From: Jingxian He <hejingxian@huawei.com>
Date: Mon, 1 Mar 2021 17:44:59 +0800
Subject: [PATCH openEuler-21.03 2/2] pid: add pid reserve method for checkpoint and recover
hulk inclusion
category: feature
bugzilla: 48159
CVE: N/A
We record the pid of dump tasks in the reserved memory,
and reserve the pids before init task start.
In the recover process, free the reserved pids and realloc them for use.
Signed-off-by: Jingxian He <hejingxian@huawei.com>
Reviewed-by: Wenliang He <hewenliang4@huawei.com>
Reviewed-by: Jing Xiangfeng <jingxiangfeng@huawei.com>
---
arch/arm64/configs/openeuler_defconfig | 1 +
include/linux/pin_mem.h | 6 ++++
kernel/pid.c | 10 +++++++
mm/Kconfig | 10 +++++++
mm/pin_mem.c | 51 ++++++++++++++++++++++++++++++++++
5 files changed, 78 insertions(+)
diff --git a/arch/arm64/configs/openeuler_defconfig b/arch/arm64/configs/openeuler_defconfig
index 76fda68..de6db02 100644
--- a/arch/arm64/configs/openeuler_defconfig
+++ b/arch/arm64/configs/openeuler_defconfig
@@ -1037,6 +1037,7 @@ CONFIG_FRAME_VECTOR=y
# CONFIG_READ_ONLY_THP_FOR_FS is not set
CONFIG_ARCH_HAS_PTE_SPECIAL=y
CONFIG_PIN_MEMORY=y
+CONFIG_PID_RESERVE=y
# end of Memory Management options
CONFIG_NET=y
diff --git a/include/linux/pin_mem.h b/include/linux/pin_mem.h
index bc8b03e..a9fe2ef 100644
--- a/include/linux/pin_mem.h
+++ b/include/linux/pin_mem.h
@@ -74,5 +74,11 @@ extern struct resource pin_memory_resource;
#endif
extern void init_reserve_page_map(unsigned long map_addr, unsigned long map_size);
+#ifdef CONFIG_PID_RESERVE
+extern bool is_need_reserve_pids(void);
+extern void free_reserved_pid(struct idr *idr, int pid);
+extern void reserve_pids(struct idr *idr, int pid_max);
+#endif
+
#endif /* CONFIG_PIN_MEMORY */
#endif /* _LINUX_PIN_MEMORY_H */
diff --git a/kernel/pid.c b/kernel/pid.c
index 4856818..32ab9ef 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -44,6 +44,9 @@
#include <linux/idr.h>
#include <net/sock.h>
#include <uapi/linux/pidfd.h>
+#ifdef CONFIG_PID_RESERVE
+#include <linux/pin_mem.h>
+#endif
struct pid init_struct_pid = {
.count = REFCOUNT_INIT(1),
@@ -209,6 +212,9 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
spin_lock_irq(&pidmap_lock);
if (tid) {
+#ifdef CONFIG_PID_RESERVE
+ free_reserved_pid(&tmp->idr, tid);
+#endif
nr = idr_alloc(&tmp->idr, NULL, tid,
tid + 1, GFP_ATOMIC);
/*
@@ -621,6 +627,10 @@ void __init pid_idr_init(void)
init_pid_ns.pid_cachep = KMEM_CACHE(pid,
SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT);
+#ifdef CONFIG_PID_RESERVE
+ if (is_need_reserve_pids())
+ reserve_pids(&init_pid_ns.idr, pid_max);
+#endif
}
static struct file *__pidfd_fget(struct task_struct *task, int fd)
diff --git a/mm/Kconfig b/mm/Kconfig
index 930dc13..e27d2c6 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -868,3 +868,13 @@ config PIN_MEMORY
the corresponding physical pages mapping info in checkpoint,
and remap the physical pages to restore tasks in restore.
endmenu
+
+config PID_RESERVE
+ bool "Support for reserve pid"
+ depends on PIN_MEMORY
+ help
+ Say y here to enable the pid reserved feature for checkpoint.
+ and restore.
+ We record the pid of dump task in the reserve memory,
+ and reserve the pids before init task start. In restore process,
+ free the reserved pids and realloc them for use.
diff --git a/mm/pin_mem.c b/mm/pin_mem.c
index 0a143b6..a040853 100644
--- a/mm/pin_mem.c
+++ b/mm/pin_mem.c
@@ -947,4 +947,55 @@ void clear_pin_memory_record(void)
}
EXPORT_SYMBOL_GPL(clear_pin_memory_record);
+#ifdef CONFIG_PID_RESERVE
+struct idr *reserve_idr;
+
+/* test if there exist pin memory tasks */
+bool is_need_reserve_pids(void)
+{
+ return (pin_pid_num > 0);
+}
+
+void free_reserved_pid(struct idr *idr, int pid)
+{
+ unsigned int index;
+ struct page_map_info *pmi;
+
+ if (!max_pin_pid_num || idr != reserve_idr)
+ return;
+
+ for (index = 0; index < pin_pid_num; index++) {
+ pmi = &(user_space_reserve_start[index]);
+ if (pmi->pid == pid && pmi->pid_reserved) {
+ idr_remove(idr, pid);
+ return;
+ }
+ }
+}
+
+/* reserve pids for check point tasks which pinned memory */
+void reserve_pids(struct idr *idr, int pid_max)
+{
+ int alloc_pid;
+ unsigned int index;
+ struct page_map_info *pmi;
+
+ if (!max_pin_pid_num)
+ return;
+ reserve_idr = idr;
+ for (index = 0; index < pin_pid_num; index++) {
+ pmi = &(user_space_reserve_start[index]);
+ pmi->pid_reserved = true;
+ alloc_pid = idr_alloc(idr, NULL, pmi->pid, pid_max, GFP_ATOMIC);
+ if (alloc_pid != pmi->pid) {
+ if (alloc_pid > 0)
+ idr_remove(idr, alloc_pid);
+ pr_warn("Reserve pid (%d) fail, real pid is %d.\n", alloc_pid, pmi->pid);
+ pmi->pid_reserved = false;
+ continue;
+ }
+ }
+}
+#endif /* CONFIG_PID_RESERVE */
+
#endif /* CONFIG_PIN_MEMORY */
--
2.9.5