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 --- arch/alpha/lib/strlen.S | 59 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 59 insertions(+) create mode 100644 arch/alpha/lib/strlen.S (limited to 'arch/alpha/lib/strlen.S') diff --git a/arch/alpha/lib/strlen.S b/arch/alpha/lib/strlen.S new file mode 100644 index 000000000..4fc6a6ff2 --- /dev/null +++ b/arch/alpha/lib/strlen.S @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * strlen.S (c) 1995 David Mosberger (davidm@cs.arizona.edu) + * + * Finds length of a 0-terminated string. Optimized for the + * Alpha architecture: + * + * - memory accessed as aligned quadwords only + * - uses bcmpge to compare 8 bytes in parallel + * - does binary search to find 0 byte in last + * quadword (HAKMEM needed 12 instructions to + * do this instead of the 9 instructions that + * binary search needs). + */ +#include + .set noreorder + .set noat + + .align 3 + + .globl strlen + .ent strlen + +strlen: + ldq_u $1, 0($16) # load first quadword ($16 may be misaligned) + lda $2, -1($31) + insqh $2, $16, $2 + andnot $16, 7, $0 + or $2, $1, $1 + cmpbge $31, $1, $2 # $2 <- bitmask: bit i == 1 <==> i-th byte == 0 + bne $2, found + +loop: ldq $1, 8($0) + addq $0, 8, $0 # addr += 8 + nop # helps dual issue last two insns + cmpbge $31, $1, $2 + beq $2, loop + +found: blbs $2, done # make aligned case fast + negq $2, $3 + and $2, $3, $2 + + and $2, 0x0f, $1 + addq $0, 4, $3 + cmoveq $1, $3, $0 + + and $2, 0x33, $1 + addq $0, 2, $3 + cmoveq $1, $3, $0 + + and $2, 0x55, $1 + addq $0, 1, $3 + cmoveq $1, $3, $0 + +done: subq $0, $16, $0 + ret $31, ($26) + + .end strlen + EXPORT_SYMBOL(strlen) -- cgit v1.3.1