From 29cc0f3aa7c64d3b3cb9d94c0a0984ba6717bf72 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 13 Feb 2026 14:16:19 +0000 Subject: [PATCH 1/2] arm64: Force the use of CNTVCT_EL0 in __delay() Quentin forwards a report from Hyesoo Yu, describing an interesting problem with the use of WFxT in __delay() when a vcpu is loaded and that KVM is *not* in VHE mode (either nVHE or hVHE). In this case, CNTVOFF_EL2 is set to a non-zero value to reflect the state of the guest virtual counter. At the same time, __delay() is using get_cycles() to read the counter value, which is indirected to reading CNTPCT_EL0. The core of the issue is that WFxT is using the *virtual* counter, while the kernel is using the physical counter, and that the offset introduces a really bad discrepancy between the two. Fix this by forcing the use of CNTVCT_EL0, making __delay() consistent irrespective of the value of CNTVOFF_EL2. Reported-by: Hyesoo Yu Reported-by: Quentin Perret Reviewed-by: Quentin Perret Fixes: 7d26b0516a0d ("arm64: Use WFxT for __delay() when possible") Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/ktosachvft2cgqd5qkukn275ugmhy6xrhxur4zqpdxlfr3qh5h@o3zrfnsq63od Cc: stable@vger.kernel.org Signed-off-by: Will Deacon --- arch/arm64/lib/delay.c | 19 +++++++++++++++---- 1 file changed, 15 insertions(+), 4 deletions(-) diff --git a/arch/arm64/lib/delay.c b/arch/arm64/lib/delay.c index cb2062e7e234..d02341303899 100644 --- a/arch/arm64/lib/delay.c +++ b/arch/arm64/lib/delay.c @@ -23,9 +23,20 @@ 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. + */ +#define __delay_cycles() __arch_counter_get_cntvct_stable() + void __delay(unsigned long cycles) { - cycles_t start = get_cycles(); + cycles_t start = __delay_cycles(); if (alternative_has_cap_unlikely(ARM64_HAS_WFXT)) { u64 end = start + cycles; @@ -35,17 +46,17 @@ void __delay(unsigned long cycles) * early, use a WFET loop to complete the delay. */ wfit(end); - while ((get_cycles() - start) < cycles) + 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 ((get_cycles() - start + timer_evt_period) < cycles) + while ((__delay_cycles() - start + timer_evt_period) < cycles) wfe(); } - while ((get_cycles() - start) < cycles) + while ((__delay_cycles() - start) < cycles) cpu_relax(); } EXPORT_SYMBOL(__delay); From 729a2e8e9ac47099a967567389cc9d73ef4194ca Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 16 Feb 2026 11:54:21 +0100 Subject: [PATCH 2/2] arm64: hugetlbpage: avoid unused-but-set-parameter warning (gcc-16) gcc-16 warns about an instance that older compilers did not: arch/arm64/mm/hugetlbpage.c: In function 'huge_pte_clear': arch/arm64/mm/hugetlbpage.c:369:57: error: parameter 'addr' set but not used [-Werror=unused-but-set-parameter=] The issue here is that __pte_clear() does not actually use its second argument, but when CONFIG_ARM64_CONTPTE is enabled it still gets updated. Replace the macro with an inline function to let the compiler see the argument getting passed down. Suggested-by: Catalin Marinas Signed-off-by: Arnd Bergmann Reviewed-by: Dev Jain Signed-off-by: Will Deacon --- arch/arm64/include/asm/pgtable.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 64d5f1d9cce9..5ab5fe3bef25 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -179,8 +179,6 @@ static inline pteval_t __phys_to_pte_val(phys_addr_t phys) __pte(__phys_to_pte_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)) #define pte_none(pte) (!pte_val(pte)) -#define __pte_clear(mm, addr, ptep) \ - __set_pte(ptep, __pte(0)) #define pte_page(pte) (pfn_to_page(pte_pfn(pte))) /* @@ -1320,6 +1318,13 @@ static inline bool pud_user_accessible_page(pud_t pud) /* * Atomic pte/pmd modifications. */ + +static inline void __pte_clear(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + __set_pte(ptep, __pte(0)); +} + static inline int __ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep)