linux/kernel/resource.c

1641 lines
41 KiB
C
Raw Normal View History

/*
* linux/kernel/resource.c
*
* Copyright (C) 1999 Linus Torvalds
* Copyright (C) 1999 Martin Mares <mj@ucw.cz>
*
* Arbitrary resource management.
*/
resource: make sure requested range is included in the root range When the requested range is outside of the root range the logic in __reserve_region_with_split will cause an infinite recursion which will overflow the stack as seen in the warning bellow. This particular stack overflow was caused by requesting the (100000000-107ffffff) range while the root range was (0-ffffffff). In this case __request_resource would return the whole root range as conflict range (i.e. 0-ffffffff). Then, the logic in __reserve_region_with_split would continue the recursion requesting the new range as (conflict->end+1, end) which incidentally in this case equals the originally requested range. This patch aborts looking for an usable range when the request does not intersect with the root range. When the request partially overlaps with the root range, it ajust the request to fall in the root range and then continues with the new request. When the request is modified or aborted errors and a stack trace are logged to allow catching the errors in the upper layers. [ 5.968374] WARNING: at kernel/sched.c:4129 sub_preempt_count+0x63/0x89() [ 5.975150] Modules linked in: [ 5.978184] Pid: 1, comm: swapper Not tainted 3.0.22-mid27-00004-gb72c817 #46 [ 5.985324] Call Trace: [ 5.987759] [<c1039dfc>] ? console_unlock+0x17b/0x18d [ 5.992891] [<c1039620>] warn_slowpath_common+0x48/0x5d [ 5.998194] [<c1031758>] ? sub_preempt_count+0x63/0x89 [ 6.003412] [<c1039644>] warn_slowpath_null+0xf/0x13 [ 6.008453] [<c1031758>] sub_preempt_count+0x63/0x89 [ 6.013499] [<c14d60c4>] _raw_spin_unlock+0x27/0x3f [ 6.018453] [<c10c6349>] add_partial+0x36/0x3b [ 6.022973] [<c10c7c0a>] deactivate_slab+0x96/0xb4 [ 6.027842] [<c14cf9d9>] __slab_alloc.isra.54.constprop.63+0x204/0x241 [ 6.034456] [<c103f78f>] ? kzalloc.constprop.5+0x29/0x38 [ 6.039842] [<c103f78f>] ? kzalloc.constprop.5+0x29/0x38 [ 6.045232] [<c10c7dc9>] kmem_cache_alloc_trace+0x51/0xb0 [ 6.050710] [<c103f78f>] ? kzalloc.constprop.5+0x29/0x38 [ 6.056100] [<c103f78f>] kzalloc.constprop.5+0x29/0x38 [ 6.061320] [<c17b45e9>] __reserve_region_with_split+0x1c/0xd1 [ 6.067230] [<c17b4693>] __reserve_region_with_split+0xc6/0xd1 ... [ 7.179057] [<c17b4693>] __reserve_region_with_split+0xc6/0xd1 [ 7.184970] [<c17b4779>] reserve_region_with_split+0x30/0x42 [ 7.190709] [<c17a8ebf>] e820_reserve_resources_late+0xd1/0xe9 [ 7.196623] [<c17c9526>] pcibios_resource_survey+0x23/0x2a [ 7.202184] [<c17cad8a>] pcibios_init+0x23/0x35 [ 7.206789] [<c17ca574>] pci_subsys_init+0x3f/0x44 [ 7.211659] [<c1002088>] do_one_initcall+0x72/0x122 [ 7.216615] [<c17ca535>] ? pci_legacy_init+0x3d/0x3d [ 7.221659] [<c17a27ff>] kernel_init+0xa6/0x118 [ 7.226265] [<c17a2759>] ? start_kernel+0x334/0x334 [ 7.231223] [<c14d7482>] kernel_thread_helper+0x6/0x10 Signed-off-by: Octavian Purdila <octavian.purdila@intel.com> Signed-off-by: Ram Pai <linuxram@us.ibm.com> Cc: Jesse Barnes <jbarnes@virtuousgeek.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-07-31 05:42:58 +08:00
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/export.h>
#include <linux/errno.h>
#include <linux/ioport.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/fs.h>
#include <linux/proc_fs.h>
#include <linux/sched.h>
#include <linux/seq_file.h>
#include <linux/device.h>
#include <linux/pfn.h>
mem hotunplug: fix kfree() of bootmem memory When hot removing memory presented at boot time, following messages are shown: kernel BUG at mm/slub.c:3409! invalid opcode: 0000 [#1] SMP Modules linked in: ebtable_nat ebtables xt_CHECKSUM iptable_mangle bridge stp llc ipmi_devintf ipmi_msghandler sunrpc ipt_REJECT nf_conntrack_ipv4 nf_defrag_ipv4 iptable_filter ip_tables ip6t_REJECT nf_conntrack_ipv6 nf_defrag_ipv6 xt_state nf_conntrack ip6table_filter ip6_tables binfmt_misc vfat fat dm_mirror dm_region_hash dm_log dm_mod vhost_net macvtap macvlan tun uinput iTCO_wdt iTCO_vendor_support coretemp kvm_intel kvm crc32c_intel ghash_clmulni_intel microcode pcspkr sg i2c_i801 lpc_ich mfd_core igb i2c_algo_bit i2c_core e1000e ptp pps_core tpm_infineon ioatdma dca sr_mod cdrom sd_mod crc_t10dif usb_storage megaraid_sas lpfc scsi_transport_fc scsi_tgt scsi_mod CPU 0 Pid: 5091, comm: kworker/0:2 Tainted: G W 3.9.0-rc6+ #15 RIP: kfree+0x232/0x240 Process kworker/0:2 (pid: 5091, threadinfo ffff88084678c000, task ffff88083928ca80) Call Trace: __release_region+0xd4/0xe0 __remove_pages+0x52/0x110 arch_remove_memory+0x89/0xd0 remove_memory+0xc4/0x100 acpi_memory_device_remove+0x6d/0xb1 acpi_device_remove+0x89/0xab __device_release_driver+0x7c/0xf0 device_release_driver+0x2f/0x50 acpi_bus_device_detach+0x6c/0x70 acpi_ns_walk_namespace+0x11a/0x250 acpi_walk_namespace+0xee/0x137 acpi_bus_trim+0x33/0x7a acpi_bus_hot_remove_device+0xc4/0x1a1 acpi_os_execute_deferred+0x27/0x34 process_one_work+0x1f7/0x590 worker_thread+0x11a/0x370 kthread+0xee/0x100 ret_from_fork+0x7c/0xb0 RIP [<ffffffff811c41d2>] kfree+0x232/0x240 RSP <ffff88084678d968> The reason why the messages are shown is to release a resource structure, allocated by bootmem, by kfree(). So when we release a resource structure, we should check whether it is allocated by bootmem or not. But even if we know a resource structure is allocated by bootmem, we cannot release it since SLxB cannot treat it. So for reusing a resource structure, this patch remembers it by using bootmem_resource as follows: When releasing a resource structure by free_resource(), free_resource() checks whether the resource structure is allocated by bootmem or not. If it is allocated by bootmem, free_resource() adds it to bootmem_resource. If it is not allocated by bootmem, free_resource() release it by kfree(). And when getting a new resource structure by get_resource(), get_resource() checks whether bootmem_resource has released resource structures or not. If there is a released resource structure, get_resource() returns it. If there is not a releaed resource structure, get_resource() returns new resource structure allocated by kzalloc(). [akpm@linux-foundation.org: s/get_resource/alloc_resource/] Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Reviewed-by: Toshi Kani <toshi.kani@hp.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Ram Pai <linuxram@us.ibm.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-30 06:08:56 +08:00
#include <linux/mm.h>
#include <linux/resource_ext.h>
#include <asm/io.h>
struct resource ioport_resource = {
.name = "PCI IO",
.start = 0,
.end = IO_SPACE_LIMIT,
.flags = IORESOURCE_IO,
};
EXPORT_SYMBOL(ioport_resource);
struct resource iomem_resource = {
.name = "PCI mem",
.start = 0,
.end = -1,
.flags = IORESOURCE_MEM,
};
EXPORT_SYMBOL(iomem_resource);
/* constraints to be met while allocating resources */
struct resource_constraint {
resource_size_t min, max, align;
resource_size_t (*alignf)(void *, const struct resource *,
resource_size_t, resource_size_t);
void *alignf_data;
};
static DEFINE_RWLOCK(resource_lock);
mem hotunplug: fix kfree() of bootmem memory When hot removing memory presented at boot time, following messages are shown: kernel BUG at mm/slub.c:3409! invalid opcode: 0000 [#1] SMP Modules linked in: ebtable_nat ebtables xt_CHECKSUM iptable_mangle bridge stp llc ipmi_devintf ipmi_msghandler sunrpc ipt_REJECT nf_conntrack_ipv4 nf_defrag_ipv4 iptable_filter ip_tables ip6t_REJECT nf_conntrack_ipv6 nf_defrag_ipv6 xt_state nf_conntrack ip6table_filter ip6_tables binfmt_misc vfat fat dm_mirror dm_region_hash dm_log dm_mod vhost_net macvtap macvlan tun uinput iTCO_wdt iTCO_vendor_support coretemp kvm_intel kvm crc32c_intel ghash_clmulni_intel microcode pcspkr sg i2c_i801 lpc_ich mfd_core igb i2c_algo_bit i2c_core e1000e ptp pps_core tpm_infineon ioatdma dca sr_mod cdrom sd_mod crc_t10dif usb_storage megaraid_sas lpfc scsi_transport_fc scsi_tgt scsi_mod CPU 0 Pid: 5091, comm: kworker/0:2 Tainted: G W 3.9.0-rc6+ #15 RIP: kfree+0x232/0x240 Process kworker/0:2 (pid: 5091, threadinfo ffff88084678c000, task ffff88083928ca80) Call Trace: __release_region+0xd4/0xe0 __remove_pages+0x52/0x110 arch_remove_memory+0x89/0xd0 remove_memory+0xc4/0x100 acpi_memory_device_remove+0x6d/0xb1 acpi_device_remove+0x89/0xab __device_release_driver+0x7c/0xf0 device_release_driver+0x2f/0x50 acpi_bus_device_detach+0x6c/0x70 acpi_ns_walk_namespace+0x11a/0x250 acpi_walk_namespace+0xee/0x137 acpi_bus_trim+0x33/0x7a acpi_bus_hot_remove_device+0xc4/0x1a1 acpi_os_execute_deferred+0x27/0x34 process_one_work+0x1f7/0x590 worker_thread+0x11a/0x370 kthread+0xee/0x100 ret_from_fork+0x7c/0xb0 RIP [<ffffffff811c41d2>] kfree+0x232/0x240 RSP <ffff88084678d968> The reason why the messages are shown is to release a resource structure, allocated by bootmem, by kfree(). So when we release a resource structure, we should check whether it is allocated by bootmem or not. But even if we know a resource structure is allocated by bootmem, we cannot release it since SLxB cannot treat it. So for reusing a resource structure, this patch remembers it by using bootmem_resource as follows: When releasing a resource structure by free_resource(), free_resource() checks whether the resource structure is allocated by bootmem or not. If it is allocated by bootmem, free_resource() adds it to bootmem_resource. If it is not allocated by bootmem, free_resource() release it by kfree(). And when getting a new resource structure by get_resource(), get_resource() checks whether bootmem_resource has released resource structures or not. If there is a released resource structure, get_resource() returns it. If there is not a releaed resource structure, get_resource() returns new resource structure allocated by kzalloc(). [akpm@linux-foundation.org: s/get_resource/alloc_resource/] Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Reviewed-by: Toshi Kani <toshi.kani@hp.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Ram Pai <linuxram@us.ibm.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-30 06:08:56 +08:00
/*
* For memory hotplug, there is no way to free resource entries allocated
* by boot mem after the system is up. So for reusing the resource entry
* we need to remember the resource.
*/
static struct resource *bootmem_resource_free;
static DEFINE_SPINLOCK(bootmem_resource_lock);
resource: provide new functions to walk through resources I have added two more functions to walk through resources. Currently walk_system_ram_range() deals with pfn and /proc/iomem can contain partial pages. By dealing in pfn, callback function loses the info that last page of a memory range is a partial page and not the full page. So I implemented walk_system_ram_res() which returns u64 values to callback functions and now it properly return start and end address. walk_system_ram_range() uses find_next_system_ram() to find the next ram resource. This in turn only travels through siblings of top level child and does not travers through all the nodes of the resoruce tree. I also need another function where I can walk through all the resources, for example figure out where "GART" aperture is. Figure out where ACPI memory is. So I wrote another function walk_iomem_res() which walks through all /proc/iomem resources and returns matches as asked by caller. Caller can specify "name" of resource, start and end and flags. Got rid of find_next_system_ram_res() and instead implemented more generic find_next_iomem_res() which can be used to traverse top level children only based on an argument. Signed-off-by: Vivek Goyal <vgoyal@redhat.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Borislav Petkov <bp@suse.de> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: Eric Biederman <ebiederm@xmission.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Matthew Garrett <mjg59@srcf.ucam.org> Cc: Greg Kroah-Hartman <greg@kroah.com> Cc: Dave Young <dyoung@redhat.com> Cc: WANG Chao <chaowang@redhat.com> Cc: Baoquan He <bhe@redhat.com> Cc: Andy Lutomirski <luto@amacapital.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-09 05:25:50 +08:00
static struct resource *next_resource(struct resource *p, bool sibling_only)
{
resource: provide new functions to walk through resources I have added two more functions to walk through resources. Currently walk_system_ram_range() deals with pfn and /proc/iomem can contain partial pages. By dealing in pfn, callback function loses the info that last page of a memory range is a partial page and not the full page. So I implemented walk_system_ram_res() which returns u64 values to callback functions and now it properly return start and end address. walk_system_ram_range() uses find_next_system_ram() to find the next ram resource. This in turn only travels through siblings of top level child and does not travers through all the nodes of the resoruce tree. I also need another function where I can walk through all the resources, for example figure out where "GART" aperture is. Figure out where ACPI memory is. So I wrote another function walk_iomem_res() which walks through all /proc/iomem resources and returns matches as asked by caller. Caller can specify "name" of resource, start and end and flags. Got rid of find_next_system_ram_res() and instead implemented more generic find_next_iomem_res() which can be used to traverse top level children only based on an argument. Signed-off-by: Vivek Goyal <vgoyal@redhat.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Borislav Petkov <bp@suse.de> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: Eric Biederman <ebiederm@xmission.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Matthew Garrett <mjg59@srcf.ucam.org> Cc: Greg Kroah-Hartman <greg@kroah.com> Cc: Dave Young <dyoung@redhat.com> Cc: WANG Chao <chaowang@redhat.com> Cc: Baoquan He <bhe@redhat.com> Cc: Andy Lutomirski <luto@amacapital.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-09 05:25:50 +08:00
/* Caller wants to traverse through siblings only */
if (sibling_only)
return p->sibling;
if (p->child)
return p->child;
while (!p->sibling && p->parent)
p = p->parent;
return p->sibling;
}
resource: provide new functions to walk through resources I have added two more functions to walk through resources. Currently walk_system_ram_range() deals with pfn and /proc/iomem can contain partial pages. By dealing in pfn, callback function loses the info that last page of a memory range is a partial page and not the full page. So I implemented walk_system_ram_res() which returns u64 values to callback functions and now it properly return start and end address. walk_system_ram_range() uses find_next_system_ram() to find the next ram resource. This in turn only travels through siblings of top level child and does not travers through all the nodes of the resoruce tree. I also need another function where I can walk through all the resources, for example figure out where "GART" aperture is. Figure out where ACPI memory is. So I wrote another function walk_iomem_res() which walks through all /proc/iomem resources and returns matches as asked by caller. Caller can specify "name" of resource, start and end and flags. Got rid of find_next_system_ram_res() and instead implemented more generic find_next_iomem_res() which can be used to traverse top level children only based on an argument. Signed-off-by: Vivek Goyal <vgoyal@redhat.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Borislav Petkov <bp@suse.de> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: Eric Biederman <ebiederm@xmission.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Matthew Garrett <mjg59@srcf.ucam.org> Cc: Greg Kroah-Hartman <greg@kroah.com> Cc: Dave Young <dyoung@redhat.com> Cc: WANG Chao <chaowang@redhat.com> Cc: Baoquan He <bhe@redhat.com> Cc: Andy Lutomirski <luto@amacapital.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-09 05:25:50 +08:00
static void *r_next(struct seq_file *m, void *v, loff_t *pos)
{
struct resource *p = v;
(*pos)++;
return (void *)next_resource(p, false);
}
#ifdef CONFIG_PROC_FS
enum { MAX_IORES_LEVEL = 5 };
static void *r_start(struct seq_file *m, loff_t *pos)
__acquires(resource_lock)
{
struct resource *p = PDE_DATA(file_inode(m->file));
loff_t l = 0;
read_lock(&resource_lock);
for (p = p->child; p && l < *pos; p = r_next(m, p, &l))
;
return p;
}
static void r_stop(struct seq_file *m, void *v)
__releases(resource_lock)
{
read_unlock(&resource_lock);
}
static int r_show(struct seq_file *m, void *v)
{
struct resource *root = PDE_DATA(file_inode(m->file));
struct resource *r = v, *p;
unsigned long long start, end;
int width = root->end < 0x10000 ? 4 : 8;
int depth;
for (depth = 0, p = r; depth < MAX_IORES_LEVEL; depth++, p = p->parent)
if (p->parent == root)
break;
if (file_ns_capable(m->file, &init_user_ns, CAP_SYS_ADMIN)) {
start = r->start;
end = r->end;
} else {
start = end = 0;
}
seq_printf(m, "%*s%0*llx-%0*llx : %s\n",
depth * 2, "",
width, start,
width, end,
r->name ? r->name : "<BAD>");
return 0;
}
static const struct seq_operations resource_op = {
.start = r_start,
.next = r_next,
.stop = r_stop,
.show = r_show,
};
static int __init ioresources_init(void)
{
proc_create_seq_data("ioports", 0, NULL, &resource_op,
&ioport_resource);
proc_create_seq_data("iomem", 0, NULL, &resource_op, &iomem_resource);
return 0;
}
__initcall(ioresources_init);
#endif /* CONFIG_PROC_FS */
mem hotunplug: fix kfree() of bootmem memory When hot removing memory presented at boot time, following messages are shown: kernel BUG at mm/slub.c:3409! invalid opcode: 0000 [#1] SMP Modules linked in: ebtable_nat ebtables xt_CHECKSUM iptable_mangle bridge stp llc ipmi_devintf ipmi_msghandler sunrpc ipt_REJECT nf_conntrack_ipv4 nf_defrag_ipv4 iptable_filter ip_tables ip6t_REJECT nf_conntrack_ipv6 nf_defrag_ipv6 xt_state nf_conntrack ip6table_filter ip6_tables binfmt_misc vfat fat dm_mirror dm_region_hash dm_log dm_mod vhost_net macvtap macvlan tun uinput iTCO_wdt iTCO_vendor_support coretemp kvm_intel kvm crc32c_intel ghash_clmulni_intel microcode pcspkr sg i2c_i801 lpc_ich mfd_core igb i2c_algo_bit i2c_core e1000e ptp pps_core tpm_infineon ioatdma dca sr_mod cdrom sd_mod crc_t10dif usb_storage megaraid_sas lpfc scsi_transport_fc scsi_tgt scsi_mod CPU 0 Pid: 5091, comm: kworker/0:2 Tainted: G W 3.9.0-rc6+ #15 RIP: kfree+0x232/0x240 Process kworker/0:2 (pid: 5091, threadinfo ffff88084678c000, task ffff88083928ca80) Call Trace: __release_region+0xd4/0xe0 __remove_pages+0x52/0x110 arch_remove_memory+0x89/0xd0 remove_memory+0xc4/0x100 acpi_memory_device_remove+0x6d/0xb1 acpi_device_remove+0x89/0xab __device_release_driver+0x7c/0xf0 device_release_driver+0x2f/0x50 acpi_bus_device_detach+0x6c/0x70 acpi_ns_walk_namespace+0x11a/0x250 acpi_walk_namespace+0xee/0x137 acpi_bus_trim+0x33/0x7a acpi_bus_hot_remove_device+0xc4/0x1a1 acpi_os_execute_deferred+0x27/0x34 process_one_work+0x1f7/0x590 worker_thread+0x11a/0x370 kthread+0xee/0x100 ret_from_fork+0x7c/0xb0 RIP [<ffffffff811c41d2>] kfree+0x232/0x240 RSP <ffff88084678d968> The reason why the messages are shown is to release a resource structure, allocated by bootmem, by kfree(). So when we release a resource structure, we should check whether it is allocated by bootmem or not. But even if we know a resource structure is allocated by bootmem, we cannot release it since SLxB cannot treat it. So for reusing a resource structure, this patch remembers it by using bootmem_resource as follows: When releasing a resource structure by free_resource(), free_resource() checks whether the resource structure is allocated by bootmem or not. If it is allocated by bootmem, free_resource() adds it to bootmem_resource. If it is not allocated by bootmem, free_resource() release it by kfree(). And when getting a new resource structure by get_resource(), get_resource() checks whether bootmem_resource has released resource structures or not. If there is a released resource structure, get_resource() returns it. If there is not a releaed resource structure, get_resource() returns new resource structure allocated by kzalloc(). [akpm@linux-foundation.org: s/get_resource/alloc_resource/] Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Reviewed-by: Toshi Kani <toshi.kani@hp.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Ram Pai <linuxram@us.ibm.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-30 06:08:56 +08:00
static void free_resource(struct resource *res)
{
if (!res)
return;
if (!PageSlab(virt_to_head_page(res))) {
spin_lock(&bootmem_resource_lock);
res->sibling = bootmem_resource_free;
bootmem_resource_free = res;
spin_unlock(&bootmem_resource_lock);
} else {
kfree(res);
}
}
static struct resource *alloc_resource(gfp_t flags)
{
struct resource *res = NULL;
spin_lock(&bootmem_resource_lock);
if (bootmem_resource_free) {
res = bootmem_resource_free;
bootmem_resource_free = res->sibling;
}
spin_unlock(&bootmem_resource_lock);
if (res)
memset(res, 0, sizeof(struct resource));
else
res = kzalloc(sizeof(struct resource), flags);
return res;
}
/* Return the conflict entry if you can't request it */
static struct resource * __request_resource(struct resource *root, struct resource *new)
{
resource_size_t start = new->start;
resource_size_t end = new->end;
struct resource *tmp, **p;
if (end < start)
return root;
if (start < root->start)
return root;
if (end > root->end)
return root;
p = &root->child;
for (;;) {
tmp = *p;
if (!tmp || tmp->start > end) {
new->sibling = tmp;
*p = new;
new->parent = root;
return NULL;
}
p = &tmp->sibling;
if (tmp->end < start)
continue;
return tmp;
}
}
static int __release_resource(struct resource *old, bool release_child)
{
struct resource *tmp, **p, *chd;
p = &old->parent->child;
for (;;) {
tmp = *p;
if (!tmp)
break;
if (tmp == old) {
if (release_child || !(tmp->child)) {
*p = tmp->sibling;
} else {
for (chd = tmp->child;; chd = chd->sibling) {
chd->parent = tmp->parent;
if (!(chd->sibling))
break;
}
*p = tmp->child;
chd->sibling = tmp->sibling;
}
old->parent = NULL;
return 0;
}
p = &tmp->sibling;
}
return -EINVAL;
}
static void __release_child_resources(struct resource *r)
{
struct resource *tmp, *p;
resource_size_t size;
p = r->child;
r->child = NULL;
while (p) {
tmp = p;
p = p->sibling;
tmp->parent = NULL;
tmp->sibling = NULL;
__release_child_resources(tmp);
printk(KERN_DEBUG "release child resource %pR\n", tmp);
/* need to restore size, and keep flags */
size = resource_size(tmp);
tmp->start = 0;
tmp->end = size - 1;
}
}
void release_child_resources(struct resource *r)
{
write_lock(&resource_lock);
__release_child_resources(r);
write_unlock(&resource_lock);
}
/**
* request_resource_conflict - request and reserve an I/O or memory resource
* @root: root resource descriptor
* @new: resource descriptor desired by caller
*
* Returns 0 for success, conflict resource on error.
*/
struct resource *request_resource_conflict(struct resource *root, struct resource *new)
{
struct resource *conflict;
write_lock(&resource_lock);
conflict = __request_resource(root, new);
write_unlock(&resource_lock);
return conflict;
}
/**
* request_resource - request and reserve an I/O or memory resource
* @root: root resource descriptor
* @new: resource descriptor desired by caller
*
* Returns 0 for success, negative error code on error.
*/
int request_resource(struct resource *root, struct resource *new)
{
struct resource *conflict;
conflict = request_resource_conflict(root, new);
return conflict ? -EBUSY : 0;
}
EXPORT_SYMBOL(request_resource);
/**
* release_resource - release a previously reserved resource
* @old: resource pointer
*/
int release_resource(struct resource *old)
{
int retval;
write_lock(&resource_lock);
retval = __release_resource(old, true);
write_unlock(&resource_lock);
return retval;
}
EXPORT_SYMBOL(release_resource);
/**
* Finds the lowest iomem resource that covers part of [@start..@end]. The
* caller must specify @start, @end, @flags, and @desc (which may be
resource: Fix find_next_iomem_res() iteration issue Previously find_next_iomem_res() used "*res" as both an input parameter for the range to search and the type of resource to search for, and an output parameter for the resource we found, which makes the interface confusing. The current callers use find_next_iomem_res() incorrectly because they allocate a single struct resource and use it for repeated calls to find_next_iomem_res(). When find_next_iomem_res() returns a resource, it overwrites the start, end, flags, and desc members of the struct. If we call find_next_iomem_res() again, we must update or restore these fields. The previous code restored res.start and res.end, but not res.flags or res.desc. Since the callers did not restore res.flags, if they searched for flags IORESOURCE_MEM | IORESOURCE_BUSY and found a resource with flags IORESOURCE_MEM | IORESOURCE_BUSY | IORESOURCE_SYSRAM, the next search would incorrectly skip resources unless they were also marked as IORESOURCE_SYSRAM. Fix this by restructuring the interface so it takes explicit "start, end, flags" parameters and uses "*res" only as an output parameter. Based on a patch by Lianbo Jiang <lijiang@redhat.com>. [ bp: While at it: - make comments kernel-doc style. - Originally-by: http://lore.kernel.org/lkml/20180921073211.20097-2-lijiang@redhat.com Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Signed-off-by: Borislav Petkov <bp@suse.de> CC: Andrew Morton <akpm@linux-foundation.org> CC: Brijesh Singh <brijesh.singh@amd.com> CC: Dan Williams <dan.j.williams@intel.com> CC: H. Peter Anvin <hpa@zytor.com> CC: Lianbo Jiang <lijiang@redhat.com> CC: Takashi Iwai <tiwai@suse.de> CC: Thomas Gleixner <tglx@linutronix.de> CC: Tom Lendacky <thomas.lendacky@amd.com> CC: Vivek Goyal <vgoyal@redhat.com> CC: Yaowei Bai <baiyaowei@cmss.chinamobile.com> CC: bhe@redhat.com CC: dan.j.williams@intel.com CC: dyoung@redhat.com CC: kexec@lists.infradead.org CC: mingo@redhat.com CC: x86-ml <x86@kernel.org> Link: http://lkml.kernel.org/r/153805812916.1157.177580438135143788.stgit@bhelgaas-glaptop.roam.corp.google.com
2018-09-27 22:22:09 +08:00
* IORES_DESC_NONE).
*
* If a resource is found, returns 0 and @*res is overwritten with the part
* of the resource that's within [@start..@end]; if none is found, returns
* -1 or -EINVAL for other invalid parameters.
resource: Fix find_next_iomem_res() iteration issue Previously find_next_iomem_res() used "*res" as both an input parameter for the range to search and the type of resource to search for, and an output parameter for the resource we found, which makes the interface confusing. The current callers use find_next_iomem_res() incorrectly because they allocate a single struct resource and use it for repeated calls to find_next_iomem_res(). When find_next_iomem_res() returns a resource, it overwrites the start, end, flags, and desc members of the struct. If we call find_next_iomem_res() again, we must update or restore these fields. The previous code restored res.start and res.end, but not res.flags or res.desc. Since the callers did not restore res.flags, if they searched for flags IORESOURCE_MEM | IORESOURCE_BUSY and found a resource with flags IORESOURCE_MEM | IORESOURCE_BUSY | IORESOURCE_SYSRAM, the next search would incorrectly skip resources unless they were also marked as IORESOURCE_SYSRAM. Fix this by restructuring the interface so it takes explicit "start, end, flags" parameters and uses "*res" only as an output parameter. Based on a patch by Lianbo Jiang <lijiang@redhat.com>. [ bp: While at it: - make comments kernel-doc style. - Originally-by: http://lore.kernel.org/lkml/20180921073211.20097-2-lijiang@redhat.com Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Signed-off-by: Borislav Petkov <bp@suse.de> CC: Andrew Morton <akpm@linux-foundation.org> CC: Brijesh Singh <brijesh.singh@amd.com> CC: Dan Williams <dan.j.williams@intel.com> CC: H. Peter Anvin <hpa@zytor.com> CC: Lianbo Jiang <lijiang@redhat.com> CC: Takashi Iwai <tiwai@suse.de> CC: Thomas Gleixner <tglx@linutronix.de> CC: Tom Lendacky <thomas.lendacky@amd.com> CC: Vivek Goyal <vgoyal@redhat.com> CC: Yaowei Bai <baiyaowei@cmss.chinamobile.com> CC: bhe@redhat.com CC: dan.j.williams@intel.com CC: dyoung@redhat.com CC: kexec@lists.infradead.org CC: mingo@redhat.com CC: x86-ml <x86@kernel.org> Link: http://lkml.kernel.org/r/153805812916.1157.177580438135143788.stgit@bhelgaas-glaptop.roam.corp.google.com
2018-09-27 22:22:09 +08:00
*
* This function walks the whole tree and not just first level children
* unless @first_lvl is true.
*
* @start: start address of the resource searched for
* @end: end address of same resource
* @flags: flags which the resource must have
* @desc: descriptor the resource must have
* @first_lvl: walk only the first level children, if set
* @res: return ptr, if resource found
*/
resource: Fix find_next_iomem_res() iteration issue Previously find_next_iomem_res() used "*res" as both an input parameter for the range to search and the type of resource to search for, and an output parameter for the resource we found, which makes the interface confusing. The current callers use find_next_iomem_res() incorrectly because they allocate a single struct resource and use it for repeated calls to find_next_iomem_res(). When find_next_iomem_res() returns a resource, it overwrites the start, end, flags, and desc members of the struct. If we call find_next_iomem_res() again, we must update or restore these fields. The previous code restored res.start and res.end, but not res.flags or res.desc. Since the callers did not restore res.flags, if they searched for flags IORESOURCE_MEM | IORESOURCE_BUSY and found a resource with flags IORESOURCE_MEM | IORESOURCE_BUSY | IORESOURCE_SYSRAM, the next search would incorrectly skip resources unless they were also marked as IORESOURCE_SYSRAM. Fix this by restructuring the interface so it takes explicit "start, end, flags" parameters and uses "*res" only as an output parameter. Based on a patch by Lianbo Jiang <lijiang@redhat.com>. [ bp: While at it: - make comments kernel-doc style. - Originally-by: http://lore.kernel.org/lkml/20180921073211.20097-2-lijiang@redhat.com Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Signed-off-by: Borislav Petkov <bp@suse.de> CC: Andrew Morton <akpm@linux-foundation.org> CC: Brijesh Singh <brijesh.singh@amd.com> CC: Dan Williams <dan.j.williams@intel.com> CC: H. Peter Anvin <hpa@zytor.com> CC: Lianbo Jiang <lijiang@redhat.com> CC: Takashi Iwai <tiwai@suse.de> CC: Thomas Gleixner <tglx@linutronix.de> CC: Tom Lendacky <thomas.lendacky@amd.com> CC: Vivek Goyal <vgoyal@redhat.com> CC: Yaowei Bai <baiyaowei@cmss.chinamobile.com> CC: bhe@redhat.com CC: dan.j.williams@intel.com CC: dyoung@redhat.com CC: kexec@lists.infradead.org CC: mingo@redhat.com CC: x86-ml <x86@kernel.org> Link: http://lkml.kernel.org/r/153805812916.1157.177580438135143788.stgit@bhelgaas-glaptop.roam.corp.google.com
2018-09-27 22:22:09 +08:00
static int find_next_iomem_res(resource_size_t start, resource_size_t end,
unsigned long flags, unsigned long desc,
bool first_lvl, struct resource *res)
{
struct resource *p;
if (!res)
return -EINVAL;
if (start >= end)
return -EINVAL;
resource: provide new functions to walk through resources I have added two more functions to walk through resources. Currently walk_system_ram_range() deals with pfn and /proc/iomem can contain partial pages. By dealing in pfn, callback function loses the info that last page of a memory range is a partial page and not the full page. So I implemented walk_system_ram_res() which returns u64 values to callback functions and now it properly return start and end address. walk_system_ram_range() uses find_next_system_ram() to find the next ram resource. This in turn only travels through siblings of top level child and does not travers through all the nodes of the resoruce tree. I also need another function where I can walk through all the resources, for example figure out where "GART" aperture is. Figure out where ACPI memory is. So I wrote another function walk_iomem_res() which walks through all /proc/iomem resources and returns matches as asked by caller. Caller can specify "name" of resource, start and end and flags. Got rid of find_next_system_ram_res() and instead implemented more generic find_next_iomem_res() which can be used to traverse top level children only based on an argument. Signed-off-by: Vivek Goyal <vgoyal@redhat.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Borislav Petkov <bp@suse.de> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: Eric Biederman <ebiederm@xmission.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Matthew Garrett <mjg59@srcf.ucam.org> Cc: Greg Kroah-Hartman <greg@kroah.com> Cc: Dave Young <dyoung@redhat.com> Cc: WANG Chao <chaowang@redhat.com> Cc: Baoquan He <bhe@redhat.com> Cc: Andy Lutomirski <luto@amacapital.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-09 05:25:50 +08:00
resource: fix the case of null pointer access Richard and Daniel reported that UML is broken due to changes to resource traversal functions. Problem is that iomem_resource.child can be null and new code does not consider that possibility. Old code used a for loop and that loop will not even execute if p was null. Revert back to for() loop logic and bail out if p is null. I also moved sibling_only check out of resource_lock. There is no reason to keep it inside the lock. Following is backtrace of the UML crash. RIP: 0033:[<0000000060039b9f>] RSP: 0000000081459da0 EFLAGS: 00010202 RAX: 0000000000000000 RBX: 00000000219b3fff RCX: 000000006010d1d9 RDX: 0000000000000001 RSI: 00000000602dfb94 RDI: 0000000081459df8 RBP: 0000000081459de0 R08: 00000000601b59f4 R09: ffffffff0000ff00 R10: ffffffff0000ff00 R11: 0000000081459e88 R12: 0000000081459df8 R13: 00000000219b3fff R14: 00000000602dfb94 R15: 0000000000000000 Kernel panic - not syncing: Segfault with no mm CPU: 0 PID: 1 Comm: swapper Not tainted 3.16.0-10454-g58d08e3 #13 Stack: 00000000 000080d0 81459df0 219b3fff 81459e70 6010d1d9 ffffffff 6033e010 81459e50 6003a269 81459e30 00000000 Call Trace: [<6010d1d9>] ? kclist_add_private+0x0/0xe7 [<6003a269>] walk_system_ram_range+0x61/0xb7 [<6000e859>] ? proc_kcore_init+0x0/0xf1 [<6010d574>] kcore_update_ram+0x4c/0x168 [<6010d72e>] ? kclist_add+0x0/0x2e [<6000e943>] proc_kcore_init+0xea/0xf1 [<6000e859>] ? proc_kcore_init+0x0/0xf1 [<6000e859>] ? proc_kcore_init+0x0/0xf1 [<600189f0>] do_one_initcall+0x13c/0x204 [<6004ca46>] ? parse_args+0x1df/0x2e0 [<6004c82d>] ? parameq+0x0/0x3a [<601b5990>] ? strcpy+0x0/0x18 [<60001e1a>] kernel_init_freeable+0x240/0x31e [<6026f1c0>] kernel_init+0x12/0x148 [<60019fad>] new_thread_handler+0x81/0xa3 Fixes 8c86e70acead629aacb4a ("resource: provide new functions to walk through resources"). Reported-by: Daniel Walter <sahne@0x90.at> Tested-by: Richard Weinberger <richard@nod.at> Tested-by: Toralf Förster <toralf.foerster@gmx.de> Tested-by: Daniel Walter <sahne@0x90.at> Signed-off-by: Vivek Goyal <vgoyal@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-30 06:18:29 +08:00
read_lock(&resource_lock);
for (p = iomem_resource.child; p; p = next_resource(p, first_lvl)) {
resource: Fix find_next_iomem_res() iteration issue Previously find_next_iomem_res() used "*res" as both an input parameter for the range to search and the type of resource to search for, and an output parameter for the resource we found, which makes the interface confusing. The current callers use find_next_iomem_res() incorrectly because they allocate a single struct resource and use it for repeated calls to find_next_iomem_res(). When find_next_iomem_res() returns a resource, it overwrites the start, end, flags, and desc members of the struct. If we call find_next_iomem_res() again, we must update or restore these fields. The previous code restored res.start and res.end, but not res.flags or res.desc. Since the callers did not restore res.flags, if they searched for flags IORESOURCE_MEM | IORESOURCE_BUSY and found a resource with flags IORESOURCE_MEM | IORESOURCE_BUSY | IORESOURCE_SYSRAM, the next search would incorrectly skip resources unless they were also marked as IORESOURCE_SYSRAM. Fix this by restructuring the interface so it takes explicit "start, end, flags" parameters and uses "*res" only as an output parameter. Based on a patch by Lianbo Jiang <lijiang@redhat.com>. [ bp: While at it: - make comments kernel-doc style. - Originally-by: http://lore.kernel.org/lkml/20180921073211.20097-2-lijiang@redhat.com Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Signed-off-by: Borislav Petkov <bp@suse.de> CC: Andrew Morton <akpm@linux-foundation.org> CC: Brijesh Singh <brijesh.singh@amd.com> CC: Dan Williams <dan.j.williams@intel.com> CC: H. Peter Anvin <hpa@zytor.com> CC: Lianbo Jiang <lijiang@redhat.com> CC: Takashi Iwai <tiwai@suse.de> CC: Thomas Gleixner <tglx@linutronix.de> CC: Tom Lendacky <thomas.lendacky@amd.com> CC: Vivek Goyal <vgoyal@redhat.com> CC: Yaowei Bai <baiyaowei@cmss.chinamobile.com> CC: bhe@redhat.com CC: dan.j.williams@intel.com CC: dyoung@redhat.com CC: kexec@lists.infradead.org CC: mingo@redhat.com CC: x86-ml <x86@kernel.org> Link: http://lkml.kernel.org/r/153805812916.1157.177580438135143788.stgit@bhelgaas-glaptop.roam.corp.google.com
2018-09-27 22:22:09 +08:00
if ((p->flags & flags) != flags)
continue;
if ((desc != IORES_DESC_NONE) && (desc != p->desc))
continue;
if (p->start > end) {
p = NULL;
break;
}
resource: Include resource end in walk_*() interfaces find_next_iomem_res() finds an iomem resource that covers part of a range described by "start, end". All callers expect that range to be inclusive, i.e., both start and end are included, but find_next_iomem_res() doesn't handle the end address correctly. If it finds an iomem resource that contains exactly the end address, it skips it, e.g., if "start, end" is [0x0-0x10000] and there happens to be an iomem resource [mem 0x10000-0x10000] (the single byte at 0x10000), we skip it: find_next_iomem_res(...) { start = 0x0; end = 0x10000; for (p = next_resource(...)) { # p->start = 0x10000; # p->end = 0x10000; # we *should* return this resource, but this condition is false: if ((p->end >= start) && (p->start < end)) break; Adjust find_next_iomem_res() so it allows a resource that includes the single byte at the end of the range. This is a corner case that we probably don't see in practice. Fixes: 58c1b5b07907 ("[PATCH] memory hotadd fixes: find_next_system_ram catch range fix") Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Signed-off-by: Borislav Petkov <bp@suse.de> CC: Andrew Morton <akpm@linux-foundation.org> CC: Brijesh Singh <brijesh.singh@amd.com> CC: Dan Williams <dan.j.williams@intel.com> CC: H. Peter Anvin <hpa@zytor.com> CC: Lianbo Jiang <lijiang@redhat.com> CC: Takashi Iwai <tiwai@suse.de> CC: Thomas Gleixner <tglx@linutronix.de> CC: Tom Lendacky <thomas.lendacky@amd.com> CC: Vivek Goyal <vgoyal@redhat.com> CC: Yaowei Bai <baiyaowei@cmss.chinamobile.com> CC: bhe@redhat.com CC: dan.j.williams@intel.com CC: dyoung@redhat.com CC: kexec@lists.infradead.org CC: mingo@redhat.com CC: x86-ml <x86@kernel.org> Link: http://lkml.kernel.org/r/153805812254.1157.16736368485811773752.stgit@bhelgaas-glaptop.roam.corp.google.com
2018-09-27 22:22:02 +08:00
if ((p->end >= start) && (p->start <= end))
break;
}
resource: provide new functions to walk through resources I have added two more functions to walk through resources. Currently walk_system_ram_range() deals with pfn and /proc/iomem can contain partial pages. By dealing in pfn, callback function loses the info that last page of a memory range is a partial page and not the full page. So I implemented walk_system_ram_res() which returns u64 values to callback functions and now it properly return start and end address. walk_system_ram_range() uses find_next_system_ram() to find the next ram resource. This in turn only travels through siblings of top level child and does not travers through all the nodes of the resoruce tree. I also need another function where I can walk through all the resources, for example figure out where "GART" aperture is. Figure out where ACPI memory is. So I wrote another function walk_iomem_res() which walks through all /proc/iomem resources and returns matches as asked by caller. Caller can specify "name" of resource, start and end and flags. Got rid of find_next_system_ram_res() and instead implemented more generic find_next_iomem_res() which can be used to traverse top level children only based on an argument. Signed-off-by: Vivek Goyal <vgoyal@redhat.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Borislav Petkov <bp@suse.de> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: Eric Biederman <ebiederm@xmission.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Matthew Garrett <mjg59@srcf.ucam.org> Cc: Greg Kroah-Hartman <greg@kroah.com> Cc: Dave Young <dyoung@redhat.com> Cc: WANG Chao <chaowang@redhat.com> Cc: Baoquan He <bhe@redhat.com> Cc: Andy Lutomirski <luto@amacapital.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-09 05:25:50 +08:00
read_unlock(&resource_lock);
if (!p)
return -1;
resource: Fix find_next_iomem_res() iteration issue Previously find_next_iomem_res() used "*res" as both an input parameter for the range to search and the type of resource to search for, and an output parameter for the resource we found, which makes the interface confusing. The current callers use find_next_iomem_res() incorrectly because they allocate a single struct resource and use it for repeated calls to find_next_iomem_res(). When find_next_iomem_res() returns a resource, it overwrites the start, end, flags, and desc members of the struct. If we call find_next_iomem_res() again, we must update or restore these fields. The previous code restored res.start and res.end, but not res.flags or res.desc. Since the callers did not restore res.flags, if they searched for flags IORESOURCE_MEM | IORESOURCE_BUSY and found a resource with flags IORESOURCE_MEM | IORESOURCE_BUSY | IORESOURCE_SYSRAM, the next search would incorrectly skip resources unless they were also marked as IORESOURCE_SYSRAM. Fix this by restructuring the interface so it takes explicit "start, end, flags" parameters and uses "*res" only as an output parameter. Based on a patch by Lianbo Jiang <lijiang@redhat.com>. [ bp: While at it: - make comments kernel-doc style. - Originally-by: http://lore.kernel.org/lkml/20180921073211.20097-2-lijiang@redhat.com Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Signed-off-by: Borislav Petkov <bp@suse.de> CC: Andrew Morton <akpm@linux-foundation.org> CC: Brijesh Singh <brijesh.singh@amd.com> CC: Dan Williams <dan.j.williams@intel.com> CC: H. Peter Anvin <hpa@zytor.com> CC: Lianbo Jiang <lijiang@redhat.com> CC: Takashi Iwai <tiwai@suse.de> CC: Thomas Gleixner <tglx@linutronix.de> CC: Tom Lendacky <thomas.lendacky@amd.com> CC: Vivek Goyal <vgoyal@redhat.com> CC: Yaowei Bai <baiyaowei@cmss.chinamobile.com> CC: bhe@redhat.com CC: dan.j.williams@intel.com CC: dyoung@redhat.com CC: kexec@lists.infradead.org CC: mingo@redhat.com CC: x86-ml <x86@kernel.org> Link: http://lkml.kernel.org/r/153805812916.1157.177580438135143788.stgit@bhelgaas-glaptop.roam.corp.google.com
2018-09-27 22:22:09 +08:00
/* copy data */
resource: Fix find_next_iomem_res() iteration issue Previously find_next_iomem_res() used "*res" as both an input parameter for the range to search and the type of resource to search for, and an output parameter for the resource we found, which makes the interface confusing. The current callers use find_next_iomem_res() incorrectly because they allocate a single struct resource and use it for repeated calls to find_next_iomem_res(). When find_next_iomem_res() returns a resource, it overwrites the start, end, flags, and desc members of the struct. If we call find_next_iomem_res() again, we must update or restore these fields. The previous code restored res.start and res.end, but not res.flags or res.desc. Since the callers did not restore res.flags, if they searched for flags IORESOURCE_MEM | IORESOURCE_BUSY and found a resource with flags IORESOURCE_MEM | IORESOURCE_BUSY | IORESOURCE_SYSRAM, the next search would incorrectly skip resources unless they were also marked as IORESOURCE_SYSRAM. Fix this by restructuring the interface so it takes explicit "start, end, flags" parameters and uses "*res" only as an output parameter. Based on a patch by Lianbo Jiang <lijiang@redhat.com>. [ bp: While at it: - make comments kernel-doc style. - Originally-by: http://lore.kernel.org/lkml/20180921073211.20097-2-lijiang@redhat.com Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Signed-off-by: Borislav Petkov <bp@suse.de> CC: Andrew Morton <akpm@linux-foundation.org> CC: Brijesh Singh <brijesh.singh@amd.com> CC: Dan Williams <dan.j.williams@intel.com> CC: H. Peter Anvin <hpa@zytor.com> CC: Lianbo Jiang <lijiang@redhat.com> CC: Takashi Iwai <tiwai@suse.de> CC: Thomas Gleixner <tglx@linutronix.de> CC: Tom Lendacky <thomas.lendacky@amd.com> CC: Vivek Goyal <vgoyal@redhat.com> CC: Yaowei Bai <baiyaowei@cmss.chinamobile.com> CC: bhe@redhat.com CC: dan.j.williams@intel.com CC: dyoung@redhat.com CC: kexec@lists.infradead.org CC: mingo@redhat.com CC: x86-ml <x86@kernel.org> Link: http://lkml.kernel.org/r/153805812916.1157.177580438135143788.stgit@bhelgaas-glaptop.roam.corp.google.com
2018-09-27 22:22:09 +08:00
res->start = max(start, p->start);
res->end = min(end, p->end);
res->flags = p->flags;
res->desc = p->desc;
return 0;
}
resource: Fix find_next_iomem_res() iteration issue Previously find_next_iomem_res() used "*res" as both an input parameter for the range to search and the type of resource to search for, and an output parameter for the resource we found, which makes the interface confusing. The current callers use find_next_iomem_res() incorrectly because they allocate a single struct resource and use it for repeated calls to find_next_iomem_res(). When find_next_iomem_res() returns a resource, it overwrites the start, end, flags, and desc members of the struct. If we call find_next_iomem_res() again, we must update or restore these fields. The previous code restored res.start and res.end, but not res.flags or res.desc. Since the callers did not restore res.flags, if they searched for flags IORESOURCE_MEM | IORESOURCE_BUSY and found a resource with flags IORESOURCE_MEM | IORESOURCE_BUSY | IORESOURCE_SYSRAM, the next search would incorrectly skip resources unless they were also marked as IORESOURCE_SYSRAM. Fix this by restructuring the interface so it takes explicit "start, end, flags" parameters and uses "*res" only as an output parameter. Based on a patch by Lianbo Jiang <lijiang@redhat.com>. [ bp: While at it: - make comments kernel-doc style. - Originally-by: http://lore.kernel.org/lkml/20180921073211.20097-2-lijiang@redhat.com Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Signed-off-by: Borislav Petkov <bp@suse.de> CC: Andrew Morton <akpm@linux-foundation.org> CC: Brijesh Singh <brijesh.singh@amd.com> CC: Dan Williams <dan.j.williams@intel.com> CC: H. Peter Anvin <hpa@zytor.com> CC: Lianbo Jiang <lijiang@redhat.com> CC: Takashi Iwai <tiwai@suse.de> CC: Thomas Gleixner <tglx@linutronix.de> CC: Tom Lendacky <thomas.lendacky@amd.com> CC: Vivek Goyal <vgoyal@redhat.com> CC: Yaowei Bai <baiyaowei@cmss.chinamobile.com> CC: bhe@redhat.com CC: dan.j.williams@intel.com CC: dyoung@redhat.com CC: kexec@lists.infradead.org CC: mingo@redhat.com CC: x86-ml <x86@kernel.org> Link: http://lkml.kernel.org/r/153805812916.1157.177580438135143788.stgit@bhelgaas-glaptop.roam.corp.google.com
2018-09-27 22:22:09 +08:00
static int __walk_iomem_res_desc(resource_size_t start, resource_size_t end,
unsigned long flags, unsigned long desc,
bool first_lvl, void *arg,
int (*func)(struct resource *, void *))
{
resource: Fix find_next_iomem_res() iteration issue Previously find_next_iomem_res() used "*res" as both an input parameter for the range to search and the type of resource to search for, and an output parameter for the resource we found, which makes the interface confusing. The current callers use find_next_iomem_res() incorrectly because they allocate a single struct resource and use it for repeated calls to find_next_iomem_res(). When find_next_iomem_res() returns a resource, it overwrites the start, end, flags, and desc members of the struct. If we call find_next_iomem_res() again, we must update or restore these fields. The previous code restored res.start and res.end, but not res.flags or res.desc. Since the callers did not restore res.flags, if they searched for flags IORESOURCE_MEM | IORESOURCE_BUSY and found a resource with flags IORESOURCE_MEM | IORESOURCE_BUSY | IORESOURCE_SYSRAM, the next search would incorrectly skip resources unless they were also marked as IORESOURCE_SYSRAM. Fix this by restructuring the interface so it takes explicit "start, end, flags" parameters and uses "*res" only as an output parameter. Based on a patch by Lianbo Jiang <lijiang@redhat.com>. [ bp: While at it: - make comments kernel-doc style. - Originally-by: http://lore.kernel.org/lkml/20180921073211.20097-2-lijiang@redhat.com Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Signed-off-by: Borislav Petkov <bp@suse.de> CC: Andrew Morton <akpm@linux-foundation.org> CC: Brijesh Singh <brijesh.singh@amd.com> CC: Dan Williams <dan.j.williams@intel.com> CC: H. Peter Anvin <hpa@zytor.com> CC: Lianbo Jiang <lijiang@redhat.com> CC: Takashi Iwai <tiwai@suse.de> CC: Thomas Gleixner <tglx@linutronix.de> CC: Tom Lendacky <thomas.lendacky@amd.com> CC: Vivek Goyal <vgoyal@redhat.com> CC: Yaowei Bai <baiyaowei@cmss.chinamobile.com> CC: bhe@redhat.com CC: dan.j.williams@intel.com CC: dyoung@redhat.com CC: kexec@lists.infradead.org CC: mingo@redhat.com CC: x86-ml <x86@kernel.org> Link: http://lkml.kernel.org/r/153805812916.1157.177580438135143788.stgit@bhelgaas-glaptop.roam.corp.google.com
2018-09-27 22:22:09 +08:00
struct resource res;
mm/resource: Return real error codes from walk failures walk_system_ram_range() can return an error code either becuase *it* failed, or because the 'func' that it calls returned an error. The memory hotplug does the following: ret = walk_system_ram_range(..., func); if (ret) return ret; and 'ret' makes it out to userspace, eventually. The problem s, walk_system_ram_range() failues that result from *it* failing (as opposed to 'func') return -1. That leads to a very odd -EPERM (-1) return code out to userspace. Make walk_system_ram_range() return -EINVAL for internal failures to keep userspace less confused. This return code is compatible with all the callers that I audited. Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Reviewed-by: Bjorn Helgaas <bhelgaas@google.com> Acked-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc) Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Ross Zwisler <zwisler@kernel.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Michal Hocko <mhocko@suse.com> Cc: linux-nvdimm@lists.01.org Cc: linux-kernel@vger.kernel.org Cc: linux-mm@kvack.org Cc: Huang Ying <ying.huang@intel.com> Cc: Fengguang Wu <fengguang.wu@intel.com> Cc: Borislav Petkov <bp@suse.de> Cc: Yaowei Bai <baiyaowei@cmss.chinamobile.com> Cc: Takashi Iwai <tiwai@suse.de> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: linuxppc-dev@lists.ozlabs.org Cc: Keith Busch <keith.busch@intel.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2019-02-26 02:57:30 +08:00
int ret = -EINVAL;
resource: Fix find_next_iomem_res() iteration issue Previously find_next_iomem_res() used "*res" as both an input parameter for the range to search and the type of resource to search for, and an output parameter for the resource we found, which makes the interface confusing. The current callers use find_next_iomem_res() incorrectly because they allocate a single struct resource and use it for repeated calls to find_next_iomem_res(). When find_next_iomem_res() returns a resource, it overwrites the start, end, flags, and desc members of the struct. If we call find_next_iomem_res() again, we must update or restore these fields. The previous code restored res.start and res.end, but not res.flags or res.desc. Since the callers did not restore res.flags, if they searched for flags IORESOURCE_MEM | IORESOURCE_BUSY and found a resource with flags IORESOURCE_MEM | IORESOURCE_BUSY | IORESOURCE_SYSRAM, the next search would incorrectly skip resources unless they were also marked as IORESOURCE_SYSRAM. Fix this by restructuring the interface so it takes explicit "start, end, flags" parameters and uses "*res" only as an output parameter. Based on a patch by Lianbo Jiang <lijiang@redhat.com>. [ bp: While at it: - make comments kernel-doc style. - Originally-by: http://lore.kernel.org/lkml/20180921073211.20097-2-lijiang@redhat.com Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Signed-off-by: Borislav Petkov <bp@suse.de> CC: Andrew Morton <akpm@linux-foundation.org> CC: Brijesh Singh <brijesh.singh@amd.com> CC: Dan Williams <dan.j.williams@intel.com> CC: H. Peter Anvin <hpa@zytor.com> CC: Lianbo Jiang <lijiang@redhat.com> CC: Takashi Iwai <tiwai@suse.de> CC: Thomas Gleixner <tglx@linutronix.de> CC: Tom Lendacky <thomas.lendacky@amd.com> CC: Vivek Goyal <vgoyal@redhat.com> CC: Yaowei Bai <baiyaowei@cmss.chinamobile.com> CC: bhe@redhat.com CC: dan.j.williams@intel.com CC: dyoung@redhat.com CC: kexec@lists.infradead.org CC: mingo@redhat.com CC: x86-ml <x86@kernel.org> Link: http://lkml.kernel.org/r/153805812916.1157.177580438135143788.stgit@bhelgaas-glaptop.roam.corp.google.com
2018-09-27 22:22:09 +08:00
while (start < end &&
!find_next_iomem_res(start, end, flags, desc, first_lvl, &res)) {
resource: Fix find_next_iomem_res() iteration issue Previously find_next_iomem_res() used "*res" as both an input parameter for the range to search and the type of resource to search for, and an output parameter for the resource we found, which makes the interface confusing. The current callers use find_next_iomem_res() incorrectly because they allocate a single struct resource and use it for repeated calls to find_next_iomem_res(). When find_next_iomem_res() returns a resource, it overwrites the start, end, flags, and desc members of the struct. If we call find_next_iomem_res() again, we must update or restore these fields. The previous code restored res.start and res.end, but not res.flags or res.desc. Since the callers did not restore res.flags, if they searched for flags IORESOURCE_MEM | IORESOURCE_BUSY and found a resource with flags IORESOURCE_MEM | IORESOURCE_BUSY | IORESOURCE_SYSRAM, the next search would incorrectly skip resources unless they were also marked as IORESOURCE_SYSRAM. Fix this by restructuring the interface so it takes explicit "start, end, flags" parameters and uses "*res" only as an output parameter. Based on a patch by Lianbo Jiang <lijiang@redhat.com>. [ bp: While at it: - make comments kernel-doc style. - Originally-by: http://lore.kernel.org/lkml/20180921073211.20097-2-lijiang@redhat.com Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Signed-off-by: Borislav Petkov <bp@suse.de> CC: Andrew Morton <akpm@linux-foundation.org> CC: Brijesh Singh <brijesh.singh@amd.com> CC: Dan Williams <dan.j.williams@intel.com> CC: H. Peter Anvin <hpa@zytor.com> CC: Lianbo Jiang <lijiang@redhat.com> CC: Takashi Iwai <tiwai@suse.de> CC: Thomas Gleixner <tglx@linutronix.de> CC: Tom Lendacky <thomas.lendacky@amd.com> CC: Vivek Goyal <vgoyal@redhat.com> CC: Yaowei Bai <baiyaowei@cmss.chinamobile.com> CC: bhe@redhat.com CC: dan.j.williams@intel.com CC: dyoung@redhat.com CC: kexec@lists.infradead.org CC: mingo@redhat.com CC: x86-ml <x86@kernel.org> Link: http://lkml.kernel.org/r/153805812916.1157.177580438135143788.stgit@bhelgaas-glaptop.roam.corp.google.com
2018-09-27 22:22:09 +08:00
ret = (*func)(&res, arg);
if (ret)
break;
resource: Fix find_next_iomem_res() iteration issue Previously find_next_iomem_res() used "*res" as both an input parameter for the range to search and the type of resource to search for, and an output parameter for the resource we found, which makes the interface confusing. The current callers use find_next_iomem_res() incorrectly because they allocate a single struct resource and use it for repeated calls to find_next_iomem_res(). When find_next_iomem_res() returns a resource, it overwrites the start, end, flags, and desc members of the struct. If we call find_next_iomem_res() again, we must update or restore these fields. The previous code restored res.start and res.end, but not res.flags or res.desc. Since the callers did not restore res.flags, if they searched for flags IORESOURCE_MEM | IORESOURCE_BUSY and found a resource with flags IORESOURCE_MEM | IORESOURCE_BUSY | IORESOURCE_SYSRAM, the next search would incorrectly skip resources unless they were also marked as IORESOURCE_SYSRAM. Fix this by restructuring the interface so it takes explicit "start, end, flags" parameters and uses "*res" only as an output parameter. Based on a patch by Lianbo Jiang <lijiang@redhat.com>. [ bp: While at it: - make comments kernel-doc style. - Originally-by: http://lore.kernel.org/lkml/20180921073211.20097-2-lijiang@redhat.com Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Signed-off-by: Borislav Petkov <bp@suse.de> CC: Andrew Morton <akpm@linux-foundation.org> CC: Brijesh Singh <brijesh.singh@amd.com> CC: Dan Williams <dan.j.williams@intel.com> CC: H. Peter Anvin <hpa@zytor.com> CC: Lianbo Jiang <lijiang@redhat.com> CC: Takashi Iwai <tiwai@suse.de> CC: Thomas Gleixner <tglx@linutronix.de> CC: Tom Lendacky <thomas.lendacky@amd.com> CC: Vivek Goyal <vgoyal@redhat.com> CC: Yaowei Bai <baiyaowei@cmss.chinamobile.com> CC: bhe@redhat.com CC: dan.j.williams@intel.com CC: dyoung@redhat.com CC: kexec@lists.infradead.org CC: mingo@redhat.com CC: x86-ml <x86@kernel.org> Link: http://lkml.kernel.org/r/153805812916.1157.177580438135143788.stgit@bhelgaas-glaptop.roam.corp.google.com
2018-09-27 22:22:09 +08:00
start = res.end + 1;
}
return ret;
}
/**
* Walks through iomem resources and calls func() with matching resource
resource: provide new functions to walk through resources I have added two more functions to walk through resources. Currently walk_system_ram_range() deals with pfn and /proc/iomem can contain partial pages. By dealing in pfn, callback function loses the info that last page of a memory range is a partial page and not the full page. So I implemented walk_system_ram_res() which returns u64 values to callback functions and now it properly return start and end address. walk_system_ram_range() uses find_next_system_ram() to find the next ram resource. This in turn only travels through siblings of top level child and does not travers through all the nodes of the resoruce tree. I also need another function where I can walk through all the resources, for example figure out where "GART" aperture is. Figure out where ACPI memory is. So I wrote another function walk_iomem_res() which walks through all /proc/iomem resources and returns matches as asked by caller. Caller can specify "name" of resource, start and end and flags. Got rid of find_next_system_ram_res() and instead implemented more generic find_next_iomem_res() which can be used to traverse top level children only based on an argument. Signed-off-by: Vivek Goyal <vgoyal@redhat.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Borislav Petkov <bp@suse.de> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: Eric Biederman <ebiederm@xmission.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Matthew Garrett <mjg59@srcf.ucam.org> Cc: Greg Kroah-Hartman <greg@kroah.com> Cc: Dave Young <dyoung@redhat.com> Cc: WANG Chao <chaowang@redhat.com> Cc: Baoquan He <bhe@redhat.com> Cc: Andy Lutomirski <luto@amacapital.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-09 05:25:50 +08:00
* ranges. This walks through whole tree and not just first level children.
* All the memory ranges which overlap start,end and also match flags and
* desc are valid candidates.
*
* @desc: I/O resource descriptor. Use IORES_DESC_NONE to skip @desc check.
* @flags: I/O resource flags
* @start: start addr
* @end: end addr
resource/docs: Fix new kernel-doc warnings The first group of warnings is caused by a "/**" kernel-doc notation marker but the function comments are not in kernel-doc format. Also add another error return value here. ../kernel/resource.c:337: warning: Function parameter or member 'start' not described in 'find_next_iomem_res' ../kernel/resource.c:337: warning: Function parameter or member 'end' not described in 'find_next_iomem_res' ../kernel/resource.c:337: warning: Function parameter or member 'flags' not described in 'find_next_iomem_res' ../kernel/resource.c:337: warning: Function parameter or member 'desc' not described in 'find_next_iomem_res' ../kernel/resource.c:337: warning: Function parameter or member 'first_lvl' not described in 'find_next_iomem_res' ../kernel/resource.c:337: warning: Function parameter or member 'res' not described in 'find_next_iomem_res' Add the missing function parameter documentation for the other warnings: ../kernel/resource.c:409: warning: Function parameter or member 'arg' not described in 'walk_iomem_res_desc' ../kernel/resource.c:409: warning: Function parameter or member 'func' not described in 'walk_iomem_res_desc' Signed-off-by: Randy Dunlap <rdunlap@infradead.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Borislav Petkov <bp@suse.de> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Fixes: b69c2e20f6e4 ("resource: Clean it up a bit") Link: http://lkml.kernel.org/r/dda2e4d8-bedd-3167-20fe-8c7d2d35b354@infradead.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2018-11-05 10:40:14 +08:00
* @arg: function argument for the callback @func
* @func: callback function that is called for each qualifying resource area
*
* NOTE: For a new descriptor search, define a new IORES_DESC in
* <linux/ioport.h> and set it in 'desc' of a target resource entry.
*/
int walk_iomem_res_desc(unsigned long desc, unsigned long flags, u64 start,
u64 end, void *arg, int (*func)(struct resource *, void *))
{
resource: Fix find_next_iomem_res() iteration issue Previously find_next_iomem_res() used "*res" as both an input parameter for the range to search and the type of resource to search for, and an output parameter for the resource we found, which makes the interface confusing. The current callers use find_next_iomem_res() incorrectly because they allocate a single struct resource and use it for repeated calls to find_next_iomem_res(). When find_next_iomem_res() returns a resource, it overwrites the start, end, flags, and desc members of the struct. If we call find_next_iomem_res() again, we must update or restore these fields. The previous code restored res.start and res.end, but not res.flags or res.desc. Since the callers did not restore res.flags, if they searched for flags IORESOURCE_MEM | IORESOURCE_BUSY and found a resource with flags IORESOURCE_MEM | IORESOURCE_BUSY | IORESOURCE_SYSRAM, the next search would incorrectly skip resources unless they were also marked as IORESOURCE_SYSRAM. Fix this by restructuring the interface so it takes explicit "start, end, flags" parameters and uses "*res" only as an output parameter. Based on a patch by Lianbo Jiang <lijiang@redhat.com>. [ bp: While at it: - make comments kernel-doc style. - Originally-by: http://lore.kernel.org/lkml/20180921073211.20097-2-lijiang@redhat.com Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Signed-off-by: Borislav Petkov <bp@suse.de> CC: Andrew Morton <akpm@linux-foundation.org> CC: Brijesh Singh <brijesh.singh@amd.com> CC: Dan Williams <dan.j.williams@intel.com> CC: H. Peter Anvin <hpa@zytor.com> CC: Lianbo Jiang <lijiang@redhat.com> CC: Takashi Iwai <tiwai@suse.de> CC: Thomas Gleixner <tglx@linutronix.de> CC: Tom Lendacky <thomas.lendacky@amd.com> CC: Vivek Goyal <vgoyal@redhat.com> CC: Yaowei Bai <baiyaowei@cmss.chinamobile.com> CC: bhe@redhat.com CC: dan.j.williams@intel.com CC: dyoung@redhat.com CC: kexec@lists.infradead.org CC: mingo@redhat.com CC: x86-ml <x86@kernel.org> Link: http://lkml.kernel.org/r/153805812916.1157.177580438135143788.stgit@bhelgaas-glaptop.roam.corp.google.com
2018-09-27 22:22:09 +08:00
return __walk_iomem_res_desc(start, end, flags, desc, false, arg, func);
}
EXPORT_SYMBOL_GPL(walk_iomem_res_desc);
resource: provide new functions to walk through resources I have added two more functions to walk through resources. Currently walk_system_ram_range() deals with pfn and /proc/iomem can contain partial pages. By dealing in pfn, callback function loses the info that last page of a memory range is a partial page and not the full page. So I implemented walk_system_ram_res() which returns u64 values to callback functions and now it properly return start and end address. walk_system_ram_range() uses find_next_system_ram() to find the next ram resource. This in turn only travels through siblings of top level child and does not travers through all the nodes of the resoruce tree. I also need another function where I can walk through all the resources, for example figure out where "GART" aperture is. Figure out where ACPI memory is. So I wrote another function walk_iomem_res() which walks through all /proc/iomem resources and returns matches as asked by caller. Caller can specify "name" of resource, start and end and flags. Got rid of find_next_system_ram_res() and instead implemented more generic find_next_iomem_res() which can be used to traverse top level children only based on an argument. Signed-off-by: Vivek Goyal <vgoyal@redhat.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Borislav Petkov <bp@suse.de> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: Eric Biederman <ebiederm@xmission.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Matthew Garrett <mjg59@srcf.ucam.org> Cc: Greg Kroah-Hartman <greg@kroah.com> Cc: Dave Young <dyoung@redhat.com> Cc: WANG Chao <chaowang@redhat.com> Cc: Baoquan He <bhe@redhat.com> Cc: Andy Lutomirski <luto@amacapital.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-09 05:25:50 +08:00
/*
* This function calls the @func callback against all memory ranges of type
* System RAM which are marked as IORESOURCE_SYSTEM_RAM and IORESOUCE_BUSY.
* Now, this function is only for System RAM, it deals with full ranges and
* not PFNs. If resources are not PFN-aligned, dealing with PFNs can truncate
* ranges.
resource: provide new functions to walk through resources I have added two more functions to walk through resources. Currently walk_system_ram_range() deals with pfn and /proc/iomem can contain partial pages. By dealing in pfn, callback function loses the info that last page of a memory range is a partial page and not the full page. So I implemented walk_system_ram_res() which returns u64 values to callback functions and now it properly return start and end address. walk_system_ram_range() uses find_next_system_ram() to find the next ram resource. This in turn only travels through siblings of top level child and does not travers through all the nodes of the resoruce tree. I also need another function where I can walk through all the resources, for example figure out where "GART" aperture is. Figure out where ACPI memory is. So I wrote another function walk_iomem_res() which walks through all /proc/iomem resources and returns matches as asked by caller. Caller can specify "name" of resource, start and end and flags. Got rid of find_next_system_ram_res() and instead implemented more generic find_next_iomem_res() which can be used to traverse top level children only based on an argument. Signed-off-by: Vivek Goyal <vgoyal@redhat.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Borislav Petkov <bp@suse.de> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: Eric Biederman <ebiederm@xmission.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Matthew Garrett <mjg59@srcf.ucam.org> Cc: Greg Kroah-Hartman <greg@kroah.com> Cc: Dave Young <dyoung@redhat.com> Cc: WANG Chao <chaowang@redhat.com> Cc: Baoquan He <bhe@redhat.com> Cc: Andy Lutomirski <luto@amacapital.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-09 05:25:50 +08:00
*/
int walk_system_ram_res(u64 start, u64 end, void *arg,
int (*func)(struct resource *, void *))
resource: provide new functions to walk through resources I have added two more functions to walk through resources. Currently walk_system_ram_range() deals with pfn and /proc/iomem can contain partial pages. By dealing in pfn, callback function loses the info that last page of a memory range is a partial page and not the full page. So I implemented walk_system_ram_res() which returns u64 values to callback functions and now it properly return start and end address. walk_system_ram_range() uses find_next_system_ram() to find the next ram resource. This in turn only travels through siblings of top level child and does not travers through all the nodes of the resoruce tree. I also need another function where I can walk through all the resources, for example figure out where "GART" aperture is. Figure out where ACPI memory is. So I wrote another function walk_iomem_res() which walks through all /proc/iomem resources and returns matches as asked by caller. Caller can specify "name" of resource, start and end and flags. Got rid of find_next_system_ram_res() and instead implemented more generic find_next_iomem_res() which can be used to traverse top level children only based on an argument. Signed-off-by: Vivek Goyal <vgoyal@redhat.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Borislav Petkov <bp@suse.de> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: Eric Biederman <ebiederm@xmission.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Matthew Garrett <mjg59@srcf.ucam.org> Cc: Greg Kroah-Hartman <greg@kroah.com> Cc: Dave Young <dyoung@redhat.com> Cc: WANG Chao <chaowang@redhat.com> Cc: Baoquan He <bhe@redhat.com> Cc: Andy Lutomirski <luto@amacapital.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-09 05:25:50 +08:00
{
resource: Fix find_next_iomem_res() iteration issue Previously find_next_iomem_res() used "*res" as both an input parameter for the range to search and the type of resource to search for, and an output parameter for the resource we found, which makes the interface confusing. The current callers use find_next_iomem_res() incorrectly because they allocate a single struct resource and use it for repeated calls to find_next_iomem_res(). When find_next_iomem_res() returns a resource, it overwrites the start, end, flags, and desc members of the struct. If we call find_next_iomem_res() again, we must update or restore these fields. The previous code restored res.start and res.end, but not res.flags or res.desc. Since the callers did not restore res.flags, if they searched for flags IORESOURCE_MEM | IORESOURCE_BUSY and found a resource with flags IORESOURCE_MEM | IORESOURCE_BUSY | IORESOURCE_SYSRAM, the next search would incorrectly skip resources unless they were also marked as IORESOURCE_SYSRAM. Fix this by restructuring the interface so it takes explicit "start, end, flags" parameters and uses "*res" only as an output parameter. Based on a patch by Lianbo Jiang <lijiang@redhat.com>. [ bp: While at it: - make comments kernel-doc style. - Originally-by: http://lore.kernel.org/lkml/20180921073211.20097-2-lijiang@redhat.com Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Signed-off-by: Borislav Petkov <bp@suse.de> CC: Andrew Morton <akpm@linux-foundation.org> CC: Brijesh Singh <brijesh.singh@amd.com> CC: Dan Williams <dan.j.williams@intel.com> CC: H. Peter Anvin <hpa@zytor.com> CC: Lianbo Jiang <lijiang@redhat.com> CC: Takashi Iwai <tiwai@suse.de> CC: Thomas Gleixner <tglx@linutronix.de> CC: Tom Lendacky <thomas.lendacky@amd.com> CC: Vivek Goyal <vgoyal@redhat.com> CC: Yaowei Bai <baiyaowei@cmss.chinamobile.com> CC: bhe@redhat.com CC: dan.j.williams@intel.com CC: dyoung@redhat.com CC: kexec@lists.infradead.org CC: mingo@redhat.com CC: x86-ml <x86@kernel.org> Link: http://lkml.kernel.org/r/153805812916.1157.177580438135143788.stgit@bhelgaas-glaptop.roam.corp.google.com
2018-09-27 22:22:09 +08:00
unsigned long flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
resource: provide new functions to walk through resources I have added two more functions to walk through resources. Currently walk_system_ram_range() deals with pfn and /proc/iomem can contain partial pages. By dealing in pfn, callback function loses the info that last page of a memory range is a partial page and not the full page. So I implemented walk_system_ram_res() which returns u64 values to callback functions and now it properly return start and end address. walk_system_ram_range() uses find_next_system_ram() to find the next ram resource. This in turn only travels through siblings of top level child and does not travers through all the nodes of the resoruce tree. I also need another function where I can walk through all the resources, for example figure out where "GART" aperture is. Figure out where ACPI memory is. So I wrote another function walk_iomem_res() which walks through all /proc/iomem resources and returns matches as asked by caller. Caller can specify "name" of resource, start and end and flags. Got rid of find_next_system_ram_res() and instead implemented more generic find_next_iomem_res() which can be used to traverse top level children only based on an argument. Signed-off-by: Vivek Goyal <vgoyal@redhat.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Borislav Petkov <bp@suse.de> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: Eric Biederman <ebiederm@xmission.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Matthew Garrett <mjg59@srcf.ucam.org> Cc: Greg Kroah-Hartman <greg@kroah.com> Cc: Dave Young <dyoung@redhat.com> Cc: WANG Chao <chaowang@redhat.com> Cc: Baoquan He <bhe@redhat.com> Cc: Andy Lutomirski <luto@amacapital.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-09 05:25:50 +08:00
resource: Fix find_next_iomem_res() iteration issue Previously find_next_iomem_res() used "*res" as both an input parameter for the range to search and the type of resource to search for, and an output parameter for the resource we found, which makes the interface confusing. The current callers use find_next_iomem_res() incorrectly because they allocate a single struct resource and use it for repeated calls to find_next_iomem_res(). When find_next_iomem_res() returns a resource, it overwrites the start, end, flags, and desc members of the struct. If we call find_next_iomem_res() again, we must update or restore these fields. The previous code restored res.start and res.end, but not res.flags or res.desc. Since the callers did not restore res.flags, if they searched for flags IORESOURCE_MEM | IORESOURCE_BUSY and found a resource with flags IORESOURCE_MEM | IORESOURCE_BUSY | IORESOURCE_SYSRAM, the next search would incorrectly skip resources unless they were also marked as IORESOURCE_SYSRAM. Fix this by restructuring the interface so it takes explicit "start, end, flags" parameters and uses "*res" only as an output parameter. Based on a patch by Lianbo Jiang <lijiang@redhat.com>. [ bp: While at it: - make comments kernel-doc style. - Originally-by: http://lore.kernel.org/lkml/20180921073211.20097-2-lijiang@redhat.com Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Signed-off-by: Borislav Petkov <bp@suse.de> CC: Andrew Morton <akpm@linux-foundation.org> CC: Brijesh Singh <brijesh.singh@amd.com> CC: Dan Williams <dan.j.williams@intel.com> CC: H. Peter Anvin <hpa@zytor.com> CC: Lianbo Jiang <lijiang@redhat.com> CC: Takashi Iwai <tiwai@suse.de> CC: Thomas Gleixner <tglx@linutronix.de> CC: Tom Lendacky <thomas.lendacky@amd.com> CC: Vivek Goyal <vgoyal@redhat.com> CC: Yaowei Bai <baiyaowei@cmss.chinamobile.com> CC: bhe@redhat.com CC: dan.j.williams@intel.com CC: dyoung@redhat.com CC: kexec@lists.infradead.org CC: mingo@redhat.com CC: x86-ml <x86@kernel.org> Link: http://lkml.kernel.org/r/153805812916.1157.177580438135143788.stgit@bhelgaas-glaptop.roam.corp.google.com
2018-09-27 22:22:09 +08:00
return __walk_iomem_res_desc(start, end, flags, IORES_DESC_NONE, true,
arg, func);
}
/*
* This function calls the @func callback against all memory ranges, which
* are ranges marked as IORESOURCE_MEM and IORESOUCE_BUSY.
*/
int walk_mem_res(u64 start, u64 end, void *arg,
int (*func)(struct resource *, void *))
{
resource: Fix find_next_iomem_res() iteration issue Previously find_next_iomem_res() used "*res" as both an input parameter for the range to search and the type of resource to search for, and an output parameter for the resource we found, which makes the interface confusing. The current callers use find_next_iomem_res() incorrectly because they allocate a single struct resource and use it for repeated calls to find_next_iomem_res(). When find_next_iomem_res() returns a resource, it overwrites the start, end, flags, and desc members of the struct. If we call find_next_iomem_res() again, we must update or restore these fields. The previous code restored res.start and res.end, but not res.flags or res.desc. Since the callers did not restore res.flags, if they searched for flags IORESOURCE_MEM | IORESOURCE_BUSY and found a resource with flags IORESOURCE_MEM | IORESOURCE_BUSY | IORESOURCE_SYSRAM, the next search would incorrectly skip resources unless they were also marked as IORESOURCE_SYSRAM. Fix this by restructuring the interface so it takes explicit "start, end, flags" parameters and uses "*res" only as an output parameter. Based on a patch by Lianbo Jiang <lijiang@redhat.com>. [ bp: While at it: - make comments kernel-doc style. - Originally-by: http://lore.kernel.org/lkml/20180921073211.20097-2-lijiang@redhat.com Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Signed-off-by: Borislav Petkov <bp@suse.de> CC: Andrew Morton <akpm@linux-foundation.org> CC: Brijesh Singh <brijesh.singh@amd.com> CC: Dan Williams <dan.j.williams@intel.com> CC: H. Peter Anvin <hpa@zytor.com> CC: Lianbo Jiang <lijiang@redhat.com> CC: Takashi Iwai <tiwai@suse.de> CC: Thomas Gleixner <tglx@linutronix.de> CC: Tom Lendacky <thomas.lendacky@amd.com> CC: Vivek Goyal <vgoyal@redhat.com> CC: Yaowei Bai <baiyaowei@cmss.chinamobile.com> CC: bhe@redhat.com CC: dan.j.williams@intel.com CC: dyoung@redhat.com CC: kexec@lists.infradead.org CC: mingo@redhat.com CC: x86-ml <x86@kernel.org> Link: http://lkml.kernel.org/r/153805812916.1157.177580438135143788.stgit@bhelgaas-glaptop.roam.corp.google.com
2018-09-27 22:22:09 +08:00
unsigned long flags = IORESOURCE_MEM | IORESOURCE_BUSY;
resource: Fix find_next_iomem_res() iteration issue Previously find_next_iomem_res() used "*res" as both an input parameter for the range to search and the type of resource to search for, and an output parameter for the resource we found, which makes the interface confusing. The current callers use find_next_iomem_res() incorrectly because they allocate a single struct resource and use it for repeated calls to find_next_iomem_res(). When find_next_iomem_res() returns a resource, it overwrites the start, end, flags, and desc members of the struct. If we call find_next_iomem_res() again, we must update or restore these fields. The previous code restored res.start and res.end, but not res.flags or res.desc. Since the callers did not restore res.flags, if they searched for flags IORESOURCE_MEM | IORESOURCE_BUSY and found a resource with flags IORESOURCE_MEM | IORESOURCE_BUSY | IORESOURCE_SYSRAM, the next search would incorrectly skip resources unless they were also marked as IORESOURCE_SYSRAM. Fix this by restructuring the interface so it takes explicit "start, end, flags" parameters and uses "*res" only as an output parameter. Based on a patch by Lianbo Jiang <lijiang@redhat.com>. [ bp: While at it: - make comments kernel-doc style. - Originally-by: http://lore.kernel.org/lkml/20180921073211.20097-2-lijiang@redhat.com Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Signed-off-by: Borislav Petkov <bp@suse.de> CC: Andrew Morton <akpm@linux-foundation.org> CC: Brijesh Singh <brijesh.singh@amd.com> CC: Dan Williams <dan.j.williams@intel.com> CC: H. Peter Anvin <hpa@zytor.com> CC: Lianbo Jiang <lijiang@redhat.com> CC: Takashi Iwai <tiwai@suse.de> CC: Thomas Gleixner <tglx@linutronix.de> CC: Tom Lendacky <thomas.lendacky@amd.com> CC: Vivek Goyal <vgoyal@redhat.com> CC: Yaowei Bai <baiyaowei@cmss.chinamobile.com> CC: bhe@redhat.com CC: dan.j.williams@intel.com CC: dyoung@redhat.com CC: kexec@lists.infradead.org CC: mingo@redhat.com CC: x86-ml <x86@kernel.org> Link: http://lkml.kernel.org/r/153805812916.1157.177580438135143788.stgit@bhelgaas-glaptop.roam.corp.google.com
2018-09-27 22:22:09 +08:00
return __walk_iomem_res_desc(start, end, flags, IORES_DESC_NONE, true,
arg, func);
resource: provide new functions to walk through resources I have added two more functions to walk through resources. Currently walk_system_ram_range() deals with pfn and /proc/iomem can contain partial pages. By dealing in pfn, callback function loses the info that last page of a memory range is a partial page and not the full page. So I implemented walk_system_ram_res() which returns u64 values to callback functions and now it properly return start and end address. walk_system_ram_range() uses find_next_system_ram() to find the next ram resource. This in turn only travels through siblings of top level child and does not travers through all the nodes of the resoruce tree. I also need another function where I can walk through all the resources, for example figure out where "GART" aperture is. Figure out where ACPI memory is. So I wrote another function walk_iomem_res() which walks through all /proc/iomem resources and returns matches as asked by caller. Caller can specify "name" of resource, start and end and flags. Got rid of find_next_system_ram_res() and instead implemented more generic find_next_iomem_res() which can be used to traverse top level children only based on an argument. Signed-off-by: Vivek Goyal <vgoyal@redhat.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Borislav Petkov <bp@suse.de> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: Eric Biederman <ebiederm@xmission.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Matthew Garrett <mjg59@srcf.ucam.org> Cc: Greg Kroah-Hartman <greg@kroah.com> Cc: Dave Young <dyoung@redhat.com> Cc: WANG Chao <chaowang@redhat.com> Cc: Baoquan He <bhe@redhat.com> Cc: Andy Lutomirski <luto@amacapital.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-09 05:25:50 +08:00
}
/*
* This function calls the @func callback against all memory ranges of type
* System RAM which are marked as IORESOURCE_SYSTEM_RAM and IORESOUCE_BUSY.
* It is to be used only for System RAM.
mm/resource: Let walk_system_ram_range() search child resources In the process of onlining memory, we use walk_system_ram_range() to find the actual RAM areas inside of the area being onlined. However, it currently only finds memory resources which are "top-level" iomem_resources. Children are not currently searched which causes it to skip System RAM in areas like this (in the format of /proc/iomem): a0000000-bfffffff : Persistent Memory (legacy) a0000000-afffffff : System RAM Changing the true->false here allows children to be searched as well. We need this because we add a new "System RAM" resource underneath the "persistent memory" resource when we use persistent memory in a volatile mode. Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Cc: Keith Busch <keith.busch@intel.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Ross Zwisler <zwisler@kernel.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Michal Hocko <mhocko@suse.com> Cc: linux-nvdimm@lists.01.org Cc: linux-kernel@vger.kernel.org Cc: linux-mm@kvack.org Cc: Huang Ying <ying.huang@intel.com> Cc: Fengguang Wu <fengguang.wu@intel.com> Cc: Borislav Petkov <bp@suse.de> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Yaowei Bai <baiyaowei@cmss.chinamobile.com> Cc: Takashi Iwai <tiwai@suse.de> Cc: Jerome Glisse <jglisse@redhat.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2019-02-26 02:57:38 +08:00
*
* This will find System RAM ranges that are children of top-level resources
* in addition to top-level System RAM resources.
*/
int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages,
void *arg, int (*func)(unsigned long, unsigned long, void *))
{
resource: Fix find_next_iomem_res() iteration issue Previously find_next_iomem_res() used "*res" as both an input parameter for the range to search and the type of resource to search for, and an output parameter for the resource we found, which makes the interface confusing. The current callers use find_next_iomem_res() incorrectly because they allocate a single struct resource and use it for repeated calls to find_next_iomem_res(). When find_next_iomem_res() returns a resource, it overwrites the start, end, flags, and desc members of the struct. If we call find_next_iomem_res() again, we must update or restore these fields. The previous code restored res.start and res.end, but not res.flags or res.desc. Since the callers did not restore res.flags, if they searched for flags IORESOURCE_MEM | IORESOURCE_BUSY and found a resource with flags IORESOURCE_MEM | IORESOURCE_BUSY | IORESOURCE_SYSRAM, the next search would incorrectly skip resources unless they were also marked as IORESOURCE_SYSRAM. Fix this by restructuring the interface so it takes explicit "start, end, flags" parameters and uses "*res" only as an output parameter. Based on a patch by Lianbo Jiang <lijiang@redhat.com>. [ bp: While at it: - make comments kernel-doc style. - Originally-by: http://lore.kernel.org/lkml/20180921073211.20097-2-lijiang@redhat.com Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Signed-off-by: Borislav Petkov <bp@suse.de> CC: Andrew Morton <akpm@linux-foundation.org> CC: Brijesh Singh <brijesh.singh@amd.com> CC: Dan Williams <dan.j.williams@intel.com> CC: H. Peter Anvin <hpa@zytor.com> CC: Lianbo Jiang <lijiang@redhat.com> CC: Takashi Iwai <tiwai@suse.de> CC: Thomas Gleixner <tglx@linutronix.de> CC: Tom Lendacky <thomas.lendacky@amd.com> CC: Vivek Goyal <vgoyal@redhat.com> CC: Yaowei Bai <baiyaowei@cmss.chinamobile.com> CC: bhe@redhat.com CC: dan.j.williams@intel.com CC: dyoung@redhat.com CC: kexec@lists.infradead.org CC: mingo@redhat.com CC: x86-ml <x86@kernel.org> Link: http://lkml.kernel.org/r/153805812916.1157.177580438135143788.stgit@bhelgaas-glaptop.roam.corp.google.com
2018-09-27 22:22:09 +08:00
resource_size_t start, end;
unsigned long flags;
struct resource res;
resource: Fix generic page_is_ram() for partial RAM pages The System RAM walk shall skip partial RAM pages and avoid calling func() on them. So that page_is_ram() return 0 for a partial RAM page. In particular, it shall not call func() with len=0. This fixes a boot time bug reported by Sachin and root caused by Thomas: > >>> WARNING: at arch/x86/mm/ioremap.c:111 __ioremap_caller+0x169/0x2f1() > >>> Hardware name: BladeCenter LS21 -[79716AA]- > >>> Modules linked in: > >>> Pid: 0, comm: swapper Not tainted 2.6.33-git6-autotest #1 > >>> Call Trace: > >>> [<ffffffff81047cff>] ? __ioremap_caller+0x169/0x2f1 > >>> [<ffffffff81063b7d>] warn_slowpath_common+0x77/0xa4 > >>> [<ffffffff81063bb9>] warn_slowpath_null+0xf/0x11 > >>> [<ffffffff81047cff>] __ioremap_caller+0x169/0x2f1 > >>> [<ffffffff813747a3>] ? acpi_os_map_memory+0x12/0x1b > >>> [<ffffffff81047f10>] ioremap_nocache+0x12/0x14 > >>> [<ffffffff813747a3>] acpi_os_map_memory+0x12/0x1b > >>> [<ffffffff81282fa0>] acpi_tb_verify_table+0x29/0x5b > >>> [<ffffffff812827f0>] acpi_load_tables+0x39/0x15a > >>> [<ffffffff8191c8f8>] acpi_early_init+0x60/0xf5 > >>> [<ffffffff818f2cad>] start_kernel+0x397/0x3a7 > >>> [<ffffffff818f2295>] x86_64_start_reservations+0xa5/0xa9 > >>> [<ffffffff818f237a>] x86_64_start_kernel+0xe1/0xe8 > >>> ---[ end trace 4eaa2a86a8e2da22 ]--- > >>> ioremap reserve_memtype failed -22 The return code is -EINVAL, so it failed in the is_ram check, which is not too surprising > BIOS-provided physical RAM map: > BIOS-e820: 0000000000000000 - 000000000009c000 (usable) > BIOS-e820: 000000000009c000 - 00000000000a0000 (reserved) > BIOS-e820: 00000000000e0000 - 0000000000100000 (reserved) > BIOS-e820: 0000000000100000 - 00000000cffa3900 (usable) > BIOS-e820: 00000000cffa3900 - 00000000cffa7400 (ACPI data) The ACPI data is not starting on a page boundary and neither does the usable RAM area end on a page boundary. Very useful ! > ACPI: DSDT 00000000cffa3900 036CE (v01 IBM SERLEWIS 00001000 INTL 20060912) ACPI is trying to map DSDT at cffa3900, which results in a check vs. cffa3000 which is the relevant page boundary. The generic is_ram check correctly identifies that as RAM because it's in the usable resource area. The old e820 based is_ram check does not take overlapping resource areas into account. That's why it works. CC: Sachin Sant <sachinp@in.ibm.com> CC: Thomas Gleixner <tglx@linutronix.de> CC: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> LKML-Reference: <20100301135551.GA9998@localhost> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-03-01 21:55:51 +08:00
unsigned long pfn, end_pfn;
mm/resource: Return real error codes from walk failures walk_system_ram_range() can return an error code either becuase *it* failed, or because the 'func' that it calls returned an error. The memory hotplug does the following: ret = walk_system_ram_range(..., func); if (ret) return ret; and 'ret' makes it out to userspace, eventually. The problem s, walk_system_ram_range() failues that result from *it* failing (as opposed to 'func') return -1. That leads to a very odd -EPERM (-1) return code out to userspace. Make walk_system_ram_range() return -EINVAL for internal failures to keep userspace less confused. This return code is compatible with all the callers that I audited. Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Reviewed-by: Bjorn Helgaas <bhelgaas@google.com> Acked-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc) Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Ross Zwisler <zwisler@kernel.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Michal Hocko <mhocko@suse.com> Cc: linux-nvdimm@lists.01.org Cc: linux-kernel@vger.kernel.org Cc: linux-mm@kvack.org Cc: Huang Ying <ying.huang@intel.com> Cc: Fengguang Wu <fengguang.wu@intel.com> Cc: Borislav Petkov <bp@suse.de> Cc: Yaowei Bai <baiyaowei@cmss.chinamobile.com> Cc: Takashi Iwai <tiwai@suse.de> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: linuxppc-dev@lists.ozlabs.org Cc: Keith Busch <keith.busch@intel.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2019-02-26 02:57:30 +08:00
int ret = -EINVAL;
resource: Fix find_next_iomem_res() iteration issue Previously find_next_iomem_res() used "*res" as both an input parameter for the range to search and the type of resource to search for, and an output parameter for the resource we found, which makes the interface confusing. The current callers use find_next_iomem_res() incorrectly because they allocate a single struct resource and use it for repeated calls to find_next_iomem_res(). When find_next_iomem_res() returns a resource, it overwrites the start, end, flags, and desc members of the struct. If we call find_next_iomem_res() again, we must update or restore these fields. The previous code restored res.start and res.end, but not res.flags or res.desc. Since the callers did not restore res.flags, if they searched for flags IORESOURCE_MEM | IORESOURCE_BUSY and found a resource with flags IORESOURCE_MEM | IORESOURCE_BUSY | IORESOURCE_SYSRAM, the next search would incorrectly skip resources unless they were also marked as IORESOURCE_SYSRAM. Fix this by restructuring the interface so it takes explicit "start, end, flags" parameters and uses "*res" only as an output parameter. Based on a patch by Lianbo Jiang <lijiang@redhat.com>. [ bp: While at it: - make comments kernel-doc style. - Originally-by: http://lore.kernel.org/lkml/20180921073211.20097-2-lijiang@redhat.com Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Signed-off-by: Borislav Petkov <bp@suse.de> CC: Andrew Morton <akpm@linux-foundation.org> CC: Brijesh Singh <brijesh.singh@amd.com> CC: Dan Williams <dan.j.williams@intel.com> CC: H. Peter Anvin <hpa@zytor.com> CC: Lianbo Jiang <lijiang@redhat.com> CC: Takashi Iwai <tiwai@suse.de> CC: Thomas Gleixner <tglx@linutronix.de> CC: Tom Lendacky <thomas.lendacky@amd.com> CC: Vivek Goyal <vgoyal@redhat.com> CC: Yaowei Bai <baiyaowei@cmss.chinamobile.com> CC: bhe@redhat.com CC: dan.j.williams@intel.com CC: dyoung@redhat.com CC: kexec@lists.infradead.org CC: mingo@redhat.com CC: x86-ml <x86@kernel.org> Link: http://lkml.kernel.org/r/153805812916.1157.177580438135143788.stgit@bhelgaas-glaptop.roam.corp.google.com
2018-09-27 22:22:09 +08:00
start = (u64) start_pfn << PAGE_SHIFT;
end = ((u64)(start_pfn + nr_pages) << PAGE_SHIFT) - 1;
flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
while (start < end &&
!find_next_iomem_res(start, end, flags, IORES_DESC_NONE,
mm/resource: Let walk_system_ram_range() search child resources In the process of onlining memory, we use walk_system_ram_range() to find the actual RAM areas inside of the area being onlined. However, it currently only finds memory resources which are "top-level" iomem_resources. Children are not currently searched which causes it to skip System RAM in areas like this (in the format of /proc/iomem): a0000000-bfffffff : Persistent Memory (legacy) a0000000-afffffff : System RAM Changing the true->false here allows children to be searched as well. We need this because we add a new "System RAM" resource underneath the "persistent memory" resource when we use persistent memory in a volatile mode. Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Cc: Keith Busch <keith.busch@intel.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Ross Zwisler <zwisler@kernel.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Michal Hocko <mhocko@suse.com> Cc: linux-nvdimm@lists.01.org Cc: linux-kernel@vger.kernel.org Cc: linux-mm@kvack.org Cc: Huang Ying <ying.huang@intel.com> Cc: Fengguang Wu <fengguang.wu@intel.com> Cc: Borislav Petkov <bp@suse.de> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Yaowei Bai <baiyaowei@cmss.chinamobile.com> Cc: Takashi Iwai <tiwai@suse.de> Cc: Jerome Glisse <jglisse@redhat.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2019-02-26 02:57:38 +08:00
false, &res)) {
resource: Fix generic page_is_ram() for partial RAM pages The System RAM walk shall skip partial RAM pages and avoid calling func() on them. So that page_is_ram() return 0 for a partial RAM page. In particular, it shall not call func() with len=0. This fixes a boot time bug reported by Sachin and root caused by Thomas: > >>> WARNING: at arch/x86/mm/ioremap.c:111 __ioremap_caller+0x169/0x2f1() > >>> Hardware name: BladeCenter LS21 -[79716AA]- > >>> Modules linked in: > >>> Pid: 0, comm: swapper Not tainted 2.6.33-git6-autotest #1 > >>> Call Trace: > >>> [<ffffffff81047cff>] ? __ioremap_caller+0x169/0x2f1 > >>> [<ffffffff81063b7d>] warn_slowpath_common+0x77/0xa4 > >>> [<ffffffff81063bb9>] warn_slowpath_null+0xf/0x11 > >>> [<ffffffff81047cff>] __ioremap_caller+0x169/0x2f1 > >>> [<ffffffff813747a3>] ? acpi_os_map_memory+0x12/0x1b > >>> [<ffffffff81047f10>] ioremap_nocache+0x12/0x14 > >>> [<ffffffff813747a3>] acpi_os_map_memory+0x12/0x1b > >>> [<ffffffff81282fa0>] acpi_tb_verify_table+0x29/0x5b > >>> [<ffffffff812827f0>] acpi_load_tables+0x39/0x15a > >>> [<ffffffff8191c8f8>] acpi_early_init+0x60/0xf5 > >>> [<ffffffff818f2cad>] start_kernel+0x397/0x3a7 > >>> [<ffffffff818f2295>] x86_64_start_reservations+0xa5/0xa9 > >>> [<ffffffff818f237a>] x86_64_start_kernel+0xe1/0xe8 > >>> ---[ end trace 4eaa2a86a8e2da22 ]--- > >>> ioremap reserve_memtype failed -22 The return code is -EINVAL, so it failed in the is_ram check, which is not too surprising > BIOS-provided physical RAM map: > BIOS-e820: 0000000000000000 - 000000000009c000 (usable) > BIOS-e820: 000000000009c000 - 00000000000a0000 (reserved) > BIOS-e820: 00000000000e0000 - 0000000000100000 (reserved) > BIOS-e820: 0000000000100000 - 00000000cffa3900 (usable) > BIOS-e820: 00000000cffa3900 - 00000000cffa7400 (ACPI data) The ACPI data is not starting on a page boundary and neither does the usable RAM area end on a page boundary. Very useful ! > ACPI: DSDT 00000000cffa3900 036CE (v01 IBM SERLEWIS 00001000 INTL 20060912) ACPI is trying to map DSDT at cffa3900, which results in a check vs. cffa3000 which is the relevant page boundary. The generic is_ram check correctly identifies that as RAM because it's in the usable resource area. The old e820 based is_ram check does not take overlapping resource areas into account. That's why it works. CC: Sachin Sant <sachinp@in.ibm.com> CC: Thomas Gleixner <tglx@linutronix.de> CC: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> LKML-Reference: <20100301135551.GA9998@localhost> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-03-01 21:55:51 +08:00
pfn = (res.start + PAGE_SIZE - 1) >> PAGE_SHIFT;
end_pfn = (res.end + 1) >> PAGE_SHIFT;
if (end_pfn > pfn)
ret = (*func)(pfn, end_pfn - pfn, arg);
if (ret)
break;
resource: Fix find_next_iomem_res() iteration issue Previously find_next_iomem_res() used "*res" as both an input parameter for the range to search and the type of resource to search for, and an output parameter for the resource we found, which makes the interface confusing. The current callers use find_next_iomem_res() incorrectly because they allocate a single struct resource and use it for repeated calls to find_next_iomem_res(). When find_next_iomem_res() returns a resource, it overwrites the start, end, flags, and desc members of the struct. If we call find_next_iomem_res() again, we must update or restore these fields. The previous code restored res.start and res.end, but not res.flags or res.desc. Since the callers did not restore res.flags, if they searched for flags IORESOURCE_MEM | IORESOURCE_BUSY and found a resource with flags IORESOURCE_MEM | IORESOURCE_BUSY | IORESOURCE_SYSRAM, the next search would incorrectly skip resources unless they were also marked as IORESOURCE_SYSRAM. Fix this by restructuring the interface so it takes explicit "start, end, flags" parameters and uses "*res" only as an output parameter. Based on a patch by Lianbo Jiang <lijiang@redhat.com>. [ bp: While at it: - make comments kernel-doc style. - Originally-by: http://lore.kernel.org/lkml/20180921073211.20097-2-lijiang@redhat.com Signed-off-by: Bjorn Helgaas <bhelgaas@google.com> Signed-off-by: Borislav Petkov <bp@suse.de> CC: Andrew Morton <akpm@linux-foundation.org> CC: Brijesh Singh <brijesh.singh@amd.com> CC: Dan Williams <dan.j.williams@intel.com> CC: H. Peter Anvin <hpa@zytor.com> CC: Lianbo Jiang <lijiang@redhat.com> CC: Takashi Iwai <tiwai@suse.de> CC: Thomas Gleixner <tglx@linutronix.de> CC: Tom Lendacky <thomas.lendacky@amd.com> CC: Vivek Goyal <vgoyal@redhat.com> CC: Yaowei Bai <baiyaowei@cmss.chinamobile.com> CC: bhe@redhat.com CC: dan.j.williams@intel.com CC: dyoung@redhat.com CC: kexec@lists.infradead.org CC: mingo@redhat.com CC: x86-ml <x86@kernel.org> Link: http://lkml.kernel.org/r/153805812916.1157.177580438135143788.stgit@bhelgaas-glaptop.roam.corp.google.com
2018-09-27 22:22:09 +08:00
start = res.end + 1;
}
return ret;
}
static int __is_ram(unsigned long pfn, unsigned long nr_pages, void *arg)
{
return 1;
}
/*
* This generic page_is_ram() returns true if specified address is
* registered as System RAM in iomem_resource list.
*/
int __weak page_is_ram(unsigned long pfn)
{
return walk_system_ram_range(pfn, 1, NULL, __is_ram) == 1;
}
EXPORT_SYMBOL_GPL(page_is_ram);
/**
* region_intersects() - determine intersection of region with known resources
* @start: region start address
* @size: size of region
memremap: Change region_intersects() to take @flags and @desc Change region_intersects() to identify a target with @flags and @desc, instead of @name with strcmp(). Change the callers of region_intersects(), memremap() and devm_memremap(), to set IORESOURCE_SYSTEM_RAM in @flags and IORES_DESC_NONE in @desc when searching System RAM. Also, export region_intersects() so that the ACPI EINJ error injection driver can call this function in a later patch. Signed-off-by: Toshi Kani <toshi.kani@hpe.com> Signed-off-by: Borislav Petkov <bp@suse.de> Acked-by: Dan Williams <dan.j.williams@intel.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jakub Sitnicki <jsitnicki@gmail.com> Cc: Jan Kara <jack@suse.cz> Cc: Jiang Liu <jiang.liu@linux.intel.com> Cc: Kees Cook <keescook@chromium.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Konstantin Khlebnikov <koct9i@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Luis R. Rodriguez <mcgrof@suse.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: linux-arch@vger.kernel.org Cc: linux-mm <linux-mm@kvack.org> Link: http://lkml.kernel.org/r/1453841853-11383-13-git-send-email-bp@alien8.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-01-27 04:57:28 +08:00
* @flags: flags of resource (in iomem_resource)
* @desc: descriptor of resource (in iomem_resource) or IORES_DESC_NONE
x86: optimize resource lookups for ioremap We have a large university system in the UK that is experiencing very long delays modprobing the driver for a specific I/O device. The delay is from 8-10 minutes per device and there are 31 devices in the system. This 4 to 5 hour delay in starting up those I/O devices is very much a burden on the customer. There are two causes for requiring a restart/reload of the drivers. First is periodic preventive maintenance (PM) and the second is if any of the devices experience a fatal error. Both of these trigger this excessively long delay in bringing the system back up to full capability. The problem was tracked down to a very slow IOREMAP operation and the excessively long ioresource lookup to insure that the user is not attempting to ioremap RAM. These patches provide a speed up to that function. The modprobe time appears to be affected quite a bit by previous activity on the ioresource list, which I suspect is due to cache preloading. While the overall improvement is impacted by other overhead of starting the devices, this drastically improves the modprobe time. Also our system is considerably smaller so the percentages gained will not be the same. Best case improvement with the modprobe on our 20 device smallish system was from 'real 5m51.913s' to 'real 0m18.275s'. This patch (of 2): Since the ioremap operation is verifying that the specified address range is NOT RAM, it will search the entire ioresource list if the condition is true. To make matters worse, it does this one 4k page at a time. For a 128M BAR region this is 32 passes to determine the entire region does not contain any RAM addresses. This patch provides another resource lookup function, region_is_ram, that searches for the entire region specified, verifying that it is completely contained within the resource region. If it is found, then it is checked to be RAM or not, within a single pass. The return result reflects if it was found or not (-1), and whether it is RAM (1) or not (0). This allows the caller to fallback to the previous page by page search if it was not found. [akpm@linux-foundation.org: fix spellos and typos in comment] Signed-off-by: Mike Travis <travis@sgi.com> Acked-by: Alex Thorlton <athorlton@sgi.com> Reviewed-by: Cliff Wickman <cpw@sgi.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Mark Salter <msalter@redhat.com> Cc: Dave Young <dyoung@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-10-14 06:54:03 +08:00
*
* Check if the specified region partially overlaps or fully eclipses a
memremap: Change region_intersects() to take @flags and @desc Change region_intersects() to identify a target with @flags and @desc, instead of @name with strcmp(). Change the callers of region_intersects(), memremap() and devm_memremap(), to set IORESOURCE_SYSTEM_RAM in @flags and IORES_DESC_NONE in @desc when searching System RAM. Also, export region_intersects() so that the ACPI EINJ error injection driver can call this function in a later patch. Signed-off-by: Toshi Kani <toshi.kani@hpe.com> Signed-off-by: Borislav Petkov <bp@suse.de> Acked-by: Dan Williams <dan.j.williams@intel.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jakub Sitnicki <jsitnicki@gmail.com> Cc: Jan Kara <jack@suse.cz> Cc: Jiang Liu <jiang.liu@linux.intel.com> Cc: Kees Cook <keescook@chromium.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Konstantin Khlebnikov <koct9i@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Luis R. Rodriguez <mcgrof@suse.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: linux-arch@vger.kernel.org Cc: linux-mm <linux-mm@kvack.org> Link: http://lkml.kernel.org/r/1453841853-11383-13-git-send-email-bp@alien8.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-01-27 04:57:28 +08:00
* resource identified by @flags and @desc (optional with IORES_DESC_NONE).
* Return REGION_DISJOINT if the region does not overlap @flags/@desc,
* return REGION_MIXED if the region overlaps @flags/@desc and another
* resource, and return REGION_INTERSECTS if the region overlaps @flags/@desc
* and no other defined resource. Note that REGION_INTERSECTS is also
* returned in the case when the specified region overlaps RAM and undefined
* memory holes.
*
* region_intersect() is used by memory remapping functions to ensure
* the user is not remapping RAM and is a vast speed up over walking
* through the resource table page by page.
x86: optimize resource lookups for ioremap We have a large university system in the UK that is experiencing very long delays modprobing the driver for a specific I/O device. The delay is from 8-10 minutes per device and there are 31 devices in the system. This 4 to 5 hour delay in starting up those I/O devices is very much a burden on the customer. There are two causes for requiring a restart/reload of the drivers. First is periodic preventive maintenance (PM) and the second is if any of the devices experience a fatal error. Both of these trigger this excessively long delay in bringing the system back up to full capability. The problem was tracked down to a very slow IOREMAP operation and the excessively long ioresource lookup to insure that the user is not attempting to ioremap RAM. These patches provide a speed up to that function. The modprobe time appears to be affected quite a bit by previous activity on the ioresource list, which I suspect is due to cache preloading. While the overall improvement is impacted by other overhead of starting the devices, this drastically improves the modprobe time. Also our system is considerably smaller so the percentages gained will not be the same. Best case improvement with the modprobe on our 20 device smallish system was from 'real 5m51.913s' to 'real 0m18.275s'. This patch (of 2): Since the ioremap operation is verifying that the specified address range is NOT RAM, it will search the entire ioresource list if the condition is true. To make matters worse, it does this one 4k page at a time. For a 128M BAR region this is 32 passes to determine the entire region does not contain any RAM addresses. This patch provides another resource lookup function, region_is_ram, that searches for the entire region specified, verifying that it is completely contained within the resource region. If it is found, then it is checked to be RAM or not, within a single pass. The return result reflects if it was found or not (-1), and whether it is RAM (1) or not (0). This allows the caller to fallback to the previous page by page search if it was not found. [akpm@linux-foundation.org: fix spellos and typos in comment] Signed-off-by: Mike Travis <travis@sgi.com> Acked-by: Alex Thorlton <athorlton@sgi.com> Reviewed-by: Cliff Wickman <cpw@sgi.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Mark Salter <msalter@redhat.com> Cc: Dave Young <dyoung@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-10-14 06:54:03 +08:00
*/
memremap: Change region_intersects() to take @flags and @desc Change region_intersects() to identify a target with @flags and @desc, instead of @name with strcmp(). Change the callers of region_intersects(), memremap() and devm_memremap(), to set IORESOURCE_SYSTEM_RAM in @flags and IORES_DESC_NONE in @desc when searching System RAM. Also, export region_intersects() so that the ACPI EINJ error injection driver can call this function in a later patch. Signed-off-by: Toshi Kani <toshi.kani@hpe.com> Signed-off-by: Borislav Petkov <bp@suse.de> Acked-by: Dan Williams <dan.j.williams@intel.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jakub Sitnicki <jsitnicki@gmail.com> Cc: Jan Kara <jack@suse.cz> Cc: Jiang Liu <jiang.liu@linux.intel.com> Cc: Kees Cook <keescook@chromium.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Konstantin Khlebnikov <koct9i@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Luis R. Rodriguez <mcgrof@suse.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: linux-arch@vger.kernel.org Cc: linux-mm <linux-mm@kvack.org> Link: http://lkml.kernel.org/r/1453841853-11383-13-git-send-email-bp@alien8.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-01-27 04:57:28 +08:00
int region_intersects(resource_size_t start, size_t size, unsigned long flags,
unsigned long desc)
x86: optimize resource lookups for ioremap We have a large university system in the UK that is experiencing very long delays modprobing the driver for a specific I/O device. The delay is from 8-10 minutes per device and there are 31 devices in the system. This 4 to 5 hour delay in starting up those I/O devices is very much a burden on the customer. There are two causes for requiring a restart/reload of the drivers. First is periodic preventive maintenance (PM) and the second is if any of the devices experience a fatal error. Both of these trigger this excessively long delay in bringing the system back up to full capability. The problem was tracked down to a very slow IOREMAP operation and the excessively long ioresource lookup to insure that the user is not attempting to ioremap RAM. These patches provide a speed up to that function. The modprobe time appears to be affected quite a bit by previous activity on the ioresource list, which I suspect is due to cache preloading. While the overall improvement is impacted by other overhead of starting the devices, this drastically improves the modprobe time. Also our system is considerably smaller so the percentages gained will not be the same. Best case improvement with the modprobe on our 20 device smallish system was from 'real 5m51.913s' to 'real 0m18.275s'. This patch (of 2): Since the ioremap operation is verifying that the specified address range is NOT RAM, it will search the entire ioresource list if the condition is true. To make matters worse, it does this one 4k page at a time. For a 128M BAR region this is 32 passes to determine the entire region does not contain any RAM addresses. This patch provides another resource lookup function, region_is_ram, that searches for the entire region specified, verifying that it is completely contained within the resource region. If it is found, then it is checked to be RAM or not, within a single pass. The return result reflects if it was found or not (-1), and whether it is RAM (1) or not (0). This allows the caller to fallback to the previous page by page search if it was not found. [akpm@linux-foundation.org: fix spellos and typos in comment] Signed-off-by: Mike Travis <travis@sgi.com> Acked-by: Alex Thorlton <athorlton@sgi.com> Reviewed-by: Cliff Wickman <cpw@sgi.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Mark Salter <msalter@redhat.com> Cc: Dave Young <dyoung@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-10-14 06:54:03 +08:00
{
resource_size_t end = start + size - 1;
int type = 0; int other = 0;
struct resource *p;
x86: optimize resource lookups for ioremap We have a large university system in the UK that is experiencing very long delays modprobing the driver for a specific I/O device. The delay is from 8-10 minutes per device and there are 31 devices in the system. This 4 to 5 hour delay in starting up those I/O devices is very much a burden on the customer. There are two causes for requiring a restart/reload of the drivers. First is periodic preventive maintenance (PM) and the second is if any of the devices experience a fatal error. Both of these trigger this excessively long delay in bringing the system back up to full capability. The problem was tracked down to a very slow IOREMAP operation and the excessively long ioresource lookup to insure that the user is not attempting to ioremap RAM. These patches provide a speed up to that function. The modprobe time appears to be affected quite a bit by previous activity on the ioresource list, which I suspect is due to cache preloading. While the overall improvement is impacted by other overhead of starting the devices, this drastically improves the modprobe time. Also our system is considerably smaller so the percentages gained will not be the same. Best case improvement with the modprobe on our 20 device smallish system was from 'real 5m51.913s' to 'real 0m18.275s'. This patch (of 2): Since the ioremap operation is verifying that the specified address range is NOT RAM, it will search the entire ioresource list if the condition is true. To make matters worse, it does this one 4k page at a time. For a 128M BAR region this is 32 passes to determine the entire region does not contain any RAM addresses. This patch provides another resource lookup function, region_is_ram, that searches for the entire region specified, verifying that it is completely contained within the resource region. If it is found, then it is checked to be RAM or not, within a single pass. The return result reflects if it was found or not (-1), and whether it is RAM (1) or not (0). This allows the caller to fallback to the previous page by page search if it was not found. [akpm@linux-foundation.org: fix spellos and typos in comment] Signed-off-by: Mike Travis <travis@sgi.com> Acked-by: Alex Thorlton <athorlton@sgi.com> Reviewed-by: Cliff Wickman <cpw@sgi.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Mark Salter <msalter@redhat.com> Cc: Dave Young <dyoung@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-10-14 06:54:03 +08:00
read_lock(&resource_lock);
for (p = iomem_resource.child; p ; p = p->sibling) {
memremap: Change region_intersects() to take @flags and @desc Change region_intersects() to identify a target with @flags and @desc, instead of @name with strcmp(). Change the callers of region_intersects(), memremap() and devm_memremap(), to set IORESOURCE_SYSTEM_RAM in @flags and IORES_DESC_NONE in @desc when searching System RAM. Also, export region_intersects() so that the ACPI EINJ error injection driver can call this function in a later patch. Signed-off-by: Toshi Kani <toshi.kani@hpe.com> Signed-off-by: Borislav Petkov <bp@suse.de> Acked-by: Dan Williams <dan.j.williams@intel.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jakub Sitnicki <jsitnicki@gmail.com> Cc: Jan Kara <jack@suse.cz> Cc: Jiang Liu <jiang.liu@linux.intel.com> Cc: Kees Cook <keescook@chromium.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Konstantin Khlebnikov <koct9i@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Luis R. Rodriguez <mcgrof@suse.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: linux-arch@vger.kernel.org Cc: linux-mm <linux-mm@kvack.org> Link: http://lkml.kernel.org/r/1453841853-11383-13-git-send-email-bp@alien8.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-01-27 04:57:28 +08:00
bool is_type = (((p->flags & flags) == flags) &&
((desc == IORES_DESC_NONE) ||
(desc == p->desc)));
if (start >= p->start && start <= p->end)
is_type ? type++ : other++;
if (end >= p->start && end <= p->end)
is_type ? type++ : other++;
if (p->start >= start && p->end <= end)
is_type ? type++ : other++;
x86: optimize resource lookups for ioremap We have a large university system in the UK that is experiencing very long delays modprobing the driver for a specific I/O device. The delay is from 8-10 minutes per device and there are 31 devices in the system. This 4 to 5 hour delay in starting up those I/O devices is very much a burden on the customer. There are two causes for requiring a restart/reload of the drivers. First is periodic preventive maintenance (PM) and the second is if any of the devices experience a fatal error. Both of these trigger this excessively long delay in bringing the system back up to full capability. The problem was tracked down to a very slow IOREMAP operation and the excessively long ioresource lookup to insure that the user is not attempting to ioremap RAM. These patches provide a speed up to that function. The modprobe time appears to be affected quite a bit by previous activity on the ioresource list, which I suspect is due to cache preloading. While the overall improvement is impacted by other overhead of starting the devices, this drastically improves the modprobe time. Also our system is considerably smaller so the percentages gained will not be the same. Best case improvement with the modprobe on our 20 device smallish system was from 'real 5m51.913s' to 'real 0m18.275s'. This patch (of 2): Since the ioremap operation is verifying that the specified address range is NOT RAM, it will search the entire ioresource list if the condition is true. To make matters worse, it does this one 4k page at a time. For a 128M BAR region this is 32 passes to determine the entire region does not contain any RAM addresses. This patch provides another resource lookup function, region_is_ram, that searches for the entire region specified, verifying that it is completely contained within the resource region. If it is found, then it is checked to be RAM or not, within a single pass. The return result reflects if it was found or not (-1), and whether it is RAM (1) or not (0). This allows the caller to fallback to the previous page by page search if it was not found. [akpm@linux-foundation.org: fix spellos and typos in comment] Signed-off-by: Mike Travis <travis@sgi.com> Acked-by: Alex Thorlton <athorlton@sgi.com> Reviewed-by: Cliff Wickman <cpw@sgi.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Mark Salter <msalter@redhat.com> Cc: Dave Young <dyoung@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-10-14 06:54:03 +08:00
}
read_unlock(&resource_lock);
if (other == 0)
return type ? REGION_INTERSECTS : REGION_DISJOINT;
if (type)
return REGION_MIXED;
return REGION_DISJOINT;
x86: optimize resource lookups for ioremap We have a large university system in the UK that is experiencing very long delays modprobing the driver for a specific I/O device. The delay is from 8-10 minutes per device and there are 31 devices in the system. This 4 to 5 hour delay in starting up those I/O devices is very much a burden on the customer. There are two causes for requiring a restart/reload of the drivers. First is periodic preventive maintenance (PM) and the second is if any of the devices experience a fatal error. Both of these trigger this excessively long delay in bringing the system back up to full capability. The problem was tracked down to a very slow IOREMAP operation and the excessively long ioresource lookup to insure that the user is not attempting to ioremap RAM. These patches provide a speed up to that function. The modprobe time appears to be affected quite a bit by previous activity on the ioresource list, which I suspect is due to cache preloading. While the overall improvement is impacted by other overhead of starting the devices, this drastically improves the modprobe time. Also our system is considerably smaller so the percentages gained will not be the same. Best case improvement with the modprobe on our 20 device smallish system was from 'real 5m51.913s' to 'real 0m18.275s'. This patch (of 2): Since the ioremap operation is verifying that the specified address range is NOT RAM, it will search the entire ioresource list if the condition is true. To make matters worse, it does this one 4k page at a time. For a 128M BAR region this is 32 passes to determine the entire region does not contain any RAM addresses. This patch provides another resource lookup function, region_is_ram, that searches for the entire region specified, verifying that it is completely contained within the resource region. If it is found, then it is checked to be RAM or not, within a single pass. The return result reflects if it was found or not (-1), and whether it is RAM (1) or not (0). This allows the caller to fallback to the previous page by page search if it was not found. [akpm@linux-foundation.org: fix spellos and typos in comment] Signed-off-by: Mike Travis <travis@sgi.com> Acked-by: Alex Thorlton <athorlton@sgi.com> Reviewed-by: Cliff Wickman <cpw@sgi.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Mark Salter <msalter@redhat.com> Cc: Dave Young <dyoung@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-10-14 06:54:03 +08:00
}
memremap: Change region_intersects() to take @flags and @desc Change region_intersects() to identify a target with @flags and @desc, instead of @name with strcmp(). Change the callers of region_intersects(), memremap() and devm_memremap(), to set IORESOURCE_SYSTEM_RAM in @flags and IORES_DESC_NONE in @desc when searching System RAM. Also, export region_intersects() so that the ACPI EINJ error injection driver can call this function in a later patch. Signed-off-by: Toshi Kani <toshi.kani@hpe.com> Signed-off-by: Borislav Petkov <bp@suse.de> Acked-by: Dan Williams <dan.j.williams@intel.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jakub Sitnicki <jsitnicki@gmail.com> Cc: Jan Kara <jack@suse.cz> Cc: Jiang Liu <jiang.liu@linux.intel.com> Cc: Kees Cook <keescook@chromium.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Konstantin Khlebnikov <koct9i@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Luis R. Rodriguez <mcgrof@suse.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: linux-arch@vger.kernel.org Cc: linux-mm <linux-mm@kvack.org> Link: http://lkml.kernel.org/r/1453841853-11383-13-git-send-email-bp@alien8.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-01-27 04:57:28 +08:00
EXPORT_SYMBOL_GPL(region_intersects);
x86: optimize resource lookups for ioremap We have a large university system in the UK that is experiencing very long delays modprobing the driver for a specific I/O device. The delay is from 8-10 minutes per device and there are 31 devices in the system. This 4 to 5 hour delay in starting up those I/O devices is very much a burden on the customer. There are two causes for requiring a restart/reload of the drivers. First is periodic preventive maintenance (PM) and the second is if any of the devices experience a fatal error. Both of these trigger this excessively long delay in bringing the system back up to full capability. The problem was tracked down to a very slow IOREMAP operation and the excessively long ioresource lookup to insure that the user is not attempting to ioremap RAM. These patches provide a speed up to that function. The modprobe time appears to be affected quite a bit by previous activity on the ioresource list, which I suspect is due to cache preloading. While the overall improvement is impacted by other overhead of starting the devices, this drastically improves the modprobe time. Also our system is considerably smaller so the percentages gained will not be the same. Best case improvement with the modprobe on our 20 device smallish system was from 'real 5m51.913s' to 'real 0m18.275s'. This patch (of 2): Since the ioremap operation is verifying that the specified address range is NOT RAM, it will search the entire ioresource list if the condition is true. To make matters worse, it does this one 4k page at a time. For a 128M BAR region this is 32 passes to determine the entire region does not contain any RAM addresses. This patch provides another resource lookup function, region_is_ram, that searches for the entire region specified, verifying that it is completely contained within the resource region. If it is found, then it is checked to be RAM or not, within a single pass. The return result reflects if it was found or not (-1), and whether it is RAM (1) or not (0). This allows the caller to fallback to the previous page by page search if it was not found. [akpm@linux-foundation.org: fix spellos and typos in comment] Signed-off-by: Mike Travis <travis@sgi.com> Acked-by: Alex Thorlton <athorlton@sgi.com> Reviewed-by: Cliff Wickman <cpw@sgi.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Mark Salter <msalter@redhat.com> Cc: Dave Young <dyoung@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-10-14 06:54:03 +08:00
void __weak arch_remove_reservations(struct resource *avail)
{
}
static resource_size_t simple_align_resource(void *data,
const struct resource *avail,
resource_size_t size,
resource_size_t align)
{
return avail->start;
}
static void resource_clip(struct resource *res, resource_size_t min,
resource_size_t max)
{
if (res->start < min)
res->start = min;
if (res->end > max)
res->end = max;
}
/*
* Find empty slot in the resource tree with the given range and
* alignment constraints
*/
static int __find_resource(struct resource *root, struct resource *old,
struct resource *new,
resource_size_t size,
struct resource_constraint *constraint)
{
struct resource *this = root->child;
struct resource tmp = *new, avail, alloc;
tmp.start = root->start;
/*
* Skip past an allocated resource that starts at 0, since the assignment
* of this->start - 1 to tmp->end below would cause an underflow.
*/
if (this && this->start == root->start) {
tmp.start = (this == old) ? old->start : this->end + 1;
this = this->sibling;
}
for(;;) {
if (this)
tmp.end = (this == old) ? this->end : this->start - 1;
else
tmp.end = root->end;
if (tmp.end < tmp.start)
goto next;
resource_clip(&tmp, constraint->min, constraint->max);
arch_remove_reservations(&tmp);
/* Check for overflow after ALIGN() */
avail.start = ALIGN(tmp.start, constraint->align);
avail.end = tmp.end;
avail.flags = new->flags & ~IORESOURCE_UNSET;
if (avail.start >= tmp.start) {
alloc.flags = avail.flags;
alloc.start = constraint->alignf(constraint->alignf_data, &avail,
size, constraint->align);
alloc.end = alloc.start + size - 1;
if (alloc.start <= alloc.end &&
resource_contains(&avail, &alloc)) {
new->start = alloc.start;
new->end = alloc.end;
return 0;
}
}
next: if (!this || this->end == root->end)
break;
if (this != old)
tmp.start = this->end + 1;
this = this->sibling;
}
return -EBUSY;
}
/*
* Find empty slot in the resource tree given range and alignment.
*/
static int find_resource(struct resource *root, struct resource *new,
resource_size_t size,
struct resource_constraint *constraint)
{
return __find_resource(root, NULL, new, size, constraint);
}
/**
* reallocate_resource - allocate a slot in the resource tree given range & alignment.
* The resource will be relocated if the new size cannot be reallocated in the
* current location.
*
* @root: root resource descriptor
* @old: resource descriptor desired by caller
* @newsize: new size of the resource descriptor
* @constraint: the size and alignment constraints to be met.
*/
static int reallocate_resource(struct resource *root, struct resource *old,
resource_size_t newsize,
struct resource_constraint *constraint)
{
int err=0;
struct resource new = *old;
struct resource *conflict;
write_lock(&resource_lock);
if ((err = __find_resource(root, old, &new, newsize, constraint)))
goto out;
if (resource_contains(&new, old)) {
old->start = new.start;
old->end = new.end;
goto out;
}
if (old->child) {
err = -EBUSY;
goto out;
}
if (resource_contains(old, &new)) {
old->start = new.start;
old->end = new.end;
} else {
__release_resource(old, true);
*old = new;
conflict = __request_resource(root, old);
BUG_ON(conflict);
}
out:
write_unlock(&resource_lock);
return err;
}
/**
* allocate_resource - allocate empty slot in the resource tree given range & alignment.
* The resource will be reallocated with a new size if it was already allocated
* @root: root resource descriptor
* @new: resource descriptor desired by caller
* @size: requested resource region size
* @min: minimum boundary to allocate
* @max: maximum boundary to allocate
* @align: alignment requested, in bytes
* @alignf: alignment function, optional, called if not NULL
* @alignf_data: arbitrary data to pass to the @alignf function
*/
int allocate_resource(struct resource *root, struct resource *new,
resource_size_t size, resource_size_t min,
resource_size_t max, resource_size_t align,
resource_size_t (*alignf)(void *,
const struct resource *,
resource_size_t,
resource_size_t),
void *alignf_data)
{
int err;
struct resource_constraint constraint;
if (!alignf)
alignf = simple_align_resource;
constraint.min = min;
constraint.max = max;
constraint.align = align;
constraint.alignf = alignf;
constraint.alignf_data = alignf_data;
if ( new->parent ) {
/* resource is already allocated, try reallocating with
the new constraints */
return reallocate_resource(root, new, size, &constraint);
}
write_lock(&resource_lock);
err = find_resource(root, new, size, &constraint);
if (err >= 0 && __request_resource(root, new))
err = -EBUSY;
write_unlock(&resource_lock);
return err;
}
EXPORT_SYMBOL(allocate_resource);
/**
* lookup_resource - find an existing resource by a resource start address
* @root: root resource descriptor
* @start: resource start address
*
* Returns a pointer to the resource if found, NULL otherwise
*/
struct resource *lookup_resource(struct resource *root, resource_size_t start)
{
struct resource *res;
read_lock(&resource_lock);
for (res = root->child; res; res = res->sibling) {
if (res->start == start)
break;
}
read_unlock(&resource_lock);
return res;
}
/*
* Insert a resource into the resource tree. If successful, return NULL,
* otherwise return the conflicting resource (compare to __request_resource())
*/
static struct resource * __insert_resource(struct resource *parent, struct resource *new)
{
struct resource *first, *next;
for (;; parent = first) {
first = __request_resource(parent, new);
if (!first)
return first;
if (first == parent)
return first;
if (WARN_ON(first == new)) /* duplicated insertion */
return first;
if ((first->start > new->start) || (first->end < new->end))
break;
if ((first->start == new->start) && (first->end == new->end))
break;
}
for (next = first; ; next = next->sibling) {
/* Partial overlap? Bad, and unfixable */
if (next->start < new->start || next->end > new->end)
return next;
if (!next->sibling)
break;
if (next->sibling->start > new->end)
break;
}
new->parent = parent;
new->sibling = next->sibling;
new->child = first;
next->sibling = NULL;
for (next = first; next; next = next->sibling)
next->parent = new;
if (parent->child == first) {
parent->child = new;
} else {
next = parent->child;
while (next->sibling != first)
next = next->sibling;
next->sibling = new;
}
return NULL;
}
/**
* insert_resource_conflict - Inserts resource in the resource tree
* @parent: parent of the new resource
* @new: new resource to insert
*
* Returns 0 on success, conflict resource if the resource can't be inserted.
*
* This function is equivalent to request_resource_conflict when no conflict
* happens. If a conflict happens, and the conflicting resources
* entirely fit within the range of the new resource, then the new
* resource is inserted and the conflicting resources become children of
* the new resource.
*
* This function is intended for producers of resources, such as FW modules
* and bus drivers.
*/
struct resource *insert_resource_conflict(struct resource *parent, struct resource *new)
{
struct resource *conflict;
write_lock(&resource_lock);
conflict = __insert_resource(parent, new);
write_unlock(&resource_lock);
return conflict;
}
/**
* insert_resource - Inserts a resource in the resource tree
* @parent: parent of the new resource
* @new: new resource to insert
*
* Returns 0 on success, -EBUSY if the resource can't be inserted.
*
* This function is intended for producers of resources, such as FW modules
* and bus drivers.
*/
int insert_resource(struct resource *parent, struct resource *new)
{
struct resource *conflict;
conflict = insert_resource_conflict(parent, new);
return conflict ? -EBUSY : 0;
}
EXPORT_SYMBOL_GPL(insert_resource);
/**
* insert_resource_expand_to_fit - Insert a resource into the resource tree
* @root: root resource descriptor
* @new: new resource to insert
*
* Insert a resource into the resource tree, possibly expanding it in order
* to make it encompass any conflicting resources.
*/
void insert_resource_expand_to_fit(struct resource *root, struct resource *new)
{
if (new->parent)
return;
write_lock(&resource_lock);
for (;;) {
struct resource *conflict;
conflict = __insert_resource(root, new);
if (!conflict)
break;
if (conflict == root)
break;
/* Ok, expand resource to cover the conflict, then try again .. */
if (conflict->start < new->start)
new->start = conflict->start;
if (conflict->end > new->end)
new->end = conflict->end;
printk("Expanded resource %s due to conflict with %s\n", new->name, conflict->name);
}
write_unlock(&resource_lock);
}
/**
* remove_resource - Remove a resource in the resource tree
* @old: resource to remove
*
* Returns 0 on success, -EINVAL if the resource is not valid.
*
* This function removes a resource previously inserted by insert_resource()
* or insert_resource_conflict(), and moves the children (if any) up to
* where they were before. insert_resource() and insert_resource_conflict()
* insert a new resource, and move any conflicting resources down to the
* children of the new resource.
*
* insert_resource(), insert_resource_conflict() and remove_resource() are
* intended for producers of resources, such as FW modules and bus drivers.
*/
int remove_resource(struct resource *old)
{
int retval;
write_lock(&resource_lock);
retval = __release_resource(old, false);
write_unlock(&resource_lock);
return retval;
}
EXPORT_SYMBOL_GPL(remove_resource);
static int __adjust_resource(struct resource *res, resource_size_t start,
resource_size_t size)
{
struct resource *tmp, *parent = res->parent;
resource_size_t end = start + size - 1;
int result = -EBUSY;
if (!parent)
goto skip;
if ((start < parent->start) || (end > parent->end))
goto out;
if (res->sibling && (res->sibling->start <= end))
goto out;
tmp = parent->child;
if (tmp != res) {
while (tmp->sibling != res)
tmp = tmp->sibling;
if (start <= tmp->end)
goto out;
}
skip:
for (tmp = res->child; tmp; tmp = tmp->sibling)
if ((tmp->start < start) || (tmp->end > end))
goto out;
res->start = start;
res->end = end;
result = 0;
out:
return result;
}
/**
* adjust_resource - modify a resource's start and size
* @res: resource to modify
* @start: new start value
* @size: new size
*
* Given an existing resource, change its start and size to match the
* arguments. Returns 0 on success, -EBUSY if it can't fit.
* Existing children of the resource are assumed to be immutable.
*/
int adjust_resource(struct resource *res, resource_size_t start,
resource_size_t size)
{
int result;
write_lock(&resource_lock);
result = __adjust_resource(res, start, size);
write_unlock(&resource_lock);
return result;
}
EXPORT_SYMBOL(adjust_resource);
static void __init
__reserve_region_with_split(struct resource *root, resource_size_t start,
resource_size_t end, const char *name)
{
struct resource *parent = root;
struct resource *conflict;
mem hotunplug: fix kfree() of bootmem memory When hot removing memory presented at boot time, following messages are shown: kernel BUG at mm/slub.c:3409! invalid opcode: 0000 [#1] SMP Modules linked in: ebtable_nat ebtables xt_CHECKSUM iptable_mangle bridge stp llc ipmi_devintf ipmi_msghandler sunrpc ipt_REJECT nf_conntrack_ipv4 nf_defrag_ipv4 iptable_filter ip_tables ip6t_REJECT nf_conntrack_ipv6 nf_defrag_ipv6 xt_state nf_conntrack ip6table_filter ip6_tables binfmt_misc vfat fat dm_mirror dm_region_hash dm_log dm_mod vhost_net macvtap macvlan tun uinput iTCO_wdt iTCO_vendor_support coretemp kvm_intel kvm crc32c_intel ghash_clmulni_intel microcode pcspkr sg i2c_i801 lpc_ich mfd_core igb i2c_algo_bit i2c_core e1000e ptp pps_core tpm_infineon ioatdma dca sr_mod cdrom sd_mod crc_t10dif usb_storage megaraid_sas lpfc scsi_transport_fc scsi_tgt scsi_mod CPU 0 Pid: 5091, comm: kworker/0:2 Tainted: G W 3.9.0-rc6+ #15 RIP: kfree+0x232/0x240 Process kworker/0:2 (pid: 5091, threadinfo ffff88084678c000, task ffff88083928ca80) Call Trace: __release_region+0xd4/0xe0 __remove_pages+0x52/0x110 arch_remove_memory+0x89/0xd0 remove_memory+0xc4/0x100 acpi_memory_device_remove+0x6d/0xb1 acpi_device_remove+0x89/0xab __device_release_driver+0x7c/0xf0 device_release_driver+0x2f/0x50 acpi_bus_device_detach+0x6c/0x70 acpi_ns_walk_namespace+0x11a/0x250 acpi_walk_namespace+0xee/0x137 acpi_bus_trim+0x33/0x7a acpi_bus_hot_remove_device+0xc4/0x1a1 acpi_os_execute_deferred+0x27/0x34 process_one_work+0x1f7/0x590 worker_thread+0x11a/0x370 kthread+0xee/0x100 ret_from_fork+0x7c/0xb0 RIP [<ffffffff811c41d2>] kfree+0x232/0x240 RSP <ffff88084678d968> The reason why the messages are shown is to release a resource structure, allocated by bootmem, by kfree(). So when we release a resource structure, we should check whether it is allocated by bootmem or not. But even if we know a resource structure is allocated by bootmem, we cannot release it since SLxB cannot treat it. So for reusing a resource structure, this patch remembers it by using bootmem_resource as follows: When releasing a resource structure by free_resource(), free_resource() checks whether the resource structure is allocated by bootmem or not. If it is allocated by bootmem, free_resource() adds it to bootmem_resource. If it is not allocated by bootmem, free_resource() release it by kfree(). And when getting a new resource structure by get_resource(), get_resource() checks whether bootmem_resource has released resource structures or not. If there is a released resource structure, get_resource() returns it. If there is not a releaed resource structure, get_resource() returns new resource structure allocated by kzalloc(). [akpm@linux-foundation.org: s/get_resource/alloc_resource/] Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Reviewed-by: Toshi Kani <toshi.kani@hp.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Ram Pai <linuxram@us.ibm.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-30 06:08:56 +08:00
struct resource *res = alloc_resource(GFP_ATOMIC);
struct resource *next_res = NULL;
int type = resource_type(root);
if (!res)
return;
res->name = name;
res->start = start;
res->end = end;
res->flags = type | IORESOURCE_BUSY;
resource: Add I/O resource descriptor walk_iomem_res() and region_intersects() still need to use strcmp() for searching a resource entry by @name in the iomem table. This patch introduces I/O resource descriptor 'desc' in struct resource for the iomem search interfaces. Drivers can assign their unique descriptor to a range when they support the search interfaces. Otherwise, 'desc' is set to IORES_DESC_NONE (0). This avoids changing most of the drivers as they typically allocate resource entries statically, or by calling alloc_resource(), kzalloc(), or alloc_bootmem_low(), which set the field to zero by default. A later patch will address some drivers that use kmalloc() without zero'ing the field. Also change release_mem_region_adjustable() to set 'desc' when its resource entry gets separated. Other resource interfaces are also changed to initialize 'desc' explicitly although alloc_resource() sets it to 0. Signed-off-by: Toshi Kani <toshi.kani@hpe.com> Signed-off-by: Borislav Petkov <bp@suse.de> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jakub Sitnicki <jsitnicki@gmail.com> Cc: Jiang Liu <jiang.liu@linux.intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Luis R. Rodriguez <mcgrof@suse.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: linux-arch@vger.kernel.org Cc: linux-mm <linux-mm@kvack.org> Link: http://lkml.kernel.org/r/1453841853-11383-4-git-send-email-bp@alien8.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-01-27 04:57:19 +08:00
res->desc = IORES_DESC_NONE;
while (1) {
conflict = __request_resource(parent, res);
if (!conflict) {
if (!next_res)
break;
res = next_res;
next_res = NULL;
continue;
}
/* conflict covered whole area */
if (conflict->start <= res->start &&
conflict->end >= res->end) {
mem hotunplug: fix kfree() of bootmem memory When hot removing memory presented at boot time, following messages are shown: kernel BUG at mm/slub.c:3409! invalid opcode: 0000 [#1] SMP Modules linked in: ebtable_nat ebtables xt_CHECKSUM iptable_mangle bridge stp llc ipmi_devintf ipmi_msghandler sunrpc ipt_REJECT nf_conntrack_ipv4 nf_defrag_ipv4 iptable_filter ip_tables ip6t_REJECT nf_conntrack_ipv6 nf_defrag_ipv6 xt_state nf_conntrack ip6table_filter ip6_tables binfmt_misc vfat fat dm_mirror dm_region_hash dm_log dm_mod vhost_net macvtap macvlan tun uinput iTCO_wdt iTCO_vendor_support coretemp kvm_intel kvm crc32c_intel ghash_clmulni_intel microcode pcspkr sg i2c_i801 lpc_ich mfd_core igb i2c_algo_bit i2c_core e1000e ptp pps_core tpm_infineon ioatdma dca sr_mod cdrom sd_mod crc_t10dif usb_storage megaraid_sas lpfc scsi_transport_fc scsi_tgt scsi_mod CPU 0 Pid: 5091, comm: kworker/0:2 Tainted: G W 3.9.0-rc6+ #15 RIP: kfree+0x232/0x240 Process kworker/0:2 (pid: 5091, threadinfo ffff88084678c000, task ffff88083928ca80) Call Trace: __release_region+0xd4/0xe0 __remove_pages+0x52/0x110 arch_remove_memory+0x89/0xd0 remove_memory+0xc4/0x100 acpi_memory_device_remove+0x6d/0xb1 acpi_device_remove+0x89/0xab __device_release_driver+0x7c/0xf0 device_release_driver+0x2f/0x50 acpi_bus_device_detach+0x6c/0x70 acpi_ns_walk_namespace+0x11a/0x250 acpi_walk_namespace+0xee/0x137 acpi_bus_trim+0x33/0x7a acpi_bus_hot_remove_device+0xc4/0x1a1 acpi_os_execute_deferred+0x27/0x34 process_one_work+0x1f7/0x590 worker_thread+0x11a/0x370 kthread+0xee/0x100 ret_from_fork+0x7c/0xb0 RIP [<ffffffff811c41d2>] kfree+0x232/0x240 RSP <ffff88084678d968> The reason why the messages are shown is to release a resource structure, allocated by bootmem, by kfree(). So when we release a resource structure, we should check whether it is allocated by bootmem or not. But even if we know a resource structure is allocated by bootmem, we cannot release it since SLxB cannot treat it. So for reusing a resource structure, this patch remembers it by using bootmem_resource as follows: When releasing a resource structure by free_resource(), free_resource() checks whether the resource structure is allocated by bootmem or not. If it is allocated by bootmem, free_resource() adds it to bootmem_resource. If it is not allocated by bootmem, free_resource() release it by kfree(). And when getting a new resource structure by get_resource(), get_resource() checks whether bootmem_resource has released resource structures or not. If there is a released resource structure, get_resource() returns it. If there is not a releaed resource structure, get_resource() returns new resource structure allocated by kzalloc(). [akpm@linux-foundation.org: s/get_resource/alloc_resource/] Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Reviewed-by: Toshi Kani <toshi.kani@hp.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Ram Pai <linuxram@us.ibm.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-30 06:08:56 +08:00
free_resource(res);
WARN_ON(next_res);
break;
}
/* failed, split and try again */
if (conflict->start > res->start) {
end = res->end;
res->end = conflict->start - 1;
if (conflict->end < end) {
mem hotunplug: fix kfree() of bootmem memory When hot removing memory presented at boot time, following messages are shown: kernel BUG at mm/slub.c:3409! invalid opcode: 0000 [#1] SMP Modules linked in: ebtable_nat ebtables xt_CHECKSUM iptable_mangle bridge stp llc ipmi_devintf ipmi_msghandler sunrpc ipt_REJECT nf_conntrack_ipv4 nf_defrag_ipv4 iptable_filter ip_tables ip6t_REJECT nf_conntrack_ipv6 nf_defrag_ipv6 xt_state nf_conntrack ip6table_filter ip6_tables binfmt_misc vfat fat dm_mirror dm_region_hash dm_log dm_mod vhost_net macvtap macvlan tun uinput iTCO_wdt iTCO_vendor_support coretemp kvm_intel kvm crc32c_intel ghash_clmulni_intel microcode pcspkr sg i2c_i801 lpc_ich mfd_core igb i2c_algo_bit i2c_core e1000e ptp pps_core tpm_infineon ioatdma dca sr_mod cdrom sd_mod crc_t10dif usb_storage megaraid_sas lpfc scsi_transport_fc scsi_tgt scsi_mod CPU 0 Pid: 5091, comm: kworker/0:2 Tainted: G W 3.9.0-rc6+ #15 RIP: kfree+0x232/0x240 Process kworker/0:2 (pid: 5091, threadinfo ffff88084678c000, task ffff88083928ca80) Call Trace: __release_region+0xd4/0xe0 __remove_pages+0x52/0x110 arch_remove_memory+0x89/0xd0 remove_memory+0xc4/0x100 acpi_memory_device_remove+0x6d/0xb1 acpi_device_remove+0x89/0xab __device_release_driver+0x7c/0xf0 device_release_driver+0x2f/0x50 acpi_bus_device_detach+0x6c/0x70 acpi_ns_walk_namespace+0x11a/0x250 acpi_walk_namespace+0xee/0x137 acpi_bus_trim+0x33/0x7a acpi_bus_hot_remove_device+0xc4/0x1a1 acpi_os_execute_deferred+0x27/0x34 process_one_work+0x1f7/0x590 worker_thread+0x11a/0x370 kthread+0xee/0x100 ret_from_fork+0x7c/0xb0 RIP [<ffffffff811c41d2>] kfree+0x232/0x240 RSP <ffff88084678d968> The reason why the messages are shown is to release a resource structure, allocated by bootmem, by kfree(). So when we release a resource structure, we should check whether it is allocated by bootmem or not. But even if we know a resource structure is allocated by bootmem, we cannot release it since SLxB cannot treat it. So for reusing a resource structure, this patch remembers it by using bootmem_resource as follows: When releasing a resource structure by free_resource(), free_resource() checks whether the resource structure is allocated by bootmem or not. If it is allocated by bootmem, free_resource() adds it to bootmem_resource. If it is not allocated by bootmem, free_resource() release it by kfree(). And when getting a new resource structure by get_resource(), get_resource() checks whether bootmem_resource has released resource structures or not. If there is a released resource structure, get_resource() returns it. If there is not a releaed resource structure, get_resource() returns new resource structure allocated by kzalloc(). [akpm@linux-foundation.org: s/get_resource/alloc_resource/] Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Reviewed-by: Toshi Kani <toshi.kani@hp.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Ram Pai <linuxram@us.ibm.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-30 06:08:56 +08:00
next_res = alloc_resource(GFP_ATOMIC);
if (!next_res) {
mem hotunplug: fix kfree() of bootmem memory When hot removing memory presented at boot time, following messages are shown: kernel BUG at mm/slub.c:3409! invalid opcode: 0000 [#1] SMP Modules linked in: ebtable_nat ebtables xt_CHECKSUM iptable_mangle bridge stp llc ipmi_devintf ipmi_msghandler sunrpc ipt_REJECT nf_conntrack_ipv4 nf_defrag_ipv4 iptable_filter ip_tables ip6t_REJECT nf_conntrack_ipv6 nf_defrag_ipv6 xt_state nf_conntrack ip6table_filter ip6_tables binfmt_misc vfat fat dm_mirror dm_region_hash dm_log dm_mod vhost_net macvtap macvlan tun uinput iTCO_wdt iTCO_vendor_support coretemp kvm_intel kvm crc32c_intel ghash_clmulni_intel microcode pcspkr sg i2c_i801 lpc_ich mfd_core igb i2c_algo_bit i2c_core e1000e ptp pps_core tpm_infineon ioatdma dca sr_mod cdrom sd_mod crc_t10dif usb_storage megaraid_sas lpfc scsi_transport_fc scsi_tgt scsi_mod CPU 0 Pid: 5091, comm: kworker/0:2 Tainted: G W 3.9.0-rc6+ #15 RIP: kfree+0x232/0x240 Process kworker/0:2 (pid: 5091, threadinfo ffff88084678c000, task ffff88083928ca80) Call Trace: __release_region+0xd4/0xe0 __remove_pages+0x52/0x110 arch_remove_memory+0x89/0xd0 remove_memory+0xc4/0x100 acpi_memory_device_remove+0x6d/0xb1 acpi_device_remove+0x89/0xab __device_release_driver+0x7c/0xf0 device_release_driver+0x2f/0x50 acpi_bus_device_detach+0x6c/0x70 acpi_ns_walk_namespace+0x11a/0x250 acpi_walk_namespace+0xee/0x137 acpi_bus_trim+0x33/0x7a acpi_bus_hot_remove_device+0xc4/0x1a1 acpi_os_execute_deferred+0x27/0x34 process_one_work+0x1f7/0x590 worker_thread+0x11a/0x370 kthread+0xee/0x100 ret_from_fork+0x7c/0xb0 RIP [<ffffffff811c41d2>] kfree+0x232/0x240 RSP <ffff88084678d968> The reason why the messages are shown is to release a resource structure, allocated by bootmem, by kfree(). So when we release a resource structure, we should check whether it is allocated by bootmem or not. But even if we know a resource structure is allocated by bootmem, we cannot release it since SLxB cannot treat it. So for reusing a resource structure, this patch remembers it by using bootmem_resource as follows: When releasing a resource structure by free_resource(), free_resource() checks whether the resource structure is allocated by bootmem or not. If it is allocated by bootmem, free_resource() adds it to bootmem_resource. If it is not allocated by bootmem, free_resource() release it by kfree(). And when getting a new resource structure by get_resource(), get_resource() checks whether bootmem_resource has released resource structures or not. If there is a released resource structure, get_resource() returns it. If there is not a releaed resource structure, get_resource() returns new resource structure allocated by kzalloc(). [akpm@linux-foundation.org: s/get_resource/alloc_resource/] Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Reviewed-by: Toshi Kani <toshi.kani@hp.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Ram Pai <linuxram@us.ibm.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-30 06:08:56 +08:00
free_resource(res);
break;
}
next_res->name = name;
next_res->start = conflict->end + 1;
next_res->end = end;
next_res->flags = type | IORESOURCE_BUSY;
resource: Add I/O resource descriptor walk_iomem_res() and region_intersects() still need to use strcmp() for searching a resource entry by @name in the iomem table. This patch introduces I/O resource descriptor 'desc' in struct resource for the iomem search interfaces. Drivers can assign their unique descriptor to a range when they support the search interfaces. Otherwise, 'desc' is set to IORES_DESC_NONE (0). This avoids changing most of the drivers as they typically allocate resource entries statically, or by calling alloc_resource(), kzalloc(), or alloc_bootmem_low(), which set the field to zero by default. A later patch will address some drivers that use kmalloc() without zero'ing the field. Also change release_mem_region_adjustable() to set 'desc' when its resource entry gets separated. Other resource interfaces are also changed to initialize 'desc' explicitly although alloc_resource() sets it to 0. Signed-off-by: Toshi Kani <toshi.kani@hpe.com> Signed-off-by: Borislav Petkov <bp@suse.de> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jakub Sitnicki <jsitnicki@gmail.com> Cc: Jiang Liu <jiang.liu@linux.intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Luis R. Rodriguez <mcgrof@suse.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: linux-arch@vger.kernel.org Cc: linux-mm <linux-mm@kvack.org> Link: http://lkml.kernel.org/r/1453841853-11383-4-git-send-email-bp@alien8.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-01-27 04:57:19 +08:00
next_res->desc = IORES_DESC_NONE;
}
} else {
res->start = conflict->end + 1;
}
}
}
void __init
reserve_region_with_split(struct resource *root, resource_size_t start,
resource_size_t end, const char *name)
{
resource: make sure requested range is included in the root range When the requested range is outside of the root range the logic in __reserve_region_with_split will cause an infinite recursion which will overflow the stack as seen in the warning bellow. This particular stack overflow was caused by requesting the (100000000-107ffffff) range while the root range was (0-ffffffff). In this case __request_resource would return the whole root range as conflict range (i.e. 0-ffffffff). Then, the logic in __reserve_region_with_split would continue the recursion requesting the new range as (conflict->end+1, end) which incidentally in this case equals the originally requested range. This patch aborts looking for an usable range when the request does not intersect with the root range. When the request partially overlaps with the root range, it ajust the request to fall in the root range and then continues with the new request. When the request is modified or aborted errors and a stack trace are logged to allow catching the errors in the upper layers. [ 5.968374] WARNING: at kernel/sched.c:4129 sub_preempt_count+0x63/0x89() [ 5.975150] Modules linked in: [ 5.978184] Pid: 1, comm: swapper Not tainted 3.0.22-mid27-00004-gb72c817 #46 [ 5.985324] Call Trace: [ 5.987759] [<c1039dfc>] ? console_unlock+0x17b/0x18d [ 5.992891] [<c1039620>] warn_slowpath_common+0x48/0x5d [ 5.998194] [<c1031758>] ? sub_preempt_count+0x63/0x89 [ 6.003412] [<c1039644>] warn_slowpath_null+0xf/0x13 [ 6.008453] [<c1031758>] sub_preempt_count+0x63/0x89 [ 6.013499] [<c14d60c4>] _raw_spin_unlock+0x27/0x3f [ 6.018453] [<c10c6349>] add_partial+0x36/0x3b [ 6.022973] [<c10c7c0a>] deactivate_slab+0x96/0xb4 [ 6.027842] [<c14cf9d9>] __slab_alloc.isra.54.constprop.63+0x204/0x241 [ 6.034456] [<c103f78f>] ? kzalloc.constprop.5+0x29/0x38 [ 6.039842] [<c103f78f>] ? kzalloc.constprop.5+0x29/0x38 [ 6.045232] [<c10c7dc9>] kmem_cache_alloc_trace+0x51/0xb0 [ 6.050710] [<c103f78f>] ? kzalloc.constprop.5+0x29/0x38 [ 6.056100] [<c103f78f>] kzalloc.constprop.5+0x29/0x38 [ 6.061320] [<c17b45e9>] __reserve_region_with_split+0x1c/0xd1 [ 6.067230] [<c17b4693>] __reserve_region_with_split+0xc6/0xd1 ... [ 7.179057] [<c17b4693>] __reserve_region_with_split+0xc6/0xd1 [ 7.184970] [<c17b4779>] reserve_region_with_split+0x30/0x42 [ 7.190709] [<c17a8ebf>] e820_reserve_resources_late+0xd1/0xe9 [ 7.196623] [<c17c9526>] pcibios_resource_survey+0x23/0x2a [ 7.202184] [<c17cad8a>] pcibios_init+0x23/0x35 [ 7.206789] [<c17ca574>] pci_subsys_init+0x3f/0x44 [ 7.211659] [<c1002088>] do_one_initcall+0x72/0x122 [ 7.216615] [<c17ca535>] ? pci_legacy_init+0x3d/0x3d [ 7.221659] [<c17a27ff>] kernel_init+0xa6/0x118 [ 7.226265] [<c17a2759>] ? start_kernel+0x334/0x334 [ 7.231223] [<c14d7482>] kernel_thread_helper+0x6/0x10 Signed-off-by: Octavian Purdila <octavian.purdila@intel.com> Signed-off-by: Ram Pai <linuxram@us.ibm.com> Cc: Jesse Barnes <jbarnes@virtuousgeek.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-07-31 05:42:58 +08:00
int abort = 0;
write_lock(&resource_lock);
resource: make sure requested range is included in the root range When the requested range is outside of the root range the logic in __reserve_region_with_split will cause an infinite recursion which will overflow the stack as seen in the warning bellow. This particular stack overflow was caused by requesting the (100000000-107ffffff) range while the root range was (0-ffffffff). In this case __request_resource would return the whole root range as conflict range (i.e. 0-ffffffff). Then, the logic in __reserve_region_with_split would continue the recursion requesting the new range as (conflict->end+1, end) which incidentally in this case equals the originally requested range. This patch aborts looking for an usable range when the request does not intersect with the root range. When the request partially overlaps with the root range, it ajust the request to fall in the root range and then continues with the new request. When the request is modified or aborted errors and a stack trace are logged to allow catching the errors in the upper layers. [ 5.968374] WARNING: at kernel/sched.c:4129 sub_preempt_count+0x63/0x89() [ 5.975150] Modules linked in: [ 5.978184] Pid: 1, comm: swapper Not tainted 3.0.22-mid27-00004-gb72c817 #46 [ 5.985324] Call Trace: [ 5.987759] [<c1039dfc>] ? console_unlock+0x17b/0x18d [ 5.992891] [<c1039620>] warn_slowpath_common+0x48/0x5d [ 5.998194] [<c1031758>] ? sub_preempt_count+0x63/0x89 [ 6.003412] [<c1039644>] warn_slowpath_null+0xf/0x13 [ 6.008453] [<c1031758>] sub_preempt_count+0x63/0x89 [ 6.013499] [<c14d60c4>] _raw_spin_unlock+0x27/0x3f [ 6.018453] [<c10c6349>] add_partial+0x36/0x3b [ 6.022973] [<c10c7c0a>] deactivate_slab+0x96/0xb4 [ 6.027842] [<c14cf9d9>] __slab_alloc.isra.54.constprop.63+0x204/0x241 [ 6.034456] [<c103f78f>] ? kzalloc.constprop.5+0x29/0x38 [ 6.039842] [<c103f78f>] ? kzalloc.constprop.5+0x29/0x38 [ 6.045232] [<c10c7dc9>] kmem_cache_alloc_trace+0x51/0xb0 [ 6.050710] [<c103f78f>] ? kzalloc.constprop.5+0x29/0x38 [ 6.056100] [<c103f78f>] kzalloc.constprop.5+0x29/0x38 [ 6.061320] [<c17b45e9>] __reserve_region_with_split+0x1c/0xd1 [ 6.067230] [<c17b4693>] __reserve_region_with_split+0xc6/0xd1 ... [ 7.179057] [<c17b4693>] __reserve_region_with_split+0xc6/0xd1 [ 7.184970] [<c17b4779>] reserve_region_with_split+0x30/0x42 [ 7.190709] [<c17a8ebf>] e820_reserve_resources_late+0xd1/0xe9 [ 7.196623] [<c17c9526>] pcibios_resource_survey+0x23/0x2a [ 7.202184] [<c17cad8a>] pcibios_init+0x23/0x35 [ 7.206789] [<c17ca574>] pci_subsys_init+0x3f/0x44 [ 7.211659] [<c1002088>] do_one_initcall+0x72/0x122 [ 7.216615] [<c17ca535>] ? pci_legacy_init+0x3d/0x3d [ 7.221659] [<c17a27ff>] kernel_init+0xa6/0x118 [ 7.226265] [<c17a2759>] ? start_kernel+0x334/0x334 [ 7.231223] [<c14d7482>] kernel_thread_helper+0x6/0x10 Signed-off-by: Octavian Purdila <octavian.purdila@intel.com> Signed-off-by: Ram Pai <linuxram@us.ibm.com> Cc: Jesse Barnes <jbarnes@virtuousgeek.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-07-31 05:42:58 +08:00
if (root->start > start || root->end < end) {
pr_err("requested range [0x%llx-0x%llx] not in root %pr\n",
(unsigned long long)start, (unsigned long long)end,
root);
if (start > root->end || end < root->start)
abort = 1;
else {
if (end > root->end)
end = root->end;
if (start < root->start)
start = root->start;
pr_err("fixing request to [0x%llx-0x%llx]\n",
(unsigned long long)start,
(unsigned long long)end);
}
dump_stack();
}
if (!abort)
__reserve_region_with_split(root, start, end, name);
write_unlock(&resource_lock);
}
PCI: clean up resource alignment management Done per Linus' request and suggestions. Linus has explained that better than I'll be able to explain: On Thu, Mar 27, 2008 at 10:12:10AM -0700, Linus Torvalds wrote: > Actually, before we go any further, there might be a less intrusive > alternative: add just a couple of flags to the resource flags field (we > still have something like 8 unused bits on 32-bit), and use those to > implement a generic "resource_alignment()" routine. > > Two flags would do it: > > - IORESOURCE_SIZEALIGN: size indicates alignment (regular PCI device > resources) > > - IORESOURCE_STARTALIGN: start field is alignment (PCI bus resources > during probing) > > and then the case of both flags zero (or both bits set) would actually be > "invalid", and we would also clear the IORESOURCE_STARTALIGN flag when we > actually allocate the resource (so that we don't use the "start" field as > alignment incorrectly when it no longer indicates alignment). > > That wouldn't be totally generic, but it would have the nice property of > automatically at least add sanity checking for that whole "res->start has > the odd meaning of 'alignment' during probing" and remove the need for a > new field, and it would allow us to have a generic "resource_alignment()" > routine that just gets a resource pointer. Besides, I removed IORESOURCE_BUS_HAS_VGA flag which was unused for ages. Signed-off-by: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Gary Hade <garyhade@us.ibm.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-03-30 23:50:14 +08:00
/**
* resource_alignment - calculate resource's alignment
* @res: resource pointer
*
* Returns alignment on success, 0 (invalid alignment) on failure.
*/
resource_size_t resource_alignment(struct resource *res)
{
switch (res->flags & (IORESOURCE_SIZEALIGN | IORESOURCE_STARTALIGN)) {
case IORESOURCE_SIZEALIGN:
return resource_size(res);
PCI: clean up resource alignment management Done per Linus' request and suggestions. Linus has explained that better than I'll be able to explain: On Thu, Mar 27, 2008 at 10:12:10AM -0700, Linus Torvalds wrote: > Actually, before we go any further, there might be a less intrusive > alternative: add just a couple of flags to the resource flags field (we > still have something like 8 unused bits on 32-bit), and use those to > implement a generic "resource_alignment()" routine. > > Two flags would do it: > > - IORESOURCE_SIZEALIGN: size indicates alignment (regular PCI device > resources) > > - IORESOURCE_STARTALIGN: start field is alignment (PCI bus resources > during probing) > > and then the case of both flags zero (or both bits set) would actually be > "invalid", and we would also clear the IORESOURCE_STARTALIGN flag when we > actually allocate the resource (so that we don't use the "start" field as > alignment incorrectly when it no longer indicates alignment). > > That wouldn't be totally generic, but it would have the nice property of > automatically at least add sanity checking for that whole "res->start has > the odd meaning of 'alignment' during probing" and remove the need for a > new field, and it would allow us to have a generic "resource_alignment()" > routine that just gets a resource pointer. Besides, I removed IORESOURCE_BUS_HAS_VGA flag which was unused for ages. Signed-off-by: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Gary Hade <garyhade@us.ibm.com> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-03-30 23:50:14 +08:00
case IORESOURCE_STARTALIGN:
return res->start;
default:
return 0;
}
}
/*
* This is compatibility stuff for IO resources.
*
* Note how this, unlike the above, knows about
* the IO flag meanings (busy etc).
*
* request_region creates a new busy region.
*
* release_region releases a matching busy region.
*/
static DECLARE_WAIT_QUEUE_HEAD(muxed_resource_wait);
/**
* __request_region - create a new busy resource region
* @parent: parent resource descriptor
* @start: resource start address
* @n: resource region size
* @name: reserving caller's ID string
* @flags: IO resource flags
*/
struct resource * __request_region(struct resource *parent,
resource_size_t start, resource_size_t n,
const char *name, int flags)
{
DECLARE_WAITQUEUE(wait, current);
mem hotunplug: fix kfree() of bootmem memory When hot removing memory presented at boot time, following messages are shown: kernel BUG at mm/slub.c:3409! invalid opcode: 0000 [#1] SMP Modules linked in: ebtable_nat ebtables xt_CHECKSUM iptable_mangle bridge stp llc ipmi_devintf ipmi_msghandler sunrpc ipt_REJECT nf_conntrack_ipv4 nf_defrag_ipv4 iptable_filter ip_tables ip6t_REJECT nf_conntrack_ipv6 nf_defrag_ipv6 xt_state nf_conntrack ip6table_filter ip6_tables binfmt_misc vfat fat dm_mirror dm_region_hash dm_log dm_mod vhost_net macvtap macvlan tun uinput iTCO_wdt iTCO_vendor_support coretemp kvm_intel kvm crc32c_intel ghash_clmulni_intel microcode pcspkr sg i2c_i801 lpc_ich mfd_core igb i2c_algo_bit i2c_core e1000e ptp pps_core tpm_infineon ioatdma dca sr_mod cdrom sd_mod crc_t10dif usb_storage megaraid_sas lpfc scsi_transport_fc scsi_tgt scsi_mod CPU 0 Pid: 5091, comm: kworker/0:2 Tainted: G W 3.9.0-rc6+ #15 RIP: kfree+0x232/0x240 Process kworker/0:2 (pid: 5091, threadinfo ffff88084678c000, task ffff88083928ca80) Call Trace: __release_region+0xd4/0xe0 __remove_pages+0x52/0x110 arch_remove_memory+0x89/0xd0 remove_memory+0xc4/0x100 acpi_memory_device_remove+0x6d/0xb1 acpi_device_remove+0x89/0xab __device_release_driver+0x7c/0xf0 device_release_driver+0x2f/0x50 acpi_bus_device_detach+0x6c/0x70 acpi_ns_walk_namespace+0x11a/0x250 acpi_walk_namespace+0xee/0x137 acpi_bus_trim+0x33/0x7a acpi_bus_hot_remove_device+0xc4/0x1a1 acpi_os_execute_deferred+0x27/0x34 process_one_work+0x1f7/0x590 worker_thread+0x11a/0x370 kthread+0xee/0x100 ret_from_fork+0x7c/0xb0 RIP [<ffffffff811c41d2>] kfree+0x232/0x240 RSP <ffff88084678d968> The reason why the messages are shown is to release a resource structure, allocated by bootmem, by kfree(). So when we release a resource structure, we should check whether it is allocated by bootmem or not. But even if we know a resource structure is allocated by bootmem, we cannot release it since SLxB cannot treat it. So for reusing a resource structure, this patch remembers it by using bootmem_resource as follows: When releasing a resource structure by free_resource(), free_resource() checks whether the resource structure is allocated by bootmem or not. If it is allocated by bootmem, free_resource() adds it to bootmem_resource. If it is not allocated by bootmem, free_resource() release it by kfree(). And when getting a new resource structure by get_resource(), get_resource() checks whether bootmem_resource has released resource structures or not. If there is a released resource structure, get_resource() returns it. If there is not a releaed resource structure, get_resource() returns new resource structure allocated by kzalloc(). [akpm@linux-foundation.org: s/get_resource/alloc_resource/] Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Reviewed-by: Toshi Kani <toshi.kani@hp.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Ram Pai <linuxram@us.ibm.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-30 06:08:56 +08:00
struct resource *res = alloc_resource(GFP_KERNEL);
if (!res)
return NULL;
res->name = name;
res->start = start;
res->end = start + n - 1;
write_lock(&resource_lock);
for (;;) {
struct resource *conflict;
res->flags = resource_type(parent) | resource_ext_type(parent);
res->flags |= IORESOURCE_BUSY | flags;
res->desc = parent->desc;
conflict = __request_resource(parent, res);
if (!conflict)
break;
mm/resource: Move HMM pr_debug() deeper into resource code HMM consumes physical address space for its own use, even though nothing is mapped or accessible there. It uses a special resource description (IORES_DESC_DEVICE_PRIVATE_MEMORY) to uniquely identify these areas. When HMM consumes address space, it makes a best guess about what to consume. However, it is possible that a future memory or device hotplug can collide with the reserved area. In the case of these conflicts, there is an error message in register_memory_resource(). Later patches in this series move register_memory_resource() from using request_resource_conflict() to __request_region(). Unfortunately, __request_region() does not return the conflict like the previous function did, which makes it impossible to check for IORES_DESC_DEVICE_PRIVATE_MEMORY in a conflicting resource. Instead of warning in register_memory_resource(), move the check into the core resource code itself (__request_region()) where the conflicting resource _is_ available. This has the added bonus of producing a warning in case of HMM conflicts with devices *or* RAM address space, as opposed to the RAM- only warnings that were there previously. Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Reviewed-by: Jerome Glisse <jglisse@redhat.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Ross Zwisler <zwisler@kernel.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Michal Hocko <mhocko@suse.com> Cc: linux-nvdimm@lists.01.org Cc: linux-kernel@vger.kernel.org Cc: linux-mm@kvack.org Cc: Huang Ying <ying.huang@intel.com> Cc: Fengguang Wu <fengguang.wu@intel.com> Cc: Keith Busch <keith.busch@intel.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2019-02-26 02:57:33 +08:00
/*
* mm/hmm.c reserves physical addresses which then
* become unavailable to other users. Conflicts are
* not expected. Warn to aid debugging if encountered.
*/
if (conflict->desc == IORES_DESC_DEVICE_PRIVATE_MEMORY) {
pr_warn("Unaddressable device %s %pR conflicts with %pR",
conflict->name, conflict, res);
}
if (conflict != parent) {
if (!(conflict->flags & IORESOURCE_BUSY)) {
parent = conflict;
continue;
}
}
if (conflict->flags & flags & IORESOURCE_MUXED) {
add_wait_queue(&muxed_resource_wait, &wait);
write_unlock(&resource_lock);
set_current_state(TASK_UNINTERRUPTIBLE);
schedule();
remove_wait_queue(&muxed_resource_wait, &wait);
write_lock(&resource_lock);
continue;
}
/* Uhhuh, that didn't work out.. */
mem hotunplug: fix kfree() of bootmem memory When hot removing memory presented at boot time, following messages are shown: kernel BUG at mm/slub.c:3409! invalid opcode: 0000 [#1] SMP Modules linked in: ebtable_nat ebtables xt_CHECKSUM iptable_mangle bridge stp llc ipmi_devintf ipmi_msghandler sunrpc ipt_REJECT nf_conntrack_ipv4 nf_defrag_ipv4 iptable_filter ip_tables ip6t_REJECT nf_conntrack_ipv6 nf_defrag_ipv6 xt_state nf_conntrack ip6table_filter ip6_tables binfmt_misc vfat fat dm_mirror dm_region_hash dm_log dm_mod vhost_net macvtap macvlan tun uinput iTCO_wdt iTCO_vendor_support coretemp kvm_intel kvm crc32c_intel ghash_clmulni_intel microcode pcspkr sg i2c_i801 lpc_ich mfd_core igb i2c_algo_bit i2c_core e1000e ptp pps_core tpm_infineon ioatdma dca sr_mod cdrom sd_mod crc_t10dif usb_storage megaraid_sas lpfc scsi_transport_fc scsi_tgt scsi_mod CPU 0 Pid: 5091, comm: kworker/0:2 Tainted: G W 3.9.0-rc6+ #15 RIP: kfree+0x232/0x240 Process kworker/0:2 (pid: 5091, threadinfo ffff88084678c000, task ffff88083928ca80) Call Trace: __release_region+0xd4/0xe0 __remove_pages+0x52/0x110 arch_remove_memory+0x89/0xd0 remove_memory+0xc4/0x100 acpi_memory_device_remove+0x6d/0xb1 acpi_device_remove+0x89/0xab __device_release_driver+0x7c/0xf0 device_release_driver+0x2f/0x50 acpi_bus_device_detach+0x6c/0x70 acpi_ns_walk_namespace+0x11a/0x250 acpi_walk_namespace+0xee/0x137 acpi_bus_trim+0x33/0x7a acpi_bus_hot_remove_device+0xc4/0x1a1 acpi_os_execute_deferred+0x27/0x34 process_one_work+0x1f7/0x590 worker_thread+0x11a/0x370 kthread+0xee/0x100 ret_from_fork+0x7c/0xb0 RIP [<ffffffff811c41d2>] kfree+0x232/0x240 RSP <ffff88084678d968> The reason why the messages are shown is to release a resource structure, allocated by bootmem, by kfree(). So when we release a resource structure, we should check whether it is allocated by bootmem or not. But even if we know a resource structure is allocated by bootmem, we cannot release it since SLxB cannot treat it. So for reusing a resource structure, this patch remembers it by using bootmem_resource as follows: When releasing a resource structure by free_resource(), free_resource() checks whether the resource structure is allocated by bootmem or not. If it is allocated by bootmem, free_resource() adds it to bootmem_resource. If it is not allocated by bootmem, free_resource() release it by kfree(). And when getting a new resource structure by get_resource(), get_resource() checks whether bootmem_resource has released resource structures or not. If there is a released resource structure, get_resource() returns it. If there is not a releaed resource structure, get_resource() returns new resource structure allocated by kzalloc(). [akpm@linux-foundation.org: s/get_resource/alloc_resource/] Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Reviewed-by: Toshi Kani <toshi.kani@hp.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Ram Pai <linuxram@us.ibm.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-30 06:08:56 +08:00
free_resource(res);
res = NULL;
break;
}
write_unlock(&resource_lock);
return res;
}
EXPORT_SYMBOL(__request_region);
/**
* __release_region - release a previously reserved resource region
* @parent: parent resource descriptor
* @start: resource start address
* @n: resource region size
*
* The described resource region must match a currently busy region.
*/
void __release_region(struct resource *parent, resource_size_t start,
resource_size_t n)
{
struct resource **p;
resource_size_t end;
p = &parent->child;
end = start + n - 1;
write_lock(&resource_lock);
for (;;) {
struct resource *res = *p;
if (!res)
break;
if (res->start <= start && res->end >= end) {
if (!(res->flags & IORESOURCE_BUSY)) {
p = &res->child;
continue;
}
if (res->start != start || res->end != end)
break;
*p = res->sibling;
write_unlock(&resource_lock);
if (res->flags & IORESOURCE_MUXED)
wake_up(&muxed_resource_wait);
mem hotunplug: fix kfree() of bootmem memory When hot removing memory presented at boot time, following messages are shown: kernel BUG at mm/slub.c:3409! invalid opcode: 0000 [#1] SMP Modules linked in: ebtable_nat ebtables xt_CHECKSUM iptable_mangle bridge stp llc ipmi_devintf ipmi_msghandler sunrpc ipt_REJECT nf_conntrack_ipv4 nf_defrag_ipv4 iptable_filter ip_tables ip6t_REJECT nf_conntrack_ipv6 nf_defrag_ipv6 xt_state nf_conntrack ip6table_filter ip6_tables binfmt_misc vfat fat dm_mirror dm_region_hash dm_log dm_mod vhost_net macvtap macvlan tun uinput iTCO_wdt iTCO_vendor_support coretemp kvm_intel kvm crc32c_intel ghash_clmulni_intel microcode pcspkr sg i2c_i801 lpc_ich mfd_core igb i2c_algo_bit i2c_core e1000e ptp pps_core tpm_infineon ioatdma dca sr_mod cdrom sd_mod crc_t10dif usb_storage megaraid_sas lpfc scsi_transport_fc scsi_tgt scsi_mod CPU 0 Pid: 5091, comm: kworker/0:2 Tainted: G W 3.9.0-rc6+ #15 RIP: kfree+0x232/0x240 Process kworker/0:2 (pid: 5091, threadinfo ffff88084678c000, task ffff88083928ca80) Call Trace: __release_region+0xd4/0xe0 __remove_pages+0x52/0x110 arch_remove_memory+0x89/0xd0 remove_memory+0xc4/0x100 acpi_memory_device_remove+0x6d/0xb1 acpi_device_remove+0x89/0xab __device_release_driver+0x7c/0xf0 device_release_driver+0x2f/0x50 acpi_bus_device_detach+0x6c/0x70 acpi_ns_walk_namespace+0x11a/0x250 acpi_walk_namespace+0xee/0x137 acpi_bus_trim+0x33/0x7a acpi_bus_hot_remove_device+0xc4/0x1a1 acpi_os_execute_deferred+0x27/0x34 process_one_work+0x1f7/0x590 worker_thread+0x11a/0x370 kthread+0xee/0x100 ret_from_fork+0x7c/0xb0 RIP [<ffffffff811c41d2>] kfree+0x232/0x240 RSP <ffff88084678d968> The reason why the messages are shown is to release a resource structure, allocated by bootmem, by kfree(). So when we release a resource structure, we should check whether it is allocated by bootmem or not. But even if we know a resource structure is allocated by bootmem, we cannot release it since SLxB cannot treat it. So for reusing a resource structure, this patch remembers it by using bootmem_resource as follows: When releasing a resource structure by free_resource(), free_resource() checks whether the resource structure is allocated by bootmem or not. If it is allocated by bootmem, free_resource() adds it to bootmem_resource. If it is not allocated by bootmem, free_resource() release it by kfree(). And when getting a new resource structure by get_resource(), get_resource() checks whether bootmem_resource has released resource structures or not. If there is a released resource structure, get_resource() returns it. If there is not a releaed resource structure, get_resource() returns new resource structure allocated by kzalloc(). [akpm@linux-foundation.org: s/get_resource/alloc_resource/] Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Reviewed-by: Toshi Kani <toshi.kani@hp.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Ram Pai <linuxram@us.ibm.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-30 06:08:56 +08:00
free_resource(res);
return;
}
p = &res->sibling;
}
write_unlock(&resource_lock);
printk(KERN_WARNING "Trying to free nonexistent resource "
"<%016llx-%016llx>\n", (unsigned long long)start,
(unsigned long long)end);
}
EXPORT_SYMBOL(__release_region);
resource: add release_mem_region_adjustable() Add release_mem_region_adjustable(), which releases a requested region from a currently busy memory resource. This interface adjusts the matched memory resource accordingly even if the requested region does not match exactly but still fits into. This new interface is intended for memory hot-delete. During bootup, memory resources are inserted from the boot descriptor table, such as EFI Memory Table and e820. Each memory resource entry usually covers the whole contigous memory range. Memory hot-delete request, on the other hand, may target to a particular range of memory resource, and its size can be much smaller than the whole contiguous memory. Since the existing release interfaces like __release_region() require a requested region to be exactly matched to a resource entry, they do not allow a partial resource to be released. This new interface is restrictive (i.e. release under certain conditions), which is consistent with other release interfaces, __release_region() and __release_resource(). Additional release conditions, such as an overlapping region to a resource entry, can be supported after they are confirmed as valid cases. There is no change to the existing interfaces since their restriction is valid for I/O resources. [akpm@linux-foundation.org: use GFP_ATOMIC under write_lock()] [akpm@linux-foundation.org: switch back to GFP_KERNEL, less buggily] [akpm@linux-foundation.org: remove unneeded and wrong kfree(), per Toshi] Signed-off-by: Toshi Kani <toshi.kani@hp.com> Reviewed-by : Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: David Rientjes <rientjes@google.com> Reviewed-by: Ram Pai <linuxram@us.ibm.com> Cc: T Makphaibulchoke <tmac@hp.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Tang Chen <tangchen@cn.fujitsu.com> Cc: Jiang Liu <jiang.liu@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-30 06:08:19 +08:00
#ifdef CONFIG_MEMORY_HOTREMOVE
/**
* release_mem_region_adjustable - release a previously reserved memory region
* @parent: parent resource descriptor
* @start: resource start address
* @size: resource region size
*
* This interface is intended for memory hot-delete. The requested region
* is released from a currently busy memory resource. The requested region
* must either match exactly or fit into a single busy resource entry. In
* the latter case, the remaining resource is adjusted accordingly.
* Existing children of the busy memory resource must be immutable in the
* request.
*
* Note:
* - Additional release conditions, such as overlapping region, can be
* supported after they are confirmed as valid cases.
* - When a busy memory resource gets split into two entries, the code
* assumes that all children remain in the lower address entry for
* simplicity. Enhance this logic when necessary.
*/
int release_mem_region_adjustable(struct resource *parent,
resource_size_t start, resource_size_t size)
resource: add release_mem_region_adjustable() Add release_mem_region_adjustable(), which releases a requested region from a currently busy memory resource. This interface adjusts the matched memory resource accordingly even if the requested region does not match exactly but still fits into. This new interface is intended for memory hot-delete. During bootup, memory resources are inserted from the boot descriptor table, such as EFI Memory Table and e820. Each memory resource entry usually covers the whole contigous memory range. Memory hot-delete request, on the other hand, may target to a particular range of memory resource, and its size can be much smaller than the whole contiguous memory. Since the existing release interfaces like __release_region() require a requested region to be exactly matched to a resource entry, they do not allow a partial resource to be released. This new interface is restrictive (i.e. release under certain conditions), which is consistent with other release interfaces, __release_region() and __release_resource(). Additional release conditions, such as an overlapping region to a resource entry, can be supported after they are confirmed as valid cases. There is no change to the existing interfaces since their restriction is valid for I/O resources. [akpm@linux-foundation.org: use GFP_ATOMIC under write_lock()] [akpm@linux-foundation.org: switch back to GFP_KERNEL, less buggily] [akpm@linux-foundation.org: remove unneeded and wrong kfree(), per Toshi] Signed-off-by: Toshi Kani <toshi.kani@hp.com> Reviewed-by : Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: David Rientjes <rientjes@google.com> Reviewed-by: Ram Pai <linuxram@us.ibm.com> Cc: T Makphaibulchoke <tmac@hp.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Tang Chen <tangchen@cn.fujitsu.com> Cc: Jiang Liu <jiang.liu@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-30 06:08:19 +08:00
{
struct resource **p;
struct resource *res;
struct resource *new_res;
resource_size_t end;
int ret = -EINVAL;
end = start + size - 1;
if ((start < parent->start) || (end > parent->end))
return ret;
mem hotunplug: fix kfree() of bootmem memory When hot removing memory presented at boot time, following messages are shown: kernel BUG at mm/slub.c:3409! invalid opcode: 0000 [#1] SMP Modules linked in: ebtable_nat ebtables xt_CHECKSUM iptable_mangle bridge stp llc ipmi_devintf ipmi_msghandler sunrpc ipt_REJECT nf_conntrack_ipv4 nf_defrag_ipv4 iptable_filter ip_tables ip6t_REJECT nf_conntrack_ipv6 nf_defrag_ipv6 xt_state nf_conntrack ip6table_filter ip6_tables binfmt_misc vfat fat dm_mirror dm_region_hash dm_log dm_mod vhost_net macvtap macvlan tun uinput iTCO_wdt iTCO_vendor_support coretemp kvm_intel kvm crc32c_intel ghash_clmulni_intel microcode pcspkr sg i2c_i801 lpc_ich mfd_core igb i2c_algo_bit i2c_core e1000e ptp pps_core tpm_infineon ioatdma dca sr_mod cdrom sd_mod crc_t10dif usb_storage megaraid_sas lpfc scsi_transport_fc scsi_tgt scsi_mod CPU 0 Pid: 5091, comm: kworker/0:2 Tainted: G W 3.9.0-rc6+ #15 RIP: kfree+0x232/0x240 Process kworker/0:2 (pid: 5091, threadinfo ffff88084678c000, task ffff88083928ca80) Call Trace: __release_region+0xd4/0xe0 __remove_pages+0x52/0x110 arch_remove_memory+0x89/0xd0 remove_memory+0xc4/0x100 acpi_memory_device_remove+0x6d/0xb1 acpi_device_remove+0x89/0xab __device_release_driver+0x7c/0xf0 device_release_driver+0x2f/0x50 acpi_bus_device_detach+0x6c/0x70 acpi_ns_walk_namespace+0x11a/0x250 acpi_walk_namespace+0xee/0x137 acpi_bus_trim+0x33/0x7a acpi_bus_hot_remove_device+0xc4/0x1a1 acpi_os_execute_deferred+0x27/0x34 process_one_work+0x1f7/0x590 worker_thread+0x11a/0x370 kthread+0xee/0x100 ret_from_fork+0x7c/0xb0 RIP [<ffffffff811c41d2>] kfree+0x232/0x240 RSP <ffff88084678d968> The reason why the messages are shown is to release a resource structure, allocated by bootmem, by kfree(). So when we release a resource structure, we should check whether it is allocated by bootmem or not. But even if we know a resource structure is allocated by bootmem, we cannot release it since SLxB cannot treat it. So for reusing a resource structure, this patch remembers it by using bootmem_resource as follows: When releasing a resource structure by free_resource(), free_resource() checks whether the resource structure is allocated by bootmem or not. If it is allocated by bootmem, free_resource() adds it to bootmem_resource. If it is not allocated by bootmem, free_resource() release it by kfree(). And when getting a new resource structure by get_resource(), get_resource() checks whether bootmem_resource has released resource structures or not. If there is a released resource structure, get_resource() returns it. If there is not a releaed resource structure, get_resource() returns new resource structure allocated by kzalloc(). [akpm@linux-foundation.org: s/get_resource/alloc_resource/] Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Reviewed-by: Toshi Kani <toshi.kani@hp.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Ram Pai <linuxram@us.ibm.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-30 06:08:56 +08:00
/* The alloc_resource() result gets checked later */
new_res = alloc_resource(GFP_KERNEL);
resource: add release_mem_region_adjustable() Add release_mem_region_adjustable(), which releases a requested region from a currently busy memory resource. This interface adjusts the matched memory resource accordingly even if the requested region does not match exactly but still fits into. This new interface is intended for memory hot-delete. During bootup, memory resources are inserted from the boot descriptor table, such as EFI Memory Table and e820. Each memory resource entry usually covers the whole contigous memory range. Memory hot-delete request, on the other hand, may target to a particular range of memory resource, and its size can be much smaller than the whole contiguous memory. Since the existing release interfaces like __release_region() require a requested region to be exactly matched to a resource entry, they do not allow a partial resource to be released. This new interface is restrictive (i.e. release under certain conditions), which is consistent with other release interfaces, __release_region() and __release_resource(). Additional release conditions, such as an overlapping region to a resource entry, can be supported after they are confirmed as valid cases. There is no change to the existing interfaces since their restriction is valid for I/O resources. [akpm@linux-foundation.org: use GFP_ATOMIC under write_lock()] [akpm@linux-foundation.org: switch back to GFP_KERNEL, less buggily] [akpm@linux-foundation.org: remove unneeded and wrong kfree(), per Toshi] Signed-off-by: Toshi Kani <toshi.kani@hp.com> Reviewed-by : Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: David Rientjes <rientjes@google.com> Reviewed-by: Ram Pai <linuxram@us.ibm.com> Cc: T Makphaibulchoke <tmac@hp.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Tang Chen <tangchen@cn.fujitsu.com> Cc: Jiang Liu <jiang.liu@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-30 06:08:19 +08:00
p = &parent->child;
write_lock(&resource_lock);
while ((res = *p)) {
if (res->start >= end)
break;
/* look for the next resource if it does not fit into */
if (res->start > start || res->end < end) {
p = &res->sibling;
continue;
}
kernel, resource: check for IORESOURCE_SYSRAM in release_mem_region_adjustable This is a preparation for the next patch. Currently, we only call release_mem_region_adjustable() in __remove_pages if the zone is not ZONE_DEVICE, because resources that belong to HMM/devm are being released by themselves with devm_release_mem_region. Since we do not want to touch any zone/page stuff during the removing of the memory (but during the offlining), we do not want to check for the zone here. So we need another way to tell release_mem_region_adjustable() to not realease the resource in case it belongs to HMM/devm. HMM/devm acquires/releases a resource through devm_request_mem_region/devm_release_mem_region. These resources have the flag IORESOURCE_MEM, while resources acquired by hot-add memory path (register_memory_resource()) contain IORESOURCE_SYSTEM_RAM. So, we can check for this flag in release_mem_region_adjustable, and if the resource does not contain such flag, we know that we are dealing with a HMM/devm resource, so we can back off. Link: http://lkml.kernel.org/r/20181127162005.15833-3-osalvador@suse.de Signed-off-by: Oscar Salvador <osalvador@suse.de> Reviewed-by: David Hildenbrand <david@redhat.com> Reviewed-by: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Oscar Salvador <osalvador@suse.com> Cc: "Rafael J. Wysocki" <rafael@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-12-28 16:36:26 +08:00
/*
* All memory regions added from memory-hotplug path have the
* flag IORESOURCE_SYSTEM_RAM. If the resource does not have
* this flag, we know that we are dealing with a resource coming
* from HMM/devm. HMM/devm use another mechanism to add/release
* a resource. This goes via devm_request_mem_region and
* devm_release_mem_region.
* HMM/devm take care to release their resources when they want,
* so if we are dealing with them, let us just back off here.
*/
if (!(res->flags & IORESOURCE_SYSRAM)) {
ret = 0;
break;
}
resource: add release_mem_region_adjustable() Add release_mem_region_adjustable(), which releases a requested region from a currently busy memory resource. This interface adjusts the matched memory resource accordingly even if the requested region does not match exactly but still fits into. This new interface is intended for memory hot-delete. During bootup, memory resources are inserted from the boot descriptor table, such as EFI Memory Table and e820. Each memory resource entry usually covers the whole contigous memory range. Memory hot-delete request, on the other hand, may target to a particular range of memory resource, and its size can be much smaller than the whole contiguous memory. Since the existing release interfaces like __release_region() require a requested region to be exactly matched to a resource entry, they do not allow a partial resource to be released. This new interface is restrictive (i.e. release under certain conditions), which is consistent with other release interfaces, __release_region() and __release_resource(). Additional release conditions, such as an overlapping region to a resource entry, can be supported after they are confirmed as valid cases. There is no change to the existing interfaces since their restriction is valid for I/O resources. [akpm@linux-foundation.org: use GFP_ATOMIC under write_lock()] [akpm@linux-foundation.org: switch back to GFP_KERNEL, less buggily] [akpm@linux-foundation.org: remove unneeded and wrong kfree(), per Toshi] Signed-off-by: Toshi Kani <toshi.kani@hp.com> Reviewed-by : Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: David Rientjes <rientjes@google.com> Reviewed-by: Ram Pai <linuxram@us.ibm.com> Cc: T Makphaibulchoke <tmac@hp.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Tang Chen <tangchen@cn.fujitsu.com> Cc: Jiang Liu <jiang.liu@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-30 06:08:19 +08:00
if (!(res->flags & IORESOURCE_MEM))
break;
if (!(res->flags & IORESOURCE_BUSY)) {
p = &res->child;
continue;
}
/* found the target resource; let's adjust accordingly */
if (res->start == start && res->end == end) {
/* free the whole entry */
*p = res->sibling;
mem hotunplug: fix kfree() of bootmem memory When hot removing memory presented at boot time, following messages are shown: kernel BUG at mm/slub.c:3409! invalid opcode: 0000 [#1] SMP Modules linked in: ebtable_nat ebtables xt_CHECKSUM iptable_mangle bridge stp llc ipmi_devintf ipmi_msghandler sunrpc ipt_REJECT nf_conntrack_ipv4 nf_defrag_ipv4 iptable_filter ip_tables ip6t_REJECT nf_conntrack_ipv6 nf_defrag_ipv6 xt_state nf_conntrack ip6table_filter ip6_tables binfmt_misc vfat fat dm_mirror dm_region_hash dm_log dm_mod vhost_net macvtap macvlan tun uinput iTCO_wdt iTCO_vendor_support coretemp kvm_intel kvm crc32c_intel ghash_clmulni_intel microcode pcspkr sg i2c_i801 lpc_ich mfd_core igb i2c_algo_bit i2c_core e1000e ptp pps_core tpm_infineon ioatdma dca sr_mod cdrom sd_mod crc_t10dif usb_storage megaraid_sas lpfc scsi_transport_fc scsi_tgt scsi_mod CPU 0 Pid: 5091, comm: kworker/0:2 Tainted: G W 3.9.0-rc6+ #15 RIP: kfree+0x232/0x240 Process kworker/0:2 (pid: 5091, threadinfo ffff88084678c000, task ffff88083928ca80) Call Trace: __release_region+0xd4/0xe0 __remove_pages+0x52/0x110 arch_remove_memory+0x89/0xd0 remove_memory+0xc4/0x100 acpi_memory_device_remove+0x6d/0xb1 acpi_device_remove+0x89/0xab __device_release_driver+0x7c/0xf0 device_release_driver+0x2f/0x50 acpi_bus_device_detach+0x6c/0x70 acpi_ns_walk_namespace+0x11a/0x250 acpi_walk_namespace+0xee/0x137 acpi_bus_trim+0x33/0x7a acpi_bus_hot_remove_device+0xc4/0x1a1 acpi_os_execute_deferred+0x27/0x34 process_one_work+0x1f7/0x590 worker_thread+0x11a/0x370 kthread+0xee/0x100 ret_from_fork+0x7c/0xb0 RIP [<ffffffff811c41d2>] kfree+0x232/0x240 RSP <ffff88084678d968> The reason why the messages are shown is to release a resource structure, allocated by bootmem, by kfree(). So when we release a resource structure, we should check whether it is allocated by bootmem or not. But even if we know a resource structure is allocated by bootmem, we cannot release it since SLxB cannot treat it. So for reusing a resource structure, this patch remembers it by using bootmem_resource as follows: When releasing a resource structure by free_resource(), free_resource() checks whether the resource structure is allocated by bootmem or not. If it is allocated by bootmem, free_resource() adds it to bootmem_resource. If it is not allocated by bootmem, free_resource() release it by kfree(). And when getting a new resource structure by get_resource(), get_resource() checks whether bootmem_resource has released resource structures or not. If there is a released resource structure, get_resource() returns it. If there is not a releaed resource structure, get_resource() returns new resource structure allocated by kzalloc(). [akpm@linux-foundation.org: s/get_resource/alloc_resource/] Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Reviewed-by: Toshi Kani <toshi.kani@hp.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Ram Pai <linuxram@us.ibm.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-30 06:08:56 +08:00
free_resource(res);
resource: add release_mem_region_adjustable() Add release_mem_region_adjustable(), which releases a requested region from a currently busy memory resource. This interface adjusts the matched memory resource accordingly even if the requested region does not match exactly but still fits into. This new interface is intended for memory hot-delete. During bootup, memory resources are inserted from the boot descriptor table, such as EFI Memory Table and e820. Each memory resource entry usually covers the whole contigous memory range. Memory hot-delete request, on the other hand, may target to a particular range of memory resource, and its size can be much smaller than the whole contiguous memory. Since the existing release interfaces like __release_region() require a requested region to be exactly matched to a resource entry, they do not allow a partial resource to be released. This new interface is restrictive (i.e. release under certain conditions), which is consistent with other release interfaces, __release_region() and __release_resource(). Additional release conditions, such as an overlapping region to a resource entry, can be supported after they are confirmed as valid cases. There is no change to the existing interfaces since their restriction is valid for I/O resources. [akpm@linux-foundation.org: use GFP_ATOMIC under write_lock()] [akpm@linux-foundation.org: switch back to GFP_KERNEL, less buggily] [akpm@linux-foundation.org: remove unneeded and wrong kfree(), per Toshi] Signed-off-by: Toshi Kani <toshi.kani@hp.com> Reviewed-by : Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: David Rientjes <rientjes@google.com> Reviewed-by: Ram Pai <linuxram@us.ibm.com> Cc: T Makphaibulchoke <tmac@hp.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Tang Chen <tangchen@cn.fujitsu.com> Cc: Jiang Liu <jiang.liu@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-30 06:08:19 +08:00
ret = 0;
} else if (res->start == start && res->end != end) {
/* adjust the start */
ret = __adjust_resource(res, end + 1,
res->end - end);
} else if (res->start != start && res->end == end) {
/* adjust the end */
ret = __adjust_resource(res, res->start,
start - res->start);
} else {
/* split into two entries */
if (!new_res) {
ret = -ENOMEM;
break;
}
new_res->name = res->name;
new_res->start = end + 1;
new_res->end = res->end;
new_res->flags = res->flags;
resource: Add I/O resource descriptor walk_iomem_res() and region_intersects() still need to use strcmp() for searching a resource entry by @name in the iomem table. This patch introduces I/O resource descriptor 'desc' in struct resource for the iomem search interfaces. Drivers can assign their unique descriptor to a range when they support the search interfaces. Otherwise, 'desc' is set to IORES_DESC_NONE (0). This avoids changing most of the drivers as they typically allocate resource entries statically, or by calling alloc_resource(), kzalloc(), or alloc_bootmem_low(), which set the field to zero by default. A later patch will address some drivers that use kmalloc() without zero'ing the field. Also change release_mem_region_adjustable() to set 'desc' when its resource entry gets separated. Other resource interfaces are also changed to initialize 'desc' explicitly although alloc_resource() sets it to 0. Signed-off-by: Toshi Kani <toshi.kani@hpe.com> Signed-off-by: Borislav Petkov <bp@suse.de> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jakub Sitnicki <jsitnicki@gmail.com> Cc: Jiang Liu <jiang.liu@linux.intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Luis R. Rodriguez <mcgrof@suse.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: linux-arch@vger.kernel.org Cc: linux-mm <linux-mm@kvack.org> Link: http://lkml.kernel.org/r/1453841853-11383-4-git-send-email-bp@alien8.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-01-27 04:57:19 +08:00
new_res->desc = res->desc;
resource: add release_mem_region_adjustable() Add release_mem_region_adjustable(), which releases a requested region from a currently busy memory resource. This interface adjusts the matched memory resource accordingly even if the requested region does not match exactly but still fits into. This new interface is intended for memory hot-delete. During bootup, memory resources are inserted from the boot descriptor table, such as EFI Memory Table and e820. Each memory resource entry usually covers the whole contigous memory range. Memory hot-delete request, on the other hand, may target to a particular range of memory resource, and its size can be much smaller than the whole contiguous memory. Since the existing release interfaces like __release_region() require a requested region to be exactly matched to a resource entry, they do not allow a partial resource to be released. This new interface is restrictive (i.e. release under certain conditions), which is consistent with other release interfaces, __release_region() and __release_resource(). Additional release conditions, such as an overlapping region to a resource entry, can be supported after they are confirmed as valid cases. There is no change to the existing interfaces since their restriction is valid for I/O resources. [akpm@linux-foundation.org: use GFP_ATOMIC under write_lock()] [akpm@linux-foundation.org: switch back to GFP_KERNEL, less buggily] [akpm@linux-foundation.org: remove unneeded and wrong kfree(), per Toshi] Signed-off-by: Toshi Kani <toshi.kani@hp.com> Reviewed-by : Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: David Rientjes <rientjes@google.com> Reviewed-by: Ram Pai <linuxram@us.ibm.com> Cc: T Makphaibulchoke <tmac@hp.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Tang Chen <tangchen@cn.fujitsu.com> Cc: Jiang Liu <jiang.liu@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-30 06:08:19 +08:00
new_res->parent = res->parent;
new_res->sibling = res->sibling;
new_res->child = NULL;
ret = __adjust_resource(res, res->start,
start - res->start);
if (ret)
break;
res->sibling = new_res;
new_res = NULL;
}
break;
}
write_unlock(&resource_lock);
mem hotunplug: fix kfree() of bootmem memory When hot removing memory presented at boot time, following messages are shown: kernel BUG at mm/slub.c:3409! invalid opcode: 0000 [#1] SMP Modules linked in: ebtable_nat ebtables xt_CHECKSUM iptable_mangle bridge stp llc ipmi_devintf ipmi_msghandler sunrpc ipt_REJECT nf_conntrack_ipv4 nf_defrag_ipv4 iptable_filter ip_tables ip6t_REJECT nf_conntrack_ipv6 nf_defrag_ipv6 xt_state nf_conntrack ip6table_filter ip6_tables binfmt_misc vfat fat dm_mirror dm_region_hash dm_log dm_mod vhost_net macvtap macvlan tun uinput iTCO_wdt iTCO_vendor_support coretemp kvm_intel kvm crc32c_intel ghash_clmulni_intel microcode pcspkr sg i2c_i801 lpc_ich mfd_core igb i2c_algo_bit i2c_core e1000e ptp pps_core tpm_infineon ioatdma dca sr_mod cdrom sd_mod crc_t10dif usb_storage megaraid_sas lpfc scsi_transport_fc scsi_tgt scsi_mod CPU 0 Pid: 5091, comm: kworker/0:2 Tainted: G W 3.9.0-rc6+ #15 RIP: kfree+0x232/0x240 Process kworker/0:2 (pid: 5091, threadinfo ffff88084678c000, task ffff88083928ca80) Call Trace: __release_region+0xd4/0xe0 __remove_pages+0x52/0x110 arch_remove_memory+0x89/0xd0 remove_memory+0xc4/0x100 acpi_memory_device_remove+0x6d/0xb1 acpi_device_remove+0x89/0xab __device_release_driver+0x7c/0xf0 device_release_driver+0x2f/0x50 acpi_bus_device_detach+0x6c/0x70 acpi_ns_walk_namespace+0x11a/0x250 acpi_walk_namespace+0xee/0x137 acpi_bus_trim+0x33/0x7a acpi_bus_hot_remove_device+0xc4/0x1a1 acpi_os_execute_deferred+0x27/0x34 process_one_work+0x1f7/0x590 worker_thread+0x11a/0x370 kthread+0xee/0x100 ret_from_fork+0x7c/0xb0 RIP [<ffffffff811c41d2>] kfree+0x232/0x240 RSP <ffff88084678d968> The reason why the messages are shown is to release a resource structure, allocated by bootmem, by kfree(). So when we release a resource structure, we should check whether it is allocated by bootmem or not. But even if we know a resource structure is allocated by bootmem, we cannot release it since SLxB cannot treat it. So for reusing a resource structure, this patch remembers it by using bootmem_resource as follows: When releasing a resource structure by free_resource(), free_resource() checks whether the resource structure is allocated by bootmem or not. If it is allocated by bootmem, free_resource() adds it to bootmem_resource. If it is not allocated by bootmem, free_resource() release it by kfree(). And when getting a new resource structure by get_resource(), get_resource() checks whether bootmem_resource has released resource structures or not. If there is a released resource structure, get_resource() returns it. If there is not a releaed resource structure, get_resource() returns new resource structure allocated by kzalloc(). [akpm@linux-foundation.org: s/get_resource/alloc_resource/] Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Reviewed-by: Toshi Kani <toshi.kani@hp.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Ram Pai <linuxram@us.ibm.com> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-30 06:08:56 +08:00
free_resource(new_res);
resource: add release_mem_region_adjustable() Add release_mem_region_adjustable(), which releases a requested region from a currently busy memory resource. This interface adjusts the matched memory resource accordingly even if the requested region does not match exactly but still fits into. This new interface is intended for memory hot-delete. During bootup, memory resources are inserted from the boot descriptor table, such as EFI Memory Table and e820. Each memory resource entry usually covers the whole contigous memory range. Memory hot-delete request, on the other hand, may target to a particular range of memory resource, and its size can be much smaller than the whole contiguous memory. Since the existing release interfaces like __release_region() require a requested region to be exactly matched to a resource entry, they do not allow a partial resource to be released. This new interface is restrictive (i.e. release under certain conditions), which is consistent with other release interfaces, __release_region() and __release_resource(). Additional release conditions, such as an overlapping region to a resource entry, can be supported after they are confirmed as valid cases. There is no change to the existing interfaces since their restriction is valid for I/O resources. [akpm@linux-foundation.org: use GFP_ATOMIC under write_lock()] [akpm@linux-foundation.org: switch back to GFP_KERNEL, less buggily] [akpm@linux-foundation.org: remove unneeded and wrong kfree(), per Toshi] Signed-off-by: Toshi Kani <toshi.kani@hp.com> Reviewed-by : Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: David Rientjes <rientjes@google.com> Reviewed-by: Ram Pai <linuxram@us.ibm.com> Cc: T Makphaibulchoke <tmac@hp.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Tang Chen <tangchen@cn.fujitsu.com> Cc: Jiang Liu <jiang.liu@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-30 06:08:19 +08:00
return ret;
}
#endif /* CONFIG_MEMORY_HOTREMOVE */
/*
* Managed region resource
*/
static void devm_resource_release(struct device *dev, void *ptr)
{
struct resource **r = ptr;
release_resource(*r);
}
/**
* devm_request_resource() - request and reserve an I/O or memory resource
* @dev: device for which to request the resource
* @root: root of the resource tree from which to request the resource
* @new: descriptor of the resource to request
*
* This is a device-managed version of request_resource(). There is usually
* no need to release resources requested by this function explicitly since
* that will be taken care of when the device is unbound from its driver.
* If for some reason the resource needs to be released explicitly, because
* of ordering issues for example, drivers must call devm_release_resource()
* rather than the regular release_resource().
*
* When a conflict is detected between any existing resources and the newly
* requested resource, an error message will be printed.
*
* Returns 0 on success or a negative error code on failure.
*/
int devm_request_resource(struct device *dev, struct resource *root,
struct resource *new)
{
struct resource *conflict, **ptr;
ptr = devres_alloc(devm_resource_release, sizeof(*ptr), GFP_KERNEL);
if (!ptr)
return -ENOMEM;
*ptr = new;
conflict = request_resource_conflict(root, new);
if (conflict) {
dev_err(dev, "resource collision: %pR conflicts with %s %pR\n",
new, conflict->name, conflict);
devres_free(ptr);
return -EBUSY;
}
devres_add(dev, ptr);
return 0;
}
EXPORT_SYMBOL(devm_request_resource);
static int devm_resource_match(struct device *dev, void *res, void *data)
{
struct resource **ptr = res;
return *ptr == data;
}
/**
* devm_release_resource() - release a previously requested resource
* @dev: device for which to release the resource
* @new: descriptor of the resource to release
*
* Releases a resource previously requested using devm_request_resource().
*/
void devm_release_resource(struct device *dev, struct resource *new)
{
WARN_ON(devres_release(dev, devm_resource_release, devm_resource_match,
new));
}
EXPORT_SYMBOL(devm_release_resource);
struct region_devres {
struct resource *parent;
resource_size_t start;
resource_size_t n;
};
static void devm_region_release(struct device *dev, void *res)
{
struct region_devres *this = res;
__release_region(this->parent, this->start, this->n);
}
static int devm_region_match(struct device *dev, void *res, void *match_data)
{
struct region_devres *this = res, *match = match_data;
return this->parent == match->parent &&
this->start == match->start && this->n == match->n;
}
struct resource *
__devm_request_region(struct device *dev, struct resource *parent,
resource_size_t start, resource_size_t n, const char *name)
{
struct region_devres *dr = NULL;
struct resource *res;
dr = devres_alloc(devm_region_release, sizeof(struct region_devres),
GFP_KERNEL);
if (!dr)
return NULL;
dr->parent = parent;
dr->start = start;
dr->n = n;
res = __request_region(parent, start, n, name, 0);
if (res)
devres_add(dev, dr);
else
devres_free(dr);
return res;
}
EXPORT_SYMBOL(__devm_request_region);
void __devm_release_region(struct device *dev, struct resource *parent,
resource_size_t start, resource_size_t n)
{
struct region_devres match_data = { parent, start, n };
__release_region(parent, start, n);
WARN_ON(devres_destroy(dev, devm_region_release, devm_region_match,
&match_data));
}
EXPORT_SYMBOL(__devm_release_region);
/*
* Reserve I/O ports or memory based on "reserve=" kernel parameter.
*/
#define MAXRESERVE 4
static int __init reserve_setup(char *str)
{
static int reserved;
static struct resource reserve[MAXRESERVE];
for (;;) {
unsigned int io_start, io_num;
int x = reserved;
struct resource *parent;
if (get_option(&str, &io_start) != 2)
break;
if (get_option(&str, &io_num) == 0)
break;
if (x < MAXRESERVE) {
struct resource *res = reserve + x;
/*
* If the region starts below 0x10000, we assume it's
* I/O port space; otherwise assume it's memory.
*/
if (io_start < 0x10000) {
res->flags = IORESOURCE_IO;
parent = &ioport_resource;
} else {
res->flags = IORESOURCE_MEM;
parent = &iomem_resource;
}
res->name = "reserved";
res->start = io_start;
res->end = io_start + io_num - 1;
res->flags |= IORESOURCE_BUSY;
resource: Add I/O resource descriptor walk_iomem_res() and region_intersects() still need to use strcmp() for searching a resource entry by @name in the iomem table. This patch introduces I/O resource descriptor 'desc' in struct resource for the iomem search interfaces. Drivers can assign their unique descriptor to a range when they support the search interfaces. Otherwise, 'desc' is set to IORES_DESC_NONE (0). This avoids changing most of the drivers as they typically allocate resource entries statically, or by calling alloc_resource(), kzalloc(), or alloc_bootmem_low(), which set the field to zero by default. A later patch will address some drivers that use kmalloc() without zero'ing the field. Also change release_mem_region_adjustable() to set 'desc' when its resource entry gets separated. Other resource interfaces are also changed to initialize 'desc' explicitly although alloc_resource() sets it to 0. Signed-off-by: Toshi Kani <toshi.kani@hpe.com> Signed-off-by: Borislav Petkov <bp@suse.de> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jakub Sitnicki <jsitnicki@gmail.com> Cc: Jiang Liu <jiang.liu@linux.intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Luis R. Rodriguez <mcgrof@suse.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: linux-arch@vger.kernel.org Cc: linux-mm <linux-mm@kvack.org> Link: http://lkml.kernel.org/r/1453841853-11383-4-git-send-email-bp@alien8.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-01-27 04:57:19 +08:00
res->desc = IORES_DESC_NONE;
res->child = NULL;
if (request_resource(parent, res) == 0)
reserved = x+1;
}
}
return 1;
}
__setup("reserve=", reserve_setup);
/*
* Check if the requested addr and size spans more than any slot in the
* iomem resource tree.
*/
int iomem_map_sanity_check(resource_size_t addr, unsigned long size)
{
struct resource *p = &iomem_resource;
int err = 0;
loff_t l;
read_lock(&resource_lock);
for (p = p->child; p ; p = r_next(NULL, p, &l)) {
/*
* We can probably skip the resources without
* IORESOURCE_IO attribute?
*/
if (p->start >= addr + size)
continue;
if (p->end < addr)
continue;
if (PFN_DOWN(p->start) <= PFN_DOWN(addr) &&
PFN_DOWN(p->end) >= PFN_DOWN(addr + size - 1))
continue;
/*
* if a resource is "BUSY", it's not a hardware resource
* but a driver mapping of such a resource; we don't want
* to warn for those; some drivers legitimately map only
* partial hardware resources. (example: vesafb)
*/
if (p->flags & IORESOURCE_BUSY)
continue;
printk(KERN_WARNING "resource sanity check: requesting [mem %#010llx-%#010llx], which spans more than %s %pR\n",
(unsigned long long)addr,
(unsigned long long)(addr + size - 1),
p->name, p);
err = -1;
break;
}
read_unlock(&resource_lock);
return err;
}
#ifdef CONFIG_STRICT_DEVMEM
static int strict_iomem_checks = 1;
#else
static int strict_iomem_checks;
#endif
/*
* check if an address is reserved in the iomem resource tree
* returns true if reserved, false if not reserved.
*/
bool iomem_is_exclusive(u64 addr)
{
struct resource *p = &iomem_resource;
bool err = false;
loff_t l;
int size = PAGE_SIZE;
if (!strict_iomem_checks)
return false;
addr = addr & PAGE_MASK;
read_lock(&resource_lock);
for (p = p->child; p ; p = r_next(NULL, p, &l)) {
/*
* We can probably skip the resources without
* IORESOURCE_IO attribute?
*/
if (p->start >= addr + size)
break;
if (p->end < addr)
continue;
restrict /dev/mem to idle io memory ranges This effectively promotes IORESOURCE_BUSY to IORESOURCE_EXCLUSIVE semantics by default. If userspace really believes it is safe to access the memory region it can also perform the extra step of disabling an active driver. This protects device address ranges with read side effects and otherwise directs userspace to use the driver. Persistent memory presents a large "mistake surface" to /dev/mem as now accidental writes can corrupt a filesystem. In general if a device driver is busily using a memory region it already informs other parts of the kernel to not touch it via request_mem_region(). /dev/mem should honor the same safety restriction by default. Debugging a device driver from userspace becomes more difficult with this enabled. Any application using /dev/mem or mmap of sysfs pci resources will now need to perform the extra step of either: 1/ Disabling the driver, for example: echo <device id> > /dev/bus/<parent bus>/drivers/<driver name>/unbind 2/ Rebooting with "iomem=relaxed" on the command line 3/ Recompiling with CONFIG_IO_STRICT_DEVMEM=n Traditional users of /dev/mem like dosemu are unaffected because the first 1MB of memory is not subject to the IO_STRICT_DEVMEM restriction. Legacy X configurations use /dev/mem to talk to graphics hardware, but that functionality has since moved to kernel graphics drivers. Cc: Arnd Bergmann <arnd@arndb.de> Cc: Russell King <linux@arm.linux.org.uk> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Acked-by: Kees Cook <keescook@chromium.org> Acked-by: Ingo Molnar <mingo@redhat.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2015-11-24 07:49:03 +08:00
/*
* A resource is exclusive if IORESOURCE_EXCLUSIVE is set
* or CONFIG_IO_STRICT_DEVMEM is enabled and the
* resource is busy.
*/
if ((p->flags & IORESOURCE_BUSY) == 0)
continue;
if (IS_ENABLED(CONFIG_IO_STRICT_DEVMEM)
|| p->flags & IORESOURCE_EXCLUSIVE) {
err = true;
break;
}
}
read_unlock(&resource_lock);
return err;
}
struct resource_entry *resource_list_create_entry(struct resource *res,
size_t extra_size)
{
struct resource_entry *entry;
entry = kzalloc(sizeof(*entry) + extra_size, GFP_KERNEL);
if (entry) {
INIT_LIST_HEAD(&entry->node);
entry->res = res ? res : &entry->__res;
}
return entry;
}
EXPORT_SYMBOL(resource_list_create_entry);
void resource_list_free(struct list_head *head)
{
struct resource_entry *entry, *tmp;
list_for_each_entry_safe(entry, tmp, head, node)
resource_list_destroy_entry(entry);
}
EXPORT_SYMBOL(resource_list_free);
static int __init strict_iomem(char *str)
{
if (strstr(str, "relaxed"))
strict_iomem_checks = 0;
if (strstr(str, "strict"))
strict_iomem_checks = 1;
return 1;
}
__setup("iomem=", strict_iomem);