From 2bc6b218717b9d08f466f88209251d54bc09b207 Mon Sep 17 00:00:00 2001 From: Fuad Tabba Date: Tue, 22 Sep 2026 19:14:30 +0100 Subject: arm64/boot: Disable trapping of PMZR_EL0 writes to EL2 __init_el2_fgt2() writes one mask to both HDFGRTR2_EL2 and HDFGWTR2_EL2. PMZR_EL0 is write-only, so its trap bit, nPMZR_EL0, exists only in HDFGWTR2_EL2 and is therefore never set: a PMZR_EL0 write from the host traps to EL2, where the nVHE hypervisor has no handler and BUG()s. The kernel never writes PMZR_EL0, but kernel.perf_user_access=1 has the PMU driver set PMUSERENR_EL0.UEN for a task with a user-read event, so a write from EL0 reaches the trap and takes the host down without a panic message. Accumulate the HDFGWTR2_EL2 bits separately, as __init_el2_fgt() already does for HDFGWTR_EL2, and set nPMZR_EL0 with the other FEAT_PMUv3p9 bits. Fixes: 858c7bfcb35e1 ("arm64/boot: Enable EL2 requirements for FEAT_PMUv3p9") Cc: stable@vger.kernel.org Signed-off-by: Fuad Tabba Reviewed-by: Anshuman Khandual Reviewed-by: Oliver Upton Signed-off-by: Will Deacon --- include/vdso/math64.h | 62 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 62 insertions(+) create mode 100644 include/vdso/math64.h (limited to 'include/vdso/math64.h') diff --git a/include/vdso/math64.h b/include/vdso/math64.h new file mode 100644 index 000000000..22ae212f8 --- /dev/null +++ b/include/vdso/math64.h @@ -0,0 +1,62 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __VDSO_MATH64_H +#define __VDSO_MATH64_H + +static __always_inline u32 +__iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder) +{ + u32 ret = 0; + + while (dividend >= divisor) { + /* The following asm() prevents the compiler from + optimising this loop into a modulo operation. */ + asm("" : "+rm"(dividend)); + + dividend -= divisor; + ret++; + } + + *remainder = dividend; + + return ret; +} + +#if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__) + +#ifndef mul_u64_u32_add_u64_shr +static __always_inline u64 mul_u64_u32_add_u64_shr(u64 a, u32 mul, u64 b, unsigned int shift) +{ + return (u64)((((unsigned __int128)a * mul) + b) >> shift); +} +#endif /* mul_u64_u32_add_u64_shr */ + +#else + +#ifndef mul_u64_u32_add_u64_shr +#ifndef mul_u32_u32 +static inline u64 mul_u32_u32(u32 a, u32 b) +{ + return (u64)a * b; +} +#define mul_u32_u32 mul_u32_u32 +#endif +static __always_inline u64 mul_u64_u32_add_u64_shr(u64 a, u32 mul, u64 b, unsigned int shift) +{ + u32 ah = a >> 32, al = a; + bool ovf; + u64 ret; + + ovf = __builtin_add_overflow(mul_u32_u32(al, mul), b, &ret); + ret >>= shift; + if (ovf && shift) + ret += 1ULL << (64 - shift); + if (ah) + ret += mul_u32_u32(ah, mul) << (32 - shift); + + return ret; +} +#endif /* mul_u64_u32_add_u64_shr */ + +#endif + +#endif /* __VDSO_MATH64_H */ -- cgit v1.3.1