6038f373a3
All file_operations should get a .llseek operation so we can make nonseekable_open the default for future file operations without a .llseek pointer. The three cases that we can automatically detect are no_llseek, seq_lseek and default_llseek. For cases where we can we can automatically prove that the file offset is always ignored, we use noop_llseek, which maintains the current behavior of not returning an error from a seek. New drivers should normally not use noop_llseek but instead use no_llseek and call nonseekable_open at open time. Existing drivers can be converted to do the same when the maintainer knows for certain that no user code relies on calling seek on the device file. The generated code is often incorrectly indented and right now contains comments that clarify for each added line why a specific variant was chosen. In the version that gets submitted upstream, the comments will be gone and I will manually fix the indentation, because there does not seem to be a way to do that using coccinelle. Some amount of new code is currently sitting in linux-next that should get the same modifications, which I will do at the end of the merge window. Many thanks to Julia Lawall for helping me learn to write a semantic patch that does all this. ===== begin semantic patch ===== // This adds an llseek= method to all file operations, // as a preparation for making no_llseek the default. // // The rules are // - use no_llseek explicitly if we do nonseekable_open // - use seq_lseek for sequential files // - use default_llseek if we know we access f_pos // - use noop_llseek if we know we don't access f_pos, // but we still want to allow users to call lseek // @ open1 exists @ identifier nested_open; @@ nested_open(...) { <+... nonseekable_open(...) ...+> } @ open exists@ identifier open_f; identifier i, f; identifier open1.nested_open; @@ int open_f(struct inode *i, struct file *f) { <+... ( nonseekable_open(...) | nested_open(...) ) ...+> } @ read disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ read_no_fpos disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { ... when != off } @ write @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ write_no_fpos @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { ... when != off } @ fops0 @ identifier fops; @@ struct file_operations fops = { ... }; @ has_llseek depends on fops0 @ identifier fops0.fops; identifier llseek_f; @@ struct file_operations fops = { ... .llseek = llseek_f, ... }; @ has_read depends on fops0 @ identifier fops0.fops; identifier read_f; @@ struct file_operations fops = { ... .read = read_f, ... }; @ has_write depends on fops0 @ identifier fops0.fops; identifier write_f; @@ struct file_operations fops = { ... .write = write_f, ... }; @ has_open depends on fops0 @ identifier fops0.fops; identifier open_f; @@ struct file_operations fops = { ... .open = open_f, ... }; // use no_llseek if we call nonseekable_open //////////////////////////////////////////// @ nonseekable1 depends on !has_llseek && has_open @ identifier fops0.fops; identifier nso ~= "nonseekable_open"; @@ struct file_operations fops = { ... .open = nso, ... +.llseek = no_llseek, /* nonseekable */ }; @ nonseekable2 depends on !has_llseek @ identifier fops0.fops; identifier open.open_f; @@ struct file_operations fops = { ... .open = open_f, ... +.llseek = no_llseek, /* open uses nonseekable */ }; // use seq_lseek for sequential files ///////////////////////////////////// @ seq depends on !has_llseek @ identifier fops0.fops; identifier sr ~= "seq_read"; @@ struct file_operations fops = { ... .read = sr, ... +.llseek = seq_lseek, /* we have seq_read */ }; // use default_llseek if there is a readdir /////////////////////////////////////////// @ fops1 depends on !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier readdir_e; @@ // any other fop is used that changes pos struct file_operations fops = { ... .readdir = readdir_e, ... +.llseek = default_llseek, /* readdir is present */ }; // use default_llseek if at least one of read/write touches f_pos ///////////////////////////////////////////////////////////////// @ fops2 depends on !fops1 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read.read_f; @@ // read fops use offset struct file_operations fops = { ... .read = read_f, ... +.llseek = default_llseek, /* read accesses f_pos */ }; @ fops3 depends on !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, ... + .llseek = default_llseek, /* write accesses f_pos */ }; // Use noop_llseek if neither read nor write accesses f_pos /////////////////////////////////////////////////////////// @ fops4 depends on !fops1 && !fops2 && !fops3 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; identifier write_no_fpos.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, .read = read_f, ... +.llseek = noop_llseek, /* read and write both use no f_pos */ }; @ depends on has_write && !has_read && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write_no_fpos.write_f; @@ struct file_operations fops = { ... .write = write_f, ... +.llseek = noop_llseek, /* write uses no f_pos */ }; @ depends on has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; @@ struct file_operations fops = { ... .read = read_f, ... +.llseek = noop_llseek, /* read uses no f_pos */ }; @ depends on !has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; @@ struct file_operations fops = { ... +.llseek = noop_llseek, /* no read or write fn */ }; ===== End semantic patch ===== Signed-off-by: Arnd Bergmann <arnd@arndb.de> Cc: Julia Lawall <julia@diku.dk> Cc: Christoph Hellwig <hch@infradead.org>
306 lines
7.2 KiB
C
306 lines
7.2 KiB
C
/*
|
|
* Hypervisor filesystem for Linux on s390. z/VM implementation.
|
|
*
|
|
* Copyright (C) IBM Corp. 2006
|
|
* Author(s): Michael Holzheu <holzheu@de.ibm.com>
|
|
*/
|
|
|
|
#include <linux/types.h>
|
|
#include <linux/errno.h>
|
|
#include <linux/string.h>
|
|
#include <linux/vmalloc.h>
|
|
#include <asm/ebcdic.h>
|
|
#include <asm/timex.h>
|
|
#include "hypfs.h"
|
|
|
|
#define NAME_LEN 8
|
|
#define DBFS_D2FC_HDR_VERSION 0
|
|
|
|
static char local_guest[] = " ";
|
|
static char all_guests[] = "* ";
|
|
static char *guest_query;
|
|
|
|
static struct dentry *dbfs_d2fc_file;
|
|
|
|
struct diag2fc_data {
|
|
__u32 version;
|
|
__u32 flags;
|
|
__u64 used_cpu;
|
|
__u64 el_time;
|
|
__u64 mem_min_kb;
|
|
__u64 mem_max_kb;
|
|
__u64 mem_share_kb;
|
|
__u64 mem_used_kb;
|
|
__u32 pcpus;
|
|
__u32 lcpus;
|
|
__u32 vcpus;
|
|
__u32 cpu_min;
|
|
__u32 cpu_max;
|
|
__u32 cpu_shares;
|
|
__u32 cpu_use_samp;
|
|
__u32 cpu_delay_samp;
|
|
__u32 page_wait_samp;
|
|
__u32 idle_samp;
|
|
__u32 other_samp;
|
|
__u32 total_samp;
|
|
char guest_name[NAME_LEN];
|
|
};
|
|
|
|
struct diag2fc_parm_list {
|
|
char userid[NAME_LEN];
|
|
char aci_grp[NAME_LEN];
|
|
__u64 addr;
|
|
__u32 size;
|
|
__u32 fmt;
|
|
};
|
|
|
|
static int diag2fc(int size, char* query, void *addr)
|
|
{
|
|
unsigned long residual_cnt;
|
|
unsigned long rc;
|
|
struct diag2fc_parm_list parm_list;
|
|
|
|
memcpy(parm_list.userid, query, NAME_LEN);
|
|
ASCEBC(parm_list.userid, NAME_LEN);
|
|
parm_list.addr = (unsigned long) addr ;
|
|
parm_list.size = size;
|
|
parm_list.fmt = 0x02;
|
|
memset(parm_list.aci_grp, 0x40, NAME_LEN);
|
|
rc = -1;
|
|
|
|
asm volatile(
|
|
" diag %0,%1,0x2fc\n"
|
|
"0:\n"
|
|
EX_TABLE(0b,0b)
|
|
: "=d" (residual_cnt), "+d" (rc) : "0" (&parm_list) : "memory");
|
|
|
|
if ((rc != 0 ) && (rc != -2))
|
|
return rc;
|
|
else
|
|
return -residual_cnt;
|
|
}
|
|
|
|
/*
|
|
* Allocate buffer for "query" and store diag 2fc at "offset"
|
|
*/
|
|
static void *diag2fc_store(char *query, unsigned int *count, int offset)
|
|
{
|
|
void *data;
|
|
int size;
|
|
|
|
do {
|
|
size = diag2fc(0, query, NULL);
|
|
if (size < 0)
|
|
return ERR_PTR(-EACCES);
|
|
data = vmalloc(size + offset);
|
|
if (!data)
|
|
return ERR_PTR(-ENOMEM);
|
|
if (diag2fc(size, query, data + offset) == 0)
|
|
break;
|
|
vfree(data);
|
|
} while (1);
|
|
*count = (size / sizeof(struct diag2fc_data));
|
|
|
|
return data;
|
|
}
|
|
|
|
static void diag2fc_free(void *data)
|
|
{
|
|
vfree(data);
|
|
}
|
|
|
|
#define ATTRIBUTE(sb, dir, name, member) \
|
|
do { \
|
|
void *rc; \
|
|
rc = hypfs_create_u64(sb, dir, name, member); \
|
|
if (IS_ERR(rc)) \
|
|
return PTR_ERR(rc); \
|
|
} while(0)
|
|
|
|
static int hpyfs_vm_create_guest(struct super_block *sb,
|
|
struct dentry *systems_dir,
|
|
struct diag2fc_data *data)
|
|
{
|
|
char guest_name[NAME_LEN + 1] = {};
|
|
struct dentry *guest_dir, *cpus_dir, *samples_dir, *mem_dir;
|
|
int dedicated_flag, capped_value;
|
|
|
|
capped_value = (data->flags & 0x00000006) >> 1;
|
|
dedicated_flag = (data->flags & 0x00000008) >> 3;
|
|
|
|
/* guest dir */
|
|
memcpy(guest_name, data->guest_name, NAME_LEN);
|
|
EBCASC(guest_name, NAME_LEN);
|
|
strim(guest_name);
|
|
guest_dir = hypfs_mkdir(sb, systems_dir, guest_name);
|
|
if (IS_ERR(guest_dir))
|
|
return PTR_ERR(guest_dir);
|
|
ATTRIBUTE(sb, guest_dir, "onlinetime_us", data->el_time);
|
|
|
|
/* logical cpu information */
|
|
cpus_dir = hypfs_mkdir(sb, guest_dir, "cpus");
|
|
if (IS_ERR(cpus_dir))
|
|
return PTR_ERR(cpus_dir);
|
|
ATTRIBUTE(sb, cpus_dir, "cputime_us", data->used_cpu);
|
|
ATTRIBUTE(sb, cpus_dir, "capped", capped_value);
|
|
ATTRIBUTE(sb, cpus_dir, "dedicated", dedicated_flag);
|
|
ATTRIBUTE(sb, cpus_dir, "count", data->vcpus);
|
|
ATTRIBUTE(sb, cpus_dir, "weight_min", data->cpu_min);
|
|
ATTRIBUTE(sb, cpus_dir, "weight_max", data->cpu_max);
|
|
ATTRIBUTE(sb, cpus_dir, "weight_cur", data->cpu_shares);
|
|
|
|
/* memory information */
|
|
mem_dir = hypfs_mkdir(sb, guest_dir, "mem");
|
|
if (IS_ERR(mem_dir))
|
|
return PTR_ERR(mem_dir);
|
|
ATTRIBUTE(sb, mem_dir, "min_KiB", data->mem_min_kb);
|
|
ATTRIBUTE(sb, mem_dir, "max_KiB", data->mem_max_kb);
|
|
ATTRIBUTE(sb, mem_dir, "used_KiB", data->mem_used_kb);
|
|
ATTRIBUTE(sb, mem_dir, "share_KiB", data->mem_share_kb);
|
|
|
|
/* samples */
|
|
samples_dir = hypfs_mkdir(sb, guest_dir, "samples");
|
|
if (IS_ERR(samples_dir))
|
|
return PTR_ERR(samples_dir);
|
|
ATTRIBUTE(sb, samples_dir, "cpu_using", data->cpu_use_samp);
|
|
ATTRIBUTE(sb, samples_dir, "cpu_delay", data->cpu_delay_samp);
|
|
ATTRIBUTE(sb, samples_dir, "mem_delay", data->page_wait_samp);
|
|
ATTRIBUTE(sb, samples_dir, "idle", data->idle_samp);
|
|
ATTRIBUTE(sb, samples_dir, "other", data->other_samp);
|
|
ATTRIBUTE(sb, samples_dir, "total", data->total_samp);
|
|
return 0;
|
|
}
|
|
|
|
int hypfs_vm_create_files(struct super_block *sb, struct dentry *root)
|
|
{
|
|
struct dentry *dir, *file;
|
|
struct diag2fc_data *data;
|
|
unsigned int count = 0;
|
|
int rc, i;
|
|
|
|
data = diag2fc_store(guest_query, &count, 0);
|
|
if (IS_ERR(data))
|
|
return PTR_ERR(data);
|
|
|
|
/* Hpervisor Info */
|
|
dir = hypfs_mkdir(sb, root, "hyp");
|
|
if (IS_ERR(dir)) {
|
|
rc = PTR_ERR(dir);
|
|
goto failed;
|
|
}
|
|
file = hypfs_create_str(sb, dir, "type", "z/VM Hypervisor");
|
|
if (IS_ERR(file)) {
|
|
rc = PTR_ERR(file);
|
|
goto failed;
|
|
}
|
|
|
|
/* physical cpus */
|
|
dir = hypfs_mkdir(sb, root, "cpus");
|
|
if (IS_ERR(dir)) {
|
|
rc = PTR_ERR(dir);
|
|
goto failed;
|
|
}
|
|
file = hypfs_create_u64(sb, dir, "count", data->lcpus);
|
|
if (IS_ERR(file)) {
|
|
rc = PTR_ERR(file);
|
|
goto failed;
|
|
}
|
|
|
|
/* guests */
|
|
dir = hypfs_mkdir(sb, root, "systems");
|
|
if (IS_ERR(dir)) {
|
|
rc = PTR_ERR(dir);
|
|
goto failed;
|
|
}
|
|
|
|
for (i = 0; i < count; i++) {
|
|
rc = hpyfs_vm_create_guest(sb, dir, &(data[i]));
|
|
if (rc)
|
|
goto failed;
|
|
}
|
|
diag2fc_free(data);
|
|
return 0;
|
|
|
|
failed:
|
|
diag2fc_free(data);
|
|
return rc;
|
|
}
|
|
|
|
struct dbfs_d2fc_hdr {
|
|
u64 len; /* Length of d2fc buffer without header */
|
|
u16 version; /* Version of header */
|
|
char tod_ext[16]; /* TOD clock for d2fc */
|
|
u64 count; /* Number of VM guests in d2fc buffer */
|
|
char reserved[30];
|
|
} __attribute__ ((packed));
|
|
|
|
struct dbfs_d2fc {
|
|
struct dbfs_d2fc_hdr hdr; /* 64 byte header */
|
|
char buf[]; /* d2fc buffer */
|
|
} __attribute__ ((packed));
|
|
|
|
static int dbfs_d2fc_open(struct inode *inode, struct file *file)
|
|
{
|
|
struct dbfs_d2fc *data;
|
|
unsigned int count;
|
|
|
|
data = diag2fc_store(guest_query, &count, sizeof(data->hdr));
|
|
if (IS_ERR(data))
|
|
return PTR_ERR(data);
|
|
get_clock_ext(data->hdr.tod_ext);
|
|
data->hdr.len = count * sizeof(struct diag2fc_data);
|
|
data->hdr.version = DBFS_D2FC_HDR_VERSION;
|
|
data->hdr.count = count;
|
|
memset(&data->hdr.reserved, 0, sizeof(data->hdr.reserved));
|
|
file->private_data = data;
|
|
return nonseekable_open(inode, file);
|
|
}
|
|
|
|
static int dbfs_d2fc_release(struct inode *inode, struct file *file)
|
|
{
|
|
diag2fc_free(file->private_data);
|
|
return 0;
|
|
}
|
|
|
|
static ssize_t dbfs_d2fc_read(struct file *file, char __user *buf,
|
|
size_t size, loff_t *ppos)
|
|
{
|
|
struct dbfs_d2fc *data = file->private_data;
|
|
|
|
return simple_read_from_buffer(buf, size, ppos, data, data->hdr.len +
|
|
sizeof(struct dbfs_d2fc_hdr));
|
|
}
|
|
|
|
static const struct file_operations dbfs_d2fc_ops = {
|
|
.open = dbfs_d2fc_open,
|
|
.read = dbfs_d2fc_read,
|
|
.release = dbfs_d2fc_release,
|
|
.llseek = no_llseek,
|
|
};
|
|
|
|
int hypfs_vm_init(void)
|
|
{
|
|
if (!MACHINE_IS_VM)
|
|
return 0;
|
|
if (diag2fc(0, all_guests, NULL) > 0)
|
|
guest_query = all_guests;
|
|
else if (diag2fc(0, local_guest, NULL) > 0)
|
|
guest_query = local_guest;
|
|
else
|
|
return -EACCES;
|
|
|
|
dbfs_d2fc_file = debugfs_create_file("diag_2fc", 0400, hypfs_dbfs_dir,
|
|
NULL, &dbfs_d2fc_ops);
|
|
if (IS_ERR(dbfs_d2fc_file))
|
|
return PTR_ERR(dbfs_d2fc_file);
|
|
|
|
return 0;
|
|
}
|
|
|
|
void hypfs_vm_exit(void)
|
|
{
|
|
if (!MACHINE_IS_VM)
|
|
return;
|
|
debugfs_remove(dbfs_d2fc_file);
|
|
}
|