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/arm64/lib/delay.c | 84 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 84 insertions(+) create mode 100644 arch/arm64/lib/delay.c (limited to 'arch/arm64/lib/delay.c') diff --git a/arch/arm64/lib/delay.c b/arch/arm64/lib/delay.c new file mode 100644 index 000000000..e278e060e --- /dev/null +++ b/arch/arm64/lib/delay.c @@ -0,0 +1,84 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Delay loops based on the OpenRISC implementation. + * + * Copyright (C) 2012 ARM Limited + * + * Author: Will Deacon + */ + +#include +#include +#include +#include +#include + +#include + +#define USECS_TO_CYCLES(time_usecs) \ + xloops_to_cycles((time_usecs) * 0x10C7UL) + +static inline unsigned long xloops_to_cycles(unsigned long xloops) +{ + return (xloops * loops_per_jiffy * HZ) >> 32; +} + +/* + * Force the use of CNTVCT_EL0 in order to have the same base as WFxT. + * This avoids some annoying issues when CNTVOFF_EL2 is not reset 0 on a + * KVM host running at EL1 until we do a vcpu_put() on the vcpu. When + * running at EL2, the effective offset is always 0. + * + * Note that userspace cannot change the offset behind our back either, + * as the vcpu mutex is held as long as KVM_RUN is in progress. + */ +static cycles_t notrace __delay_cycles(void) +{ + guard(preempt_notrace)(); + return __arch_counter_get_cntvct_stable(); +} + +void __delay(unsigned long cycles) +{ + cycles_t start = __delay_cycles(); + + if (alternative_has_cap_unlikely(ARM64_HAS_WFXT)) { + u64 end = start + cycles; + + /* + * Start with WFIT. If an interrupt makes us resume + * early, use a WFET loop to complete the delay. + */ + wfit(end); + while ((__delay_cycles() - start) < cycles) + wfet(end); + } else if (arch_timer_evtstrm_available()) { + const cycles_t timer_evt_period = + USECS_TO_CYCLES(ARCH_TIMER_EVT_STREAM_PERIOD_US); + + while ((__delay_cycles() - start + timer_evt_period) < cycles) + wfe(); + } + + while ((__delay_cycles() - start) < cycles) + cpu_relax(); +} +EXPORT_SYMBOL(__delay); + +inline void __const_udelay(unsigned long xloops) +{ + __delay(xloops_to_cycles(xloops)); +} +EXPORT_SYMBOL(__const_udelay); + +void __udelay(unsigned long usecs) +{ + __const_udelay(usecs * 0x10C7UL); /* 2**32 / 1000000 (rounded up) */ +} +EXPORT_SYMBOL(__udelay); + +void __ndelay(unsigned long nsecs) +{ + __const_udelay(nsecs * 0x5UL); /* 2**32 / 1000000000 (rounded up) */ +} +EXPORT_SYMBOL(__ndelay); -- cgit v1.3.1