diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 7109cbfcad4f..187d527ef73b 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -498,6 +498,7 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r) struct rdt_hw_mon_domain *hw_dom; struct rdt_domain_hdr *hdr; struct rdt_mon_domain *d; + struct cacheinfo *ci; int err; lockdep_assert_held(&domain_list_lock); @@ -525,12 +526,13 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r) d = &hw_dom->d_resctrl; d->hdr.id = id; d->hdr.type = RESCTRL_MON_DOMAIN; - d->ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE); - if (!d->ci) { + ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE); + if (!ci) { pr_warn_once("Can't find L3 cache for CPU:%d resource %s\n", cpu, r->name); mon_domain_free(hw_dom); return; } + d->ci_id = ci->id; cpumask_set_cpu(cpu, &d->hdr.cpu_mask); arch_mon_domain_online(r, d); diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c index 6ed2dfd4dbbd..d98e0d2de09f 100644 --- a/fs/resctrl/ctrlmondata.c +++ b/fs/resctrl/ctrlmondata.c @@ -594,9 +594,10 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg) struct rmid_read rr = {0}; struct rdt_mon_domain *d; struct rdtgroup *rdtgrp; + int domid, cpu, ret = 0; struct rdt_resource *r; + struct cacheinfo *ci; struct mon_data *md; - int domid, ret = 0; rdtgrp = rdtgroup_kn_lock_live(of->kn); if (!rdtgrp) { @@ -623,10 +624,14 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg) * one that matches this cache id. */ list_for_each_entry(d, &r->mon_domains, hdr.list) { - if (d->ci->id == domid) { - rr.ci = d->ci; + if (d->ci_id == domid) { + rr.ci_id = d->ci_id; + cpu = cpumask_any(&d->hdr.cpu_mask); + ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE); + if (!ci) + continue; mon_event_read(&rr, r, NULL, rdtgrp, - &d->ci->shared_cpu_map, evtid, false); + &ci->shared_cpu_map, evtid, false); goto checkresult; } } diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h index 9a8cf6f11151..0a1eedba2b03 100644 --- a/fs/resctrl/internal.h +++ b/fs/resctrl/internal.h @@ -98,7 +98,7 @@ struct mon_data { * domains in @r sharing L3 @ci.id * @evtid: Which monitor event to read. * @first: Initialize MBM counter when true. - * @ci: Cacheinfo for L3. Only set when @d is NULL. Used when summing domains. + * @ci_id: Cacheinfo id for L3. Only set when @d is NULL. Used when summing domains. * @err: Error encountered when reading counter. * @val: Returned value of event counter. If @rgrp is a parent resource group, * @val includes the sum of event counts from its child resource groups. @@ -112,7 +112,7 @@ struct rmid_read { struct rdt_mon_domain *d; enum resctrl_event_id evtid; bool first; - struct cacheinfo *ci; + unsigned int ci_id; int err; u64 val; void *arch_mon_ctx; diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c index bde2801289d3..f5637855c3ac 100644 --- a/fs/resctrl/monitor.c +++ b/fs/resctrl/monitor.c @@ -361,6 +361,7 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr) { int cpu = smp_processor_id(); struct rdt_mon_domain *d; + struct cacheinfo *ci; struct mbm_state *m; int err, ret; u64 tval = 0; @@ -388,7 +389,8 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr) } /* Summing domains that share a cache, must be on a CPU for that cache. */ - if (!cpumask_test_cpu(cpu, &rr->ci->shared_cpu_map)) + ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE); + if (!ci || ci->id != rr->ci_id) return -EINVAL; /* @@ -400,7 +402,7 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr) */ ret = -EINVAL; list_for_each_entry(d, &rr->r->mon_domains, hdr.list) { - if (d->ci->id != rr->ci->id) + if (d->ci_id != rr->ci_id) continue; err = resctrl_arch_rmid_read(rr->r, d, closid, rmid, rr->evtid, &tval, rr->arch_mon_ctx); diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c index 1beb124e25f6..77d08229d855 100644 --- a/fs/resctrl/rdtgroup.c +++ b/fs/resctrl/rdtgroup.c @@ -3036,7 +3036,7 @@ static void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, char name[32]; snc_mode = r->mon_scope == RESCTRL_L3_NODE; - sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci->id : d->hdr.id); + sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci_id : d->hdr.id); if (snc_mode) sprintf(subname, "mon_sub_%s_%02d", r->name, d->hdr.id); @@ -3061,7 +3061,7 @@ static int mon_add_all_files(struct kernfs_node *kn, struct rdt_mon_domain *d, return -EPERM; list_for_each_entry(mevt, &r->evt_list, list) { - domid = do_sum ? d->ci->id : d->hdr.id; + domid = do_sum ? d->ci_id : d->hdr.id; priv = mon_get_kn_priv(r->rid, domid, mevt, do_sum); if (WARN_ON_ONCE(!priv)) return -EINVAL; @@ -3089,7 +3089,7 @@ static int mkdir_mondata_subdir(struct kernfs_node *parent_kn, lockdep_assert_held(&rdtgroup_mutex); snc_mode = r->mon_scope == RESCTRL_L3_NODE; - sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci->id : d->hdr.id); + sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci_id : d->hdr.id); kn = kernfs_find_and_get(parent_kn, name); if (kn) { /* diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index 9ba771f2ddea..6fb4894b8cfd 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -159,7 +159,7 @@ struct rdt_ctrl_domain { /** * struct rdt_mon_domain - group of CPUs sharing a resctrl monitor resource * @hdr: common header for different domain types - * @ci: cache info for this domain + * @ci_id: cache info id for this domain * @rmid_busy_llc: bitmap of which limbo RMIDs are above threshold * @mbm_total: saved state for MBM total bandwidth * @mbm_local: saved state for MBM local bandwidth @@ -170,7 +170,7 @@ struct rdt_ctrl_domain { */ struct rdt_mon_domain { struct rdt_domain_hdr hdr; - struct cacheinfo *ci; + unsigned int ci_id; unsigned long *rmid_busy_llc; struct mbm_state *mbm_total; struct mbm_state *mbm_local; -- knotmirror 0.0.1 From 94a17f2dc90bc7eae36c0f478515d4bd1c23e877 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Tue, 10 Jun 2025 15:24:20 -0700 Subject: [PATCH 2/5] x86/mm: Disable INVLPGB when PTI is enabled PTI uses separate ASIDs (aka. PCIDs) for kernel and user address spaces. When the kernel needs to flush the user address space, it just sets a bit in a bitmap and then flushes the entire PCID on the next switch to userspace. This bitmap is a single 'unsigned long' which is plenty for all 6 dynamic ASIDs. But, unfortunately, the INVLPGB support brings along a bunch more user ASIDs, as many as ~2k more. The bitmap can't address that many. Fortunately, the bitmap is only needed for PTI and all the CPUs with INVLPGB are AMD CPUs that aren't vulnerable to Meltdown and don't need PTI. The only way someone can run into an issue in practice is by booting with pti=on on a newer AMD CPU. Disable INVLPGB if PTI is enabled. Avoid overrunning the small bitmap. Note: this will be fixed up properly by making the bitmap bigger. For now, just avoid the mostly theoretical bug. Fixes: 4afeb0ed1753 ("x86/mm: Enable broadcast TLB invalidation for multi-threaded processes") Signed-off-by: Dave Hansen Acked-by: Rik van Riel Cc:stable@vger.kernel.org Link: https://lore.kernel.org/all/20250610222420.E8CBF472%40davehans-spike.ostc.intel.com --- arch/x86/mm/pti.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c index 190299834011..c0c40b67524e 100644 --- a/arch/x86/mm/pti.c +++ b/arch/x86/mm/pti.c @@ -98,6 +98,11 @@ void __init pti_check_boottime_disable(void) return; setup_force_cpu_cap(X86_FEATURE_PTI); + + if (cpu_feature_enabled(X86_FEATURE_INVLPGB)) { + pr_debug("PTI enabled, disabling INVLPGB\n"); + setup_clear_cpu_cap(X86_FEATURE_INVLPGB); + } } static int __init pti_parse_cmdline(char *arg) -- knotmirror 0.0.1 From 3c902383f2da91cba3821b73aa6edd49f4db6023 Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Mon, 16 Jun 2025 12:04:32 +0200 Subject: [PATCH 3/5] x86/its: Fix an ifdef typo in its_alloc() Commit a82b26451de1 ("x86/its: explicitly manage permissions for ITS pages") reworks its_alloc() and introduces a typo in an ifdef conditional, referring to CONFIG_MODULE instead of CONFIG_MODULES. Fix this typo in its_alloc(). Fixes: a82b26451de1 ("x86/its: explicitly manage permissions for ITS pages") Signed-off-by: Lukas Bulwahn Signed-off-by: Dave Hansen Link: https://lore.kernel.org/all/20250616100432.22941-1-lukas.bulwahn%40redhat.com --- arch/x86/kernel/alternative.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 6455f7f751b3..9ae80fa904a2 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -228,7 +228,7 @@ static void *its_alloc(void) struct its_array *pages = &its_pages; void *page; -#ifdef CONFIG_MODULE +#ifdef CONFIG_MODULES if (its_mod) pages = &its_mod->arch.its_pages; #endif -- knotmirror 0.0.1 From cb6075bc62dc6a9cd7ab3572758685fdf78e3e20 Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Fri, 6 Jun 2025 13:10:34 -0400 Subject: [PATCH 4/5] x86/mm: Fix early boot use of INVPLGB The INVLPGB instruction has limits on how many pages it can invalidate at once. That limit is enumerated in CPUID, read by the kernel, and stored in 'invpgb_count_max'. Ranged invalidation, like invlpgb_kernel_range_flush() break up their invalidations so that they do not exceed the limit. However, early boot code currently attempts to do ranged invalidation before populating 'invlpgb_count_max'. There is a for loop which is basically: for (...; addr < end; addr += invlpgb_count_max*PAGE_SIZE) If invlpgb_kernel_range_flush is called before the kernel has read the value of invlpgb_count_max from the hardware, the normally bounded loop can become an infinite loop if invlpgb_count_max is initialized to zero. Fix that issue by initializing invlpgb_count_max to 1. This way INVPLGB at early boot time will be a little bit slower than normal (with initialized invplgb_count_max), and not an instant hang at bootup time. Fixes: b7aa05cbdc52 ("x86/mm: Add INVLPGB support code") Signed-off-by: Rik van Riel Signed-off-by: Dave Hansen Link: https://lore.kernel.org/all/20250606171112.4013261-3-riel%40surriel.com --- arch/x86/kernel/cpu/amd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 93da466dfe2c..b2ad8d13211a 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -31,7 +31,7 @@ #include "cpu.h" -u16 invlpgb_count_max __ro_after_init; +u16 invlpgb_count_max __ro_after_init = 1; static inline int rdmsrq_amd_safe(unsigned msr, u64 *p) { -- knotmirror 0.0.1 From 2aebf5ee43bf0ed225a09a30cf515d9f2813b759 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Wed, 18 Jun 2025 09:05:23 +0900 Subject: [PATCH 5/5] x86/alternatives: Fix int3 handling failure from broken text_poke array Since smp_text_poke_single() does not expect there is another text_poke request is queued, it can make text_poke_array not sorted or cause a buffer overflow on the text_poke_array.vec[]. This will cause an Oops in int3 because of bsearch failing; CPU 0 CPU 1 CPU 2 ----- ----- ----- smp_text_poke_batch_add() smp_text_poke_single() <<-- Adds out of order [Fails o find address in text_poke_array ] OOPS! Or unhandled page fault because of a buffer overflow; CPU 0 CPU 1 ----- ----- smp_text_poke_batch_add() <<+ ... | smp_text_poke_batch_add() <<-- Adds TEXT_POKE_ARRAY_MAX times. smp_text_poke_single() { __smp_text_poke_batch_add() <<-- Adds entry at TEXT_POKE_ARRAY_MAX + 1 smp_text_poke_batch_finish() [Unhandled page fault because text_poke_array.nr_entries is overwritten] BUG! } Use smp_text_poke_batch_add() instead of __smp_text_poke_batch_add() so that it correctly flush the queue if needed. Closes: https://lore.kernel.org/all/CA+G9fYsLu0roY3DV=tKyqP7FEKbOEETRvTDhnpPxJGbA=Cg+4w@mail.gmail.com/ Fixes: c8976ade0c1b ("x86/alternatives: Simplify smp_text_poke_single() by using tp_vec and existing APIs") Reported-by: Linux Kernel Functional Testing Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Steven Rostedt (Google) Tested-by: Linux Kernel Functional Testing Link: https://lkml.kernel.org/r/\ 175020512308.3582717.13631440385506146631.stgit@mhiramat.tok.corp.google.com --- arch/x86/kernel/alternative.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 9ae80fa904a2..ea1d984166cd 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -3138,6 +3138,6 @@ void __ref smp_text_poke_batch_add(void *addr, const void *opcode, size_t len, c */ void __ref smp_text_poke_single(void *addr, const void *opcode, size_t len, const void *emulate) { - __smp_text_poke_batch_add(addr, opcode, len, emulate); + smp_text_poke_batch_add(addr, opcode, len, emulate); smp_text_poke_batch_finish(); }