From 0d6526f82c3cdefcca47f73f5fc08dc6f335eac6 Mon Sep 17 00:00:00 2001 From: Tim Chen Date: Mon, 21 Sep 2026 17:37:22 -0700 Subject: sched/cache: Keep nr_pref_llc_running in the runnable domain, to fix LLC mis-scheduling bug alb_break_llc() decides whether to break LLC preference during active load balance. It does so by testing that every runnable fair task on the source rq prefers its LLC: env->src_rq->nr_pref_llc_running == env->src_rq->cfs.h_nr_runnable But the two counters cover different sets. nr_pref_llc_running is updated in account_llc_enqueue()/account_llc_dequeue(), next to cfs_rq->nr_queued, so it follows queued tasks. h_nr_runnable is updated in set_delayed()/ clear_delayed() and drops delay-dequeued tasks. So under DELAY_DEQUEUE, a preferring task that goes to sleep stays counted in nr_pref_llc_running while h_nr_runnable falls. The equality then breaks, alb_break_llc() returns false, and active balance is free to pull a task off its preferred LLC. Active balance only moves runnable tasks, and this is the only LLC check it consults: once the stopper runs, LBF_ACTIVE_LB skips the per-task test in can_migrate_task(). The runnable set is the one we want. Fix it on the counter side. A task should be counted in nr_pref_llc_running exactly while it is both queued on its preferred LLC (pref_llc_queued) and runnable (!sched_delayed). Define that membership once in task_pref_llc_runnable(), and adjust the counter only through pref_llc_running_inc()/pref_llc_running_dec() from the four sites that change either input: account_llc_enqueue(), account_llc_dequeue(), set_delayed() and clear_delayed(). Gating every update on the same predicate keeps the delay, wake and dequeue paths from double-counting or underflowing; see the comments at those sites for the ordering. nr_llc_running and sd->llc_counts are not touched and stay on queued semantics. Fixes: 714059f79ff0 ("sched/cache: Handle moving single tasks to/from their preferred LLC") Closes: https://lore.kernel.org/lkml/20260827135000.735138-1-zhanxusheng@xiaomi.com/ Reported-by: Zhan Xusheng Suggested-by: Chen Yu Signed-off-by: Tim Chen Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Reviewed-by: Kayra Cizmeci Cc: # v7.2.x Link: https://patch.msgid.link/06af61afedac32e6477f57feb4d658f6c411c3af.1790035273.git.tim.c.chen@linux.intel.com --- drivers/crypto/ccp/sev-dev.h | 89 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 89 insertions(+) create mode 100644 drivers/crypto/ccp/sev-dev.h (limited to 'drivers/crypto/ccp/sev-dev.h') diff --git a/drivers/crypto/ccp/sev-dev.h b/drivers/crypto/ccp/sev-dev.h new file mode 100644 index 000000000..d5e596606 --- /dev/null +++ b/drivers/crypto/ccp/sev-dev.h @@ -0,0 +1,89 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * AMD Platform Security Processor (PSP) interface driver + * + * Copyright (C) 2017-2019 Advanced Micro Devices, Inc. + * + * Author: Brijesh Singh + */ + +#ifndef __SEV_DEV_H__ +#define __SEV_DEV_H__ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define SEV_CMDRESP_CMD GENMASK(26, 16) +#define SEV_CMD_COMPLETE BIT(1) +#define SEV_CMDRESP_IOC BIT(0) + +struct sev_misc_dev { + struct kref refcount; + struct miscdevice misc; +}; + +struct sev_tio_status; + +struct sev_device { + struct device *dev; + struct psp_device *psp; + + void __iomem *io_regs; + + struct sev_vdata *vdata; + + unsigned int int_rcvd; + wait_queue_head_t int_queue; + struct sev_misc_dev *misc; + + u8 api_major; + u8 api_minor; + u8 build; + + void *cmd_buf; + void *cmd_buf_backup; + bool cmd_buf_active; + bool cmd_buf_backup_active; + + bool snp_initialized; + + struct kobject *sev_kobj; + struct kobject *verify_mit; + + struct sev_user_data_status sev_plat_status; + + struct sev_user_data_snp_status snp_plat_status; + struct snp_feature_info snp_feat_info_0; + + struct tsm_dev *tsmdev; + struct sev_tio_status *tio_status; +}; + +int sev_dev_init(struct psp_device *psp); +void sev_dev_destroy(struct psp_device *psp); + +int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret); + +void sev_pci_init(void); +void sev_pci_exit(void); + +struct page *snp_alloc_hv_fixed_pages(unsigned int num_2mb_pages); +void snp_free_hv_fixed_pages(struct page *page); + +void sev_tsm_init_locked(struct sev_device *sev, void *tio_status_page); +void sev_tsm_uninit(struct sev_device *sev); +int sev_tio_cmd_buffer_len(int cmd); + +#endif /* __SEV_DEV_H */ -- cgit v1.3.1