Revision bbcd53c960713507ae764bf81970651b5577b95a authored by David Hildenbrand on 07 May 2021, 01:05:55 UTC, committed by Linus Torvalds on 07 May 2021, 07:26:34 UTC
Patch series "drivers/char: remove /dev/kmem for good". Exploring /dev/kmem and /dev/mem in the context of memory hot(un)plug and memory ballooning, I started questioning the existence of /dev/kmem. Comparing it with the /proc/kcore implementation, it does not seem to be able to deal with things like a) Pages unmapped from the direct mapping (e.g., to be used by secretmem) -> kern_addr_valid(). virt_addr_valid() is not sufficient. b) Special cases like gart aperture memory that is not to be touched -> mem_pfn_is_ram() Unless I am missing something, it's at least broken in some cases and might fault/crash the machine. Looks like its existence has been questioned before in 2005 and 2010 [1], after ~11 additional years, it might make sense to revive the discussion. CONFIG_DEVKMEM is only enabled in a single defconfig (on purpose or by mistake?). All distributions disable it: in Ubuntu it has been disabled for more than 10 years, in Debian since 2.6.31, in Fedora at least starting with FC3, in RHEL starting with RHEL4, in SUSE starting from 15sp2, and OpenSUSE has it disabled as well. 1) /dev/kmem was popular for rootkits [2] before it got disabled basically everywhere. Ubuntu documents [3] "There is no modern user of /dev/kmem any more beyond attackers using it to load kernel rootkits.". RHEL documents in a BZ [5] "it served no practical purpose other than to serve as a potential security problem or to enable binary module drivers to access structures/functions they shouldn't be touching" 2) /proc/kcore is a decent interface to have a controlled way to read kernel memory for debugging puposes. (will need some extensions to deal with memory offlining/unplug, memory ballooning, and poisoned pages, though) 3) It might be useful for corner case debugging [1]. KDB/KGDB might be a better fit, especially, to write random memory; harder to shoot yourself into the foot. 4) "Kernel Memory Editor" [4] hasn't seen any updates since 2000 and seems to be incompatible with 64bit [1]. For educational purposes, /proc/kcore might be used to monitor value updates -- or older kernels can be used. 5) It's broken on arm64, and therefore, completely disabled there. Looks like it's essentially unused and has been replaced by better suited interfaces for individual tasks (/proc/kcore, KDB/KGDB). Let's just remove it. [1] https://lwn.net/Articles/147901/ [2] https://www.linuxjournal.com/article/10505 [3] https://wiki.ubuntu.com/Security/Features#A.2Fdev.2Fkmem_disabled [4] https://sourceforge.net/projects/kme/ [5] https://bugzilla.redhat.com/show_bug.cgi?id=154796 Link: https://lkml.kernel.org/r/20210324102351.6932-1-david@redhat.com Link: https://lkml.kernel.org/r/20210324102351.6932-2-david@redhat.com Signed-off-by: David Hildenbrand <david@redhat.com> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Kees Cook <keescook@chromium.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "Alexander A. Klimov" <grandmaster@al2klimov.de> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Alexandre Belloni <alexandre.belloni@bootlin.com> Cc: Andrew Lunn <andrew@lunn.ch> Cc: Andrey Zhizhikin <andrey.zhizhikin@leica-geosystems.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Brian Cain <bcain@codeaurora.org> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Cc: Chris Zankel <chris@zankel.net> Cc: Corentin Labbe <clabbe@baylibre.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com> Cc: Greentime Hu <green.hu@gmail.com> Cc: Gregory Clement <gregory.clement@bootlin.com> Cc: Heiko Carstens <hca@linux.ibm.com> Cc: Helge Deller <deller@gmx.de> Cc: Hillf Danton <hdanton@sina.com> Cc: huang ying <huang.ying.caritas@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com> Cc: James Troup <james.troup@canonical.com> Cc: Jiaxun Yang <jiaxun.yang@flygoat.com> Cc: Jonas Bonn <jonas@southpole.se> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Kairui Song <kasong@redhat.com> Cc: Krzysztof Kozlowski <krzk@kernel.org> Cc: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Cc: Liviu Dudau <liviu.dudau@arm.com> Cc: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> Cc: Luc Van Oostenryck <luc.vanoostenryck@gmail.com> Cc: Luis Chamberlain <mcgrof@kernel.org> 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: Mike Rapoport <rppt@kernel.org> Cc: Mikulas Patocka <mpatocka@redhat.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Niklas Schnelle <schnelle@linux.ibm.com> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: openrisc@lists.librecores.org Cc: Palmer Dabbelt <palmerdabbelt@google.com> Cc: Paul Mackerras <paulus@samba.org> Cc: "Pavel Machek (CIP)" <pavel@denx.de> Cc: Pavel Machek <pavel@ucw.cz> Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org> Cc: Pierre Morel <pmorel@linux.ibm.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Rich Felker <dalias@libc.org> Cc: Robert Richter <rric@kernel.org> Cc: Rob Herring <robh@kernel.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Sam Ravnborg <sam@ravnborg.org> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com> Cc: sparclinux@vger.kernel.org Cc: Stafford Horne <shorne@gmail.com> Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Sudeep Holla <sudeep.holla@arm.com> Cc: Theodore Dubois <tblodt@icloud.com> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Viresh Kumar <viresh.kumar@linaro.org> Cc: William Cohen <wcohen@redhat.com> Cc: Xiaoming Ni <nixiaoming@huawei.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent cb152a1
bitmap.c
// SPDX-License-Identifier: GPL-2.0
/*
* linux/fs/hfsplus/bitmap.c
*
* Copyright (C) 2001
* Brad Boyer (flar@allandria.com)
* (C) 2003 Ardis Technologies <roman@ardistech.com>
*
* Handling of allocation file
*/
#include <linux/pagemap.h>
#include "hfsplus_fs.h"
#include "hfsplus_raw.h"
#define PAGE_CACHE_BITS (PAGE_SIZE * 8)
int hfsplus_block_allocate(struct super_block *sb, u32 size,
u32 offset, u32 *max)
{
struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
struct page *page;
struct address_space *mapping;
__be32 *pptr, *curr, *end;
u32 mask, start, len, n;
__be32 val;
int i;
len = *max;
if (!len)
return size;
hfs_dbg(BITMAP, "block_allocate: %u,%u,%u\n", size, offset, len);
mutex_lock(&sbi->alloc_mutex);
mapping = sbi->alloc_file->i_mapping;
page = read_mapping_page(mapping, offset / PAGE_CACHE_BITS, NULL);
if (IS_ERR(page)) {
start = size;
goto out;
}
pptr = kmap(page);
curr = pptr + (offset & (PAGE_CACHE_BITS - 1)) / 32;
i = offset % 32;
offset &= ~(PAGE_CACHE_BITS - 1);
if ((size ^ offset) / PAGE_CACHE_BITS)
end = pptr + PAGE_CACHE_BITS / 32;
else
end = pptr + ((size + 31) & (PAGE_CACHE_BITS - 1)) / 32;
/* scan the first partial u32 for zero bits */
val = *curr;
if (~val) {
n = be32_to_cpu(val);
mask = (1U << 31) >> i;
for (; i < 32; mask >>= 1, i++) {
if (!(n & mask))
goto found;
}
}
curr++;
/* scan complete u32s for the first zero bit */
while (1) {
while (curr < end) {
val = *curr;
if (~val) {
n = be32_to_cpu(val);
mask = 1 << 31;
for (i = 0; i < 32; mask >>= 1, i++) {
if (!(n & mask))
goto found;
}
}
curr++;
}
kunmap(page);
offset += PAGE_CACHE_BITS;
if (offset >= size)
break;
page = read_mapping_page(mapping, offset / PAGE_CACHE_BITS,
NULL);
if (IS_ERR(page)) {
start = size;
goto out;
}
curr = pptr = kmap(page);
if ((size ^ offset) / PAGE_CACHE_BITS)
end = pptr + PAGE_CACHE_BITS / 32;
else
end = pptr + ((size + 31) & (PAGE_CACHE_BITS - 1)) / 32;
}
hfs_dbg(BITMAP, "bitmap full\n");
start = size;
goto out;
found:
start = offset + (curr - pptr) * 32 + i;
if (start >= size) {
hfs_dbg(BITMAP, "bitmap full\n");
goto out;
}
/* do any partial u32 at the start */
len = min(size - start, len);
while (1) {
n |= mask;
if (++i >= 32)
break;
mask >>= 1;
if (!--len || n & mask)
goto done;
}
if (!--len)
goto done;
*curr++ = cpu_to_be32(n);
/* do full u32s */
while (1) {
while (curr < end) {
n = be32_to_cpu(*curr);
if (len < 32)
goto last;
if (n) {
len = 32;
goto last;
}
*curr++ = cpu_to_be32(0xffffffff);
len -= 32;
}
set_page_dirty(page);
kunmap(page);
offset += PAGE_CACHE_BITS;
page = read_mapping_page(mapping, offset / PAGE_CACHE_BITS,
NULL);
if (IS_ERR(page)) {
start = size;
goto out;
}
pptr = kmap(page);
curr = pptr;
end = pptr + PAGE_CACHE_BITS / 32;
}
last:
/* do any partial u32 at end */
mask = 1U << 31;
for (i = 0; i < len; i++) {
if (n & mask)
break;
n |= mask;
mask >>= 1;
}
done:
*curr = cpu_to_be32(n);
set_page_dirty(page);
kunmap(page);
*max = offset + (curr - pptr) * 32 + i - start;
sbi->free_blocks -= *max;
hfsplus_mark_mdb_dirty(sb);
hfs_dbg(BITMAP, "-> %u,%u\n", start, *max);
out:
mutex_unlock(&sbi->alloc_mutex);
return start;
}
int hfsplus_block_free(struct super_block *sb, u32 offset, u32 count)
{
struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
struct page *page;
struct address_space *mapping;
__be32 *pptr, *curr, *end;
u32 mask, len, pnr;
int i;
/* is there any actual work to be done? */
if (!count)
return 0;
hfs_dbg(BITMAP, "block_free: %u,%u\n", offset, count);
/* are all of the bits in range? */
if ((offset + count) > sbi->total_blocks)
return -ENOENT;
mutex_lock(&sbi->alloc_mutex);
mapping = sbi->alloc_file->i_mapping;
pnr = offset / PAGE_CACHE_BITS;
page = read_mapping_page(mapping, pnr, NULL);
if (IS_ERR(page))
goto kaboom;
pptr = kmap(page);
curr = pptr + (offset & (PAGE_CACHE_BITS - 1)) / 32;
end = pptr + PAGE_CACHE_BITS / 32;
len = count;
/* do any partial u32 at the start */
i = offset % 32;
if (i) {
int j = 32 - i;
mask = 0xffffffffU << j;
if (j > count) {
mask |= 0xffffffffU >> (i + count);
*curr++ &= cpu_to_be32(mask);
goto out;
}
*curr++ &= cpu_to_be32(mask);
count -= j;
}
/* do full u32s */
while (1) {
while (curr < end) {
if (count < 32)
goto done;
*curr++ = 0;
count -= 32;
}
if (!count)
break;
set_page_dirty(page);
kunmap(page);
page = read_mapping_page(mapping, ++pnr, NULL);
if (IS_ERR(page))
goto kaboom;
pptr = kmap(page);
curr = pptr;
end = pptr + PAGE_CACHE_BITS / 32;
}
done:
/* do any partial u32 at end */
if (count) {
mask = 0xffffffffU >> count;
*curr &= cpu_to_be32(mask);
}
out:
set_page_dirty(page);
kunmap(page);
sbi->free_blocks += len;
hfsplus_mark_mdb_dirty(sb);
mutex_unlock(&sbi->alloc_mutex);
return 0;
kaboom:
pr_crit("unable to mark blocks free: error %ld\n", PTR_ERR(page));
mutex_unlock(&sbi->alloc_mutex);
return -EIO;
}
Computing file changes ...
