| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1436914040-13206-23-git-send-email-yinghai@kernel.org>
Date: Tue, 14 Jul 2015 15:46:53 -0700
From: Yinghai Lu <yinghai@...nel.org>
To: Bjorn Helgaas <bhelgaas@...gle.com>,
David Miller <davem@...emloft.net>,
Benjamin Herrenschmidt <benh@...nel.crashing.org>,
Wei Yang <weiyang@...ux.vnet.ibm.com>, TJ <linux@....tj>,
Yijing Wang <wangyijing@...wei.com>
Cc: Andrew Morton <akpm@...ux-foundation.org>,
linux-pci@...r.kernel.org, linux-kernel@...r.kernel.org,
Yinghai Lu <yinghai@...nel.org>
Subject: [PATCH v2 22/49] PCI: Add alt_size allocation support
On system with several pcie switches, BIOS allocate very tight resources
to the bridge bar, and it is not aligned to min_align as kernel allocation
code.
For example:
02:03.0---0c:00.0---0d:04.0---18:00.0
18:00.0 need 0x10000000, and 0x00010000.
BIOS only allocate 0x10100000 to 0d:04.0 and above bridges.
Later after using /sys/bus/pci/devices/0000:0c:00.0/remove to remove 0c:00.0,
rescan with /sys/bus/pci/rescan can not allocate 0x18000000 to 0c:00.0.
another example:
00:1c.0-[02-21]----00.0-[03-21]--+-01.0-[04-12]----00.0-[05-12]----19.0-[06-12]----00.0
+-05.0-[13]--
+-07.0-[14-20]----00.0-[15-20]--+-08.0-[16]--+-00.0
| | \-00.1
| +-14.0-[17]----00.0
| \-19.0-[18-20]----00.0
\-09.0-[21]--
06:00.0 need 0x4000000 and 0x800000.
BIOS only allocate 0x4800000 to 05:19.0 and 04:00.0.
when 05:19.0 get removed via /sys/bus/pci/devices/0000:05:19.0/remove,
rescan with /sys/bus/pci/rescan will fail.
pci 0000:05:19.0: BAR 14: no space for [mem size 0x06000000]
pci 0000:05:19.0: BAR 14: failed to assign [mem size 0x06000000]
pci 0000:06:00.0: BAR 2: no space for [mem size 0x04000000 64bit]
pci 0000:06:00.0: BAR 2: failed to assign [mem size 0x04000000 64bit]
pci 0000:06:00.0: BAR 0: no space for [mem size 0x00800000]
pci 0000:06:00.0: BAR 0: failed to assign [mem size 0x00800000]
current code try to use align 0x2000000 and size 0x6000000, but parent
bridge only have 0x4800000.
Introduce alt_align/alt_size and store them in realloc list in addition
to addon info, and will try it after min_align/min_size allocation fails.
The alt_align is max_align, and alt_size is aligned size with bridge
minimum window alignment.
on my test setup:
00:1c.7---61:00.0---62:00.0
62:00.0 needs 0x800000 and 0x20000.
and 00:1c.7 only have 9M allocated for mmio, with this patch we have
pci 0000:61:00.0: bridge window [mem 0x00400000-0x00ffffff] to [bus 62] add_size 0 add_align 0 alt_size 900000 alt_align 800000 must_size c00000 must_align 400000
pci 0000:61:00.0: BAR 14: no space for [mem size 0x00c00000]
pci 0000:61:00.0: BAR 14: failed to assign [mem size 0x00c00000]
pci 0000:61:00.0: BAR 14: assigned [mem 0xdf000000-0xdf8fffff]
pci 0000:62:00.0: BAR 0: assigned [mem 0xdf000000-0xdf7fffff pref]
pci 0000:62:00.0: BAR 1: assigned [mem 0xdf800000-0xdf81ffff]
pci 0000:61:00.0: PCI bridge to [bus 62]
pci 0000:61:00.0: bridge window [io 0x6000-0x6fff]
pci 0000:61:00.0: bridge window [mem 0xdf000000-0xdf8fffff]
pci 0000:00:1c.7: PCI bridge to [bus 61-68]
pci 0000:00:1c.7: bridge window [io 0x6000-0x6fff]
pci 0000:00:1c.7: bridge window [mem 0xdf000000-0xdf8fffff]
so for 61:00.0 first try with 12M fails, and second try with 9M the
alt_size works. Later 62:00.0 get correct resource allocated too.
Link: https://bugzilla.kernel.org/show_bug.cgi?id=100451
Reported-by: Yijing Wang <wangyijing@...wei.com>
Signed-off-by: Yinghai Lu <yinghai@...nel.org>
---
drivers/pci/setup-bus.c | 203 +++++++++++++++++++++++++++++++++++++++++++++---
1 file changed, 191 insertions(+), 12 deletions(-)
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index 1c0b4c5..9da8b23 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -324,7 +324,7 @@ static void reassign_resources_sorted(struct list_head *realloc_head,
{
struct resource *res;
struct pci_dev_resource *add_res, *tmp;
- resource_size_t add_size, align;
+ resource_size_t add_size, align, r_size;
int idx;
list_for_each_entry_safe(add_res, tmp, realloc_head, list) {
@@ -340,12 +340,23 @@ static void reassign_resources_sorted(struct list_head *realloc_head,
idx = res - &add_res->dev->resource[0];
add_size = add_res->add_size;
align = add_res->min_align;
- if (!resource_size(res)) {
+ if (!add_size || !align) /* alt_size only */
+ goto out;
+
+ r_size = resource_size(res);
+ if (!r_size) {
res->start = align;
res->end = res->start + add_size - 1;
if (pci_assign_resource(add_res->dev, idx))
reset_resource(res);
} else {
+ /* could just assigned with alt, add difference ? */
+ resource_size_t must_size;
+
+ must_size = add_res->end - add_res->start + 1;
+ if (r_size < must_size)
+ add_size += must_size - r_size;
+
res->flags |= add_res->flags &
(IORESOURCE_STARTALIGN|IORESOURCE_SIZEALIGN);
if (pci_reassign_resource(add_res->dev, idx,
@@ -583,6 +594,104 @@ static bool __assign_resources_must_add_sorted(struct list_head *head,
return false;
}
+static bool __has_alt(struct list_head *head,
+ struct list_head *realloc_head)
+{
+ int alt_count = 0;
+ struct pci_dev_resource *dev_res, *alt_res;
+
+ if (!realloc_head)
+ return false;
+
+ /* check if we have alt really */
+ list_for_each_entry(dev_res, head, list) {
+ alt_res = res_to_dev_res(realloc_head, dev_res->res);
+ if (!alt_res || !alt_res->alt_size)
+ continue;
+
+ alt_count++;
+ }
+
+ if (!alt_count)
+ return false;
+
+ return true;
+}
+
+static void __assign_resources_alt_sorted(struct list_head *head,
+ struct list_head *save_head,
+ struct list_head *realloc_head,
+ struct list_head *local_fail_head)
+{
+ LIST_HEAD(local_alt_fail_head);
+ struct pci_dev_resource *dev_res;
+ struct pci_dev_resource *alt_res, *fail_res, *save_res;
+ unsigned long fail_type;
+ struct resource *res;
+
+ /* check failed type */
+ fail_type = pci_fail_res_type_mask(local_fail_head);
+ /* release resource with same type that failes */
+ list_for_each_entry(dev_res, head, list) {
+ res = dev_res->res;
+ if (res->parent) {
+ if (!pci_need_to_release(fail_type, res))
+ continue;
+
+ /*
+ * have to use saved info, as resource that does not
+ * have addon/alt is not in realloc list.
+ */
+ save_res = res_to_dev_res(save_head, res);
+ if (!save_res)
+ continue;
+
+ dev_printk(KERN_DEBUG, &dev_res->dev->dev,
+ "BAR %d: released %pR\n",
+ (int)(res - &dev_res->dev->resource[0]),
+ res);
+ release_resource(dev_res->res);
+ restore_resource(save_res, res);
+ } else {
+ /* restore fail one */
+ fail_res = res_to_dev_res(local_fail_head, res);
+ if (fail_res) {
+ restore_resource(fail_res, res);
+ remove_from_list(local_fail_head, res);
+ }
+ }
+
+ alt_res = res_to_dev_res(realloc_head, res);
+ if (!alt_res || !alt_res->alt_size)
+ continue;
+
+ /* change res to alt */
+ if (res->flags & IORESOURCE_STARTALIGN)
+ res->start = alt_res->alt_align;
+ else
+ res->start = 0;
+ res->end = res->start + alt_res->alt_size - 1;
+ }
+
+ __sort_resources(head);
+ /* Satisfy the alt resource requests */
+ assign_requested_resources_sorted(head, &local_alt_fail_head);
+
+ /* update local fail list */
+ list_for_each_entry(fail_res, &local_alt_fail_head, list) {
+ res = fail_res->res;
+ dev_res = res_to_dev_res(realloc_head, res);
+ /* change res back to must */
+ if (dev_res && dev_res->alt_size)
+ restore_resource(dev_res, res);
+
+ if (!res_to_dev_res(local_fail_head, res))
+ add_to_list(local_fail_head, fail_res->dev, res);
+ reset_resource(res);
+ }
+ free_list(&local_alt_fail_head);
+}
+
static void __assign_resources_sorted(struct list_head *head,
struct list_head *realloc_head,
struct list_head *fail_head)
@@ -598,6 +707,8 @@ static void __assign_resources_sorted(struct list_head *head,
*/
LIST_HEAD(save_head);
+ LIST_HEAD(local_fail_head);
+ bool has_alt;
/* Check must+optional add */
if (__has_addon(head, realloc_head) &&
@@ -610,15 +721,29 @@ static void __assign_resources_sorted(struct list_head *head,
__sort_resources(head);
+ has_alt = __has_alt(head, realloc_head);
+ if (has_alt && list_empty(&save_head))
+ save_resources(head, &save_head);
+
/* Satisfy the must-have resource requests */
- assign_requested_resources_sorted(head, fail_head);
+ assign_requested_resources_sorted(head, &local_fail_head);
+
+ if (has_alt && !list_empty(&local_fail_head) && !list_empty(&save_head))
+ __assign_resources_alt_sorted(head, &save_head,
+ realloc_head,
+ &local_fail_head);
free_list(&save_head);
- /* Try to satisfy any additional optional resource
- requests */
+ /* Try to satisfy any additional optional resource requests */
if (realloc_head)
reassign_resources_sorted(realloc_head, head);
+
+ if (fail_head)
+ list_splice_tail(&local_fail_head, fail_head);
+ else
+ free_list(&local_fail_head);
+
free_list(head);
}
@@ -1256,6 +1381,7 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask,
mask | IORESOURCE_PREFETCH, type);
LIST_HEAD(align_test_list);
LIST_HEAD(align_test_add_list);
+ resource_size_t alt_size = 0, alt_align = 0;
resource_size_t window_align;
if (!b_res)
@@ -1312,6 +1438,7 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask,
if (realloc_head) {
resource_size_t add_r_size, add_align;
+ struct pci_dev_resource *dev_res;
add_r_size = get_res_add_size(realloc_head, r);
add_align = get_res_add_align(realloc_head, r);
@@ -1324,6 +1451,17 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask,
sum_add_size += r_size + add_r_size;
if (add_align > max_add_align)
max_add_align = add_align;
+
+ dev_res = res_to_dev_res(realloc_head, r);
+ if (dev_res && dev_res->alt_size) {
+ alt_size += dev_res->alt_size;
+ if (alt_align < dev_res->alt_align)
+ alt_align = dev_res->alt_align;
+ } else if (r_size > 1) {
+ alt_size += r_size;
+ if (alt_align < align)
+ alt_align = align;
+ }
}
}
}
@@ -1337,6 +1475,17 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask,
}
free_align_test_list(&align_test_list);
+ if (size0 && realloc_head) {
+ alt_align = max(alt_align, window_align);
+ alt_size = calculate_memsize(alt_size, min_size,
+ 0, window_align);
+ /* must is better ? */
+ if (alt_size >= size0) {
+ alt_align = 0;
+ alt_size = 0;
+ }
+ }
+
if (sum_add_size < min_sum_size)
sum_add_size = min_sum_size;
if (sum_add_size > size && realloc_head) {
@@ -1358,13 +1507,43 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask,
b_res->start = min_align;
b_res->end = size0 + min_align - 1;
b_res->flags |= IORESOURCE_STARTALIGN;
- if (size1 > size0 && realloc_head) {
- __add_to_list(realloc_head, bus->self, b_res, size1 - size0,
- min_add_align, 0, 0);
- dev_printk(KERN_DEBUG, &bus->self->dev, "bridge window %pR to %pR add_size %llx add_align %llx\n",
- b_res, &bus->busn_res,
- (unsigned long long) (size1 - size0),
- (unsigned long long) min_add_align);
+ if (realloc_head) {
+ resource_size_t final_add_size = 0;
+
+ if (size1 > size0)
+ final_add_size = size1 - size0;
+ else
+ min_add_align = 0;
+
+ /*
+ * realloc list include three type entries
+ * 1. optional only:
+ * add_size != 0, alt_size == 0, must_size == 0
+ * 2. must only with smaller alt_size.
+ * add_size == 0, alt_size != 0, must_size > alt_size
+ * 3. must + optional:
+ * add_size != 0, alt_size < must_size, must_size != 0
+ *
+ * So there is no must_size != 0, and alt_size == must_size.
+ * in that case, we already set alt_size = 0.
+ *
+ * must_align/must_size is not stored directly, and we have
+ * dev_res start/end/flags instead.
+ */
+ if (final_add_size || alt_size) {
+ __add_to_list(realloc_head, bus->self, b_res,
+ final_add_size, min_add_align,
+ alt_size, alt_align);
+ dev_printk(KERN_DEBUG, &bus->self->dev,
+ "bridge window %pR to %pR add_size %llx add_align %llx alt_size %llx alt_align %llx must_size %llx must_align %llx\n",
+ b_res, &bus->busn_res,
+ (unsigned long long)final_add_size,
+ (unsigned long long)min_add_align,
+ (unsigned long long)alt_size,
+ (unsigned long long)alt_align,
+ (unsigned long long)size0,
+ (unsigned long long)min_align);
+ }
}
return 0;
}
--
1.8.4.5
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists