Commit e47690d7 authored by Steven Price's avatar Steven Price Committed by Linus Torvalds

x86: mm: avoid allocating struct mm_struct on the stack

struct mm_struct is quite large (~1664 bytes) and so allocating on the
stack may cause problems as the kernel stack size is small.

Since ptdump_walk_pgd_level_core() was only allocating the structure so
that it could modify the pgd argument we can instead introduce a pgd
override in struct mm_walk and pass this down the call stack to where it
is needed.

Since the correct mm_struct is now being passed down, it is now also
unnecessary to take the mmap_sem semaphore because ptdump_walk_pgd() will
now take the semaphore on the real mm.

[steven.price@arm.com: restore missed arm64 changes]
  Link: http://lkml.kernel.org/r/20200108145710.34314-1-steven.price@arm.com
Link: http://lkml.kernel.org/r/20200108145710.34314-1-steven.price@arm.comSigned-off-by: default avatarSteven Price <steven.price@arm.com>
Reported-by: default avatarStephen Rothwell <sfr@canb.auug.org.au>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Hogan <jhogan@kernel.org>
Cc: James Morse <james.morse@arm.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: "Liang, Kan" <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Paul Burton <paul.burton@mips.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vineet Gupta <vgupta@synopsys.com>
Cc: Will Deacon <will@kernel.org>
Cc: Zong Li <zong.li@sifive.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent f8f0d0b6
......@@ -323,7 +323,7 @@ void ptdump_walk(struct seq_file *s, struct ptdump_info *info)
}
};
ptdump_walk_pgd(&st.ptdump, info->mm);
ptdump_walk_pgd(&st.ptdump, info->mm, NULL);
}
static void ptdump_initialize(void)
......@@ -361,7 +361,7 @@ void ptdump_check_wx(void)
}
};
ptdump_walk_pgd(&st.ptdump, &init_mm);
ptdump_walk_pgd(&st.ptdump, &init_mm, NULL);
if (st.wx_pages || st.uxn_pages)
pr_warn("Checked W+X mappings: FAILED, %lu W+X pages found, %lu non-UXN pages found\n",
......
......@@ -15,11 +15,8 @@ DEFINE_SHOW_ATTRIBUTE(ptdump);
static int ptdump_curknl_show(struct seq_file *m, void *v)
{
if (current->mm->pgd) {
down_read(&current->mm->mmap_sem);
if (current->mm->pgd)
ptdump_walk_pgd_level_debugfs(m, current->mm, false);
up_read(&current->mm->mmap_sem);
}
return 0;
}
......@@ -28,11 +25,8 @@ DEFINE_SHOW_ATTRIBUTE(ptdump_curknl);
#ifdef CONFIG_PAGE_TABLE_ISOLATION
static int ptdump_curusr_show(struct seq_file *m, void *v)
{
if (current->mm->pgd) {
down_read(&current->mm->mmap_sem);
if (current->mm->pgd)
ptdump_walk_pgd_level_debugfs(m, current->mm, true);
up_read(&current->mm->mmap_sem);
}
return 0;
}
......
......@@ -357,7 +357,8 @@ static void note_page(struct ptdump_state *pt_st, unsigned long addr, int level,
}
}
static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
static void ptdump_walk_pgd_level_core(struct seq_file *m,
struct mm_struct *mm, pgd_t *pgd,
bool checkwx, bool dmesg)
{
const struct ptdump_range ptdump_ranges[] = {
......@@ -386,12 +387,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
.seq = m
};
struct mm_struct fake_mm = {
.pgd = pgd
};
init_rwsem(&fake_mm.mmap_sem);
ptdump_walk_pgd(&st.ptdump, &fake_mm);
ptdump_walk_pgd(&st.ptdump, mm, pgd);
if (!checkwx)
return;
......@@ -404,7 +400,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
void ptdump_walk_pgd_level(struct seq_file *m, struct mm_struct *mm)
{
ptdump_walk_pgd_level_core(m, mm->pgd, false, true);
ptdump_walk_pgd_level_core(m, mm, mm->pgd, false, true);
}
void ptdump_walk_pgd_level_debugfs(struct seq_file *m, struct mm_struct *mm,
......@@ -415,7 +411,7 @@ void ptdump_walk_pgd_level_debugfs(struct seq_file *m, struct mm_struct *mm,
if (user && boot_cpu_has(X86_FEATURE_PTI))
pgd = kernel_to_user_pgdp(pgd);
#endif
ptdump_walk_pgd_level_core(m, pgd, false, false);
ptdump_walk_pgd_level_core(m, mm, pgd, false, false);
}
EXPORT_SYMBOL_GPL(ptdump_walk_pgd_level_debugfs);
......@@ -430,13 +426,13 @@ void ptdump_walk_user_pgd_level_checkwx(void)
pr_info("x86/mm: Checking user space page tables\n");
pgd = kernel_to_user_pgdp(pgd);
ptdump_walk_pgd_level_core(NULL, pgd, true, false);
ptdump_walk_pgd_level_core(NULL, &init_mm, pgd, true, false);
#endif
}
void ptdump_walk_pgd_level_checkwx(void)
{
ptdump_walk_pgd_level_core(NULL, INIT_PGD, true, false);
ptdump_walk_pgd_level_core(NULL, &init_mm, INIT_PGD, true, false);
}
static int __init pt_dump_init(void)
......
......@@ -74,6 +74,7 @@ enum page_walk_action {
* mm_walk - walk_page_range data
* @ops: operation to call during the walk
* @mm: mm_struct representing the target process of page table walk
* @pgd: pointer to PGD; only valid with no_vma (otherwise set to NULL)
* @vma: vma currently walked (NULL if walking outside vmas)
* @action: next action to perform (see enum page_walk_action)
* @no_vma: walk ignoring vmas (vma will always be NULL)
......@@ -84,6 +85,7 @@ enum page_walk_action {
struct mm_walk {
const struct mm_walk_ops *ops;
struct mm_struct *mm;
pgd_t *pgd;
struct vm_area_struct *vma;
enum page_walk_action action;
bool no_vma;
......@@ -95,6 +97,7 @@ int walk_page_range(struct mm_struct *mm, unsigned long start,
void *private);
int walk_page_range_novma(struct mm_struct *mm, unsigned long start,
unsigned long end, const struct mm_walk_ops *ops,
pgd_t *pgd,
void *private);
int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops,
void *private);
......
......@@ -17,6 +17,6 @@ struct ptdump_state {
const struct ptdump_range *range;
};
void ptdump_walk_pgd(struct ptdump_state *st, struct mm_struct *mm);
void ptdump_walk_pgd(struct ptdump_state *st, struct mm_struct *mm, pgd_t *pgd);
#endif /* _LINUX_PTDUMP_H */
......@@ -206,7 +206,10 @@ static int walk_pgd_range(unsigned long addr, unsigned long end,
const struct mm_walk_ops *ops = walk->ops;
int err = 0;
pgd = pgd_offset(walk->mm, addr);
if (walk->pgd)
pgd = walk->pgd + pgd_index(addr);
else
pgd = pgd_offset(walk->mm, addr);
do {
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd)) {
......@@ -436,11 +439,13 @@ int walk_page_range(struct mm_struct *mm, unsigned long start,
*/
int walk_page_range_novma(struct mm_struct *mm, unsigned long start,
unsigned long end, const struct mm_walk_ops *ops,
pgd_t *pgd,
void *private)
{
struct mm_walk walk = {
.ops = ops,
.mm = mm,
.pgd = pgd,
.private = private,
.no_vma = true
};
......
......@@ -122,14 +122,14 @@ static const struct mm_walk_ops ptdump_ops = {
.pte_hole = ptdump_hole,
};
void ptdump_walk_pgd(struct ptdump_state *st, struct mm_struct *mm)
void ptdump_walk_pgd(struct ptdump_state *st, struct mm_struct *mm, pgd_t *pgd)
{
const struct ptdump_range *range = st->range;
down_read(&mm->mmap_sem);
while (range->start != range->end) {
walk_page_range_novma(mm, range->start, range->end,
&ptdump_ops, st);
&ptdump_ops, pgd, st);
range++;
}
up_read(&mm->mmap_sem);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment