From fe06a0c09b47ea58ba2b01c8941af16bd45c02df Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Sun, 23 Jan 2022 10:38:37 -0800 Subject: KVM: x86: replace bitmap_weight with bitmap_empty where appropriate In some places kvm/hyperv.c code calls bitmap_weight() to check if any bit of a given bitmap is set. It's better to use bitmap_empty() in that case because bitmap_empty() stops traversing the bitmap as soon as it finds first set bit, while bitmap_weight() counts all bits unconditionally. Signed-off-by: Yury Norov Reviewed-by: Vitaly Kuznetsov Reviewed-by: Sean Christopherson Reviewed-by: Andy Shevchenko --- arch/x86/kvm/hyperv.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 123b677111c5..c964923a7684 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -90,7 +90,7 @@ static void synic_update_vector(struct kvm_vcpu_hv_synic *synic, { struct kvm_vcpu *vcpu = hv_synic_to_vcpu(synic); struct kvm_hv *hv = to_kvm_hv(vcpu->kvm); - int auto_eoi_old, auto_eoi_new; + bool auto_eoi_old, auto_eoi_new; if (vector < HV_SYNIC_FIRST_VALID_VECTOR) return; @@ -100,16 +100,16 @@ static void synic_update_vector(struct kvm_vcpu_hv_synic *synic, else __clear_bit(vector, synic->vec_bitmap); - auto_eoi_old = bitmap_weight(synic->auto_eoi_bitmap, 256); + auto_eoi_old = !bitmap_empty(synic->auto_eoi_bitmap, 256); if (synic_has_vector_auto_eoi(synic, vector)) __set_bit(vector, synic->auto_eoi_bitmap); else __clear_bit(vector, synic->auto_eoi_bitmap); - auto_eoi_new = bitmap_weight(synic->auto_eoi_bitmap, 256); + auto_eoi_new = !bitmap_empty(synic->auto_eoi_bitmap, 256); - if (!!auto_eoi_old == !!auto_eoi_new) + if (auto_eoi_old == auto_eoi_new) return; if (!enable_apicv) -- cgit v1.2.3 From 4aec74bccf5d047347bdfef3638e3031dd75c0a0 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Sun, 23 Jan 2022 10:38:46 -0800 Subject: arch/x86: replace cpumask_weight with cpumask_empty where appropriate In some cases, arch/x86 code calls cpumask_weight() to check if any bit of a given cpumask is set. We can do it more efficiently with cpumask_empty() because cpumask_empty() stops traversing the cpumask as soon as it finds first set bit, while cpumask_weight() counts all bits unconditionally. Signed-off-by: Yury Norov Reviewed-by: Steve Wahl --- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 14 +++++++------- arch/x86/mm/mmio-mod.c | 2 +- arch/x86/platform/uv/uv_nmi.c | 2 +- 3 files changed, 9 insertions(+), 9 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 83f901e2c2df..f276aff521e8 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -341,14 +341,14 @@ static int cpus_mon_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask, /* Check whether cpus belong to parent ctrl group */ cpumask_andnot(tmpmask, newmask, &prgrp->cpu_mask); - if (cpumask_weight(tmpmask)) { + if (!cpumask_empty(tmpmask)) { rdt_last_cmd_puts("Can only add CPUs to mongroup that belong to parent\n"); return -EINVAL; } /* Check whether cpus are dropped from this group */ cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask); - if (cpumask_weight(tmpmask)) { + if (!cpumask_empty(tmpmask)) { /* Give any dropped cpus to parent rdtgroup */ cpumask_or(&prgrp->cpu_mask, &prgrp->cpu_mask, tmpmask); update_closid_rmid(tmpmask, prgrp); @@ -359,7 +359,7 @@ static int cpus_mon_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask, * and update per-cpu rmid */ cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask); - if (cpumask_weight(tmpmask)) { + if (!cpumask_empty(tmpmask)) { head = &prgrp->mon.crdtgrp_list; list_for_each_entry(crgrp, head, mon.crdtgrp_list) { if (crgrp == rdtgrp) @@ -394,7 +394,7 @@ static int cpus_ctrl_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask, /* Check whether cpus are dropped from this group */ cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask); - if (cpumask_weight(tmpmask)) { + if (!cpumask_empty(tmpmask)) { /* Can't drop from default group */ if (rdtgrp == &rdtgroup_default) { rdt_last_cmd_puts("Can't drop CPUs from default group\n"); @@ -413,12 +413,12 @@ static int cpus_ctrl_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask, * and update per-cpu closid/rmid. */ cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask); - if (cpumask_weight(tmpmask)) { + if (!cpumask_empty(tmpmask)) { list_for_each_entry(r, &rdt_all_groups, rdtgroup_list) { if (r == rdtgrp) continue; cpumask_and(tmpmask1, &r->cpu_mask, tmpmask); - if (cpumask_weight(tmpmask1)) + if (!cpumask_empty(tmpmask1)) cpumask_rdtgrp_clear(r, tmpmask1); } update_closid_rmid(tmpmask, rdtgrp); @@ -488,7 +488,7 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of, /* check that user didn't specify any offline cpus */ cpumask_andnot(tmpmask, newmask, cpu_online_mask); - if (cpumask_weight(tmpmask)) { + if (!cpumask_empty(tmpmask)) { ret = -EINVAL; rdt_last_cmd_puts("Can only assign online CPUs\n"); goto unlock; diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c index 933a2ebad471..c3317f0650d8 100644 --- a/arch/x86/mm/mmio-mod.c +++ b/arch/x86/mm/mmio-mod.c @@ -400,7 +400,7 @@ static void leave_uniprocessor(void) int cpu; int err; - if (!cpumask_available(downed_cpus) || cpumask_weight(downed_cpus) == 0) + if (!cpumask_available(downed_cpus) || cpumask_empty(downed_cpus)) return; pr_notice("Re-enabling CPUs...\n"); for_each_cpu(cpu, downed_cpus) { diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c index 1e9ff28bc2e0..ea277fc08357 100644 --- a/arch/x86/platform/uv/uv_nmi.c +++ b/arch/x86/platform/uv/uv_nmi.c @@ -985,7 +985,7 @@ static int uv_handle_nmi(unsigned int reason, struct pt_regs *regs) /* Clear global flags */ if (master) { - if (cpumask_weight(uv_nmi_cpu_mask)) + if (!cpumask_empty(uv_nmi_cpu_mask)) uv_nmi_cleanup_mask(); atomic_set(&uv_nmi_cpus_in_nmi, -1); atomic_set(&uv_nmi_cpu, -1); -- cgit v1.2.3 From dcf23cca930d1a60f7cd6b3a245a5081d77b8081 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Sun, 23 Jan 2022 10:38:57 -0800 Subject: arch/x86: replace nodes_weight with nodes_empty where appropriate mm code calls nodes_weight() to check if any bit of a given nodemask is set. We can do it more efficiently with nodes_empty() because nodes_empty() stops traversing the nodemask as soon as it finds first set bit, while nodes_weight() counts all bits unconditionally. Signed-off-by: Yury Norov --- arch/x86/mm/amdtopology.c | 2 +- arch/x86/mm/numa_emulation.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/mm/amdtopology.c b/arch/x86/mm/amdtopology.c index 058b2f36b3a6..b3ca7d23e4b0 100644 --- a/arch/x86/mm/amdtopology.c +++ b/arch/x86/mm/amdtopology.c @@ -154,7 +154,7 @@ int __init amd_numa_init(void) node_set(nodeid, numa_nodes_parsed); } - if (!nodes_weight(numa_nodes_parsed)) + if (nodes_empty(numa_nodes_parsed)) return -ENOENT; /* diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c index 1a02b791d273..9a9305367fdd 100644 --- a/arch/x86/mm/numa_emulation.c +++ b/arch/x86/mm/numa_emulation.c @@ -123,7 +123,7 @@ static int __init split_nodes_interleave(struct numa_meminfo *ei, * Continue to fill physical nodes with fake nodes until there is no * memory left on any of them. */ - while (nodes_weight(physnode_mask)) { + while (!nodes_empty(physnode_mask)) { for_each_node_mask(i, physnode_mask) { u64 dma32_end = PFN_PHYS(MAX_DMA32_PFN); u64 start, limit, end; @@ -270,7 +270,7 @@ static int __init split_nodes_size_interleave_uniform(struct numa_meminfo *ei, * Fill physical nodes with fake nodes of size until there is no memory * left on any of them. */ - while (nodes_weight(physnode_mask)) { + while (!nodes_empty(physnode_mask)) { for_each_node_mask(i, physnode_mask) { u64 dma32_end = PFN_PHYS(MAX_DMA32_PFN); u64 start, limit, end; -- cgit v1.2.3 From a7ef9b455c7ca8f07a5b4bd967a3c39c7434d43f Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Thu, 19 May 2022 10:15:04 -0700 Subject: KVM: x86: hyper-v: fix type of valid_bank_mask In kvm_hv_flush_tlb(), valid_bank_mask is declared as unsigned long, but is used as u64, which is wrong for i386, and has been spotted by LKP after applying "KVM: x86: hyper-v: replace bitmap_weight() with hweight64()" https://lore.kernel.org/lkml/20220510154750.212913-12-yury.norov@gmail.com/ But it's wrong even without that patch because now bitmap_weight() dereferences a word after valid_bank_mask on i386. >> include/asm-generic/bitops/const_hweight.h:21:76: warning: right shift count >= width of type +[-Wshift-count-overflow] 21 | #define __const_hweight64(w) (__const_hweight32(w) + __const_hweight32((w) >> 32)) | ^~ include/asm-generic/bitops/const_hweight.h:10:16: note: in definition of macro '__const_hweight8' 10 | ((!!((w) & (1ULL << 0))) + \ | ^ include/asm-generic/bitops/const_hweight.h:20:31: note: in expansion of macro '__const_hweight16' 20 | #define __const_hweight32(w) (__const_hweight16(w) + __const_hweight16((w) >> 16)) | ^~~~~~~~~~~~~~~~~ include/asm-generic/bitops/const_hweight.h:21:54: note: in expansion of macro '__const_hweight32' 21 | #define __const_hweight64(w) (__const_hweight32(w) + __const_hweight32((w) >> 32)) | ^~~~~~~~~~~~~~~~~ include/asm-generic/bitops/const_hweight.h:29:49: note: in expansion of macro '__const_hweight64' 29 | #define hweight64(w) (__builtin_constant_p(w) ? __const_hweight64(w) : __arch_hweight64(w)) | ^~~~~~~~~~~~~~~~~ arch/x86/kvm/hyperv.c:1983:36: note: in expansion of macro 'hweight64' 1983 | if (hc->var_cnt != hweight64(valid_bank_mask)) | ^~~~~~~~~ CC: Borislav Petkov CC: Dave Hansen CC: H. Peter Anvin CC: Ingo Molnar CC: Jim Mattson CC: Joerg Roedel CC: Paolo Bonzini CC: Sean Christopherson CC: Thomas Gleixner CC: Vitaly Kuznetsov CC: Wanpeng Li CC: kvm@vger.kernel.org CC: linux-kernel@vger.kernel.org CC: x86@kernel.org Reported-by: kernel test robot Signed-off-by: Yury Norov Message-Id: <20220519171504.1238724-1-yury.norov@gmail.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/hyperv.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index c964923a7684..18325e0ae7bc 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1938,7 +1938,7 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) struct hv_send_ipi_ex send_ipi_ex; struct hv_send_ipi send_ipi; DECLARE_BITMAP(vcpu_mask, KVM_MAX_VCPUS); - unsigned long valid_bank_mask; + u64 valid_bank_mask; u64 sparse_banks[KVM_HV_MAX_SPARSE_VCPU_SET_BITS]; u32 vector; bool all_cpus; @@ -1980,7 +1980,7 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) valid_bank_mask = send_ipi_ex.vp_set.valid_bank_mask; all_cpus = send_ipi_ex.vp_set.format == HV_GENERIC_SET_ALL; - if (hc->var_cnt != bitmap_weight(&valid_bank_mask, 64)) + if (hc->var_cnt != bitmap_weight((unsigned long *)&valid_bank_mask, 64)) return HV_STATUS_INVALID_HYPERCALL_INPUT; if (all_cpus) -- cgit v1.2.3 From d603fd8dd35f6028bb09cd2e9ec6557c4bc0dd95 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Mon, 9 May 2022 18:54:23 -0700 Subject: KVM: x86: hyper-v: replace bitmap_weight() with hweight64() kvm_hv_flush_tlb() applies bitmap API to a u64 variable valid_bank_mask. Since valid_bank_mask has a fixed size, we can use hweight64() and avoid excessive bloating. CC: Borislav Petkov CC: Dave Hansen CC: H. Peter Anvin CC: Ingo Molnar CC: Jim Mattson CC: Joerg Roedel CC: Paolo Bonzini CC: Sean Christopherson CC: Thomas Gleixner CC: Vitaly Kuznetsov CC: Wanpeng Li CC: kvm@vger.kernel.org CC: linux-kernel@vger.kernel.org CC: x86@kernel.org Acked-by: Vitaly Kuznetsov Signed-off-by: Yury Norov --- arch/x86/kvm/hyperv.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 18325e0ae7bc..c8ca95d4e4e9 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1879,7 +1879,7 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) all_cpus = flush_ex.hv_vp_set.format != HV_GENERIC_SET_SPARSE_4K; - if (hc->var_cnt != bitmap_weight((unsigned long *)&valid_bank_mask, 64)) + if (hc->var_cnt != hweight64(valid_bank_mask)) return HV_STATUS_INVALID_HYPERCALL_INPUT; if (all_cpus) @@ -1980,7 +1980,7 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) valid_bank_mask = send_ipi_ex.vp_set.valid_bank_mask; all_cpus = send_ipi_ex.vp_set.format == HV_GENERIC_SET_ALL; - if (hc->var_cnt != bitmap_weight((unsigned long *)&valid_bank_mask, 64)) + if (hc->var_cnt != hweight64(valid_bank_mask)) return HV_STATUS_INVALID_HYPERCALL_INPUT; if (all_cpus) -- cgit v1.2.3