From 27600805e62f800bacf990354632eae4e487d34c Mon Sep 17 00:00:00 2001 From: Yazen Ghannam Date: Thu, 3 Sep 2026 10:43:25 -0500 Subject: x86/amd_node: Fix PCI device reference counting in amd_smn_init() The local "root" pointer is a temporary variable used during the device search. Therefore, refcount related to the search iterators should be cleaned up after the search is complete. Use the __free() cleanup macro to ensure the refcount is decremented when the temporary pointer goes out of scope. Additionally, increment the refcount when caching a root pointer. This ensures the in-use refcount is separate from the temporary search refcounting. Finally, drop the redundant "root = NULL" before the second search loop. The pci_get_class() iterator always decrements the refcount of its "from" argument, so the first loop can only fall through with "root" already NULL. Fixes: 0a4b61d9c2e4 ("x86/amd_node: Fix AMD root device caching") Closes: https://sashiko.dev/#/patchset/20260806160159.230453-1-jason.andryuk%40amd.com Reported-by: Sashiko Assisted-by: LLM Signed-off-by: Yazen Ghannam Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Mario Limonciello (AMD) Cc: Link: https://patch.msgid.link/20260903154325.74343-1-yazen.ghannam@amd.com --- 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