1
0
Fork 0
alistair23-linux/arch/x86/power/hibernate.c

281 lines
6.7 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* Hibernation support for x86
*
* Copyright (c) 2007 Rafael J. Wysocki <rjw@sisk.pl>
* Copyright (c) 2002 Pavel Machek <pavel@ucw.cz>
* Copyright (c) 2001 Patrick Mochel <mochel@osdl.org>
*/
#include <linux/gfp.h>
#include <linux/smp.h>
#include <linux/suspend.h>
#include <linux/scatterlist.h>
#include <linux/kdebug.h>
x86/power: Fix 'nosmt' vs hibernation triple fault during resume As explained in 0cc3cd21657b ("cpu/hotplug: Boot HT siblings at least once") we always, no matter what, have to bring up x86 HT siblings during boot at least once in order to avoid first MCE bringing the system to its knees. That means that whenever 'nosmt' is supplied on the kernel command-line, all the HT siblings are as a result sitting in mwait or cpudile after going through the online-offline cycle at least once. This causes a serious issue though when a kernel, which saw 'nosmt' on its commandline, is going to perform resume from hibernation: if the resume from the hibernated image is successful, cr3 is flipped in order to point to the address space of the kernel that is being resumed, which in turn means that all the HT siblings are all of a sudden mwaiting on address which is no longer valid. That results in triple fault shortly after cr3 is switched, and machine reboots. Fix this by always waking up all the SMT siblings before initiating the 'restore from hibernation' process; this guarantees that all the HT siblings will be properly carried over to the resumed kernel waiting in resume_play_dead(), and acted upon accordingly afterwards, based on the target kernel configuration. Symmetricaly, the resumed kernel has to push the SMT siblings to mwait again in case it has SMT disabled; this means it has to online all the siblings when resuming (so that they come out of hlt) and offline them again to let them reach mwait. Cc: 4.19+ <stable@vger.kernel.org> # v4.19+ Debugged-by: Thomas Gleixner <tglx@linutronix.de> Fixes: 0cc3cd21657b ("cpu/hotplug: Boot HT siblings at least once") Signed-off-by: Jiri Kosina <jkosina@suse.cz> Acked-by: Pavel Machek <pavel@ucw.cz> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2019-05-29 16:09:39 -06:00
#include <linux/cpu.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 22:32:42 -06:00
#include <linux/pgtable.h>
#include <crypto/hash.h>
#include <asm/e820/api.h>
#include <asm/init.h>
#include <asm/proto.h>
#include <asm/page.h>
#include <asm/mtrr.h>
#include <asm/sections.h>
#include <asm/suspend.h>
#include <asm/tlbflush.h>
/*
* Address to jump to in the last phase of restore in order to get to the image
* kernel's text (this value is passed in the image header).
*/
unsigned long restore_jump_address __visible;
unsigned long jump_address_phys;
/*
* Value of the cr3 register from before the hibernation (this value is passed
* in the image header).
*/
unsigned long restore_cr3 __visible;
unsigned long temp_pgt __visible;
unsigned long relocated_restore_code __visible;
/**
* pfn_is_nosave - check if given pfn is in the 'nosave' section
*/
int pfn_is_nosave(unsigned long pfn)
{
unsigned long nosave_begin_pfn;
unsigned long nosave_end_pfn;
nosave_begin_pfn = __pa_symbol(&__nosave_begin) >> PAGE_SHIFT;
nosave_end_pfn = PAGE_ALIGN(__pa_symbol(&__nosave_end)) >> PAGE_SHIFT;
return pfn >= nosave_begin_pfn && pfn < nosave_end_pfn;
}
#define MD5_DIGEST_SIZE 16
struct restore_data_record {
unsigned long jump_address;
unsigned long jump_address_phys;
unsigned long cr3;
unsigned long magic;
u8 e820_digest[MD5_DIGEST_SIZE];
};
#if IS_BUILTIN(CONFIG_CRYPTO_MD5)
/**
* get_e820_md5 - calculate md5 according to given e820 table
*
* @table: the e820 table to be calculated
* @buf: the md5 result to be stored to
*/
static int get_e820_md5(struct e820_table *table, void *buf)
{
struct crypto_shash *tfm;
struct shash_desc *desc;
int size;
int ret = 0;
tfm = crypto_alloc_shash("md5", 0, 0);
if (IS_ERR(tfm))
return -ENOMEM;
desc = kmalloc(sizeof(struct shash_desc) + crypto_shash_descsize(tfm),
GFP_KERNEL);
if (!desc) {
ret = -ENOMEM;
goto free_tfm;
}
desc->tfm = tfm;
size = offsetof(struct e820_table, entries) +
sizeof(struct e820_entry) * table->nr_entries;
if (crypto_shash_digest(desc, (u8 *)table, size, buf))
ret = -EINVAL;
mm, treewide: rename kzfree() to kfree_sensitive() As said by Linus: A symmetric naming is only helpful if it implies symmetries in use. Otherwise it's actively misleading. In "kzalloc()", the z is meaningful and an important part of what the caller wants. In "kzfree()", the z is actively detrimental, because maybe in the future we really _might_ want to use that "memfill(0xdeadbeef)" or something. The "zero" part of the interface isn't even _relevant_. The main reason that kzfree() exists is to clear sensitive information that should not be leaked to other future users of the same memory objects. Rename kzfree() to kfree_sensitive() to follow the example of the recently added kvfree_sensitive() and make the intention of the API more explicit. In addition, memzero_explicit() is used to clear the memory to make sure that it won't get optimized away by the compiler. The renaming is done by using the command sequence: git grep -w --name-only kzfree |\ xargs sed -i 's/kzfree/kfree_sensitive/' followed by some editing of the kfree_sensitive() kerneldoc and adding a kzfree backward compatibility macro in slab.h. [akpm@linux-foundation.org: fs/crypto/inline_crypt.c needs linux/slab.h] [akpm@linux-foundation.org: fix fs/crypto/inline_crypt.c some more] Suggested-by: Joe Perches <joe@perches.com> Signed-off-by: Waiman Long <longman@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: David Howells <dhowells@redhat.com> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com> Cc: James Morris <jmorris@namei.org> Cc: "Serge E. Hallyn" <serge@hallyn.com> Cc: Joe Perches <joe@perches.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: David Rientjes <rientjes@google.com> Cc: Dan Carpenter <dan.carpenter@oracle.com> Cc: "Jason A . Donenfeld" <Jason@zx2c4.com> Link: http://lkml.kernel.org/r/20200616154311.12314-3-longman@redhat.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-08-07 00:18:13 -06:00
kfree_sensitive(desc);
free_tfm:
crypto_free_shash(tfm);
return ret;
}
static int hibernation_e820_save(void *buf)
{
return get_e820_md5(e820_table_firmware, buf);
}
static bool hibernation_e820_mismatch(void *buf)
{
int ret;
u8 result[MD5_DIGEST_SIZE];
memset(result, 0, MD5_DIGEST_SIZE);
/* If there is no digest in suspend kernel, let it go. */
if (!memcmp(result, buf, MD5_DIGEST_SIZE))
return false;
ret = get_e820_md5(e820_table_firmware, result);
if (ret)
return true;
return memcmp(result, buf, MD5_DIGEST_SIZE) ? true : false;
}
#else
static int hibernation_e820_save(void *buf)
{
return 0;
}
static bool hibernation_e820_mismatch(void *buf)
{
/* If md5 is not builtin for restore kernel, let it go. */
return false;
}
#endif
#ifdef CONFIG_X86_64
#define RESTORE_MAGIC 0x23456789ABCDEF01UL
#else
#define RESTORE_MAGIC 0x12345678UL
#endif
/**
* arch_hibernation_header_save - populate the architecture specific part
* of a hibernation image header
* @addr: address to save the data at
*/
int arch_hibernation_header_save(void *addr, unsigned int max_size)
{
struct restore_data_record *rdr = addr;
if (max_size < sizeof(struct restore_data_record))
return -EOVERFLOW;
rdr->magic = RESTORE_MAGIC;
rdr->jump_address = (unsigned long)restore_registers;
rdr->jump_address_phys = __pa_symbol(restore_registers);
/*
* The restore code fixes up CR3 and CR4 in the following sequence:
*
* [in hibernation asm]
* 1. CR3 <= temporary page tables
* 2. CR4 <= mmu_cr4_features (from the kernel that restores us)
* 3. CR3 <= rdr->cr3
* 4. CR4 <= mmu_cr4_features (from us, i.e. the image kernel)
* [in restore_processor_state()]
* 5. CR4 <= saved CR4
* 6. CR3 <= saved CR3
*
* Our mmu_cr4_features has CR4.PCIDE=0, and toggling
* CR4.PCIDE while CR3's PCID bits are nonzero is illegal, so
* rdr->cr3 needs to point to valid page tables but must not
* have any of the PCID bits set.
*/
rdr->cr3 = restore_cr3 & ~CR3_PCID_MASK;
return hibernation_e820_save(rdr->e820_digest);
}
/**
* arch_hibernation_header_restore - read the architecture specific data
* from the hibernation image header
* @addr: address to read the data from
*/
int arch_hibernation_header_restore(void *addr)
{
struct restore_data_record *rdr = addr;
if (rdr->magic != RESTORE_MAGIC) {
pr_crit("Unrecognized hibernate image header format!\n");
return -EINVAL;
}
restore_jump_address = rdr->jump_address;
jump_address_phys = rdr->jump_address_phys;
restore_cr3 = rdr->cr3;
if (hibernation_e820_mismatch(rdr->e820_digest)) {
pr_crit("Hibernate inconsistent memory map detected!\n");
return -ENODEV;
}
return 0;
}
int relocate_restore_code(void)
{
pgd_t *pgd;
p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
relocated_restore_code = get_safe_page(GFP_ATOMIC);
if (!relocated_restore_code)
return -ENOMEM;
memcpy((void *)relocated_restore_code, core_restore_code, PAGE_SIZE);
/* Make the page containing the relocated code executable */
pgd = (pgd_t *)__va(read_cr3_pa()) +
pgd_index(relocated_restore_code);
p4d = p4d_offset(pgd, relocated_restore_code);
if (p4d_large(*p4d)) {
set_p4d(p4d, __p4d(p4d_val(*p4d) & ~_PAGE_NX));
goto out;
}
pud = pud_offset(p4d, relocated_restore_code);
if (pud_large(*pud)) {
set_pud(pud, __pud(pud_val(*pud) & ~_PAGE_NX));
goto out;
}
pmd = pmd_offset(pud, relocated_restore_code);
if (pmd_large(*pmd)) {
set_pmd(pmd, __pmd(pmd_val(*pmd) & ~_PAGE_NX));
goto out;
}
pte = pte_offset_kernel(pmd, relocated_restore_code);
set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_NX));
out:
__flush_tlb_all();
return 0;
}
x86/power: Fix 'nosmt' vs hibernation triple fault during resume As explained in 0cc3cd21657b ("cpu/hotplug: Boot HT siblings at least once") we always, no matter what, have to bring up x86 HT siblings during boot at least once in order to avoid first MCE bringing the system to its knees. That means that whenever 'nosmt' is supplied on the kernel command-line, all the HT siblings are as a result sitting in mwait or cpudile after going through the online-offline cycle at least once. This causes a serious issue though when a kernel, which saw 'nosmt' on its commandline, is going to perform resume from hibernation: if the resume from the hibernated image is successful, cr3 is flipped in order to point to the address space of the kernel that is being resumed, which in turn means that all the HT siblings are all of a sudden mwaiting on address which is no longer valid. That results in triple fault shortly after cr3 is switched, and machine reboots. Fix this by always waking up all the SMT siblings before initiating the 'restore from hibernation' process; this guarantees that all the HT siblings will be properly carried over to the resumed kernel waiting in resume_play_dead(), and acted upon accordingly afterwards, based on the target kernel configuration. Symmetricaly, the resumed kernel has to push the SMT siblings to mwait again in case it has SMT disabled; this means it has to online all the siblings when resuming (so that they come out of hlt) and offline them again to let them reach mwait. Cc: 4.19+ <stable@vger.kernel.org> # v4.19+ Debugged-by: Thomas Gleixner <tglx@linutronix.de> Fixes: 0cc3cd21657b ("cpu/hotplug: Boot HT siblings at least once") Signed-off-by: Jiri Kosina <jkosina@suse.cz> Acked-by: Pavel Machek <pavel@ucw.cz> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2019-05-29 16:09:39 -06:00
int arch_resume_nosmt(void)
{
int ret = 0;
/*
* We reached this while coming out of hibernation. This means
* that SMT siblings are sleeping in hlt, as mwait is not safe
* against control transition during resume (see comment in
* hibernate_resume_nonboot_cpu_disable()).
*
* If the resumed kernel has SMT disabled, we have to take all the
* SMT siblings out of hlt, and offline them again so that they
* end up in mwait proper.
*
* Called with hotplug disabled.
*/
cpu_hotplug_enable();
if (cpu_smt_control == CPU_SMT_DISABLED ||
cpu_smt_control == CPU_SMT_FORCE_DISABLED) {
enum cpuhp_smt_control old = cpu_smt_control;
ret = cpuhp_smt_enable();
if (ret)
goto out;
ret = cpuhp_smt_disable(old);
if (ret)
goto out;
}
out:
cpu_hotplug_disable();
return ret;
}