From 119e9db233ad0f4cbd4cfb9f9385a7bca378b37d Mon Sep 17 00:00:00 2001 From: Zeng Chi Date: Mon, 21 Sep 2026 18:24:42 +0800 Subject: KVM: Don't pre-reserve xarray entries when storing empty/NULL attributes Skip the xarray reservation loop when clearing all memory attributes, as storing NULL only erases the entry and never needs to allocate, so no reservation (and no cleanup of a failed one) is required in that case. Suggested-by: Sean Christopherson Cc: David Ballesteros Signed-off-by: Zeng Chi Link: https://patch.msgid.link/20260921102442.1232375-1-zeng_chi911@163.com [sean: split to separate patch] Signed-off-by: Sean Christopherson --- fs/proc/namespaces.c | 196 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 196 insertions(+) create mode 100644 fs/proc/namespaces.c (limited to 'fs/proc/namespaces.c') diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c new file mode 100644 index 000000000..ea6ec61a0 --- /dev/null +++ b/fs/proc/namespaces.c @@ -0,0 +1,196 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "internal.h" + + +static const struct proc_ns_operations *const ns_entries[] = { +#ifdef CONFIG_NET_NS + &netns_operations, +#endif +#ifdef CONFIG_UTS_NS + &utsns_operations, +#endif +#ifdef CONFIG_IPC_NS + &ipcns_operations, +#endif +#ifdef CONFIG_PID_NS + &pidns_operations, + &pidns_for_children_operations, +#endif +#ifdef CONFIG_USER_NS + &userns_operations, +#endif + &mntns_operations, +#ifdef CONFIG_CGROUPS + &cgroupns_operations, +#endif +#ifdef CONFIG_TIME_NS + &timens_operations, + &timens_for_children_operations, +#endif +}; + +static const char *proc_ns_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) +{ + const struct proc_ns_operations *ns_ops = PROC_I(inode)->ns_ops; + struct task_struct *task; + struct path ns_path; + int error; + + if (!dentry) + return ERR_PTR(-ECHILD); + + task = get_proc_task(inode); + if (!task) + return ERR_PTR(-EACCES); + + error = down_read_killable(&task->signal->exec_update_lock); + if (error) + goto out_put_task; + + error = -EACCES; + if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) + goto out; + + error = ns_get_path(&ns_path, task, ns_ops); + if (error) + goto out; + + error = nd_jump_link(&ns_path); +out: + up_read(&task->signal->exec_update_lock); +out_put_task: + put_task_struct(task); + return ERR_PTR(error); +} + +static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int buflen) +{ + struct inode *inode = d_inode(dentry); + const struct proc_ns_operations *ns_ops = PROC_I(inode)->ns_ops; + struct task_struct *task; + char name[50]; + int res = -EACCES; + + task = get_proc_task(inode); + if (!task) + return res; + + res = down_read_killable(&task->signal->exec_update_lock); + if (res) + goto out_put_task; + + res = -EACCES; + if (ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) { + res = ns_get_name(name, sizeof(name), task, ns_ops); + if (res >= 0) + res = readlink_copy(buffer, buflen, name, strlen(name)); + } + up_read(&task->signal->exec_update_lock); +out_put_task: + put_task_struct(task); + return res; +} + +static const struct inode_operations proc_ns_link_inode_operations = { + .readlink = proc_ns_readlink, + .get_link = proc_ns_get_link, + .setattr = proc_nochmod_setattr, +}; + +static struct dentry *proc_ns_instantiate(struct dentry *dentry, + struct task_struct *task, const void *ptr) +{ + const struct proc_ns_operations *ns_ops = ptr; + struct inode *inode; + struct proc_inode *ei; + + inode = proc_pid_make_inode(dentry->d_sb, task, S_IFLNK | S_IRWXUGO); + if (!inode) + return ERR_PTR(-ENOENT); + + ei = PROC_I(inode); + inode->i_op = &proc_ns_link_inode_operations; + ei->ns_ops = ns_ops; + pid_update_inode(task, inode); + + return d_splice_alias_ops(inode, dentry, &pid_dentry_operations); +} + +static int proc_ns_dir_readdir(struct file *file, struct dir_context *ctx) +{ + struct task_struct *task = get_proc_task(file_inode(file)); + const struct proc_ns_operations *const *entry, *const *last; + + if (!task) + return -ENOENT; + + if (!dir_emit_dots(file, ctx)) + goto out; + if (ctx->pos >= 2 + ARRAY_SIZE(ns_entries)) + goto out; + entry = ns_entries + (ctx->pos - 2); + last = &ns_entries[ARRAY_SIZE(ns_entries) - 1]; + while (entry <= last) { + const struct proc_ns_operations *ops = *entry; + if (!proc_fill_cache(file, ctx, ops->name, strlen(ops->name), + proc_ns_instantiate, task, ops)) + break; + ctx->pos++; + entry++; + } +out: + put_task_struct(task); + return 0; +} + +const struct file_operations proc_ns_dir_operations = { + .read = generic_read_dir, + .iterate_shared = proc_ns_dir_readdir, + .llseek = generic_file_llseek, +}; + +static struct dentry *proc_ns_dir_lookup(struct inode *dir, + struct dentry *dentry, unsigned int flags) +{ + struct task_struct *task = get_proc_task(dir); + const struct proc_ns_operations *const *entry, *const *last; + unsigned int len = dentry->d_name.len; + struct dentry *res = ERR_PTR(-ENOENT); + + if (!task) + goto out_no_task; + + last = &ns_entries[ARRAY_SIZE(ns_entries)]; + for (entry = ns_entries; entry < last; entry++) { + if (strlen((*entry)->name) != len) + continue; + if (!memcmp(dentry->d_name.name, (*entry)->name, len)) + break; + } + if (entry == last) + goto out; + + res = proc_ns_instantiate(dentry, task, *entry); +out: + put_task_struct(task); +out_no_task: + return res; +} + +const struct inode_operations proc_ns_dir_inode_operations = { + .lookup = proc_ns_dir_lookup, + .getattr = pid_getattr, + .setattr = proc_nochmod_setattr, +}; -- cgit v1.3.1