Merge branches 'for-next/gcs', 'for-next/probes', 'for-next/asm-offsets', 'for-next/tlb', 'for-next/misc', 'for-next/mte', 'for-next/sysreg', 'for-next/stacktrace', 'for-next/hwcap3', 'for-next/kselftest', 'for-next/crc32', 'for-next/guest-cca', 'for-next/haft' and 'for-next/scs', remote-tracking branch 'arm64/for-next/perf' into for-next/core

* arm64/for-next/perf:
  perf: Switch back to struct platform_driver::remove()
  perf: arm_pmuv3: Add support for Samsung Mongoose PMU
  dt-bindings: arm: pmu: Add Samsung Mongoose core compatible
  perf/dwc_pcie: Fix typos in event names
  perf/dwc_pcie: Add support for Ampere SoCs
  ARM: pmuv3: Add missing write_pmuacr()
  perf/marvell: Marvell PEM performance monitor support
  perf/arm_pmuv3: Add PMUv3.9 per counter EL0 access control
  perf/dwc_pcie: Convert the events with mixed case to lowercase
  perf/cxlpmu: Support missing events in 3.1 spec
  perf: imx_perf: add support for i.MX91 platform
  dt-bindings: perf: fsl-imx-ddr: Add i.MX91 compatible
  drivers perf: remove unused field pmu_node

* for-next/gcs: (42 commits)
  : arm64 Guarded Control Stack user-space support
  kselftest/arm64: Fix missing printf() argument in gcs/gcs-stress.c
  arm64/gcs: Fix outdated ptrace documentation
  kselftest/arm64: Ensure stable names for GCS stress test results
  kselftest/arm64: Validate that GCS push and write permissions work
  kselftest/arm64: Enable GCS for the FP stress tests
  kselftest/arm64: Add a GCS stress test
  kselftest/arm64: Add GCS signal tests
  kselftest/arm64: Add test coverage for GCS mode locking
  kselftest/arm64: Add a GCS test program built with the system libc
  kselftest/arm64: Add very basic GCS test program
  kselftest/arm64: Always run signals tests with GCS enabled
  kselftest/arm64: Allow signals tests to specify an expected si_code
  kselftest/arm64: Add framework support for GCS to signal handling tests
  kselftest/arm64: Add GCS as a detected feature in the signal tests
  kselftest/arm64: Verify the GCS hwcap
  arm64: Add Kconfig for Guarded Control Stack (GCS)
  arm64/ptrace: Expose GCS via ptrace and core files
  arm64/signal: Expose GCS state in signal frames
  arm64/signal: Set up and restore the GCS context for signal handlers
  arm64/mm: Implement map_shadow_stack()
  ...

* for-next/probes:
  : Various arm64 uprobes/kprobes cleanups
  arm64: insn: Simulate nop instruction for better uprobe performance
  arm64: probes: Remove probe_opcode_t
  arm64: probes: Cleanup kprobes endianness conversions
  arm64: probes: Move kprobes-specific fields
  arm64: probes: Fix uprobes for big-endian kernels
  arm64: probes: Fix simulate_ldr*_literal()
  arm64: probes: Remove broken LDR (literal) uprobe support

* for-next/asm-offsets:
  : arm64 asm-offsets.c cleanup (remove unused offsets)
  arm64: asm-offsets: remove PREEMPT_DISABLE_OFFSET
  arm64: asm-offsets: remove DMA_{TO,FROM}_DEVICE
  arm64: asm-offsets: remove VM_EXEC and PAGE_SZ
  arm64: asm-offsets: remove MM_CONTEXT_ID
  arm64: asm-offsets: remove COMPAT_{RT_,SIGFRAME_REGS_OFFSET
  arm64: asm-offsets: remove VMA_VM_*
  arm64: asm-offsets: remove TSK_ACTIVE_MM

* for-next/tlb:
  : TLB flushing optimisations
  arm64: optimize flush tlb kernel range
  arm64: tlbflush: add __flush_tlb_range_limit_excess()

* for-next/misc:
  : Miscellaneous patches
  arm64: tls: Fix context-switching of tpidrro_el0 when kpti is enabled
  arm64/ptrace: Clarify documentation of VL configuration via ptrace
  acpi/arm64: remove unnecessary cast
  arm64/mm: Change protval as 'pteval_t' in map_range()
  arm64: uprobes: Optimize cache flushes for xol slot
  acpi/arm64: Adjust error handling procedure in gtdt_parse_timer_block()
  arm64: fix .data.rel.ro size assertion when CONFIG_LTO_CLANG
  arm64/ptdump: Test both PTE_TABLE_BIT and PTE_VALID for block mappings
  arm64/mm: Sanity check PTE address before runtime P4D/PUD folding
  arm64/mm: Drop setting PTE_TYPE_PAGE in pte_mkcont()
  ACPI: GTDT: Tighten the check for the array of platform timer structures
  arm64/fpsimd: Fix a typo
  arm64: Expose ID_AA64ISAR1_EL1.XS to sanitised feature consumers
  arm64: Return early when break handler is found on linked-list
  arm64/mm: Re-organize arch_make_huge_pte()
  arm64/mm: Drop _PROT_SECT_DEFAULT
  arm64: Add command-line override for ID_AA64MMFR0_EL1.ECV
  arm64: head: Drop SWAPPER_TABLE_SHIFT
  arm64: cpufeature: add POE to cpucap_is_possible()
  arm64/mm: Change pgattr_change_is_safe() arguments as pteval_t

* for-next/mte:
  : Various MTE improvements
  selftests: arm64: add hugetlb mte tests
  hugetlb: arm64: add mte support

* for-next/sysreg:
  : arm64 sysreg updates
  arm64/sysreg: Update ID_AA64MMFR1_EL1 to DDI0601 2024-09

* for-next/stacktrace:
  : arm64 stacktrace improvements
  arm64: preserve pt_regs::stackframe during exec*()
  arm64: stacktrace: unwind exception boundaries
  arm64: stacktrace: split unwind_consume_stack()
  arm64: stacktrace: report recovered PCs
  arm64: stacktrace: report source of unwind data
  arm64: stacktrace: move dump_backtrace() to kunwind_stack_walk()
  arm64: use a common struct frame_record
  arm64: pt_regs: swap 'unused' and 'pmr' fields
  arm64: pt_regs: rename "pmr_save" -> "pmr"
  arm64: pt_regs: remove stale big-endian layout
  arm64: pt_regs: assert pt_regs is a multiple of 16 bytes

* for-next/hwcap3:
  : Add AT_HWCAP3 support for arm64 (also wire up AT_HWCAP4)
  arm64: Support AT_HWCAP3
  binfmt_elf: Wire up AT_HWCAP3 at AT_HWCAP4

* for-next/kselftest: (30 commits)
  : arm64 kselftest fixes/cleanups
  kselftest/arm64: Try harder to generate different keys during PAC tests
  kselftest/arm64: Don't leak pipe fds in pac.exec_sign_all()
  kselftest/arm64: Corrupt P0 in the irritator when testing SSVE
  kselftest/arm64: Add FPMR coverage to fp-ptrace
  kselftest/arm64: Expand the set of ZA writes fp-ptrace does
  kselftets/arm64: Use flag bits for features in fp-ptrace assembler code
  kselftest/arm64: Enable build of PAC tests with LLVM=1
  kselftest/arm64: Check that SVCR is 0 in signal handlers
  kselftest/arm64: Fix printf() compiler warnings in the arm64 syscall-abi.c tests
  kselftest/arm64: Fix printf() warning in the arm64 MTE prctl() test
  kselftest/arm64: Fix printf() compiler warnings in the arm64 fp tests
  kselftest/arm64: Fix build with stricter assemblers
  kselftest/arm64: Test signal handler state modification in fp-stress
  kselftest/arm64: Provide a SIGUSR1 handler in the kernel mode FP stress test
  kselftest/arm64: Implement irritators for ZA and ZT
  kselftest/arm64: Remove unused ADRs from irritator handlers
  kselftest/arm64: Correct misleading comments on fp-stress irritators
  kselftest/arm64: Poll less often while waiting for fp-stress children
  kselftest/arm64: Increase frequency of signal delivery in fp-stress
  kselftest/arm64: Fix encoding for SVE B16B16 test
  ...

* for-next/crc32:
  : Optimise CRC32 using PMULL instructions
  arm64/crc32: Implement 4-way interleave using PMULL
  arm64/crc32: Reorganize bit/byte ordering macros
  arm64/lib: Handle CRC-32 alternative in C code

* for-next/guest-cca:
  : Support for running Linux as a guest in Arm CCA
  arm64: Document Arm Confidential Compute
  virt: arm-cca-guest: TSM_REPORT support for realms
  arm64: Enable memory encrypt for Realms
  arm64: mm: Avoid TLBI when marking pages as valid
  arm64: Enforce bounce buffers for realm DMA
  efi: arm64: Map Device with Prot Shared
  arm64: rsi: Map unprotected MMIO as decrypted
  arm64: rsi: Add support for checking whether an MMIO is protected
  arm64: realm: Query IPA size from the RMM
  arm64: Detect if in a realm and set RIPAS RAM
  arm64: rsi: Add RSI definitions

* for-next/haft:
  : Support for arm64 FEAT_HAFT
  arm64: pgtable: Warn unexpected pmdp_test_and_clear_young()
  arm64: Enable ARCH_HAS_NONLEAF_PMD_YOUNG
  arm64: Add support for FEAT_HAFT
  arm64: setup: name 'tcr2' register
  arm64/sysreg: Update ID_AA64MMFR1_EL1 register

* for-next/scs:
  : Dynamic shadow call stack fixes
  arm64/scs: Drop unused prototype __pi_scs_patch_vmlinux()
  arm64/scs: Deal with 64-bit relative offsets in FDE frames
  arm64/scs: Fix handling of DWARF augmentation data in CIE/FDE frames
This commit is contained in:
166 changed files with 7091 additions and 527 deletions

View File

@@ -265,8 +265,7 @@ static inline pte_t pte_mkspecial(pte_t pte)
static inline pte_t pte_mkcont(pte_t pte)
{
pte = set_pte_bit(pte, __pgprot(PTE_CONT));
return set_pte_bit(pte, __pgprot(PTE_TYPE_PAGE));
return set_pte_bit(pte, __pgprot(PTE_CONT));
}
static inline pte_t pte_mknoncont(pte_t pte)
@@ -338,7 +337,7 @@ static inline pte_t __ptep_get(pte_t *ptep)
}
extern void __sync_icache_dcache(pte_t pteval);
bool pgattr_change_is_safe(u64 old, u64 new);
bool pgattr_change_is_safe(pteval_t old, pteval_t new);
/*
* PTE bits configuration in the presence of hardware Dirty Bit Management
@@ -438,11 +437,6 @@ static inline void __set_ptes(struct mm_struct *mm,
}
}
/*
* Huge pte definitions.
*/
#define pte_mkhuge(pte) (__pte(pte_val(pte) & ~PTE_TABLE_BIT))
/*
* Hugetlb definitions.
*/
@@ -684,6 +678,11 @@ static inline void set_pud_at(struct mm_struct *mm, unsigned long addr,
#define pgprot_nx(prot) \
__pgprot_modify(prot, PTE_MAYBE_GP, PTE_PXN)
#define pgprot_decrypted(prot) \
__pgprot_modify(prot, PROT_NS_SHARED, PROT_NS_SHARED)
#define pgprot_encrypted(prot) \
__pgprot_modify(prot, PROT_NS_SHARED, 0)
/*
* Mark the prot value as uncacheable and unbufferable.
*/
@@ -927,6 +926,9 @@ static inline phys_addr_t p4d_page_paddr(p4d_t p4d)
static inline pud_t *p4d_to_folded_pud(p4d_t *p4dp, unsigned long addr)
{
/* Ensure that 'p4dp' indexes a page table according to 'addr' */
VM_BUG_ON(((addr >> P4D_SHIFT) ^ ((u64)p4dp >> 3)) % PTRS_PER_P4D);
return (pud_t *)PTR_ALIGN_DOWN(p4dp, PAGE_SIZE) + pud_index(addr);
}
@@ -1051,6 +1053,9 @@ static inline phys_addr_t pgd_page_paddr(pgd_t pgd)
static inline p4d_t *pgd_to_folded_p4d(pgd_t *pgdp, unsigned long addr)
{
/* Ensure that 'pgdp' indexes a page table according to 'addr' */
VM_BUG_ON(((addr >> PGDIR_SHIFT) ^ ((u64)pgdp >> 3)) % PTRS_PER_PGD);
return (p4d_t *)PTR_ALIGN_DOWN(pgdp, PAGE_SIZE) + p4d_index(addr);
}
@@ -1259,15 +1264,17 @@ static inline int __ptep_clear_flush_young(struct vm_area_struct *vma,
return young;
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG)
#define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
unsigned long address,
pmd_t *pmdp)
{
/* Operation applies to PMD table entry only if FEAT_HAFT is enabled */
VM_WARN_ON(pmd_table(READ_ONCE(*pmdp)) && !system_supports_haft());
return __ptep_test_and_clear_young(vma, address, (pte_t *)pmdp);
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG */
static inline pte_t __ptep_get_and_clear(struct mm_struct *mm,
unsigned long address, pte_t *ptep)
@@ -1502,6 +1509,10 @@ static inline void update_mmu_cache_range(struct vm_fault *vmf,
*/
#define arch_has_hw_pte_young cpu_has_hw_af
#ifdef CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG
#define arch_has_hw_nonleaf_pmd_young system_supports_haft
#endif
/*
* Experimentally, it's cheap to set the access flag in hardware and we
* benefit from prefaulting mappings as 'old' to start with.