linux/arch/s390/boot/ipl_parm.c

326 lines
7.5 KiB
C
Raw Permalink Normal View History

// SPDX-License-Identifier: GPL-2.0
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/ctype.h>
mm: reorder includes after introduction of linux/pgtable.h The replacement of <asm/pgrable.h> with <linux/pgtable.h> made the include of the latter in the middle of asm includes. Fix this up with the aid of the below script and manual adjustments here and there. import sys import re if len(sys.argv) is not 3: print "USAGE: %s <file> <header>" % (sys.argv[0]) sys.exit(1) hdr_to_move="#include <linux/%s>" % sys.argv[2] moved = False in_hdrs = False with open(sys.argv[1], "r") as f: lines = f.readlines() for _line in lines: line = _line.rstrip(' ') if line == hdr_to_move: continue if line.startswith("#include <linux/"): in_hdrs = True elif not moved and in_hdrs: moved = True print hdr_to_move print line Signed-off-by: Mike Rapoport <rppt@linux.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Cain <bcain@codeaurora.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chris Zankel <chris@zankel.net> Cc: "David S. Miller" <davem@davemloft.net> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Greentime Hu <green.hu@gmail.com> Cc: Greg Ungerer <gerg@linux-m68k.org> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Guo Ren <guoren@kernel.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Helge Deller <deller@gmx.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: Ley Foon Tan <ley.foon.tan@intel.com> Cc: Mark Salter <msalter@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Nick Hu <nickhu@andestech.com> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Richard Weinberger <richard@nod.at> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stafford Horne <shorne@gmail.com> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Cc: Vincent Chen <deanbo422@gmail.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will@kernel.org> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Link: http://lkml.kernel.org/r/20200514170327.31389-4-rppt@kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-08 21:32:42 -07:00
#include <linux/pgtable.h>
s390: Add infrastructure to patch lowcore accesses The s390 architecture defines two special per-CPU data pages called the "prefix area". In s390-linux terminology this is usually called "lowcore". This memory area contains system configuration data like old/new PSW's for system call/interrupt/machine check handlers and lots of other data. It is normally mapped to logical address 0. This area can only be accessed when in supervisor mode. This means that kernel code can dereference NULL pointers, because accesses to address 0 are allowed. Parts of lowcore can be write protected, but read accesses and write accesses outside of the write protected areas are not caught. To remove this limitation for debugging and testing, remap lowcore to another address and define a function get_lowcore() which simply returns the address where lowcore is mapped at. This would normally introduce a pointer dereference (=memory read). As lowcore is used for several very often used variables, add code to patch this function during runtime, so we avoid the memory reads. For C code get_lowcore() has to be used, for assembly code it is the GET_LC macro. When using this macro/function a reference is added to alternative patching. All these locations will be patched to the actual lowcore location when the kernel is booted or a module is loaded. To make debugging/bisecting problems easier, this patch adds all the infrastructure but the lowcore address is still hardwired to 0. This way the code can be converted on a per function basis, and the functionality is enabled in a patch after all the functions have been converted. Note that this requires at least z16 because the old lpsw instruction only allowed a 12 bit displacement. z16 introduced lpswey which allows 20 bits (signed), so the lowcore can effectively be mapped from address 0 - 0x7e000. To use 0x7e000 as address, a 6 byte lgfi instruction would have to be used in the alternative. To save two bytes, llilh can be used, but this only allows to set bits 16-31 of the address. In order to use the llilh instruction, use 0x70000 as alternative lowcore address. This is still large enough to catch NULL pointer dereferences into large arrays. Reviewed-by: Heiko Carstens <hca@linux.ibm.com> Signed-off-by: Sven Schnelle <svens@linux.ibm.com> Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
2024-07-22 15:41:14 +02:00
#include <asm/abs_lowcore.h>
#include <asm/page-states.h>
#include <asm/machine.h>
#include <asm/ebcdic.h>
#include <asm/sclp.h>
#include <asm/sections.h>
#include <asm/boot_data.h>
#include <asm/facility.h>
#include <asm/setup.h>
#include <asm/uv.h>
#include "boot.h"
struct parmarea parmarea __section(".parmarea") = {
.kernel_version = (unsigned long)kernel_version,
.max_command_line_size = COMMAND_LINE_SIZE,
.command_line = "root=/dev/ram0 ro",
};
char __bootdata(early_command_line)[COMMAND_LINE_SIZE];
unsigned int __bootdata_preserved(zlib_dfltcc_support) = ZLIB_DFLTCC_FULL;
struct ipl_parameter_block __bootdata_preserved(ipl_block);
int __bootdata_preserved(ipl_block_valid);
int __bootdata_preserved(__kaslr_enabled);
int __bootdata_preserved(cmma_flag) = 1;
unsigned long vmalloc_size = VMALLOC_DEFAULT_SIZE;
unsigned long memory_limit;
int vmalloc_size_set;
static inline int __diag308(unsigned long subcode, void *addr)
{
union register_pair r1 = { .even = (unsigned long)addr, .odd = 0 };
asm_inline volatile(
" diag %[r1],%[subcode],0x308\n"
"0:\n"
EX_TABLE(0b, 0b)
: [r1] "+d" (r1.pair)
: [subcode] "d" (subcode)
: "cc", "memory");
return r1.odd;
}
void store_ipl_parmblock(void)
{
int rc;
rc = __diag308(DIAG308_STORE, &ipl_block);
if (rc == DIAG308_RC_OK &&
ipl_block.hdr.version <= IPL_MAX_SUPPORTED_VERSION)
ipl_block_valid = 1;
}
bool is_ipl_block_dump(void)
{
if (ipl_block.pb0_hdr.pbt == IPL_PBT_FCP &&
ipl_block.fcp.opt == IPL_PB0_FCP_OPT_DUMP)
return true;
if (ipl_block.pb0_hdr.pbt == IPL_PBT_NVME &&
ipl_block.nvme.opt == IPL_PB0_NVME_OPT_DUMP)
return true;
if (ipl_block.pb0_hdr.pbt == IPL_PBT_ECKD &&
ipl_block.eckd.opt == IPL_PB0_ECKD_OPT_DUMP)
return true;
return false;
}
static size_t scpdata_length(const u8 *buf, size_t count)
{
while (count) {
if (buf[count - 1] != '\0' && buf[count - 1] != ' ')
break;
count--;
}
return count;
}
static size_t ipl_block_get_ascii_scpdata(char *dest, size_t size,
const struct ipl_parameter_block *ipb)
{
const __u8 *scp_data;
__u32 scp_data_len;
int has_lowercase;
size_t count = 0;
size_t i;
switch (ipb->pb0_hdr.pbt) {
case IPL_PBT_FCP:
scp_data_len = ipb->fcp.scp_data_len;
scp_data = ipb->fcp.scp_data;
break;
case IPL_PBT_NVME:
scp_data_len = ipb->nvme.scp_data_len;
scp_data = ipb->nvme.scp_data;
break;
case IPL_PBT_ECKD:
scp_data_len = ipb->eckd.scp_data_len;
scp_data = ipb->eckd.scp_data;
break;
default:
goto out;
}
count = min(size - 1, scpdata_length(scp_data, scp_data_len));
if (!count)
goto out;
has_lowercase = 0;
for (i = 0; i < count; i++) {
if (!isascii(scp_data[i])) {
count = 0;
goto out;
}
if (!has_lowercase && islower(scp_data[i]))
has_lowercase = 1;
}
if (has_lowercase)
memcpy(dest, scp_data, count);
else
for (i = 0; i < count; i++)
dest[i] = tolower(scp_data[i]);
out:
dest[count] = '\0';
return count;
}
static void append_ipl_block_parm(void)
{
char *parm, *delim;
size_t len, rc = 0;
len = strlen(early_command_line);
delim = early_command_line + len; /* '\0' character position */
parm = early_command_line + len + 1; /* append right after '\0' */
switch (ipl_block.pb0_hdr.pbt) {
case IPL_PBT_CCW:
rc = ipl_block_get_ascii_vmparm(
parm, COMMAND_LINE_SIZE - len - 1, &ipl_block);
break;
case IPL_PBT_FCP:
case IPL_PBT_NVME:
case IPL_PBT_ECKD:
rc = ipl_block_get_ascii_scpdata(
parm, COMMAND_LINE_SIZE - len - 1, &ipl_block);
break;
}
if (rc) {
if (*parm == '=')
memmove(early_command_line, parm + 1, rc);
else
*delim = ' '; /* replace '\0' with space */
}
}
static inline int has_ebcdic_char(const char *str)
{
int i;
for (i = 0; str[i]; i++)
if (str[i] & 0x80)
return 1;
return 0;
}
void setup_boot_command_line(void)
{
parmarea.command_line[COMMAND_LINE_SIZE - 1] = 0;
/* convert arch command line to ascii if necessary */
if (has_ebcdic_char(parmarea.command_line))
EBCASC(parmarea.command_line, COMMAND_LINE_SIZE);
/* copy arch command line */
strscpy(early_command_line, strim(parmarea.command_line));
/* append IPL PARM data to the boot command line */
if (!is_prot_virt_guest() && ipl_block_valid)
append_ipl_block_parm();
}
static void modify_facility(unsigned long nr, bool clear)
{
if (clear)
__clear_facility(nr, stfle_fac_list);
else
__set_facility(nr, stfle_fac_list);
}
static void check_cleared_facilities(void)
{
unsigned long als[] = { FACILITIES_ALS };
int i;
for (i = 0; i < ARRAY_SIZE(als); i++) {
if ((stfle_fac_list[i] & als[i]) != als[i]) {
boot_emerg("The Linux kernel requires facilities cleared via command line option\n");
print_missing_facilities();
break;
}
}
}
static void modify_fac_list(char *str)
{
unsigned long val, endval;
char *endp;
bool clear;
while (*str) {
clear = false;
if (*str == '!') {
clear = true;
str++;
}
val = simple_strtoull(str, &endp, 0);
if (str == endp)
break;
str = endp;
if (*str == '-') {
str++;
endval = simple_strtoull(str, &endp, 0);
if (str == endp)
break;
str = endp;
while (val <= endval) {
modify_facility(val, clear);
val++;
}
} else {
modify_facility(val, clear);
}
if (*str != ',')
break;
str++;
}
check_cleared_facilities();
}
static char command_line_buf[COMMAND_LINE_SIZE];
void parse_boot_command_line(void)
{
char *param, *val;
bool enabled;
char *args;
int rc;
__kaslr_enabled = IS_ENABLED(CONFIG_RANDOMIZE_BASE);
strscpy(command_line_buf, early_command_line);
args = command_line_buf;
while (*args) {
args = next_arg(args, &param, &val);
if (!strcmp(param, "mem") && val)
memory_limit = round_down(memparse(val, NULL), PAGE_SIZE);
if (!strcmp(param, "vmalloc") && val) {
vmalloc_size = round_up(memparse(val, NULL), _SEGMENT_SIZE);
vmalloc_size_set = 1;
}
if (!strcmp(param, "dfltcc") && val) {
if (!strcmp(val, "off"))
zlib_dfltcc_support = ZLIB_DFLTCC_DISABLED;
else if (!strcmp(val, "on"))
zlib_dfltcc_support = ZLIB_DFLTCC_FULL;
else if (!strcmp(val, "def_only"))
zlib_dfltcc_support = ZLIB_DFLTCC_DEFLATE_ONLY;
else if (!strcmp(val, "inf_only"))
zlib_dfltcc_support = ZLIB_DFLTCC_INFLATE_ONLY;
else if (!strcmp(val, "always"))
zlib_dfltcc_support = ZLIB_DFLTCC_FULL_DEBUG;
}
if (!strcmp(param, "facilities") && val)
modify_fac_list(val);
s390/alternatives: Add debug functionality Similar to x86 and loongarch add a "debug-alternative" command line parameter, which allows for alternative debugging. The parameter itself comes with architecture specific semantics: "debug-alternative" -> print debug message for every single alternative "debug-alternative=0;2" -> print debug message for all alternatives with type 0 and 2 "debug-alternative=0:0-7" -> print debug message for all alternatives with type 0 which have a facility number within the range of 0-7 "debug-alternative=0:!8;1" -> print debug message for all alternatives with type 0, for all facility numbers, except facility 8, and in addition print all alternatives with type 1 A defconfig build currently results in a kernel with more than 20.000 alternatives, where the majority is for the niai alternative (spinlocks), and the relocated lowcore alternative. The following kernel command like options limit alternative debug output, and enable dynamic debug messages: debug-alternative=0:!49;1:!0 earlyprintk bootdebug ignore_loglevel loglevel=8 dyndbg="file alternative.c +p" This results in output like this: alt: [0/ 11] 0000021b9ce8680c: c0f400000089 -> c00400000000 alt: [0/ 64] 0000021b9ce87e60: c0f400000043 -> c00400000000 alt: [0/133] 0000021b9ce88c56: c0f400000027 -> c00400000000 alt: [0/ 74] 0000021b9ce89410: c0f40000002a -> c00400000000 alt: [0/ 40] 0000021b9dc3720a: 47000000 -> b280d398 alt: [0/193] 0000021b9dc37306: 47000000 -> b201d2b0 alt: [0/193] 0000021b9dc37354: c00400000000 -> d20720c0d2b0 alt: [1/ 5] 0000038d720d7bf2: c0f400000016 -> c00400000000 With [<alternative type>/<alternative data>] <address> oldcode -> newcode Alternative data depends on the alternative type: for type 0 (ALT_TYPE_FACILITY) data is the facility. For type 1 (ALT_TYPE_FEATURE) data is the corresponding machine feature. Acked-by: Vasily Gorbik <gor@linux.ibm.com> Signed-off-by: Heiko Carstens <hca@linux.ibm.com> Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
2025-02-07 15:49:11 +01:00
if (!strcmp(param, "debug-alternative"))
alt_debug_setup(val);
if (!strcmp(param, "nokaslr"))
__kaslr_enabled = 0;
if (!strcmp(param, "cmma")) {
rc = kstrtobool(val, &enabled);
if (!rc && !enabled)
cmma_flag = 0;
}
#if IS_ENABLED(CONFIG_KVM)
if (!strcmp(param, "prot_virt")) {
rc = kstrtobool(val, &enabled);
if (!rc && enabled)
prot_virt_host = 1;
}
#endif
if (!strcmp(param, "relocate_lowcore") && test_facility(193))
set_machine_feature(MFEATURE_LOWCORE);
if (!strcmp(param, "earlyprintk"))
boot_earlyprintk = true;
if (!strcmp(param, "debug"))
boot_console_loglevel = CONSOLE_LOGLEVEL_DEBUG;
if (!strcmp(param, "bootdebug")) {
bootdebug = true;
if (val)
strscpy(bootdebug_filter, val);
}
if (!strcmp(param, "quiet"))
boot_console_loglevel = CONSOLE_LOGLEVEL_QUIET;
if (!strcmp(param, "ignore_loglevel"))
boot_ignore_loglevel = true;
if (!strcmp(param, "loglevel")) {
boot_console_loglevel = simple_strtoull(val, NULL, 10);
if (boot_console_loglevel < CONSOLE_LOGLEVEL_MIN)
boot_console_loglevel = CONSOLE_LOGLEVEL_MIN;
}
}
}