summaryrefslogtreecommitdiff
path: root/virt/kvm/binary_stats.c
diff options
context:
space:
mode:
authorJing Zhang <jingzhangos@google.com>2021-06-18 22:27:04 +0000
committerPaolo Bonzini <pbonzini@redhat.com>2021-06-24 11:47:57 -0400
commitcb082bfab59a224a49ae803fed52cd03e8d6b5e0 (patch)
treea2c44bb780df8a32581373e05a054b640687cf3f /virt/kvm/binary_stats.c
parent0193cc908b5ae8aff2e2d2997ca5d4ae26ed24d4 (diff)
KVM: stats: Add fd-based API to read binary stats data
This commit defines the API for userspace and prepare the common functionalities to support per VM/VCPU binary stats data readings. The KVM stats now is only accessible by debugfs, which has some shortcomings this change series are supposed to fix: 1. The current debugfs stats solution in KVM could be disabled when kernel Lockdown mode is enabled, which is a potential rick for production. 2. The current debugfs stats solution in KVM is organized as "one stats per file", it is good for debugging, but not efficient for production. 3. The stats read/clear in current debugfs solution in KVM are protected by the global kvm_lock. Besides that, there are some other benefits with this change: 1. All KVM VM/VCPU stats can be read out in a bulk by one copy to userspace. 2. A schema is used to describe KVM statistics. From userspace's perspective, the KVM statistics are self-describing. 3. With the fd-based solution, a separate telemetry would be able to read KVM stats in a less privileged environment. 4. After the initial setup by reading in stats descriptors, a telemetry only needs to read the stats data itself, no more parsing or setup is needed. Reviewed-by: David Matlack <dmatlack@google.com> Reviewed-by: Ricardo Koller <ricarkol@google.com> Reviewed-by: Krish Sadhukhan <krish.sadhukhan@oracle.com> Reviewed-by: Fuad Tabba <tabba@google.com> Tested-by: Fuad Tabba <tabba@google.com> #arm64 Signed-off-by: Jing Zhang <jingzhangos@google.com> Message-Id: <20210618222709.1858088-3-jingzhangos@google.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Diffstat (limited to 'virt/kvm/binary_stats.c')
-rw-r--r--virt/kvm/binary_stats.c146
1 files changed, 146 insertions, 0 deletions
diff --git a/virt/kvm/binary_stats.c b/virt/kvm/binary_stats.c
new file mode 100644
index 000000000000..e609d428811a
--- /dev/null
+++ b/virt/kvm/binary_stats.c
@@ -0,0 +1,146 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * KVM binary statistics interface implementation
+ *
+ * Copyright 2021 Google LLC
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/kvm.h>
+#include <linux/errno.h>
+#include <linux/uaccess.h>
+
+/**
+ * kvm_stats_read() - Common function to read from the binary statistics
+ * file descriptor.
+ *
+ * @id: identification string of the stats
+ * @header: stats header for a vm or a vcpu
+ * @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
+ * @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
+ * corresponding vm or vcp file descriptor
+ *
+ * The file content of a vm/vcpu file descriptor is now defined as below:
+ * +-------------+
+ * | Header |
+ * +-------------+
+ * | id string |
+ * +-------------+
+ * | Descriptors |
+ * +-------------+
+ * | 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:
+ * 1. Read header from offset 0. Get the offset of descriptors and stats data
+ * and some other necessary information. This is a one-time work for the
+ * lifecycle of the corresponding vm/vcpu stats fd.
+ * 2. Read id string from its offset. This is a one-time work for the lifecycle
+ * of the corresponding vm/vcpu stats fd.
+ * 3. Read descriptors from its offset and discover all the stats by parsing
+ * descriptors. This is a one-time work for the lifecycle of the
+ * corresponding vm/vcpu stats fd.
+ * 4. Periodically read stats data from its offset using pread.
+ *
+ * Return: the number of bytes that has been successfully read
+ */
+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,
+ char __user *user_buffer, size_t size, loff_t *offset)
+{
+ ssize_t len;
+ ssize_t copylen;
+ ssize_t remain = size;
+ size_t size_desc;
+ size_t size_header;
+ void *src;
+ loff_t pos = *offset;
+ char __user *dest = user_buffer;
+
+ size_header = sizeof(*header);
+ size_desc = header->num_desc * sizeof(*desc);
+
+ len = KVM_STATS_NAME_SIZE + size_header + size_desc + size_stats - pos;
+ len = min(len, remain);
+ if (len <= 0)
+ return 0;
+ remain = len;
+
+ /*
+ * Copy kvm stats header.
+ * The header is the first block of content userspace usually read out.
+ * The pos is 0 and the copylen and remain would be the size of header.
+ * The copy of the header would be skipped if offset is larger than the
+ * size of header. That usually happens when userspace reads stats
+ * descriptors and stats data.
+ */
+ copylen = size_header - pos;
+ copylen = min(copylen, remain);
+ if (copylen > 0) {
+ src = (void *)header + pos;
+ if (copy_to_user(dest, src, copylen))
+ return -EFAULT;
+ remain -= copylen;
+ pos += copylen;
+ dest += copylen;
+ }
+
+ /*
+ * Copy kvm stats header id string.
+ * The id string is unique for every vm/vcpu, which is stored in kvm
+ * and kvm_vcpu structure.
+ * The id string is part of the stat header from the perspective of
+ * userspace, it is usually read out together with previous constant
+ * header part and could be skipped for later descriptors and stats
+ * data readings.
+ */
+ copylen = header->id_offset + KVM_STATS_NAME_SIZE - pos;
+ copylen = min(copylen, remain);
+ if (copylen > 0) {
+ src = id + pos - header->id_offset;
+ if (copy_to_user(dest, src, copylen))
+ return -EFAULT;
+ remain -= copylen;
+ pos += copylen;
+ dest += copylen;
+ }
+
+ /*
+ * Copy kvm stats descriptors.
+ * The descriptors copy would be skipped in the typical case that
+ * userspace periodically read stats data, since the pos would be
+ * greater than the end address of descriptors
+ * (header->header.desc_offset + size_desc) causing copylen <= 0.
+ */
+ copylen = header->desc_offset + size_desc - pos;
+ copylen = min(copylen, remain);
+ if (copylen > 0) {
+ src = (void *)desc + pos - header->desc_offset;
+ if (copy_to_user(dest, src, copylen))
+ return -EFAULT;
+ remain -= copylen;
+ pos += copylen;
+ dest += copylen;
+ }
+
+ /* Copy kvm stats values */
+ copylen = header->data_offset + size_stats - pos;
+ copylen = min(copylen, remain);
+ if (copylen > 0) {
+ src = stats + pos - header->data_offset;
+ if (copy_to_user(dest, src, copylen))
+ return -EFAULT;
+ remain -= copylen;
+ pos += copylen;
+ dest += copylen;
+ }
+
+ *offset = pos;
+ return len;
+}