Skip to contentSkip to conversation

KVM: Rework how halt-polling stats and per-VM debugfs use memory

RFC PATCH Superseded Peng Hao 2 participants 5 messages Nov 16

Subsystems (5)
Documentation KVM PowerPC Tracing +1 more subsystems

v1 of 2 Superseded Latest is v2 →

lore
Share & tools
lore

Peng Hao

author
#0 lore raw

cover KVM: Rework how halt-polling stats and per-VM debugfs use memory

This series replaces the halt-polling histogram Kconfig patch, as a first step towards a general plan for KVM stats.

Take a VM with 8 vCPUs on x86. Each vCPU has 1104 bytes of stats, 768 of which are the three halt-polling histograms, i.e. 6KiB for the VM. The VM also gets ~95 debugfs entries (one file per stat, plus a directory and a few files per vCPU), each costing a dentry and an inode, i.e. ~70KiB, all duplicating the binary stats.

The plan:

1. Counters stay embedded in the stats structs; they're cheap and monitoring wants them always on.

2. Arrays and histograms move to a separately allocated block, controlled by kvm.extended_stats (default on). The binary stats ABI doesn't change; the values read as zero if the block isn't allocated. (patch 3)

3. Debug-only data goes to tracepoints and is aggregated with BPF. Adding the halt-polling time to kvm_vcpu_wakeup is enough to rebuild the three histograms. (patch 1)

In addition, kvm.per_vm_debugfs (default on) allows skipping the per-VM debugfs directories. (patch 2)

With patch 3, struct vcpu_vmx shrinks from 8384 to 7616 bytes and struct vcpu_svm from 6728 to 5968 bytes.

Peng Hao (3):
KVM: Add the halt-polling time to the kvm_vcpu_wakeup tracepoint
KVM: Add a module param to disable the per-VM debugfs directories
KVM: Move the halt-polling histograms out of struct kvm_vcpu_stat

 .../admin-guide/kernel-parameters.txt         | 13 ++++
 arch/powerpc/kvm/book3s_hv.c                  | 11 ++-
 include/linux/kvm_host.h                      | 24 +++++-
 include/linux/kvm_types.h                     | 10 ++-
 include/trace/events/kvm.h                    | 16 ++--
 virt/kvm/binary_stats.c                       | 29 +++++++-
 virt/kvm/kvm_main.c                           | 73 +++++++++++++++----
 7 files changed, 144 insertions(+), 32 deletions(-)
Signature · 1 line
2.43.7
author
#1 lore raw

RFC PATCH 1/3 KVM: Add the halt-polling time to the kvm_vcpu_wakeup tracepoint

kvm_vcpu_wakeup only reports the total halt time, which includes both the time spent halt-polling and the time spent blocking. Report the halt-polling time as well, so that the split between polling and waiting can be derived from the tracepoint, e.g. to build histograms equivalent to the halt_poll_success_hist, halt_poll_fail_hist and halt_wait_hist stats with BPF.

---
 include/trace/events/kvm.h | 16 +++++++++-------
 virt/kvm/kvm_main.c        |  3 ++-
 2 files changed, 11 insertions(+), 8 deletions(-)
include/trace/events/kvm.h +9 -7
index 07013f88e655..d03e3954ca37 100644
@@ -47,24 +47,26 @@ TRACE_EVENT(kvm_userspace_exit,
 );
 
 TRACE_EVENT(kvm_vcpu_wakeup,
-	    TP_PROTO(__u64 ns, bool waited, bool valid),
-	    TP_ARGS(ns, waited, valid),
+	    TP_PROTO(__u64 ns, __u64 poll_ns, bool waited, bool valid),
+	    TP_ARGS(ns, poll_ns, waited, valid),
 
 	TP_STRUCT__entry(
-		__field(	__u64,		ns		)
-		__field(	bool,		waited		)
-		__field(	bool,		valid		)
+		__field(__u64, ns)
+		__field(__u64, poll_ns)
+		__field(bool, waited)
+		__field(bool, valid)
 	),
 
 	TP_fast_assign(
 		__entry->ns		= ns;
+		__entry->poll_ns	= poll_ns;
 		__entry->waited		= waited;
 		__entry->valid		= valid;
 	),
 
-	TP_printk("%s time %lld ns, polling %s",
+	TP_printk("%s time %lld ns (poll %lld ns), polling %s",
 		  __entry->waited ? "wait" : "poll",
-		  __entry->ns,
+		  __entry->ns, __entry->poll_ns,
 		  __entry->valid ? "valid" : "invalid")
 );
 
virt/kvm/kvm_main.c +2 -1
index cf4cb586f140..fff19e9239d2 100644
@@ -3888,7 +3888,8 @@ void kvm_vcpu_halt(struct kvm_vcpu *vcpu)
 		}
 	}
 
-	trace_kvm_vcpu_wakeup(halt_ns, waited, vcpu_valid_wakeup(vcpu));
+	trace_kvm_vcpu_wakeup(halt_ns, ktime_to_ns(ktime_sub(poll_end, start)),
+			      waited, vcpu_valid_wakeup(vcpu));
 }
 EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_vcpu_halt);
 
Signature · 1 line
2.43.7
author
#2 lore raw

RFC PATCH 2/3 KVM: Add a module param to disable the per-VM debugfs directories

In reply to Peng Hao

Every VM gets a debugfs directory with one file per stat, plus a directory and a few files per vCPU, i.e. ~95 entries for an 8-vCPU VM on x86. Each entry costs a dentry and an inode, and the stats files duplicate the binary stats.

Add kvm.per_vm_debugfs (default on) so that these directories can be skipped.

---
 Documentation/admin-guide/kernel-parameters.txt |  7 +++++++
 virt/kvm/kvm_main.c                             | 12 ++++++++++--
 2 files changed, 17 insertions(+), 2 deletions(-)
Documentation/admin-guide/kernel-parameters.txt +7 -0
index 42ff19defe16..c1e0f6bf4c24 100644
@@ -3211,6 +3211,13 @@ Kernel parameters
 			If the value is 0 (the default), KVM will pick a period based
 			on the ratio, such that a page is zapped after 1 hour on average.
 
+	kvm.per_vm_debugfs=
+			[KVM] Create a debugfs directory for each VM and vCPU,
+			containing per-VM stats and architecture specific
+			debug files.  Global stats in debugfs and binary stats
+			are not affected.
+			Default is Y (on).
+
 	kvm-{amd,intel}.enable_mediated_pmu=[KVM,AMD,INTEL]
 			If enabled, KVM will provide a mediated virtual PMU,
 			instead of the default perf-based virtual PMU (if
virt/kvm/kvm_main.c +10 -2
index fff19e9239d2..54a2924f9b92 100644
@@ -104,6 +104,14 @@ EXPORT_SYMBOL_FOR_KVM_INTERNAL(halt_poll_ns_shrink);
 static bool __ro_after_init allow_unsafe_mappings;
 module_param(allow_unsafe_mappings, bool, 0444);
 
+/*
+ * Create a debugfs directory for every VM and vCPU.  The per-VM stats files
+ * duplicate the binary stats, and each file costs a dentry and an inode, which
+ * adds up when running many VMs.
+ */
+static bool __ro_after_init per_vm_debugfs = true;
+module_param(per_vm_debugfs, bool, 0444);
+
 #ifdef CONFIG_KVM_PRIVATE_MEMATTR_VM
 bool __ro_after_init gmem_in_place_conversion = false;
 module_param(gmem_in_place_conversion, bool, 0444);
@@ -1024,7 +1032,7 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, const char *fdname)
 	int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc +
 				      kvm_vcpu_stats_header.num_desc;
 
-	if (!debugfs_initialized())
+	if (!debugfs_initialized() || !per_vm_debugfs)
 		return 0;
 
 	snprintf(dir_name, sizeof(dir_name), "%d-%s", task_pid_nr(current), fdname);
@@ -4235,7 +4243,7 @@ static void kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
 	struct dentry *debugfs_dentry;
 	char dir_name[ITOA_MAX_LEN * 2];
 
-	if (!debugfs_initialized())
+	if (!debugfs_initialized() || !per_vm_debugfs)
 		return;
 
 	snprintf(dir_name, sizeof(dir_name), "vcpu%d", vcpu->vcpu_id);
Signature · 1 line
2.43.7
#3 lore raw

Re: [RFC PATCH 2/3] KVM: Add a module param to disable the per-VM debugfs directories

Thank you for your contribution! Sashiko AI review found 1 potential issue to consider: - [Medium] KVM: debugfs leak and UAF in kvm_nested_s2_ptdump_create_debugfs() --

Thank you for your contribution! Sashiko AI review found 1 potential issue to consider:
- [Medium] KVM: debugfs leak and UAF in kvm_nested_s2_ptdump_create_debugfs()
--

commit 6b8cad730d46b448b05e32a4f22f6d9fe9cf399b
Author: Peng Hao <[email protected]>

KVM: Add a module param to disable the per-VM debugfs directories

This commit adds the kvm.per_vm_debugfs module parameter to allow skipping the creation of per-VM and per-vCPU debugfs directories and files.

Quoted 4 lines
virt/kvm/kvm_main.c +0 -0
index fff19e9239d2b..54a2924f9b928 100644

[ ... ]

virt/kvm/kvm_main.c static int kvm_create_vm_debugfs(struct kvm *kvm, const char *fdname) · line 1036

Quoted 7 lines
virt/kvm/kvm_main.c +1 -1
@@ -1024,7 +1032,7 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, const char *fdname)
 	int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc +
 				      kvm_vcpu_stats_header.num_desc;
 
-	if (!debugfs_initialized())
+	if (!debugfs_initialized() || !per_vm_debugfs)
 		return 0;

[Severity: Medium]
On arm64 with CONFIG_PTDUMP_STAGE2_DEBUGFS=y, does returning early here when per_vm_debugfs is false cause kvm_nested_s2_ptdump_create_debugfs() to leak nested_mmu* files in the root of debugfs and leave dangling pointers?

kvm_create_vm() initializes kvm->debugfs_dentry to ERR_PTR(-ENOENT), so callers passing it as a parent to debugfs_create_file() or debugfs_create_dir() fail as expected. However, kvm->arch.debugfs_nv_dentry is zero-allocated (NULL) and is only populated when kvm_create_vm_debugfs() reaches kvm_arch_create_vm_debugfs() -> kvm_s2_ptdump_create_debugfs().

When per_vm_debugfs is false while debugfs_initialized() is true, kvm->arch.debugfs_nv_dentry remains NULL. Initializing a nested vCPU in kvm_vcpu_init_nested() then calls kvm_nested_s2_ptdump_create_debugfs(), passing NULL as the parent dentry:

arch/arm64/kvm/ptdump.c:kvm_nested_s2_ptdump_create_debugfs() {
...

	debugfs_create_file(file_name, 0400,
			    mmu->arch->debugfs_nv_dentry, mmu,
			    &kvm_ptdump_guest_fops);
}

debugfs interprets a NULL parent as the root of the debugfs mount and creates /sys/kernel/debug/nested_mmu* with inode->i_private pointing to mmu. When the VM is destroyed, these root files are never removed while kvm_destroy_nested() frees the nested_mmus arrays and kvm_destroy_vm() frees struct kvm, so opening /sys/kernel/debug/nested_mmu* afterwards triggers a use-after-free in kvm_ptdump_guest_open().

Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=2
author
#4 lore raw

RFC PATCH 3/3 KVM: Move the halt-polling histograms out of struct kvm_vcpu_stat

In reply to Peng Hao

The halt_poll_success_hist, halt_poll_fail_hist and halt_wait_hist histograms take 768 bytes in every vCPU, out of 1104 bytes of stats on x86. Move them into a separately allocated struct kvm_vcpu_stat_ext, and add kvm.extended_stats (default on) so that it can be skipped.

The descriptors don't change and the extended stats are laid out after struct kvm_vcpu_stat in the stats data block, so the binary stats ABI is unchanged; if the block isn't allocated the histograms read as zero.

This shrinks struct kvm_vcpu from 5776 to 5016 bytes, struct vcpu_vmx from 8384 to 7616 bytes and struct vcpu_svm from 6728 to 5968 bytes.

---
 .../admin-guide/kernel-parameters.txt         |  6 ++
 arch/powerpc/kvm/book3s_hv.c                  | 11 ++--
 include/linux/kvm_host.h                      | 24 ++++++--
 include/linux/kvm_types.h                     | 10 +++-
 virt/kvm/binary_stats.c                       | 29 +++++++++-
 virt/kvm/kvm_main.c                           | 58 +++++++++++++++----
 6 files changed, 116 insertions(+), 22 deletions(-)
Documentation/admin-guide/kernel-parameters.txt +6 -0
index c1e0f6bf4c24..181f9a920b26 100644
@@ -3159,6 +3159,12 @@ Kernel parameters
 	kvm.enable_vmware_backdoor=[KVM] Support VMware backdoor PV interface.
 				   Default is false (don't support).
 
+	kvm.extended_stats=
+			[KVM] Allocate the extended per-vCPU stats, e.g. the
+			halt-polling histograms.  If disabled, the extended
+			stats are still reported but always read as zero.
+			Default is Y (on).
+
 	kvm.gmem_in_place_conversion=
 			[KVM] Controls whether KVM enables in-place conversion
 			support for guest_memfd and tracks the private/shared
arch/powerpc/kvm/book3s_hv.c +5 -6
index f2d9f16c2e44..fc9fba16ce48 100644
@@ -4684,16 +4684,15 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 	if (do_sleep) {
 		vc->runner->stat.generic.halt_wait_ns +=
 			ktime_to_ns(cur) - ktime_to_ns(start_wait);
-		KVM_STATS_LOG_HIST_UPDATE(
-				vc->runner->stat.generic.halt_wait_hist,
+		KVM_VCPU_STATS_EXT_LOG_HIST_UPDATE(vc->runner, halt_wait_hist,
 				ktime_to_ns(cur) - ktime_to_ns(start_wait));
 		/* Attribute failed poll time */
 		if (vc->halt_poll_ns) {
 			vc->runner->stat.generic.halt_poll_fail_ns +=
 				ktime_to_ns(start_wait) -
 				ktime_to_ns(start_poll);
-			KVM_STATS_LOG_HIST_UPDATE(
-				vc->runner->stat.generic.halt_poll_fail_hist,
+			KVM_VCPU_STATS_EXT_LOG_HIST_UPDATE(vc->runner,
+				halt_poll_fail_hist,
 				ktime_to_ns(start_wait) -
 				ktime_to_ns(start_poll));
 		}
@@ -4703,8 +4702,8 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 			vc->runner->stat.generic.halt_poll_success_ns +=
 				ktime_to_ns(cur) -
 				ktime_to_ns(start_poll);
-			KVM_STATS_LOG_HIST_UPDATE(
-				vc->runner->stat.generic.halt_poll_success_hist,
+			KVM_VCPU_STATS_EXT_LOG_HIST_UPDATE(vc->runner,
+				halt_poll_success_hist,
 				ktime_to_ns(cur) - ktime_to_ns(start_poll));
 		}
 	}
include/linux/kvm_host.h +20 -4
index e7fc94e2910a..fd07a626fdaf 100644
@@ -391,6 +391,7 @@ struct kvm_vcpu {
 	bool scheduled_out;
 	struct kvm_vcpu_arch arch;
 	struct kvm_vcpu_stat stat;
+	struct kvm_vcpu_stat_ext *stat_ext;
 	char stats_id[KVM_STATS_NAME_SIZE];
 	struct kvm_dirty_ring dirty_ring;
 
@@ -2029,7 +2030,15 @@ struct kvm_stat_data {
 	.offset = offsetof(struct kvm_vcpu_stat, stat),			\
 	.name = #stat,							\
 }
-/* SCOPE: VM, VM_GENERIC, VCPU, VCPU_GENERIC */
+/* Extended vCPU stats are laid out after struct kvm_vcpu_stat. */
+#define VCPU_EXT_STATS_DESC(stat, type, unit, base, exp, sz, bsz)	\
+{									\
+	STATS_DESC_COMMON(type, unit, base, exp, sz, bsz),		\
+	.offset = sizeof(struct kvm_vcpu_stat) +			\
+		  offsetof(struct kvm_vcpu_stat_ext, stat),		\
+	.name = #stat,							\
+}
+/* SCOPE: VM, VM_GENERIC, VCPU, VCPU_GENERIC, VCPU_EXT */
 #define STATS_DESC(SCOPE, stat, type, unit, base, exp, sz, bsz)		       \
 	SCOPE##_STATS_DESC(stat, type, unit, base, exp, sz, bsz)
 
@@ -2096,17 +2105,18 @@ struct kvm_stat_data {
 	STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_poll_success_ns),	       \
 	STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_poll_fail_ns),		       \
 	STATS_DESC_TIME_NSEC(VCPU_GENERIC, halt_wait_ns),		       \
-	STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_poll_success_hist,     \
+	STATS_DESC_LOGHIST_TIME_NSEC(VCPU_EXT, halt_poll_success_hist,	       \
 			HALT_POLL_HIST_COUNT),				       \
-	STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_poll_fail_hist,	       \
+	STATS_DESC_LOGHIST_TIME_NSEC(VCPU_EXT, halt_poll_fail_hist,	       \
 			HALT_POLL_HIST_COUNT),				       \
-	STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_wait_hist,	       \
+	STATS_DESC_LOGHIST_TIME_NSEC(VCPU_EXT, halt_wait_hist,		       \
 			HALT_POLL_HIST_COUNT),				       \
 	STATS_DESC_IBOOLEAN(VCPU_GENERIC, blocking)
 
 ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header,
 		       const struct kvm_stats_desc *desc,
 		       void *stats, size_t size_stats,
+		       void *stats_ext, size_t size_stats_ext,
 		       char __user *user_buffer, size_t size, loff_t *offset);
 
 /**
@@ -2148,6 +2158,12 @@ static inline void kvm_stats_log_hist_update(u64 *data, size_t size, u64 value)
 #define KVM_STATS_LOG_HIST_UPDATE(array, value)				       \
 	kvm_stats_log_hist_update(array, ARRAY_SIZE(array), value)
 
+#define KVM_VCPU_STATS_EXT_LOG_HIST_UPDATE(vcpu, hist, value)		       \
+do {									       \
+	if ((vcpu)->stat_ext)						       \
+		KVM_STATS_LOG_HIST_UPDATE((vcpu)->stat_ext->hist, value);      \
+} while (0)
+
 
 extern const struct kvm_stats_header kvm_vm_stats_header;
 extern const struct kvm_stats_desc kvm_vm_stats_desc[];
include/linux/kvm_types.h +9 -1
index a568d8e6f4e8..fd7426627928 100644
@@ -133,10 +133,18 @@ struct kvm_vcpu_stat_generic {
 	u64 halt_poll_success_ns;
 	u64 halt_poll_fail_ns;
 	u64 halt_wait_ns;
+	u64 blocking;
+};
+
+/*
+ * vCPU stats that are too big to embed in every vCPU, e.g. histograms.  They
+ * are allocated only if kvm.extended_stats is enabled, and read as zero
+ * otherwise.
+ */
+struct kvm_vcpu_stat_ext {
 	u64 halt_poll_success_hist[HALT_POLL_HIST_COUNT];
 	u64 halt_poll_fail_hist[HALT_POLL_HIST_COUNT];
 	u64 halt_wait_hist[HALT_POLL_HIST_COUNT];
-	u64 blocking;
 };
 
 #define KVM_STATS_NAME_SIZE	48
virt/kvm/binary_stats.c +28 -1
index 76ce697c773b..c4f8bed1f01d 100644
@@ -19,6 +19,9 @@
  * @desc: start address of an array of stats descriptors for a vm or a vcpu
  * @stats: start address of stats data block for a vm or a vcpu
  * @size_stats: the size of stats data block pointed by @stats
+ * @stats_ext: start address of the extended stats data block, which follows
+ *             the stats data block, or NULL if it isn't allocated
+ * @size_stats_ext: the size of the extended stats data block
  * @user_buffer: start address of userspace buffer
  * @size: requested read size from userspace
  * @offset: the start position from which the content will be read for the
@@ -34,6 +37,9 @@
  * +-------------+
  * | Stats Data  |
  * +-------------+
+ * |  Extended   |
+ * | Stats Data  |
+ * +-------------+
  * Although this function allows userspace to read any amount of data (as long
  * as in the limit) from any position, the typical usage would follow below
  * steps:
@@ -52,6 +58,7 @@
 ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header,
 		       const struct kvm_stats_desc *desc,
 		       void *stats, size_t size_stats,
+		       void *stats_ext, size_t size_stats_ext,
 		       char __user *user_buffer, size_t size, loff_t *offset)
 {
 	ssize_t len;
@@ -66,7 +73,8 @@ ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header,
 	size_header = sizeof(*header);
 	size_desc = header->num_desc * sizeof(*desc);
 
-	len = KVM_STATS_NAME_SIZE + size_header + size_desc + size_stats - pos;
+	len = KVM_STATS_NAME_SIZE + size_header + size_desc + size_stats +
+	      size_stats_ext - pos;
 	len = min(len, remain);
 	if (len <= 0)
 		return 0;
@@ -136,6 +144,25 @@ ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header,
 		src = stats + pos - header->data_offset;
 		if (copy_to_user(dest, src, copylen))
 			return -EFAULT;
+		remain -= copylen;
+		pos += copylen;
+		dest += copylen;
+	}
+
+	/*
+	 * Copy extended kvm stats values, which read as zero if the extended
+	 * stats data block isn't allocated.
+	 */
+	copylen = header->data_offset + size_stats + size_stats_ext - pos;
+	copylen = min(copylen, remain);
+	if (copylen > 0) {
+		if (stats_ext) {
+			src = stats_ext + pos - header->data_offset - size_stats;
+			if (copy_to_user(dest, src, copylen))
+				return -EFAULT;
+		} else if (clear_user(dest, copylen)) {
+			return -EFAULT;
+		}
 		pos += copylen;
 	}
 
virt/kvm/kvm_main.c +48 -10

132 lines not on this page · raw message

Signature · 1 line
2.43.7