linux-stable/drivers/xen/grant-table.c

1700 lines
42 KiB
C
Raw Normal View History

/******************************************************************************
* grant_table.c
*
* Granting foreign access to our memory reservation.
*
* Copyright (c) 2005-2006, Christopher Clark
* Copyright (c) 2004-2005, K A Fraser
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License version 2
* as published by the Free Software Foundation; or, when distributed
* separately from the Linux kernel or incorporated into other
* software packages, subject to the following license:
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this source file (the "Software"), to deal in the Software without
* restriction, including without limitation the rights to use, copy, modify,
* merge, publish, distribute, sublicense, and/or sell copies of the Software,
* and to permit persons to whom the Software is furnished to do so, subject to
* the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
* IN THE SOFTWARE.
*/
#define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt
#include <linux/bitmap.h>
mm: remove include/linux/bootmem.h Move remaining definitions and declarations from include/linux/bootmem.h into include/linux/memblock.h and remove the redundant header. The includes were replaced with the semantic patch below and then semi-automated removal of duplicated '#include <linux/memblock.h> @@ @@ - #include <linux/bootmem.h> + #include <linux/memblock.h> [sfr@canb.auug.org.au: dma-direct: fix up for the removal of linux/bootmem.h] Link: http://lkml.kernel.org/r/20181002185342.133d1680@canb.auug.org.au [sfr@canb.auug.org.au: powerpc: fix up for removal of linux/bootmem.h] Link: http://lkml.kernel.org/r/20181005161406.73ef8727@canb.auug.org.au [sfr@canb.auug.org.au: x86/kaslr, ACPI/NUMA: fix for linux/bootmem.h removal] Link: http://lkml.kernel.org/r/20181008190341.5e396491@canb.auug.org.au Link: http://lkml.kernel.org/r/1536927045-23536-30-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Acked-by: Michal Hocko <mhocko@suse.com> 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 Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Ingo Molnar <mingo@redhat.com> Cc: "James E.J. Bottomley" <jejb@parisc-linux.org> Cc: Jonas Bonn <jonas@southpole.se> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Ley Foon Tan <lftan@altera.com> Cc: Mark Salter <msalter@redhat.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Palmer Dabbelt <palmer@sifive.com> Cc: Paul Burton <paul.burton@mips.com> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: Richard Weinberger <richard@nod.at> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Serge Semin <fancer.lancer@gmail.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Cc: Vineet Gupta <vgupta@synopsys.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>
2018-10-30 22:09:49 +00:00
#include <linux/memblock.h>
#include <linux/sched.h>
#include <linux/mm.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/uaccess.h>
#include <linux/io.h>
xen/gndev: Xen backend support for paged out grant targets V4. Since Xen-4.2, hvm domains may have portions of their memory paged out. When a foreign domain (such as dom0) attempts to map these frames, the map will initially fail. The hypervisor returns a suitable errno, and kicks an asynchronous page-in operation carried out by a helper. The foreign domain is expected to retry the mapping operation until it eventually succeeds. The foreign domain is not put to sleep because itself could be the one running the pager assist (typical scenario for dom0). This patch adds support for this mechanism for backend drivers using grant mapping and copying operations. Specifically, this covers the blkback and gntdev drivers (which map foreign grants), and the netback driver (which copies foreign grants). * Add a retry method for grants that fail with GNTST_eagain (i.e. because the target foreign frame is paged out). * Insert hooks with appropriate wrappers in the aforementioned drivers. The retry loop is only invoked if the grant operation status is GNTST_eagain. It guarantees to leave a new status code different from GNTST_eagain. Any other status code results in identical code execution as before. The retry loop performs 256 attempts with increasing time intervals through a 32 second period. It uses msleep to yield while waiting for the next retry. V2 after feedback from David Vrabel: * Explicit MAX_DELAY instead of wrap-around delay into zero * Abstract GNTST_eagain check into core grant table code for netback module. V3 after feedback from Ian Campbell: * Add placeholder in array of grant table error descriptions for unrelated error code we jump over. * Eliminate single map and retry macro in favor of a generic batch flavor. * Some renaming. * Bury most implementation in grant_table.c, cleaner interface. V4 rebased on top of sync of Xen grant table interface headers. Signed-off-by: Andres Lagar-Cavilla <andres@lagarcavilla.org> Acked-by: Ian Campbell <ian.campbell@citrix.com> [v5: Fixed whitespace issues] Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
2012-09-14 14:26:59 +00:00
#include <linux/delay.h>
#include <linux/hardirq.h>
#include <linux/workqueue.h>
#include <linux/ratelimit.h>
#include <linux/moduleparam.h>
#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
#include <linux/dma-mapping.h>
#endif
#include <xen/xen.h>
#include <xen/interface/xen.h>
#include <xen/page.h>
#include <xen/grant_table.h>
#include <xen/interface/memory.h>
#include <xen/hvc-console.h>
#include <xen/swiotlb-xen.h>
#include <xen/balloon.h>
#ifdef CONFIG_X86
#include <asm/xen/cpuid.h>
#endif
#include <xen/mem-reservation.h>
#include <asm/xen/hypercall.h>
#include <asm/xen/interface.h>
#include <asm/sync_bitops.h>
#define GNTTAB_LIST_END 0xffffffff
static grant_ref_t **gnttab_list;
static unsigned int nr_grant_frames;
/*
* Handling of free grants:
*
* Free grants are in a simple list anchored in gnttab_free_head. They are
* linked by grant ref, the last element contains GNTTAB_LIST_END. The number
* of free entries is stored in gnttab_free_count.
* Additionally there is a bitmap of free entries anchored in
* gnttab_free_bitmap. This is being used for simplifying allocation of
* multiple consecutive grants, which is needed e.g. for support of virtio.
* gnttab_last_free is used to add free entries of new frames at the end of
* the free list.
* gnttab_free_tail_ptr specifies the variable which references the start
* of consecutive free grants ending with gnttab_last_free. This pointer is
* updated in a rather defensive way, in order to avoid performance hits in
* hot paths.
* All those variables are protected by gnttab_list_lock.
*/
static int gnttab_free_count;
static unsigned int gnttab_size;
static grant_ref_t gnttab_free_head = GNTTAB_LIST_END;
static grant_ref_t gnttab_last_free = GNTTAB_LIST_END;
static grant_ref_t *gnttab_free_tail_ptr;
static unsigned long *gnttab_free_bitmap;
static DEFINE_SPINLOCK(gnttab_list_lock);
struct grant_frames xen_auto_xlat_grant_frames;
static unsigned int xen_gnttab_version;
module_param_named(version, xen_gnttab_version, uint, 0);
static union {
struct grant_entry_v1 *v1;
union grant_entry_v2 *v2;
void *addr;
} gnttab_shared;
/*This is a structure of function pointers for grant table*/
struct gnttab_ops {
/*
* Version of the grant interface.
*/
unsigned int version;
/*
* Grant refs per grant frame.
*/
unsigned int grefs_per_grant_frame;
/*
* Mapping a list of frames for storing grant entries. Frames parameter
* is used to store grant table address when grant table being setup,
* nr_gframes is the number of frames to map grant table. Returning
* GNTST_okay means success and negative value means failure.
*/
int (*map_frames)(xen_pfn_t *frames, unsigned int nr_gframes);
/*
* Release a list of frames which are mapped in map_frames for grant
* entry status.
*/
void (*unmap_frames)(void);
/*
* Introducing a valid entry into the grant table, granting the frame of
* this grant entry to domain for accessing. Ref
* parameter is reference of this introduced grant entry, domid is id of
* granted domain, frame is the page frame to be granted, and flags is
* status of the grant entry to be updated.
*/
void (*update_entry)(grant_ref_t ref, domid_t domid,
unsigned long frame, unsigned flags);
/*
* Stop granting a grant entry to domain for accessing. Ref parameter is
* reference of a grant entry whose grant access will be stopped.
* If the grant entry is currently mapped for reading or writing, just
* return failure(==0) directly and don't tear down the grant access.
* Otherwise, stop grant access for this entry and return success(==1).
*/
int (*end_foreign_access_ref)(grant_ref_t ref);
/*
* Read the frame number related to a given grant reference.
*/
unsigned long (*read_frame)(grant_ref_t ref);
};
struct unmap_refs_callback_data {
struct completion completion;
int result;
};
static const struct gnttab_ops *gnttab_interface;
/* This reflects status of grant entries, so act as a global value. */
static grant_status_t *grstatus;
static struct gnttab_free_callback *gnttab_free_callback_list;
static int gnttab_expand(unsigned int req_entries);
#define RPP (PAGE_SIZE / sizeof(grant_ref_t))
#define SPP (PAGE_SIZE / sizeof(grant_status_t))
static inline grant_ref_t *__gnttab_entry(grant_ref_t entry)
{
return &gnttab_list[(entry) / RPP][(entry) % RPP];
}
/* This can be used as an l-value */
#define gnttab_entry(entry) (*__gnttab_entry(entry))
static int get_free_entries(unsigned count)
{
unsigned long flags;
int ref, rc = 0;
grant_ref_t head;
spin_lock_irqsave(&gnttab_list_lock, flags);
if ((gnttab_free_count < count) &&
((rc = gnttab_expand(count - gnttab_free_count)) < 0)) {
spin_unlock_irqrestore(&gnttab_list_lock, flags);
return rc;
}
ref = head = gnttab_free_head;
gnttab_free_count -= count;
while (count--) {
bitmap_clear(gnttab_free_bitmap, head, 1);
if (gnttab_free_tail_ptr == __gnttab_entry(head))
gnttab_free_tail_ptr = &gnttab_free_head;
if (count)
head = gnttab_entry(head);
}
gnttab_free_head = gnttab_entry(head);
gnttab_entry(head) = GNTTAB_LIST_END;
if (!gnttab_free_count) {
gnttab_last_free = GNTTAB_LIST_END;
gnttab_free_tail_ptr = NULL;
}
spin_unlock_irqrestore(&gnttab_list_lock, flags);
return ref;
}
static int get_seq_entry_count(void)
{
if (gnttab_last_free == GNTTAB_LIST_END || !gnttab_free_tail_ptr ||
*gnttab_free_tail_ptr == GNTTAB_LIST_END)
return 0;
return gnttab_last_free - *gnttab_free_tail_ptr + 1;
}
/* Rebuilds the free grant list and tries to find count consecutive entries. */
static int get_free_seq(unsigned int count)
{
int ret = -ENOSPC;
unsigned int from, to;
grant_ref_t *last;
gnttab_free_tail_ptr = &gnttab_free_head;
last = &gnttab_free_head;
for (from = find_first_bit(gnttab_free_bitmap, gnttab_size);
from < gnttab_size;
from = find_next_bit(gnttab_free_bitmap, gnttab_size, to + 1)) {
to = find_next_zero_bit(gnttab_free_bitmap, gnttab_size,
from + 1);
if (ret < 0 && to - from >= count) {
ret = from;
bitmap_clear(gnttab_free_bitmap, ret, count);
from += count;
gnttab_free_count -= count;
if (from == to)
continue;
}
/*
* Recreate the free list in order to have it properly sorted.
* This is needed to make sure that the free tail has the maximum
* possible size.
*/
while (from < to) {
*last = from;
last = __gnttab_entry(from);
gnttab_last_free = from;
from++;
}
if (to < gnttab_size)
gnttab_free_tail_ptr = __gnttab_entry(to - 1);
}
*last = GNTTAB_LIST_END;
if (gnttab_last_free != gnttab_size - 1)
gnttab_free_tail_ptr = NULL;
return ret;
}
static int get_free_entries_seq(unsigned int count)
{
unsigned long flags;
int ret = 0;
spin_lock_irqsave(&gnttab_list_lock, flags);
if (gnttab_free_count < count) {
ret = gnttab_expand(count - gnttab_free_count);
if (ret < 0)
goto out;
}
if (get_seq_entry_count() < count) {
ret = get_free_seq(count);
if (ret >= 0)
goto out;
ret = gnttab_expand(count - get_seq_entry_count());
if (ret < 0)
goto out;
}
ret = *gnttab_free_tail_ptr;
*gnttab_free_tail_ptr = gnttab_entry(ret + count - 1);
gnttab_free_count -= count;
if (!gnttab_free_count)
gnttab_free_tail_ptr = NULL;
bitmap_clear(gnttab_free_bitmap, ret, count);
out:
spin_unlock_irqrestore(&gnttab_list_lock, flags);
return ret;
}
static void do_free_callbacks(void)
{
struct gnttab_free_callback *callback, *next;
callback = gnttab_free_callback_list;
gnttab_free_callback_list = NULL;
while (callback != NULL) {
next = callback->next;
if (gnttab_free_count >= callback->count) {
callback->next = NULL;
callback->fn(callback->arg);
} else {
callback->next = gnttab_free_callback_list;
gnttab_free_callback_list = callback;
}
callback = next;
}
}
static inline void check_free_callbacks(void)
{
if (unlikely(gnttab_free_callback_list))
do_free_callbacks();
}
static void put_free_entry_locked(grant_ref_t ref)
{
if (unlikely(ref < GNTTAB_NR_RESERVED_ENTRIES))
return;
gnttab_entry(ref) = gnttab_free_head;
gnttab_free_head = ref;
if (!gnttab_free_count)
gnttab_last_free = ref;
if (gnttab_free_tail_ptr == &gnttab_free_head)
gnttab_free_tail_ptr = __gnttab_entry(ref);
gnttab_free_count++;
bitmap_set(gnttab_free_bitmap, ref, 1);
}
static void put_free_entry(grant_ref_t ref)
{
unsigned long flags;
spin_lock_irqsave(&gnttab_list_lock, flags);
put_free_entry_locked(ref);
check_free_callbacks();
spin_unlock_irqrestore(&gnttab_list_lock, flags);
}
static void gnttab_set_free(unsigned int start, unsigned int n)
{
unsigned int i;
for (i = start; i < start + n - 1; i++)
gnttab_entry(i) = i + 1;
gnttab_entry(i) = GNTTAB_LIST_END;
if (!gnttab_free_count) {
gnttab_free_head = start;
gnttab_free_tail_ptr = &gnttab_free_head;
} else {
gnttab_entry(gnttab_last_free) = start;
}
gnttab_free_count += n;
gnttab_last_free = i;
bitmap_set(gnttab_free_bitmap, start, n);
}
/*
* Following applies to gnttab_update_entry_v1 and gnttab_update_entry_v2.
* Introducing a valid entry into the grant table:
* 1. Write ent->domid.
* 2. Write ent->frame: Frame to which access is permitted.
* 3. Write memory barrier (WMB).
* 4. Write ent->flags, inc. valid type.
*/
static void gnttab_update_entry_v1(grant_ref_t ref, domid_t domid,
unsigned long frame, unsigned flags)
{
gnttab_shared.v1[ref].domid = domid;
gnttab_shared.v1[ref].frame = frame;
wmb();
gnttab_shared.v1[ref].flags = flags;
}
static void gnttab_update_entry_v2(grant_ref_t ref, domid_t domid,
unsigned long frame, unsigned int flags)
{
gnttab_shared.v2[ref].hdr.domid = domid;
gnttab_shared.v2[ref].full_page.frame = frame;
wmb(); /* Hypervisor concurrent accesses. */
gnttab_shared.v2[ref].hdr.flags = GTF_permit_access | flags;
}
/*
* Public grant-issuing interface functions
*/
void gnttab_grant_foreign_access_ref(grant_ref_t ref, domid_t domid,
unsigned long frame, int readonly)
{
gnttab_interface->update_entry(ref, domid, frame,
GTF_permit_access | (readonly ? GTF_readonly : 0));
}
EXPORT_SYMBOL_GPL(gnttab_grant_foreign_access_ref);
int gnttab_grant_foreign_access(domid_t domid, unsigned long frame,
int readonly)
{
int ref;
ref = get_free_entries(1);
if (unlikely(ref < 0))
return -ENOSPC;
gnttab_grant_foreign_access_ref(ref, domid, frame, readonly);
return ref;
}
EXPORT_SYMBOL_GPL(gnttab_grant_foreign_access);
static int gnttab_end_foreign_access_ref_v1(grant_ref_t ref)
{
u16 *pflags = &gnttab_shared.v1[ref].flags;
u16 flags;
flags = *pflags;
do {
if (flags & (GTF_reading|GTF_writing))
return 0;
} while (!sync_try_cmpxchg(pflags, &flags, 0));
return 1;
}
static int gnttab_end_foreign_access_ref_v2(grant_ref_t ref)
{
gnttab_shared.v2[ref].hdr.flags = 0;
mb(); /* Concurrent access by hypervisor. */
if (grstatus[ref] & (GTF_reading|GTF_writing)) {
return 0;
} else {
/*
* The read of grstatus needs to have acquire semantics.
* On x86, reads already have that, and we just need to
* protect against compiler reorderings.
* On other architectures we may need a full barrier.
*/
#ifdef CONFIG_X86
barrier();
#else
mb();
#endif
}
return 1;
}
static inline int _gnttab_end_foreign_access_ref(grant_ref_t ref)
{
return gnttab_interface->end_foreign_access_ref(ref);
}
int gnttab_end_foreign_access_ref(grant_ref_t ref)
{
if (_gnttab_end_foreign_access_ref(ref))
return 1;
pr_warn("WARNING: g.e. %#x still in use!\n", ref);
return 0;
}
EXPORT_SYMBOL_GPL(gnttab_end_foreign_access_ref);
static unsigned long gnttab_read_frame_v1(grant_ref_t ref)
{
return gnttab_shared.v1[ref].frame;
}
static unsigned long gnttab_read_frame_v2(grant_ref_t ref)
{
return gnttab_shared.v2[ref].full_page.frame;
}
struct deferred_entry {
struct list_head list;
grant_ref_t ref;
uint16_t warn_delay;
struct page *page;
};
static LIST_HEAD(deferred_list);
static void gnttab_handle_deferred(struct timer_list *);
timer: Remove expires and data arguments from DEFINE_TIMER Drop the arguments from the macro and adjust all callers with the following script: perl -pi -e 's/DEFINE_TIMER\((.*), 0, 0\);/DEFINE_TIMER($1);/g;' \ $(git grep DEFINE_TIMER | cut -d: -f1 | sort -u | grep -v timer.h) Signed-off-by: Kees Cook <keescook@chromium.org> Acked-by: Geert Uytterhoeven <geert@linux-m68k.org> # for m68k parts Acked-by: Guenter Roeck <linux@roeck-us.net> # for watchdog parts Acked-by: David S. Miller <davem@davemloft.net> # for networking parts Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Acked-by: Kalle Valo <kvalo@codeaurora.org> # for wireless parts Acked-by: Arnd Bergmann <arnd@arndb.de> Cc: linux-mips@linux-mips.org Cc: Petr Mladek <pmladek@suse.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Lai Jiangshan <jiangshanlai@gmail.com> Cc: Sebastian Reichel <sre@kernel.org> Cc: Kalle Valo <kvalo@qca.qualcomm.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Pavel Machek <pavel@ucw.cz> Cc: linux1394-devel@lists.sourceforge.net Cc: Chris Metcalf <cmetcalf@mellanox.com> Cc: linux-s390@vger.kernel.org Cc: linux-wireless@vger.kernel.org Cc: "James E.J. Bottomley" <jejb@linux.vnet.ibm.com> Cc: Wim Van Sebroeck <wim@iguana.be> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Ursula Braun <ubraun@linux.vnet.ibm.com> Cc: Viresh Kumar <viresh.kumar@linaro.org> Cc: Harish Patil <harish.patil@cavium.com> Cc: Stephen Boyd <sboyd@codeaurora.org> Cc: Michael Reed <mdr@sgi.com> Cc: Manish Chopra <manish.chopra@cavium.com> Cc: Len Brown <len.brown@intel.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: linux-pm@vger.kernel.org Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Julian Wiedmann <jwi@linux.vnet.ibm.com> Cc: John Stultz <john.stultz@linaro.org> Cc: Mark Gross <mark.gross@intel.com> Cc: linux-watchdog@vger.kernel.org Cc: linux-scsi@vger.kernel.org Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Stefan Richter <stefanr@s5r6.in-berlin.de> Cc: Guenter Roeck <linux@roeck-us.net> Cc: netdev@vger.kernel.org Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: linuxppc-dev@lists.ozlabs.org Cc: Sudip Mukherjee <sudipm.mukherjee@gmail.com> Link: https://lkml.kernel.org/r/1507159627-127660-11-git-send-email-keescook@chromium.org Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2017-10-04 23:27:04 +00:00
static DEFINE_TIMER(deferred_timer, gnttab_handle_deferred);
static atomic64_t deferred_count;
static atomic64_t leaked_count;
static unsigned int free_per_iteration = 10;
module_param(free_per_iteration, uint, 0600);
static void gnttab_handle_deferred(struct timer_list *unused)
{
unsigned int nr = READ_ONCE(free_per_iteration);
const bool ignore_limit = nr == 0;
struct deferred_entry *first = NULL;
unsigned long flags;
size_t freed = 0;
spin_lock_irqsave(&gnttab_list_lock, flags);
while ((ignore_limit || nr--) && !list_empty(&deferred_list)) {
struct deferred_entry *entry
= list_first_entry(&deferred_list,
struct deferred_entry, list);
if (entry == first)
break;
list_del(&entry->list);
spin_unlock_irqrestore(&gnttab_list_lock, flags);
if (_gnttab_end_foreign_access_ref(entry->ref)) {
uint64_t ret = atomic64_dec_return(&deferred_count);
put_free_entry(entry->ref);
pr_debug("freeing g.e. %#x (pfn %#lx), %llu remaining\n",
entry->ref, page_to_pfn(entry->page),
(unsigned long long)ret);
put_page(entry->page);
freed++;
kfree(entry);
entry = NULL;
} else {
if (!--entry->warn_delay)
pr_info("g.e. %#x still pending\n", entry->ref);
if (!first)
first = entry;
}
spin_lock_irqsave(&gnttab_list_lock, flags);
if (entry)
list_add_tail(&entry->list, &deferred_list);
}
if (list_empty(&deferred_list))
WARN_ON(atomic64_read(&deferred_count));
else if (!timer_pending(&deferred_timer)) {
deferred_timer.expires = jiffies + HZ;
add_timer(&deferred_timer);
}
spin_unlock_irqrestore(&gnttab_list_lock, flags);
pr_debug("Freed %zu references", freed);
}
static void gnttab_add_deferred(grant_ref_t ref, struct page *page)
{
struct deferred_entry *entry;
gfp_t gfp = (in_atomic() || irqs_disabled()) ? GFP_ATOMIC : GFP_KERNEL;
uint64_t leaked, deferred;
entry = kmalloc(sizeof(*entry), gfp);
if (!page) {
unsigned long gfn = gnttab_interface->read_frame(ref);
page = pfn_to_page(gfn_to_pfn(gfn));
get_page(page);
}
if (entry) {
unsigned long flags;
entry->ref = ref;
entry->page = page;
entry->warn_delay = 60;
spin_lock_irqsave(&gnttab_list_lock, flags);
list_add_tail(&entry->list, &deferred_list);
if (!timer_pending(&deferred_timer)) {
deferred_timer.expires = jiffies + HZ;
add_timer(&deferred_timer);
}
spin_unlock_irqrestore(&gnttab_list_lock, flags);
deferred = atomic64_inc_return(&deferred_count);
leaked = atomic64_read(&leaked_count);
pr_debug("deferring g.e. %#x (pfn %#lx) (total deferred %llu, total leaked %llu)\n",
ref, page ? page_to_pfn(page) : -1, deferred, leaked);
} else {
deferred = atomic64_read(&deferred_count);
leaked = atomic64_inc_return(&leaked_count);
pr_warn("leaking g.e. %#x (pfn %#lx) (total deferred %llu, total leaked %llu)\n",
ref, page ? page_to_pfn(page) : -1, deferred, leaked);
}
}
int gnttab_try_end_foreign_access(grant_ref_t ref)
{
int ret = _gnttab_end_foreign_access_ref(ref);
if (ret)
put_free_entry(ref);
return ret;
}
EXPORT_SYMBOL_GPL(gnttab_try_end_foreign_access);
void gnttab_end_foreign_access(grant_ref_t ref, struct page *page)
{
if (gnttab_try_end_foreign_access(ref)) {
if (page)
put_page(page);
} else
gnttab_add_deferred(ref, page);
}
EXPORT_SYMBOL_GPL(gnttab_end_foreign_access);
void gnttab_free_grant_reference(grant_ref_t ref)
{
put_free_entry(ref);
}
EXPORT_SYMBOL_GPL(gnttab_free_grant_reference);
void gnttab_free_grant_references(grant_ref_t head)
{
grant_ref_t ref;
unsigned long flags;
spin_lock_irqsave(&gnttab_list_lock, flags);
while (head != GNTTAB_LIST_END) {
ref = gnttab_entry(head);
put_free_entry_locked(head);
head = ref;
}
check_free_callbacks();
spin_unlock_irqrestore(&gnttab_list_lock, flags);
}
EXPORT_SYMBOL_GPL(gnttab_free_grant_references);
void gnttab_free_grant_reference_seq(grant_ref_t head, unsigned int count)
{
unsigned long flags;
unsigned int i;
spin_lock_irqsave(&gnttab_list_lock, flags);
for (i = count; i > 0; i--)
put_free_entry_locked(head + i - 1);
check_free_callbacks();
spin_unlock_irqrestore(&gnttab_list_lock, flags);
}
EXPORT_SYMBOL_GPL(gnttab_free_grant_reference_seq);
int gnttab_alloc_grant_references(u16 count, grant_ref_t *head)
{
int h = get_free_entries(count);
if (h < 0)
return -ENOSPC;
*head = h;
return 0;
}
EXPORT_SYMBOL_GPL(gnttab_alloc_grant_references);
int gnttab_alloc_grant_reference_seq(unsigned int count, grant_ref_t *first)
{
int h;
if (count == 1)
h = get_free_entries(1);
else
h = get_free_entries_seq(count);
if (h < 0)
return -ENOSPC;
*first = h;
return 0;
}
EXPORT_SYMBOL_GPL(gnttab_alloc_grant_reference_seq);
int gnttab_empty_grant_references(const grant_ref_t *private_head)
{
return (*private_head == GNTTAB_LIST_END);
}
EXPORT_SYMBOL_GPL(gnttab_empty_grant_references);
int gnttab_claim_grant_reference(grant_ref_t *private_head)
{
grant_ref_t g = *private_head;
if (unlikely(g == GNTTAB_LIST_END))
return -ENOSPC;
*private_head = gnttab_entry(g);
return g;
}
EXPORT_SYMBOL_GPL(gnttab_claim_grant_reference);
void gnttab_release_grant_reference(grant_ref_t *private_head,
grant_ref_t release)
{
gnttab_entry(release) = *private_head;
*private_head = release;
}
EXPORT_SYMBOL_GPL(gnttab_release_grant_reference);
void gnttab_request_free_callback(struct gnttab_free_callback *callback,
void (*fn)(void *), void *arg, u16 count)
{
unsigned long flags;
struct gnttab_free_callback *cb;
spin_lock_irqsave(&gnttab_list_lock, flags);
/* Check if the callback is already on the list */
cb = gnttab_free_callback_list;
while (cb) {
if (cb == callback)
goto out;
cb = cb->next;
}
callback->fn = fn;
callback->arg = arg;
callback->count = count;
callback->next = gnttab_free_callback_list;
gnttab_free_callback_list = callback;
check_free_callbacks();
out:
spin_unlock_irqrestore(&gnttab_list_lock, flags);
}
EXPORT_SYMBOL_GPL(gnttab_request_free_callback);
void gnttab_cancel_free_callback(struct gnttab_free_callback *callback)
{
struct gnttab_free_callback **pcb;
unsigned long flags;
spin_lock_irqsave(&gnttab_list_lock, flags);
for (pcb = &gnttab_free_callback_list; *pcb; pcb = &(*pcb)->next) {
if (*pcb == callback) {
*pcb = callback->next;
break;
}
}
spin_unlock_irqrestore(&gnttab_list_lock, flags);
}
EXPORT_SYMBOL_GPL(gnttab_cancel_free_callback);
static unsigned int gnttab_frames(unsigned int frames, unsigned int align)
{
return (frames * gnttab_interface->grefs_per_grant_frame + align - 1) /
align;
}
static int grow_gnttab_list(unsigned int more_frames)
{
unsigned int new_nr_grant_frames, extra_entries, i;
unsigned int nr_glist_frames, new_nr_glist_frames;
unsigned int grefs_per_frame;
grefs_per_frame = gnttab_interface->grefs_per_grant_frame;
xen/grant-table: correctly initialize grant table version 1 Commit 85ff6acb075a484780b3d763fdf41596d8fc0970 (xen/granttable: Grant tables V2 implementation) changed the GREFS_PER_GRANT_FRAME macro from a constant to a conditional expression. The expression depends on grant_table_version being appropriately set. Unfortunately, at init time grant_table_version will be 0. The GREFS_PER_GRANT_FRAME conditional expression checks for "grant_table_version == 1", and therefore returns the number of grant references per frame for v2. This causes gnttab_init() to allocate fewer pages for gnttab_list, as a frame can old half the number of v2 entries than v1 entries. After gnttab_resume() is called, grant_table_version is appropriately set. nr_init_grefs will then be miscalculated and gnttab_free_count will hold a value larger than the actual number of free gref entries. If a guest is heavily utilizing improperly initialized v1 grant tables, memory corruption can occur. One common manifestation is corruption of the vmalloc list, resulting in a poisoned pointer derefrence when accessing /proc/meminfo or /proc/vmallocinfo: [ 40.770064] BUG: unable to handle kernel paging request at 0000200200001407 [ 40.770083] IP: [<ffffffff811a6fb0>] get_vmalloc_info+0x70/0x110 [ 40.770102] PGD 0 [ 40.770107] Oops: 0000 [#1] SMP [ 40.770114] CPU 10 This patch introduces a static variable, grefs_per_grant_frame, to cache the calculated value. gnttab_init() now calls gnttab_request_version() early so that grant_table_version and grefs_per_grant_frame can be appropriately set. A few BUG_ON()s have been added to prevent this type of bug from reoccurring in the future. Signed-off-by: Matt Wilson <msw@amazon.com> Reviewed-and-Tested-by: Steven Noonan <snoonan@amazon.com> Acked-by: Ian Campbell <Ian.Campbell@citrix.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Annie Li <annie.li@oracle.com> Cc: xen-devel@lists.xen.org Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org # v3.3 and newer Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
2013-01-15 13:21:27 +00:00
new_nr_grant_frames = nr_grant_frames + more_frames;
extra_entries = more_frames * grefs_per_frame;
nr_glist_frames = gnttab_frames(nr_grant_frames, RPP);
new_nr_glist_frames = gnttab_frames(new_nr_grant_frames, RPP);
for (i = nr_glist_frames; i < new_nr_glist_frames; i++) {
gnttab_list[i] = (grant_ref_t *)__get_free_page(GFP_ATOMIC);
if (!gnttab_list[i])
goto grow_nomem;
}
gnttab_set_free(gnttab_size, extra_entries);
if (!gnttab_free_tail_ptr)
gnttab_free_tail_ptr = __gnttab_entry(gnttab_size);
nr_grant_frames = new_nr_grant_frames;
gnttab_size += extra_entries;
check_free_callbacks();
return 0;
grow_nomem:
while (i-- > nr_glist_frames)
free_page((unsigned long) gnttab_list[i]);
return -ENOMEM;
}
static unsigned int __max_nr_grant_frames(void)
{
struct gnttab_query_size query;
int rc;
query.dom = DOMID_SELF;
rc = HYPERVISOR_grant_table_op(GNTTABOP_query_size, &query, 1);
if ((rc < 0) || (query.status != GNTST_okay))
return 4; /* Legacy max supported number of frames */
return query.max_nr_frames;
}
unsigned int gnttab_max_grant_frames(void)
{
unsigned int xen_max = __max_nr_grant_frames();
static unsigned int boot_max_nr_grant_frames;
/* First time, initialize it properly. */
if (!boot_max_nr_grant_frames)
boot_max_nr_grant_frames = __max_nr_grant_frames();
if (xen_max > boot_max_nr_grant_frames)
return boot_max_nr_grant_frames;
return xen_max;
}
EXPORT_SYMBOL_GPL(gnttab_max_grant_frames);
int gnttab_setup_auto_xlat_frames(phys_addr_t addr)
{
xen_pfn_t *pfn;
unsigned int max_nr_gframes = __max_nr_grant_frames();
unsigned int i;
void *vaddr;
if (xen_auto_xlat_grant_frames.count)
return -EINVAL;
vaddr = memremap(addr, XEN_PAGE_SIZE * max_nr_gframes, MEMREMAP_WB);
if (vaddr == NULL) {
pr_warn("Failed to ioremap gnttab share frames (addr=%pa)!\n",
&addr);
return -ENOMEM;
}
pfn = kcalloc(max_nr_gframes, sizeof(pfn[0]), GFP_KERNEL);
if (!pfn) {
memunmap(vaddr);
return -ENOMEM;
}
for (i = 0; i < max_nr_gframes; i++)
pfn[i] = XEN_PFN_DOWN(addr) + i;
xen_auto_xlat_grant_frames.vaddr = vaddr;
xen_auto_xlat_grant_frames.pfn = pfn;
xen_auto_xlat_grant_frames.count = max_nr_gframes;
return 0;
}
EXPORT_SYMBOL_GPL(gnttab_setup_auto_xlat_frames);
void gnttab_free_auto_xlat_frames(void)
{
if (!xen_auto_xlat_grant_frames.count)
return;
kfree(xen_auto_xlat_grant_frames.pfn);
memunmap(xen_auto_xlat_grant_frames.vaddr);
xen_auto_xlat_grant_frames.pfn = NULL;
xen_auto_xlat_grant_frames.count = 0;
xen_auto_xlat_grant_frames.vaddr = NULL;
}
EXPORT_SYMBOL_GPL(gnttab_free_auto_xlat_frames);
int gnttab_pages_set_private(int nr_pages, struct page **pages)
{
int i;
for (i = 0; i < nr_pages; i++) {
#if BITS_PER_LONG < 64
struct xen_page_foreign *foreign;
foreign = kzalloc(sizeof(*foreign), GFP_KERNEL);
if (!foreign)
return -ENOMEM;
set_page_private(pages[i], (unsigned long)foreign);
#endif
SetPagePrivate(pages[i]);
}
return 0;
}
EXPORT_SYMBOL_GPL(gnttab_pages_set_private);
/**
* gnttab_alloc_pages - alloc pages suitable for grant mapping into
* @nr_pages: number of pages to alloc
* @pages: returns the pages
*/
int gnttab_alloc_pages(int nr_pages, struct page **pages)
{
int ret;
2020-09-01 08:33:26 +00:00
ret = xen_alloc_unpopulated_pages(nr_pages, pages);
if (ret < 0)
return ret;
ret = gnttab_pages_set_private(nr_pages, pages);
if (ret < 0)
gnttab_free_pages(nr_pages, pages);
return ret;
}
EXPORT_SYMBOL_GPL(gnttab_alloc_pages);
#ifdef CONFIG_XEN_UNPOPULATED_ALLOC
static inline void cache_init(struct gnttab_page_cache *cache)
{
cache->pages = NULL;
}
static inline bool cache_empty(struct gnttab_page_cache *cache)
{
return !cache->pages;
}
static inline struct page *cache_deq(struct gnttab_page_cache *cache)
{
struct page *page;
page = cache->pages;
cache->pages = page->zone_device_data;
return page;
}
static inline void cache_enq(struct gnttab_page_cache *cache, struct page *page)
{
page->zone_device_data = cache->pages;
cache->pages = page;
}
#else
static inline void cache_init(struct gnttab_page_cache *cache)
{
INIT_LIST_HEAD(&cache->pages);
}
static inline bool cache_empty(struct gnttab_page_cache *cache)
{
return list_empty(&cache->pages);
}
static inline struct page *cache_deq(struct gnttab_page_cache *cache)
{
struct page *page;
page = list_first_entry(&cache->pages, struct page, lru);
list_del(&page->lru);
return page;
}
static inline void cache_enq(struct gnttab_page_cache *cache, struct page *page)
{
list_add(&page->lru, &cache->pages);
}
#endif
void gnttab_page_cache_init(struct gnttab_page_cache *cache)
{
spin_lock_init(&cache->lock);
cache_init(cache);
cache->num_pages = 0;
}
EXPORT_SYMBOL_GPL(gnttab_page_cache_init);
int gnttab_page_cache_get(struct gnttab_page_cache *cache, struct page **page)
{
unsigned long flags;
spin_lock_irqsave(&cache->lock, flags);
if (cache_empty(cache)) {
spin_unlock_irqrestore(&cache->lock, flags);
return gnttab_alloc_pages(1, page);
}
page[0] = cache_deq(cache);
cache->num_pages--;
spin_unlock_irqrestore(&cache->lock, flags);
return 0;
}
EXPORT_SYMBOL_GPL(gnttab_page_cache_get);
void gnttab_page_cache_put(struct gnttab_page_cache *cache, struct page **page,
unsigned int num)
{
unsigned long flags;
unsigned int i;
spin_lock_irqsave(&cache->lock, flags);
for (i = 0; i < num; i++)
cache_enq(cache, page[i]);
cache->num_pages += num;
spin_unlock_irqrestore(&cache->lock, flags);
}
EXPORT_SYMBOL_GPL(gnttab_page_cache_put);
void gnttab_page_cache_shrink(struct gnttab_page_cache *cache, unsigned int num)
{
struct page *page[10];
unsigned int i = 0;
unsigned long flags;
spin_lock_irqsave(&cache->lock, flags);
while (cache->num_pages > num) {
page[i] = cache_deq(cache);
cache->num_pages--;
if (++i == ARRAY_SIZE(page)) {
spin_unlock_irqrestore(&cache->lock, flags);
gnttab_free_pages(i, page);
i = 0;
spin_lock_irqsave(&cache->lock, flags);
}
}
spin_unlock_irqrestore(&cache->lock, flags);
if (i != 0)
gnttab_free_pages(i, page);
}
EXPORT_SYMBOL_GPL(gnttab_page_cache_shrink);
void gnttab_pages_clear_private(int nr_pages, struct page **pages)
{
int i;
for (i = 0; i < nr_pages; i++) {
if (PagePrivate(pages[i])) {
#if BITS_PER_LONG < 64
kfree((void *)page_private(pages[i]));
#endif
ClearPagePrivate(pages[i]);
}
}
}
EXPORT_SYMBOL_GPL(gnttab_pages_clear_private);
/**
* gnttab_free_pages - free pages allocated by gnttab_alloc_pages()
* @nr_pages: number of pages to free
* @pages: the pages
*/
void gnttab_free_pages(int nr_pages, struct page **pages)
{
gnttab_pages_clear_private(nr_pages, pages);
2020-09-01 08:33:26 +00:00
xen_free_unpopulated_pages(nr_pages, pages);
}
EXPORT_SYMBOL_GPL(gnttab_free_pages);
#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
/**
* gnttab_dma_alloc_pages - alloc DMAable pages suitable for grant mapping into
* @args: arguments to the function
*/
int gnttab_dma_alloc_pages(struct gnttab_dma_alloc_args *args)
{
unsigned long pfn, start_pfn;
size_t size;
int i, ret;
if (args->nr_pages < 0 || args->nr_pages > (INT_MAX >> PAGE_SHIFT))
return -ENOMEM;
size = args->nr_pages << PAGE_SHIFT;
if (args->coherent)
args->vaddr = dma_alloc_coherent(args->dev, size,
&args->dev_bus_addr,
GFP_KERNEL | __GFP_NOWARN);
else
args->vaddr = dma_alloc_wc(args->dev, size,
&args->dev_bus_addr,
GFP_KERNEL | __GFP_NOWARN);
if (!args->vaddr) {
pr_debug("Failed to allocate DMA buffer of size %zu\n", size);
return -ENOMEM;
}
start_pfn = __phys_to_pfn(args->dev_bus_addr);
for (pfn = start_pfn, i = 0; pfn < start_pfn + args->nr_pages;
pfn++, i++) {
struct page *page = pfn_to_page(pfn);
args->pages[i] = page;
args->frames[i] = xen_page_to_gfn(page);
xenmem_reservation_scrub_page(page);
}
xenmem_reservation_va_mapping_reset(args->nr_pages, args->pages);
ret = xenmem_reservation_decrease(args->nr_pages, args->frames);
if (ret != args->nr_pages) {
pr_debug("Failed to decrease reservation for DMA buffer\n");
ret = -EFAULT;
goto fail;
}
ret = gnttab_pages_set_private(args->nr_pages, args->pages);
if (ret < 0)
goto fail;
return 0;
fail:
gnttab_dma_free_pages(args);
return ret;
}
EXPORT_SYMBOL_GPL(gnttab_dma_alloc_pages);
/**
* gnttab_dma_free_pages - free DMAable pages
* @args: arguments to the function
*/
int gnttab_dma_free_pages(struct gnttab_dma_alloc_args *args)
{
size_t size;
int i, ret;
gnttab_pages_clear_private(args->nr_pages, args->pages);
for (i = 0; i < args->nr_pages; i++)
args->frames[i] = page_to_xen_pfn(args->pages[i]);
ret = xenmem_reservation_increase(args->nr_pages, args->frames);
if (ret != args->nr_pages) {
pr_debug("Failed to increase reservation for DMA buffer\n");
ret = -EFAULT;
} else {
ret = 0;
}
xenmem_reservation_va_mapping_update(args->nr_pages, args->pages,
args->frames);
size = args->nr_pages << PAGE_SHIFT;
if (args->coherent)
dma_free_coherent(args->dev, size,
args->vaddr, args->dev_bus_addr);
else
dma_free_wc(args->dev, size,
args->vaddr, args->dev_bus_addr);
return ret;
}
EXPORT_SYMBOL_GPL(gnttab_dma_free_pages);
#endif
xen/gndev: Xen backend support for paged out grant targets V4. Since Xen-4.2, hvm domains may have portions of their memory paged out. When a foreign domain (such as dom0) attempts to map these frames, the map will initially fail. The hypervisor returns a suitable errno, and kicks an asynchronous page-in operation carried out by a helper. The foreign domain is expected to retry the mapping operation until it eventually succeeds. The foreign domain is not put to sleep because itself could be the one running the pager assist (typical scenario for dom0). This patch adds support for this mechanism for backend drivers using grant mapping and copying operations. Specifically, this covers the blkback and gntdev drivers (which map foreign grants), and the netback driver (which copies foreign grants). * Add a retry method for grants that fail with GNTST_eagain (i.e. because the target foreign frame is paged out). * Insert hooks with appropriate wrappers in the aforementioned drivers. The retry loop is only invoked if the grant operation status is GNTST_eagain. It guarantees to leave a new status code different from GNTST_eagain. Any other status code results in identical code execution as before. The retry loop performs 256 attempts with increasing time intervals through a 32 second period. It uses msleep to yield while waiting for the next retry. V2 after feedback from David Vrabel: * Explicit MAX_DELAY instead of wrap-around delay into zero * Abstract GNTST_eagain check into core grant table code for netback module. V3 after feedback from Ian Campbell: * Add placeholder in array of grant table error descriptions for unrelated error code we jump over. * Eliminate single map and retry macro in favor of a generic batch flavor. * Some renaming. * Bury most implementation in grant_table.c, cleaner interface. V4 rebased on top of sync of Xen grant table interface headers. Signed-off-by: Andres Lagar-Cavilla <andres@lagarcavilla.org> Acked-by: Ian Campbell <ian.campbell@citrix.com> [v5: Fixed whitespace issues] Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
2012-09-14 14:26:59 +00:00
/* Handling of paged out grant targets (GNTST_eagain) */
#define MAX_DELAY 256
static inline void
gnttab_retry_eagain_gop(unsigned int cmd, void *gop, int16_t *status,
const char *func)
{
unsigned delay = 1;
do {
BUG_ON(HYPERVISOR_grant_table_op(cmd, gop, 1));
if (*status == GNTST_eagain)
msleep(delay++);
} while ((*status == GNTST_eagain) && (delay < MAX_DELAY));
if (delay >= MAX_DELAY) {
pr_err("%s: %s eagain grant\n", func, current->comm);
xen/gndev: Xen backend support for paged out grant targets V4. Since Xen-4.2, hvm domains may have portions of their memory paged out. When a foreign domain (such as dom0) attempts to map these frames, the map will initially fail. The hypervisor returns a suitable errno, and kicks an asynchronous page-in operation carried out by a helper. The foreign domain is expected to retry the mapping operation until it eventually succeeds. The foreign domain is not put to sleep because itself could be the one running the pager assist (typical scenario for dom0). This patch adds support for this mechanism for backend drivers using grant mapping and copying operations. Specifically, this covers the blkback and gntdev drivers (which map foreign grants), and the netback driver (which copies foreign grants). * Add a retry method for grants that fail with GNTST_eagain (i.e. because the target foreign frame is paged out). * Insert hooks with appropriate wrappers in the aforementioned drivers. The retry loop is only invoked if the grant operation status is GNTST_eagain. It guarantees to leave a new status code different from GNTST_eagain. Any other status code results in identical code execution as before. The retry loop performs 256 attempts with increasing time intervals through a 32 second period. It uses msleep to yield while waiting for the next retry. V2 after feedback from David Vrabel: * Explicit MAX_DELAY instead of wrap-around delay into zero * Abstract GNTST_eagain check into core grant table code for netback module. V3 after feedback from Ian Campbell: * Add placeholder in array of grant table error descriptions for unrelated error code we jump over. * Eliminate single map and retry macro in favor of a generic batch flavor. * Some renaming. * Bury most implementation in grant_table.c, cleaner interface. V4 rebased on top of sync of Xen grant table interface headers. Signed-off-by: Andres Lagar-Cavilla <andres@lagarcavilla.org> Acked-by: Ian Campbell <ian.campbell@citrix.com> [v5: Fixed whitespace issues] Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
2012-09-14 14:26:59 +00:00
*status = GNTST_bad_page;
}
}
void gnttab_batch_map(struct gnttab_map_grant_ref *batch, unsigned count)
{
struct gnttab_map_grant_ref *op;
if (HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref, batch, count))
BUG();
for (op = batch; op < batch + count; op++)
if (op->status == GNTST_eagain)
gnttab_retry_eagain_gop(GNTTABOP_map_grant_ref, op,
&op->status, __func__);
}
EXPORT_SYMBOL_GPL(gnttab_batch_map);
void gnttab_batch_copy(struct gnttab_copy *batch, unsigned count)
{
struct gnttab_copy *op;
if (HYPERVISOR_grant_table_op(GNTTABOP_copy, batch, count))
BUG();
for (op = batch; op < batch + count; op++)
if (op->status == GNTST_eagain)
gnttab_retry_eagain_gop(GNTTABOP_copy, op,
&op->status, __func__);
}
EXPORT_SYMBOL_GPL(gnttab_batch_copy);
void gnttab_foreach_grant_in_range(struct page *page,
unsigned int offset,
unsigned int len,
xen_grant_fn_t fn,
void *data)
{
unsigned int goffset;
unsigned int glen;
unsigned long xen_pfn;
len = min_t(unsigned int, PAGE_SIZE - offset, len);
goffset = xen_offset_in_page(offset);
xen_pfn = page_to_xen_pfn(page) + XEN_PFN_DOWN(offset);
while (len) {
glen = min_t(unsigned int, XEN_PAGE_SIZE - goffset, len);
fn(pfn_to_gfn(xen_pfn), goffset, glen, data);
goffset = 0;
xen_pfn++;
len -= glen;
}
}
EXPORT_SYMBOL_GPL(gnttab_foreach_grant_in_range);
void gnttab_foreach_grant(struct page **pages,
unsigned int nr_grefs,
xen_grant_fn_t fn,
void *data)
{
unsigned int goffset = 0;
unsigned long xen_pfn = 0;
unsigned int i;
for (i = 0; i < nr_grefs; i++) {
if ((i % XEN_PFN_PER_PAGE) == 0) {
xen_pfn = page_to_xen_pfn(pages[i / XEN_PFN_PER_PAGE]);
goffset = 0;
}
fn(pfn_to_gfn(xen_pfn), goffset, XEN_PAGE_SIZE, data);
goffset += XEN_PAGE_SIZE;
xen_pfn++;
}
}
int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
struct gnttab_map_grant_ref *kmap_ops,
struct page **pages, unsigned int count)
{
int i, ret;
ret = HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref, map_ops, count);
if (ret)
return ret;
for (i = 0; i < count; i++) {
switch (map_ops[i].status) {
case GNTST_okay:
{
struct xen_page_foreign *foreign;
SetPageForeign(pages[i]);
foreign = xen_page_foreign(pages[i]);
foreign->domid = map_ops[i].dom;
foreign->gref = map_ops[i].ref;
break;
}
case GNTST_no_device_space:
pr_warn_ratelimited("maptrack limit reached, can't map all guest pages\n");
break;
case GNTST_eagain:
/* Retry eagain maps */
gnttab_retry_eagain_gop(GNTTABOP_map_grant_ref,
map_ops + i,
&map_ops[i].status, __func__);
/* Test status in next loop iteration. */
i--;
break;
default:
break;
}
}
return set_foreign_p2m_mapping(map_ops, kmap_ops, pages, count);
}
EXPORT_SYMBOL_GPL(gnttab_map_refs);
int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops,
struct gnttab_unmap_grant_ref *kunmap_ops,
struct page **pages, unsigned int count)
{
unsigned int i;
int ret;
ret = HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, unmap_ops, count);
if (ret)
return ret;
for (i = 0; i < count; i++)
ClearPageForeign(pages[i]);
return clear_foreign_p2m_mapping(unmap_ops, kunmap_ops, pages, count);
}
EXPORT_SYMBOL_GPL(gnttab_unmap_refs);
#define GNTTAB_UNMAP_REFS_DELAY 5
static void __gnttab_unmap_refs_async(struct gntab_unmap_queue_data* item);
static void gnttab_unmap_work(struct work_struct *work)
{
struct gntab_unmap_queue_data
*unmap_data = container_of(work,
struct gntab_unmap_queue_data,
gnttab_work.work);
if (unmap_data->age != UINT_MAX)
unmap_data->age++;
__gnttab_unmap_refs_async(unmap_data);
}
static void __gnttab_unmap_refs_async(struct gntab_unmap_queue_data* item)
{
int ret;
int pc;
for (pc = 0; pc < item->count; pc++) {
if (page_count(item->pages[pc]) > 1) {
unsigned long delay = GNTTAB_UNMAP_REFS_DELAY * (item->age + 1);
schedule_delayed_work(&item->gnttab_work,
msecs_to_jiffies(delay));
return;
}
}
ret = gnttab_unmap_refs(item->unmap_ops, item->kunmap_ops,
item->pages, item->count);
item->done(ret, item);
}
void gnttab_unmap_refs_async(struct gntab_unmap_queue_data* item)
{
INIT_DELAYED_WORK(&item->gnttab_work, gnttab_unmap_work);
item->age = 0;
__gnttab_unmap_refs_async(item);
}
EXPORT_SYMBOL_GPL(gnttab_unmap_refs_async);
static void unmap_refs_callback(int result,
struct gntab_unmap_queue_data *data)
{
struct unmap_refs_callback_data *d = data->data;
d->result = result;
complete(&d->completion);
}
int gnttab_unmap_refs_sync(struct gntab_unmap_queue_data *item)
{
struct unmap_refs_callback_data data;
init_completion(&data.completion);
item->data = &data;
item->done = &unmap_refs_callback;
gnttab_unmap_refs_async(item);
wait_for_completion(&data.completion);
return data.result;
}
EXPORT_SYMBOL_GPL(gnttab_unmap_refs_sync);
static unsigned int nr_status_frames(unsigned int nr_grant_frames)
{
return gnttab_frames(nr_grant_frames, SPP);
}
static int gnttab_map_frames_v1(xen_pfn_t *frames, unsigned int nr_gframes)
{
int rc;
rc = arch_gnttab_map_shared(frames, nr_gframes,
gnttab_max_grant_frames(),
&gnttab_shared.addr);
BUG_ON(rc);
return 0;
}
static void gnttab_unmap_frames_v1(void)
{
arch_gnttab_unmap(gnttab_shared.addr, nr_grant_frames);
}
static int gnttab_map_frames_v2(xen_pfn_t *frames, unsigned int nr_gframes)
{
uint64_t *sframes;
unsigned int nr_sframes;
struct gnttab_get_status_frames getframes;
int rc;
nr_sframes = nr_status_frames(nr_gframes);
/* No need for kzalloc as it is initialized in following hypercall
* GNTTABOP_get_status_frames.
*/
sframes = kmalloc_array(nr_sframes, sizeof(uint64_t), GFP_ATOMIC);
if (!sframes)
return -ENOMEM;
getframes.dom = DOMID_SELF;
getframes.nr_frames = nr_sframes;
set_xen_guest_handle(getframes.frame_list, sframes);
rc = HYPERVISOR_grant_table_op(GNTTABOP_get_status_frames,
&getframes, 1);
if (rc == -ENOSYS) {
kfree(sframes);
return -ENOSYS;
}
BUG_ON(rc || getframes.status);
rc = arch_gnttab_map_status(sframes, nr_sframes,
nr_status_frames(gnttab_max_grant_frames()),
&grstatus);
BUG_ON(rc);
kfree(sframes);
rc = arch_gnttab_map_shared(frames, nr_gframes,
gnttab_max_grant_frames(),
&gnttab_shared.addr);
BUG_ON(rc);
return 0;
}
static void gnttab_unmap_frames_v2(void)
{
arch_gnttab_unmap(gnttab_shared.addr, nr_grant_frames);
arch_gnttab_unmap(grstatus, nr_status_frames(nr_grant_frames));
}
static int gnttab_map(unsigned int start_idx, unsigned int end_idx)
{
struct gnttab_setup_table setup;
xen_pfn_t *frames;
unsigned int nr_gframes = end_idx + 1;
int rc;
if (xen_feature(XENFEAT_auto_translated_physmap)) {
struct xen_add_to_physmap xatp;
unsigned int i = end_idx;
rc = 0;
BUG_ON(xen_auto_xlat_grant_frames.count < nr_gframes);
/*
* Loop backwards, so that the first hypercall has the largest
* index, ensuring that the table will grow only once.
*/
do {
xatp.domid = DOMID_SELF;
xatp.idx = i;
xatp.space = XENMAPSPACE_grant_table;
xatp.gpfn = xen_auto_xlat_grant_frames.pfn[i];
rc = HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp);
if (rc != 0) {
pr_warn("grant table add_to_physmap failed, err=%d\n",
rc);
break;
}
} while (i-- > start_idx);
return rc;
}
/* No need for kzalloc as it is initialized in following hypercall
* GNTTABOP_setup_table.
*/
treewide: kmalloc() -> kmalloc_array() The kmalloc() function has a 2-factor argument form, kmalloc_array(). This patch replaces cases of: kmalloc(a * b, gfp) with: kmalloc_array(a * b, gfp) as well as handling cases of: kmalloc(a * b * c, gfp) with: kmalloc(array3_size(a, b, c), gfp) as it's slightly less ugly than: kmalloc_array(array_size(a, b), c, gfp) This does, however, attempt to ignore constant size factors like: kmalloc(4 * 1024, gfp) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The tools/ directory was manually excluded, since it has its own implementation of kmalloc(). The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( kmalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | kmalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( kmalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(char) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(u8) * COUNT + COUNT , ...) | kmalloc( - sizeof(__u8) * COUNT + COUNT , ...) | kmalloc( - sizeof(char) * COUNT + COUNT , ...) | kmalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( - kmalloc + kmalloc_array ( - sizeof(TYPE) * (COUNT_ID) + COUNT_ID, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * COUNT_ID + COUNT_ID, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * (COUNT_CONST) + COUNT_CONST, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * COUNT_CONST + COUNT_CONST, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (COUNT_ID) + COUNT_ID, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * COUNT_ID + COUNT_ID, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (COUNT_CONST) + COUNT_CONST, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * COUNT_CONST + COUNT_CONST, sizeof(THING) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ - kmalloc + kmalloc_array ( - SIZE * COUNT + COUNT, SIZE , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( kmalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( kmalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kmalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kmalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( kmalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products, // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( kmalloc(C1 * C2 * C3, ...) | kmalloc( - (E1) * E2 * E3 + array3_size(E1, E2, E3) , ...) | kmalloc( - (E1) * (E2) * E3 + array3_size(E1, E2, E3) , ...) | kmalloc( - (E1) * (E2) * (E3) + array3_size(E1, E2, E3) , ...) | kmalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants, // keeping sizeof() as the second factor argument. @@ expression THING, E1, E2; type TYPE; constant C1, C2, C3; @@ ( kmalloc(sizeof(THING) * C2, ...) | kmalloc(sizeof(TYPE) * C2, ...) | kmalloc(C1 * C2 * C3, ...) | kmalloc(C1 * C2, ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * (E2) + E2, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * E2 + E2, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (E2) + E2, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * E2 + E2, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - (E1) * E2 + E1, E2 , ...) | - kmalloc + kmalloc_array ( - (E1) * (E2) + E1, E2 , ...) | - kmalloc + kmalloc_array ( - E1 * E2 + E1, E2 , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-12 20:55:00 +00:00
frames = kmalloc_array(nr_gframes, sizeof(unsigned long), GFP_ATOMIC);
if (!frames)
return -ENOMEM;
setup.dom = DOMID_SELF;
setup.nr_frames = nr_gframes;
set_xen_guest_handle(setup.frame_list, frames);
rc = HYPERVISOR_grant_table_op(GNTTABOP_setup_table, &setup, 1);
if (rc == -ENOSYS) {
kfree(frames);
return -ENOSYS;
}
BUG_ON(rc || setup.status);
rc = gnttab_interface->map_frames(frames, nr_gframes);
kfree(frames);
return rc;
}
static const struct gnttab_ops gnttab_v1_ops = {
.version = 1,
.grefs_per_grant_frame = XEN_PAGE_SIZE /
sizeof(struct grant_entry_v1),
.map_frames = gnttab_map_frames_v1,
.unmap_frames = gnttab_unmap_frames_v1,
.update_entry = gnttab_update_entry_v1,
.end_foreign_access_ref = gnttab_end_foreign_access_ref_v1,
.read_frame = gnttab_read_frame_v1,
};
static const struct gnttab_ops gnttab_v2_ops = {
.version = 2,
.grefs_per_grant_frame = XEN_PAGE_SIZE /
sizeof(union grant_entry_v2),
.map_frames = gnttab_map_frames_v2,
.unmap_frames = gnttab_unmap_frames_v2,
.update_entry = gnttab_update_entry_v2,
.end_foreign_access_ref = gnttab_end_foreign_access_ref_v2,
.read_frame = gnttab_read_frame_v2,
};
static bool gnttab_need_v2(void)
{
#ifdef CONFIG_X86
uint32_t base, width;
if (xen_pv_domain()) {
base = xen_cpuid_base();
if (cpuid_eax(base) < 5)
return false; /* Information not available, use V1. */
width = cpuid_ebx(base + 5) &
XEN_CPUID_MACHINE_ADDRESS_WIDTH_MASK;
return width > 32 + PAGE_SHIFT;
}
#endif
return !!(max_possible_pfn >> 32);
}
static void gnttab_request_version(void)
{
long rc;
struct gnttab_set_version gsv;
if (gnttab_need_v2())
gsv.version = 2;
else
gsv.version = 1;
/* Boot parameter overrides automatic selection. */
if (xen_gnttab_version >= 1 && xen_gnttab_version <= 2)
gsv.version = xen_gnttab_version;
rc = HYPERVISOR_grant_table_op(GNTTABOP_set_version, &gsv, 1);
if (rc == 0 && gsv.version == 2)
gnttab_interface = &gnttab_v2_ops;
else
gnttab_interface = &gnttab_v1_ops;
pr_info("Grant tables using version %d layout\n",
gnttab_interface->version);
}
xen/grant-table: correctly initialize grant table version 1 Commit 85ff6acb075a484780b3d763fdf41596d8fc0970 (xen/granttable: Grant tables V2 implementation) changed the GREFS_PER_GRANT_FRAME macro from a constant to a conditional expression. The expression depends on grant_table_version being appropriately set. Unfortunately, at init time grant_table_version will be 0. The GREFS_PER_GRANT_FRAME conditional expression checks for "grant_table_version == 1", and therefore returns the number of grant references per frame for v2. This causes gnttab_init() to allocate fewer pages for gnttab_list, as a frame can old half the number of v2 entries than v1 entries. After gnttab_resume() is called, grant_table_version is appropriately set. nr_init_grefs will then be miscalculated and gnttab_free_count will hold a value larger than the actual number of free gref entries. If a guest is heavily utilizing improperly initialized v1 grant tables, memory corruption can occur. One common manifestation is corruption of the vmalloc list, resulting in a poisoned pointer derefrence when accessing /proc/meminfo or /proc/vmallocinfo: [ 40.770064] BUG: unable to handle kernel paging request at 0000200200001407 [ 40.770083] IP: [<ffffffff811a6fb0>] get_vmalloc_info+0x70/0x110 [ 40.770102] PGD 0 [ 40.770107] Oops: 0000 [#1] SMP [ 40.770114] CPU 10 This patch introduces a static variable, grefs_per_grant_frame, to cache the calculated value. gnttab_init() now calls gnttab_request_version() early so that grant_table_version and grefs_per_grant_frame can be appropriately set. A few BUG_ON()s have been added to prevent this type of bug from reoccurring in the future. Signed-off-by: Matt Wilson <msw@amazon.com> Reviewed-and-Tested-by: Steven Noonan <snoonan@amazon.com> Acked-by: Ian Campbell <Ian.Campbell@citrix.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Annie Li <annie.li@oracle.com> Cc: xen-devel@lists.xen.org Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org # v3.3 and newer Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
2013-01-15 13:21:27 +00:00
static int gnttab_setup(void)
{
unsigned int max_nr_gframes;
max_nr_gframes = gnttab_max_grant_frames();
if (max_nr_gframes < nr_grant_frames)
return -ENOSYS;
if (xen_feature(XENFEAT_auto_translated_physmap) && gnttab_shared.addr == NULL) {
gnttab_shared.addr = xen_auto_xlat_grant_frames.vaddr;
if (gnttab_shared.addr == NULL) {
pr_warn("gnttab share frames is not mapped!\n");
return -ENOMEM;
}
}
return gnttab_map(0, nr_grant_frames - 1);
}
xen/grant-table: correctly initialize grant table version 1 Commit 85ff6acb075a484780b3d763fdf41596d8fc0970 (xen/granttable: Grant tables V2 implementation) changed the GREFS_PER_GRANT_FRAME macro from a constant to a conditional expression. The expression depends on grant_table_version being appropriately set. Unfortunately, at init time grant_table_version will be 0. The GREFS_PER_GRANT_FRAME conditional expression checks for "grant_table_version == 1", and therefore returns the number of grant references per frame for v2. This causes gnttab_init() to allocate fewer pages for gnttab_list, as a frame can old half the number of v2 entries than v1 entries. After gnttab_resume() is called, grant_table_version is appropriately set. nr_init_grefs will then be miscalculated and gnttab_free_count will hold a value larger than the actual number of free gref entries. If a guest is heavily utilizing improperly initialized v1 grant tables, memory corruption can occur. One common manifestation is corruption of the vmalloc list, resulting in a poisoned pointer derefrence when accessing /proc/meminfo or /proc/vmallocinfo: [ 40.770064] BUG: unable to handle kernel paging request at 0000200200001407 [ 40.770083] IP: [<ffffffff811a6fb0>] get_vmalloc_info+0x70/0x110 [ 40.770102] PGD 0 [ 40.770107] Oops: 0000 [#1] SMP [ 40.770114] CPU 10 This patch introduces a static variable, grefs_per_grant_frame, to cache the calculated value. gnttab_init() now calls gnttab_request_version() early so that grant_table_version and grefs_per_grant_frame can be appropriately set. A few BUG_ON()s have been added to prevent this type of bug from reoccurring in the future. Signed-off-by: Matt Wilson <msw@amazon.com> Reviewed-and-Tested-by: Steven Noonan <snoonan@amazon.com> Acked-by: Ian Campbell <Ian.Campbell@citrix.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Annie Li <annie.li@oracle.com> Cc: xen-devel@lists.xen.org Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org # v3.3 and newer Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
2013-01-15 13:21:27 +00:00
int gnttab_resume(void)
{
gnttab_request_version();
return gnttab_setup();
}
int gnttab_suspend(void)
{
if (!xen_feature(XENFEAT_auto_translated_physmap))
gnttab_interface->unmap_frames();
return 0;
}
static int gnttab_expand(unsigned int req_entries)
{
int rc;
unsigned int cur, extra;
cur = nr_grant_frames;
extra = ((req_entries + gnttab_interface->grefs_per_grant_frame - 1) /
gnttab_interface->grefs_per_grant_frame);
if (cur + extra > gnttab_max_grant_frames()) {
pr_warn_ratelimited("xen/grant-table: max_grant_frames reached"
" cur=%u extra=%u limit=%u"
" gnttab_free_count=%u req_entries=%u\n",
cur, extra, gnttab_max_grant_frames(),
gnttab_free_count, req_entries);
return -ENOSPC;
}
rc = gnttab_map(cur, cur + extra - 1);
if (rc == 0)
rc = grow_gnttab_list(extra);
return rc;
}
int gnttab_init(void)
{
int i;
unsigned long max_nr_grant_frames, max_nr_grefs;
unsigned int max_nr_glist_frames, nr_glist_frames;
int ret;
xen/grant-table: correctly initialize grant table version 1 Commit 85ff6acb075a484780b3d763fdf41596d8fc0970 (xen/granttable: Grant tables V2 implementation) changed the GREFS_PER_GRANT_FRAME macro from a constant to a conditional expression. The expression depends on grant_table_version being appropriately set. Unfortunately, at init time grant_table_version will be 0. The GREFS_PER_GRANT_FRAME conditional expression checks for "grant_table_version == 1", and therefore returns the number of grant references per frame for v2. This causes gnttab_init() to allocate fewer pages for gnttab_list, as a frame can old half the number of v2 entries than v1 entries. After gnttab_resume() is called, grant_table_version is appropriately set. nr_init_grefs will then be miscalculated and gnttab_free_count will hold a value larger than the actual number of free gref entries. If a guest is heavily utilizing improperly initialized v1 grant tables, memory corruption can occur. One common manifestation is corruption of the vmalloc list, resulting in a poisoned pointer derefrence when accessing /proc/meminfo or /proc/vmallocinfo: [ 40.770064] BUG: unable to handle kernel paging request at 0000200200001407 [ 40.770083] IP: [<ffffffff811a6fb0>] get_vmalloc_info+0x70/0x110 [ 40.770102] PGD 0 [ 40.770107] Oops: 0000 [#1] SMP [ 40.770114] CPU 10 This patch introduces a static variable, grefs_per_grant_frame, to cache the calculated value. gnttab_init() now calls gnttab_request_version() early so that grant_table_version and grefs_per_grant_frame can be appropriately set. A few BUG_ON()s have been added to prevent this type of bug from reoccurring in the future. Signed-off-by: Matt Wilson <msw@amazon.com> Reviewed-and-Tested-by: Steven Noonan <snoonan@amazon.com> Acked-by: Ian Campbell <Ian.Campbell@citrix.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Annie Li <annie.li@oracle.com> Cc: xen-devel@lists.xen.org Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org # v3.3 and newer Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
2013-01-15 13:21:27 +00:00
gnttab_request_version();
max_nr_grant_frames = gnttab_max_grant_frames();
max_nr_grefs = max_nr_grant_frames *
gnttab_interface->grefs_per_grant_frame;
nr_grant_frames = 1;
/* Determine the maximum number of frames required for the
* grant reference free list on the current hypervisor.
*/
max_nr_glist_frames = max_nr_grefs / RPP;
treewide: kmalloc() -> kmalloc_array() The kmalloc() function has a 2-factor argument form, kmalloc_array(). This patch replaces cases of: kmalloc(a * b, gfp) with: kmalloc_array(a * b, gfp) as well as handling cases of: kmalloc(a * b * c, gfp) with: kmalloc(array3_size(a, b, c), gfp) as it's slightly less ugly than: kmalloc_array(array_size(a, b), c, gfp) This does, however, attempt to ignore constant size factors like: kmalloc(4 * 1024, gfp) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The tools/ directory was manually excluded, since it has its own implementation of kmalloc(). The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( kmalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | kmalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( kmalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(char) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(u8) * COUNT + COUNT , ...) | kmalloc( - sizeof(__u8) * COUNT + COUNT , ...) | kmalloc( - sizeof(char) * COUNT + COUNT , ...) | kmalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( - kmalloc + kmalloc_array ( - sizeof(TYPE) * (COUNT_ID) + COUNT_ID, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * COUNT_ID + COUNT_ID, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * (COUNT_CONST) + COUNT_CONST, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * COUNT_CONST + COUNT_CONST, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (COUNT_ID) + COUNT_ID, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * COUNT_ID + COUNT_ID, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (COUNT_CONST) + COUNT_CONST, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * COUNT_CONST + COUNT_CONST, sizeof(THING) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ - kmalloc + kmalloc_array ( - SIZE * COUNT + COUNT, SIZE , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( kmalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( kmalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kmalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kmalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( kmalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products, // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( kmalloc(C1 * C2 * C3, ...) | kmalloc( - (E1) * E2 * E3 + array3_size(E1, E2, E3) , ...) | kmalloc( - (E1) * (E2) * E3 + array3_size(E1, E2, E3) , ...) | kmalloc( - (E1) * (E2) * (E3) + array3_size(E1, E2, E3) , ...) | kmalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants, // keeping sizeof() as the second factor argument. @@ expression THING, E1, E2; type TYPE; constant C1, C2, C3; @@ ( kmalloc(sizeof(THING) * C2, ...) | kmalloc(sizeof(TYPE) * C2, ...) | kmalloc(C1 * C2 * C3, ...) | kmalloc(C1 * C2, ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * (E2) + E2, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * E2 + E2, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (E2) + E2, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * E2 + E2, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - (E1) * E2 + E1, E2 , ...) | - kmalloc + kmalloc_array ( - (E1) * (E2) + E1, E2 , ...) | - kmalloc + kmalloc_array ( - E1 * E2 + E1, E2 , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-12 20:55:00 +00:00
gnttab_list = kmalloc_array(max_nr_glist_frames,
sizeof(grant_ref_t *),
GFP_KERNEL);
if (gnttab_list == NULL)
return -ENOMEM;
nr_glist_frames = gnttab_frames(nr_grant_frames, RPP);
for (i = 0; i < nr_glist_frames; i++) {
gnttab_list[i] = (grant_ref_t *)__get_free_page(GFP_KERNEL);
if (gnttab_list[i] == NULL) {
ret = -ENOMEM;
goto ini_nomem;
}
}
gnttab_free_bitmap = bitmap_zalloc(max_nr_grefs, GFP_KERNEL);
if (!gnttab_free_bitmap) {
ret = -ENOMEM;
goto ini_nomem;
}
ret = arch_gnttab_init(max_nr_grant_frames,
nr_status_frames(max_nr_grant_frames));
if (ret < 0)
goto ini_nomem;
xen/grant-table: correctly initialize grant table version 1 Commit 85ff6acb075a484780b3d763fdf41596d8fc0970 (xen/granttable: Grant tables V2 implementation) changed the GREFS_PER_GRANT_FRAME macro from a constant to a conditional expression. The expression depends on grant_table_version being appropriately set. Unfortunately, at init time grant_table_version will be 0. The GREFS_PER_GRANT_FRAME conditional expression checks for "grant_table_version == 1", and therefore returns the number of grant references per frame for v2. This causes gnttab_init() to allocate fewer pages for gnttab_list, as a frame can old half the number of v2 entries than v1 entries. After gnttab_resume() is called, grant_table_version is appropriately set. nr_init_grefs will then be miscalculated and gnttab_free_count will hold a value larger than the actual number of free gref entries. If a guest is heavily utilizing improperly initialized v1 grant tables, memory corruption can occur. One common manifestation is corruption of the vmalloc list, resulting in a poisoned pointer derefrence when accessing /proc/meminfo or /proc/vmallocinfo: [ 40.770064] BUG: unable to handle kernel paging request at 0000200200001407 [ 40.770083] IP: [<ffffffff811a6fb0>] get_vmalloc_info+0x70/0x110 [ 40.770102] PGD 0 [ 40.770107] Oops: 0000 [#1] SMP [ 40.770114] CPU 10 This patch introduces a static variable, grefs_per_grant_frame, to cache the calculated value. gnttab_init() now calls gnttab_request_version() early so that grant_table_version and grefs_per_grant_frame can be appropriately set. A few BUG_ON()s have been added to prevent this type of bug from reoccurring in the future. Signed-off-by: Matt Wilson <msw@amazon.com> Reviewed-and-Tested-by: Steven Noonan <snoonan@amazon.com> Acked-by: Ian Campbell <Ian.Campbell@citrix.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Annie Li <annie.li@oracle.com> Cc: xen-devel@lists.xen.org Cc: linux-kernel@vger.kernel.org Cc: stable@vger.kernel.org # v3.3 and newer Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
2013-01-15 13:21:27 +00:00
if (gnttab_setup() < 0) {
ret = -ENODEV;
goto ini_nomem;
}
gnttab_size = nr_grant_frames * gnttab_interface->grefs_per_grant_frame;
gnttab_set_free(GNTTAB_NR_RESERVED_ENTRIES,
gnttab_size - GNTTAB_NR_RESERVED_ENTRIES);
printk("Grant table initialized\n");
return 0;
ini_nomem:
for (i--; i >= 0; i--)
free_page((unsigned long)gnttab_list[i]);
kfree(gnttab_list);
bitmap_free(gnttab_free_bitmap);
return ret;
}
EXPORT_SYMBOL_GPL(gnttab_init);
static int __gnttab_init(void)
{
if (!xen_domain())
return -ENODEV;
/* Delay grant-table initialization in the PV on HVM case */
if (xen_hvm_domain() && !xen_pvh_domain())
return 0;
return gnttab_init();
}
/* Starts after core_initcall so that xen_pvh_gnttab_setup can be called
* beforehand to initialize xen_auto_xlat_grant_frames. */
core_initcall_sync(__gnttab_init);