avg; + return READ_ONCE(rq->avg_irq.util_avg); } static inline diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index a9f0187939f6..dc6483b78aa9 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -661,13 +661,13 @@ static void destroy_sched_domains(struct sched_domain *sd) } /* - * Keep a special pointer to the highest sched_domain that has - * SD_SHARE_PKG_RESOURCE set (Last Level Cache Domain) for this - * allows us to avoid some pointer chasing select_idle_sibling(). + * Keep a special pointer to the highest sched_domain that has SD_SHARE_LLC set + * (Last Level Cache Domain) for this allows us to avoid some pointer chasing + * select_idle_sibling(). * - * Also keep a unique ID per domain (we use the first CPU number in - * the cpumask of the domain), this allows us to quickly tell if - * two CPUs are in the same cache domain, see cpus_share_cache(). + * Also keep a unique ID per domain (we use the first CPU number in the cpumask + * of the domain), this allows us to quickly tell if two CPUs are in the same + * cache domain, see cpus_share_cache(). */ DEFINE_PER_CPU(struct sched_domain __rcu *, sd_llc); DEFINE_PER_CPU(int, sd_llc_size); @@ -688,7 +688,7 @@ static void update_top_cache_domain(int cpu) int id = cpu; int size = 1; - sd = highest_flag_domain(cpu, SD_SHARE_PKG_RESOURCES); + sd = highest_flag_domain(cpu, SD_SHARE_LLC); if (sd) { id = cpumask_first(sched_domain_span(sd)); size = cpumask_weight(sched_domain_span(sd)); @@ -1555,11 +1555,12 @@ static struct cpumask ***sched_domains_numa_masks; * * These flags are purely descriptive of the topology and do not prescribe * behaviour. Behaviour is artificial and mapped in the below sd_init() - * function: + * function. For details, see include/linux/sched/sd_flags.h. * - * SD_SHARE_CPUCAPACITY - describes SMT topologies - * SD_SHARE_PKG_RESOURCES - describes shared caches - * SD_NUMA - describes NUMA topologies + * SD_SHARE_CPUCAPACITY + * SD_SHARE_LLC + * SD_CLUSTER + * SD_NUMA * * Odd one out, which beside describing the topology has a quirk also * prescribes the desired behaviour that goes along with it: @@ -1569,7 +1570,7 @@ static struct cpumask ***sched_domains_numa_masks; #define TOPOLOGY_SD_FLAGS \ (SD_SHARE_CPUCAPACITY | \ SD_CLUSTER | \ - SD_SHARE_PKG_RESOURCES | \ + SD_SHARE_LLC | \ SD_NUMA | \ SD_ASYM_PACKING) @@ -1612,7 +1613,7 @@ sd_init(struct sched_domain_topology_level *tl, | 0*SD_BALANCE_WAKE | 1*SD_WAKE_AFFINE | 0*SD_SHARE_CPUCAPACITY - | 0*SD_SHARE_PKG_RESOURCES + | 0*SD_SHARE_LLC | 0*SD_SERIALIZE | 1*SD_PREFER_SIBLING | 0*SD_NUMA @@ -1649,7 +1650,7 @@ sd_init(struct sched_domain_topology_level *tl, if (sd->flags & SD_SHARE_CPUCAPACITY) { sd->imbalance_pct = 110; - } else if (sd->flags & SD_SHARE_PKG_RESOURCES) { + } else if (sd->flags & SD_SHARE_LLC) { sd->imbalance_pct = 117; sd->cache_nice_tries = 1; @@ -1674,7 +1675,7 @@ sd_init(struct sched_domain_topology_level *tl, * For all levels sharing cache; connect a sched_domain_shared * instance. */ - if (sd->flags & SD_SHARE_PKG_RESOURCES) { + if (sd->flags & SD_SHARE_LLC) { sd->shared = *per_cpu_ptr(sdd->sds, sd_id); atomic_inc(&sd->shared->ref); atomic_set(&sd->shared->nr_busy_cpus, sd_weight); @@ -2449,8 +2450,8 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) { struct sched_domain *child = sd->child; - if (!(sd->flags & SD_SHARE_PKG_RESOURCES) && child && - (child->flags & SD_SHARE_PKG_RESOURCES)) { + if (!(sd->flags & SD_SHARE_LLC) && child && + (child->flags & SD_SHARE_LLC)) { struct sched_domain __rcu *top_p; unsigned int nr_llcs; diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig index bae8f11070be..fc3b1a06c981 100644 --- a/kernel/time/Kconfig +++ b/kernel/time/Kconfig @@ -39,6 +39,11 @@ config GENERIC_CLOCKEVENTS_BROADCAST bool depends on GENERIC_CLOCKEVENTS +# Handle broadcast in default_idle_call() +config GENERIC_CLOCKEVENTS_BROADCAST_IDLE + bool + depends on GENERIC_CLOCKEVENTS_BROADCAST + # Automatically adjust the min. reprogramming time for # clock event device config GENERIC_CLOCKEVENTS_MIN_ADJUST diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index aa332ace108b..3103a484182e 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1022,7 +1022,7 @@ static inline u64 rb_time_stamp(struct trace_buffer *buffer) u64 ts; /* Skip retpolines :-( */ - if (IS_ENABLED(CONFIG_RETPOLINE) && likely(buffer->clock == trace_clock_local)) + if (IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) && likely(buffer->clock == trace_clock_local)) ts = trace_clock_local(); else ts = buffer->clock(); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index f3b50b47b7ea..6c596e65de8a 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1303,7 +1303,7 @@ config PROVE_LOCKING select DEBUG_SPINLOCK select DEBUG_MUTEXES if !PREEMPT_RT select DEBUG_RT_MUTEXES if RT_MUTEXES - select DEBUG_RWSEMS + select DEBUG_RWSEMS if !PREEMPT_RT select DEBUG_WW_MUTEX_SLOWPATH select DEBUG_LOCK_ALLOC select PREEMPT_COUNT if !ARCH_NO_PREEMPT @@ -1426,7 +1426,7 @@ config DEBUG_WW_MUTEX_SLOWPATH config DEBUG_RWSEMS bool "RW Semaphore debugging: basic checks" - depends on DEBUG_KERNEL + depends on DEBUG_KERNEL && !PREEMPT_RT help This debugging feature allows mismatched rw semaphore locks and unlocks to be detected and reported. diff --git a/lib/raid6/s390vx.uc b/lib/raid6/s390vx.uc index cd0b9e95f499..863e2d320938 100644 --- a/lib/raid6/s390vx.uc +++ b/lib/raid6/s390vx.uc @@ -12,15 +12,14 @@ */ #include <linux/raid/pq.h> -#include <asm/fpu/api.h> -#include <asm/vx-insn.h> +#include <asm/fpu.h> #define NSIZE 16 -static inline void LOAD_CONST(void) +static __always_inline void LOAD_CONST(void) { - asm volatile("VREPIB %v24,7"); - asm volatile("VREPIB %v25,0x1d"); + fpu_vrepib(24, 0x07); + fpu_vrepib(25, 0x1d); } /* @@ -28,10 +27,7 @@ static inline void LOAD_CONST(void) * vector register y left by 1 bit and stores the result in * vector register x. */ -static inline void SHLBYTE(int x, int y) -{ - asm volatile ("VAB %0,%1,%1" : : "i" (x), "i" (y)); -} +#define SHLBYTE(x, y) fpu_vab(x, y, y) /* * For each of the 16 bytes in the vector register y the MASK() @@ -39,49 +35,17 @@ static inline void SHLBYTE(int x, int y) * or 0x00 if the high bit is 0. The result is stored in vector * register x. */ -static inline void MASK(int x, int y) -{ - asm volatile ("VESRAVB %0,%1,24" : : "i" (x), "i" (y)); -} - -static inline void AND(int x, int y, int z) -{ - asm volatile ("VN %0,%1,%2" : : "i" (x), "i" (y), "i" (z)); -} - -static inline void XOR(int x, int y, int z) -{ - asm volatile ("VX %0,%1,%2" : : "i" (x), "i" (y), "i" (z)); -} +#define MASK(x, y) fpu_vesravb(x, y, 24) -static inline void LOAD_DATA(int x, u8 *ptr) -{ - typedef struct { u8 _[16 * $#]; } addrtype; - register addrtype *__ptr asm("1") = (addrtype *) ptr; - - asm volatile ("VLM %2,%3,0,%1" - : : "m" (*__ptr), "a" (__ptr), "i" (x), - "i" (x + $# - 1)); -} - -static inline void STORE_DATA(int x, u8 *ptr) -{ - typedef struct { u8 _[16 * $#]; } addrtype; - register addrtype *__ptr asm("1") = (addrtype *) ptr; - - asm volatile ("VSTM %2,%3,0,1" - : "=m" (*__ptr) : "a" (__ptr), "i" (x), - "i" (x + $# - 1)); -} - -static inline void COPY_VEC(int x, int y) -{ - asm volatile ("VLR %0,%1" : : "i" (x), "i" (y)); -} +#define AND(x, y, z) fpu_vn(x, y, z) +#define XOR(x, y, z) fpu_vx(x, y, z) +#define LOAD_DATA(x, ptr) fpu_vlm(x, x + $# - 1, ptr) +#define STORE_DATA(x, ptr) fpu_vstm(x, x + $# - 1, ptr) +#define COPY_VEC(x, y) fpu_vlr(x, y) static void raid6_s390vx$#_gen_syndrome(int disks, size_t bytes, void **ptrs) { - struct kernel_fpu vxstate; + DECLARE_KERNEL_FPU_ONSTACK32(vxstate); u8 **dptr, *p, *q; int d, z, z0; @@ -114,7 +78,7 @@ static void raid6_s390vx$#_gen_syndrome(int disks, size_t bytes, void **ptrs) static void raid6_s390vx$#_xor_syndrome(int disks, int start, int stop, size_t bytes, void **ptrs) { - struct kernel_fpu vxstate; + DECLARE_KERNEL_FPU_ONSTACK32(vxstate); u8 **dptr, *p, *q; int d, z, z0; diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 882ea7c80f2d..202ce0d1666c 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -101,7 +101,7 @@ endif endif ifdef CONFIG_NFT_CT -ifdef CONFIG_RETPOLINE +ifdef CONFIG_MITIGATION_RETPOLINE nf_tables-objs += nft_ct_fast.o endif endif diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index c3e635364701..a48d5f0e2f3e 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -21,7 +21,7 @@ #include <net/netfilter/nf_log.h> #include <net/netfilter/nft_meta.h> -#if defined(CONFIG_RETPOLINE) && defined(CONFIG_X86) +#if defined(CONFIG_MITIGATION_RETPOLINE) && defined(CONFIG_X86) static struct static_key_false nf_tables_skip_direct_calls; @@ -207,7 +207,7 @@ static void expr_call_ops_eval(const struct nft_expr *expr, struct nft_regs *regs, struct nft_pktinfo *pkt) { -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE unsigned long e; if (nf_skip_indirect_calls()) @@ -236,7 +236,7 @@ static void expr_call_ops_eval(const struct nft_expr *expr, X(e, nft_objref_map_eval); #undef X indirect_call: -#endif /* CONFIG_RETPOLINE */ +#endif /* CONFIG_MITIGATION_RETPOLINE */ expr->ops->eval(expr, regs, pkt); } diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 255640013ab8..452ed94c3a4d 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -754,7 +754,7 @@ static bool nft_ct_set_reduce(struct nft_regs_track *track, return false; } -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE static const struct nft_expr_ops nft_ct_get_fast_ops = { .type = &nft_ct_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_ct)), @@ -799,7 +799,7 @@ nft_ct_select_ops(const struct nft_ctx *ctx, return ERR_PTR(-EINVAL); if (tb[NFTA_CT_DREG]) { -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE u32 k = ntohl(nla_get_be32(tb[NFTA_CT_KEY])); switch (k) { diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index 870e5b113d13..a0055f510e31 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -24,7 +24,7 @@ struct nft_lookup { struct nft_set_binding binding; }; -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE bool nft_set_do_lookup(const struct net *net, const struct nft_set *set, const u32 *key, const struct nft_set_ext **ext) { diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 36b025cc4fd2..87f6e3c6daa8 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -2410,7 +2410,7 @@ static struct pernet_operations psched_net_ops = { .exit = psched_net_exit, }; -#if IS_ENABLED(CONFIG_RETPOLINE) +#if IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) DEFINE_STATIC_KEY_FALSE(tc_skip_wrapper); #endif diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index da5aa5aed1e3..13067d3ef22b 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -256,7 +256,7 @@ objtool := $(objtree)/tools/objtool/objtool objtool-args-$(CONFIG_HAVE_JUMP_LABEL_HACK) += --hacks=jump_label objtool-args-$(CONFIG_HAVE_NOINSTR_HACK) += --hacks=noinstr -objtool-args-$(CONFIG_CALL_DEPTH_TRACKING) += --hacks=skylake +objtool-args-$(CONFIG_MITIGATION_CALL_DEPTH_TRACKING) += --hacks=skylake objtool-args-$(CONFIG_X86_KERNEL_IBT) += --ibt objtool-args-$(CONFIG_FINEIBT) += --cfi objtool-args-$(CONFIG_FTRACE_MCOUNT_USE_OBJTOOL) += --mcount @@ -264,9 +264,9 @@ ifdef CONFIG_FTRACE_MCOUNT_USE_OBJTOOL objtool-args-$(CONFIG_HAVE_OBJTOOL_NOP_MCOUNT) += --mnop endif objtool-args-$(CONFIG_UNWINDER_ORC) += --orc -objtool-args-$(CONFIG_RETPOLINE) += --retpoline -objtool-args-$(CONFIG_RETHUNK) += --rethunk -objtool-args-$(CONFIG_SLS) += --sls +objtool-args-$(CONFIG_MITIGATION_RETPOLINE) += --retpoline +objtool-args-$(CONFIG_MITIGATION_RETHUNK) += --rethunk +objtool-args-$(CONFIG_MITIGATION_SLS) += --sls objtool-args-$(CONFIG_STACK_VALIDATION) += --stackval objtool-args-$(CONFIG_HAVE_STATIC_CALL_INLINE) += --static-call objtool-args-$(CONFIG_HAVE_UACCESS_VALIDATION) += --uaccess diff --git a/scripts/Makefile.vmlinux_o b/scripts/Makefile.vmlinux_o index 25b3b587d37c..6de297916ce6 100644 --- a/scripts/Makefile.vmlinux_o +++ b/scripts/Makefile.vmlinux_o @@ -38,7 +38,7 @@ objtool-enabled := $(or $(delay-objtool),$(CONFIG_NOINSTR_VALIDATION)) vmlinux-objtool-args-$(delay-objtool) += $(objtool-args-y) vmlinux-objtool-args-$(CONFIG_GCOV_KERNEL) += --no-unreachable vmlinux-objtool-args-$(CONFIG_NOINSTR_VALIDATION) += --noinstr \ - $(if $(or $(CONFIG_CPU_UNRET_ENTRY),$(CONFIG_CPU_SRSO)), --unret) + $(if $(or $(CONFIG_MITIGATION_UNRET_ENTRY),$(CONFIG_MITIGATION_SRSO)), --unret) objtool-args = $(vmlinux-objtool-args-y) --link diff --git a/scripts/atomic/kerneldoc/add_unless b/scripts/atomic/kerneldoc/add_unless index f828e5f6750c..fbc2fadfbdc4 100644 --- a/scripts/atomic/kerneldoc/add_unless +++ b/scripts/atomic/kerneldoc/add_unless @@ -10,6 +10,7 @@ cat <<EOF * @u: ${int} value to compare with * * If (@v != @u), atomically updates @v to (@v + @a) with ${desc_order} ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * ${desc_noinstr} * diff --git a/scripts/atomic/kerneldoc/cmpxchg b/scripts/atomic/kerneldoc/cmpxchg index 3bce328f50cf..02b24ee9d8a4 100644 --- a/scripts/atomic/kerneldoc/cmpxchg +++ b/scripts/atomic/kerneldoc/cmpxchg @@ -6,6 +6,7 @@ cat <<EOF * @new: ${int} value to assign * * If (@v == @old), atomically updates @v to @new with ${desc_order} ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * ${desc_noinstr} * diff --git a/scripts/atomic/kerneldoc/dec_if_positive b/scripts/atomic/kerneldoc/dec_if_positive index 04f1aed3cf83..9468b4a69603 100644 --- a/scripts/atomic/kerneldoc/dec_if_positive +++ b/scripts/atomic/kerneldoc/dec_if_positive @@ -4,6 +4,7 @@ cat <<EOF * @v: pointer to ${atomic}_t * * If (@v > 0), atomically updates @v to (@v - 1) with ${desc_order} ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * ${desc_noinstr} * diff --git a/scripts/atomic/kerneldoc/dec_unless_positive b/scripts/atomic/kerneldoc/dec_unless_positive index ee73612f0354..06a678678f71 100644 --- a/scripts/atomic/kerneldoc/dec_unless_positive +++ b/scripts/atomic/kerneldoc/dec_unless_positive @@ -4,6 +4,7 @@ cat <<EOF * @v: pointer to ${atomic}_t * * If (@v <= 0), atomically updates @v to (@v - 1) with ${desc_order} ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * ${desc_noinstr} * diff --git a/scripts/atomic/kerneldoc/inc_not_zero b/scripts/atomic/kerneldoc/inc_not_zero index 618be08e653e..c1a30fc66ee9 100644 --- a/scripts/atomic/kerneldoc/inc_not_zero +++ b/scripts/atomic/kerneldoc/inc_not_zero @@ -4,6 +4,7 @@ cat <<EOF * @v: pointer to ${atomic}_t * * If (@v != 0), atomically updates @v to (@v + 1) with ${desc_order} ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * ${desc_noinstr} * diff --git a/scripts/atomic/kerneldoc/inc_unless_negative b/scripts/atomic/kerneldoc/inc_unless_negative index 597f23d4dc8d..ece0d2c7b38f 100644 --- a/scripts/atomic/kerneldoc/inc_unless_negative +++ b/scripts/atomic/kerneldoc/inc_unless_negative @@ -4,6 +4,7 @@ cat <<EOF * @v: pointer to ${atomic}_t * * If (@v >= 0), atomically updates @v to (@v + 1) with ${desc_order} ordering. + * Otherwise, @v is not modified and relaxed ordering is provided. * * ${desc_noinstr} * diff --git a/scripts/atomic/kerneldoc/try_cmpxchg b/scripts/atomic/kerneldoc/try_cmpxchg index 296553206c06..3ccff29538f5 100644 --- a/scripts/atomic/kerneldoc/try_cmpxchg +++ b/scripts/atomic/kerneldoc/try_cmpxchg @@ -6,7 +6,8 @@ cat <<EOF * @new: ${int} value to assign * * If (@v == @old), atomically updates @v to @new with ${desc_order} ordering. - * Otherwise, updates @old to the current value of @v. + * Otherwise, @v is not modified, @old is updated to the current value of @v, + * and relaxed ordering is provided. * * ${desc_noinstr} * diff --git a/scripts/generate_rust_target.rs b/scripts/generate_rust_target.rs index 0da52b548ba5..19f72bfdbb82 100644 --- a/scripts/generate_rust_target.rs +++ b/scripts/generate_rust_target.rs @@ -155,7 +155,7 @@ fn main() { "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128", ); let mut features = "-3dnow,-3dnowa,-mmx,+soft-float".to_string(); - if cfg.has("RETPOLINE") { + if cfg.has("MITIGATION_RETPOLINE") { features += ",+retpoline-external-thunk"; } ts.push("features", features); diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 6bf5fc5560df..dc006966e097 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -1853,7 +1853,7 @@ static void add_header(struct buffer *b, struct module *mod) buf_printf(b, "\n" - "#ifdef CONFIG_RETPOLINE\n" + "#ifdef CONFIG_MITIGATION_RETPOLINE\n" "MODULE_INFO(retpoline, \"Y\");\n" "#endif\n"); diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index ccbf914b3d1a..25160d26764b 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -444,6 +444,7 @@ #define X86_FEATURE_SEV (19*32+ 1) /* AMD Secure Encrypted Virtualization */ #define X86_FEATURE_VM_PAGE_FLUSH (19*32+ 2) /* "" VM Page Flush MSR is supported */ #define X86_FEATURE_SEV_ES (19*32+ 3) /* AMD Secure Encrypted Virtualization - Encrypted State */ +#define X86_FEATURE_SEV_SNP (19*32+ 4) /* AMD Secure Encrypted Virtualization - Secure Nested Paging */ #define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* "" Virtual TSC_AUX */ #define X86_FEATURE_SME_COHERENT (19*32+10) /* "" AMD hardware-enforced cache coherency */ #define X86_FEATURE_DEBUG_SWAP (19*32+14) /* AMD SEV-ES full debug state swap support */ diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index f40b29d3abad..1f23960d2b06 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -44,32 +44,32 @@ # define DISABLE_LA57 (1<<(X86_FEATURE_LA57 & 31)) #endif -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION # define DISABLE_PTI 0 #else # define DISABLE_PTI (1 << (X86_FEATURE_PTI & 31)) #endif -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE # define DISABLE_RETPOLINE 0 #else # define DISABLE_RETPOLINE ((1 << (X86_FEATURE_RETPOLINE & 31)) | \ (1 << (X86_FEATURE_RETPOLINE_LFENCE & 31))) #endif -#ifdef CONFIG_RETHUNK +#ifdef CONFIG_MITIGATION_RETHUNK # define DISABLE_RETHUNK 0 #else # define DISABLE_RETHUNK (1 << (X86_FEATURE_RETHUNK & 31)) #endif -#ifdef CONFIG_CPU_UNRET_ENTRY +#ifdef CONFIG_MITIGATION_UNRET_ENTRY # define DISABLE_UNRET 0 #else # define DISABLE_UNRET (1 << (X86_FEATURE_UNRET & 31)) #endif -#ifdef CONFIG_CALL_DEPTH_TRACKING +#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING # define DISABLE_CALL_DEPTH_TRACKING 0 #else # define DISABLE_CALL_DEPTH_TRACKING (1 << (X86_FEATURE_CALL_DEPTH & 31)) diff --git a/tools/arch/x86/lib/insn.c b/tools/arch/x86/lib/insn.c index 8fd63a067308..ada4b4a79dd4 100644 --- a/tools/arch/x86/lib/insn.c +++ b/tools/arch/x86/lib/insn.c @@ -71,7 +71,7 @@ void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64) insn->kaddr = kaddr; insn->end_kaddr = kaddr + buf_len; insn->next_byte = kaddr; - insn->x86_64 = x86_64 ? 1 : 0; + insn->x86_64 = x86_64; insn->opnd_bytes = 4; if (x86_64) insn->addr_bytes = 8; @@ -268,11 +268,9 @@ int insn_get_opcode(struct insn *insn) if (opcode->got) return 0; - if (!insn->prefixes.got) { - ret = insn_get_prefixes(insn); - if (ret) - return ret; - } + ret = insn_get_prefixes(insn); + if (ret) + return ret; /* Get first opcode */ op = get_next(insn_byte_t, insn); @@ -339,11 +337,9 @@ int insn_get_modrm(struct insn *insn) if (modrm->got) return 0; - if (!insn->opcode.got) { - ret = insn_get_opcode(insn); - if (ret) - return ret; - } + ret = insn_get_opcode(insn); + if (ret) + return ret; if (inat_has_modrm(insn->attr)) { mod = get_next(insn_byte_t, insn); @@ -386,11 +382,9 @@ int insn_rip_relative(struct insn *insn) if (!insn->x86_64) return 0; - if (!modrm->got) { - ret = insn_get_modrm(insn); - if (ret) - return 0; - } + ret = insn_get_modrm(insn); + if (ret) + return 0; /* * For rip-relative instructions, the mod field (top 2 bits) * is zero and the r/m field (bottom 3 bits) is 0x5. @@ -417,11 +411,9 @@ int insn_get_sib(struct insn *insn) if (insn->sib.got) return 0; - if (!insn->modrm.got) { - ret = insn_get_modrm(insn); - if (ret) - return ret; - } + ret = insn_get_modrm(insn); + if (ret) + return ret; if (insn->modrm.nbytes) { modrm = insn->modrm.bytes[0]; @@ -460,11 +452,9 @@ int insn_get_displacement(struct insn *insn) if (insn->displacement.got) return 0; - if (!insn->sib.got) { - ret = insn_get_sib(insn); - if (ret) - return ret; - } + ret = insn_get_sib(insn); + if (ret) + return ret; if (insn->modrm.nbytes) { /* @@ -628,11 +618,9 @@ int insn_get_immediate(struct insn *insn) if (insn->immediate.got) return 0; - if (!insn->displacement.got) { - ret = insn_get_displacement(insn); - if (ret) - return ret; - } + ret = insn_get_displacement(insn); + if (ret) + return ret; if (inat_has_moffset(insn->attr)) { if (!__get_moffset(insn)) @@ -703,11 +691,9 @@ int insn_get_length(struct insn *insn) if (insn->length) return 0; - if (!insn->immediate.got) { - ret = insn_get_immediate(insn); - if (ret) - return ret; - } + ret = insn_get_immediate(insn); + if (ret) + return ret; insn->length = (unsigned char)((unsigned long)insn->next_byte - (unsigned long)insn->kaddr); diff --git a/tools/objtool/arch/x86/special.c b/tools/objtool/arch/x86/special.c index 29e949579ede..4134d27c696b 100644 --- a/tools/objtool/arch/x86/special.c +++ b/tools/objtool/arch/x86/special.c @@ -83,7 +83,7 @@ bool arch_support_alt_relocation(struct special_alt *special_alt, * TODO: Once we have DWARF CFI and smarter instruction decoding logic, * ensure the same register is used in the mov and jump instructions. * - * NOTE: RETPOLINE made it harder still to decode dynamic jumps. + * NOTE: MITIGATION_RETPOLINE made it harder still to decode dynamic jumps. */ struct reloc *arch_find_switch_table(struct objtool_file *file, struct instruction *insn) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 548ec3cd7c00..8440b7bb343c 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -3980,11 +3980,11 @@ static int validate_retpoline(struct objtool_file *file) if (insn->type == INSN_RETURN) { if (opts.rethunk) { - WARN_INSN(insn, "'naked' return found in RETHUNK build"); + WARN_INSN(insn, "'naked' return found in MITIGATION_RETHUNK build"); } else continue; } else { - WARN_INSN(insn, "indirect %s found in RETPOLINE build", + WARN_INSN(insn, "indirect %s found in MITIGATION_RETPOLINE build", insn->type == INSN_JUMP_DYNAMIC ? "jump" : "call"); } diff --git a/tools/testing/selftests/kvm/s390x/memop.c b/tools/testing/selftests/kvm/s390x/memop.c index bb3ca9a5d731..b6da8f71ea19 100644 --- a/tools/testing/selftests/kvm/s390x/memop.c +++ b/tools/testing/selftests/kvm/s390x/memop.c @@ -375,6 +375,32 @@ static void test_copy(void) kvm_vm_free(t.kvm_vm); } +static void test_copy_access_register(void) +{ + struct test_default t = test_default_init(guest_copy); + + HOST_SYNC(t.vcpu, STAGE_INITED); + + prepare_mem12(); + t.run->psw_mask &= ~(3UL << (63 - 17)); + t.run->psw_mask |= 1UL << (63 - 17); /* Enable AR mode */ + + /* + * Primary address space gets used if an access register + * contains zero. The host makes use of AR[1] so is a good + * candidate to ensure the guest AR (of zero) is used. + */ + CHECK_N_DO(MOP, t.vcpu, LOGICAL, WRITE, mem1, t.size, + GADDR_V(mem1), AR(1)); + HOST_SYNC(t.vcpu, STAGE_COPIED); + + CHECK_N_DO(MOP, t.vcpu, LOGICAL, READ, mem2, t.size, + GADDR_V(mem2), AR(1)); + ASSERT_MEM_EQ(mem1, mem2, t.size); + + kvm_vm_free(t.kvm_vm); +} + static void set_storage_key_range(void *addr, size_t len, uint8_t key) { uintptr_t _addr, abs, i; @@ -1102,6 +1128,11 @@ int main(int argc, char *argv[]) .requirements_met = extension_cap > 0, }, { + .name = "copy with access register mode", + .test = test_copy_access_register, + .requirements_met = true, + }, + { .name = "error checks with key", .test = test_errors_key, .requirements_met = extension_cap > 0, |