* [PATCH v6 01/30] PCI: Fix race condition in pci_enable/disable_device()
2019-10-24 17:11 [PATCH v6 00/30] PCI: Allow BAR movement during hotplug Sergey Miroshnichenko
@ 2019-10-24 17:11 ` Sergey Miroshnichenko
2019-10-25 14:33 ` Oxford Semiconductor Ltd OX16PCI954 - weird dmesg Carlo Pisani
2019-10-24 17:12 ` [PATCH v6 02/30] PCI: Enable bridge's I/O and MEM access for hotplugged devices Sergey Miroshnichenko
` (28 subsequent siblings)
29 siblings, 1 reply; 35+ messages in thread
From: Sergey Miroshnichenko @ 2019-10-24 17:11 UTC (permalink / raw)
To: linux-pci, linuxppc-dev
Cc: Bjorn Helgaas, linux, Sergey Miroshnichenko, Srinath Mannam,
Marta Rybczynska
This is a yet another approach to fix an old [1-2] concurrency issue, when:
- two or more devices are being hot-added into a bridge which was
initially empty;
- a bridge with two or more devices is being hot-added;
- during boot, if BIOS/bootloader/firmware doesn't pre-enable bridges.
The problem is that a bridge is reported as enabled before the MEM/IO bits
are actually written to the PCI_COMMAND register, so another driver thread
starts memory requests through the not-yet-enabled bridge:
CPU0 CPU1
pci_enable_device_mem() pci_enable_device_mem()
pci_enable_bridge() pci_enable_bridge()
pci_is_enabled()
return false;
atomic_inc_return(enable_cnt)
Start actual enabling the bridge
... pci_is_enabled()
... return true;
... Start memory requests <-- FAIL
...
Set the PCI_COMMAND_MEMORY bit <-- Must wait for this
Protect the pci_enable/disable_device() and pci_enable_bridge(), which is
similar to the previous solution from commit 40f11adc7cd9 ("PCI: Avoid race
while enabling upstream bridges"), but adding a per-device mutexes and
preventing the dev->enable_cnt from from incrementing early.
CC: Srinath Mannam <srinath.mannam@broadcom.com>
CC: Marta Rybczynska <mrybczyn@kalray.eu>
Signed-off-by: Sergey Miroshnichenko <s.miroshnichenko@yadro.com>
[1] https://lore.kernel.org/linux-pci/1501858648-22228-1-git-send-email-srinath.mannam@broadcom.com/T/#u
[RFC PATCH v3] pci: Concurrency issue during pci enable bridge
[2] https://lore.kernel.org/linux-pci/744877924.5841545.1521630049567.JavaMail.zimbra@kalray.eu/T/#u
[RFC PATCH] nvme: avoid race-conditions when enabling devices
---
drivers/pci/pci.c | 26 ++++++++++++++++++++++----
drivers/pci/probe.c | 1 +
include/linux/pci.h | 1 +
3 files changed, 24 insertions(+), 4 deletions(-)
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index a97e2571a527..44d0d12c80cf 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -1643,6 +1643,8 @@ static void pci_enable_bridge(struct pci_dev *dev)
struct pci_dev *bridge;
int retval;
+ mutex_lock(&dev->enable_mutex);
+
bridge = pci_upstream_bridge(dev);
if (bridge)
pci_enable_bridge(bridge);
@@ -1650,6 +1652,7 @@ static void pci_enable_bridge(struct pci_dev *dev)
if (pci_is_enabled(dev)) {
if (!dev->is_busmaster)
pci_set_master(dev);
+ mutex_unlock(&dev->enable_mutex);
return;
}
@@ -1658,11 +1661,14 @@ static void pci_enable_bridge(struct pci_dev *dev)
pci_err(dev, "Error enabling bridge (%d), continuing\n",
retval);
pci_set_master(dev);
+ mutex_unlock(&dev->enable_mutex);
}
static int pci_enable_device_flags(struct pci_dev *dev, unsigned long flags)
{
struct pci_dev *bridge;
+ /* Enable-locking of bridges is performed within the pci_enable_bridge() */
+ bool need_lock = !dev->subordinate;
int err;
int i, bars = 0;
@@ -1678,8 +1684,13 @@ static int pci_enable_device_flags(struct pci_dev *dev, unsigned long flags)
dev->current_state = (pmcsr & PCI_PM_CTRL_STATE_MASK);
}
- if (atomic_inc_return(&dev->enable_cnt) > 1)
+ if (need_lock)
+ mutex_lock(&dev->enable_mutex);
+ if (pci_is_enabled(dev)) {
+ if (need_lock)
+ mutex_unlock(&dev->enable_mutex);
return 0; /* already enabled */
+ }
bridge = pci_upstream_bridge(dev);
if (bridge)
@@ -1694,8 +1705,10 @@ static int pci_enable_device_flags(struct pci_dev *dev, unsigned long flags)
bars |= (1 << i);
err = do_pci_enable_device(dev, bars);
- if (err < 0)
- atomic_dec(&dev->enable_cnt);
+ if (err >= 0)
+ atomic_inc(&dev->enable_cnt);
+ if (need_lock)
+ mutex_unlock(&dev->enable_mutex);
return err;
}
@@ -1939,15 +1952,20 @@ void pci_disable_device(struct pci_dev *dev)
if (dr)
dr->enabled = 0;
+ mutex_lock(&dev->enable_mutex);
dev_WARN_ONCE(&dev->dev, atomic_read(&dev->enable_cnt) <= 0,
"disabling already-disabled device");
- if (atomic_dec_return(&dev->enable_cnt) != 0)
+ if (atomic_dec_return(&dev->enable_cnt) != 0) {
+ mutex_unlock(&dev->enable_mutex);
return;
+ }
do_pci_disable_device(dev);
dev->is_busmaster = 0;
+
+ mutex_unlock(&dev->enable_mutex);
}
EXPORT_SYMBOL(pci_disable_device);
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 3d5271a7a849..d4f21e413638 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -2158,6 +2158,7 @@ struct pci_dev *pci_alloc_dev(struct pci_bus *bus)
INIT_LIST_HEAD(&dev->bus_list);
dev->dev.type = &pci_dev_type;
dev->bus = pci_bus_get(bus);
+ mutex_init(&dev->enable_mutex);
return dev;
}
diff --git a/include/linux/pci.h b/include/linux/pci.h
index f9088c89a534..525140e3a460 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -425,6 +425,7 @@ struct pci_dev {
unsigned int no_vf_scan:1; /* Don't scan for VFs after IOV enablement */
pci_dev_flags_t dev_flags;
atomic_t enable_cnt; /* pci_enable_device has been called */
+ struct mutex enable_mutex;
u32 saved_config_space[16]; /* Config space saved at suspend time */
struct hlist_head saved_cap_space;
--
2.23.0
^ permalink raw reply related [flat|nested] 35+ messages in thread* Oxford Semiconductor Ltd OX16PCI954 - weird dmesg
2019-10-24 17:11 ` [PATCH v6 01/30] PCI: Fix race condition in pci_enable/disable_device() Sergey Miroshnichenko
@ 2019-10-25 14:33 ` Carlo Pisani
2019-10-25 16:37 ` Bjorn Helgaas
0 siblings, 1 reply; 35+ messages in thread
From: Carlo Pisani @ 2019-10-25 14:33 UTC (permalink / raw)
To: linux-pci, Bjorn Helgaas; +Cc: linuxppc-dev, linux
pci_bus 0000:00: root bus resource [mem 0x50000000-0x5fffffff]
pci_bus 0000:00: root bus resource [io 0x18800000-0x188fffff]
pci_bus 0000:00: root bus resource [??? 0x00000000 flags 0x0]
pci_bus 0000:00: No busn resource found for root bus, will use [bus 00-ff]
pci 0000:00:00.0: [Firmware Bug]: reg 0x14: invalid BAR (can't size)
pci 0000:00:00.0: [Firmware Bug]: reg 0x18: invalid BAR (can't size)
pci 0000:00:04.0: BAR 0: assigned [mem 0x50000000-0x5000ffff]
pci 0000:00:05.0: BAR 1: assigned [mem 0x50010000-0x50010fff]
pci 0000:00:05.0: BAR 3: assigned [mem 0x50011000-0x50011fff]
pci 0000:00:0a.0: BAR 1: assigned [mem 0x50012000-0x50012fff]
pci 0000:00:0a.0: BAR 3: assigned [mem 0x50013000-0x50013fff]
pci 0000:00:02.0: BAR 0: assigned [io 0x18800000-0x188000ff]
pci 0000:00:02.0: BAR 1: assigned [mem 0x50014000-0x500140ff]
pci 0000:00:03.0: BAR 0: assigned [io 0x18800400-0x188004ff]
pci 0000:00:03.0: BAR 1: assigned [mem 0x50014100-0x500141ff]
pci 0000:00:05.0: BAR 0: assigned [io 0x18800800-0x1880081f]
pci 0000:00:05.0: BAR 2: assigned [io 0x18800820-0x1880083f]
pci 0000:00:0a.0: BAR 0: assigned [io 0x18800840-0x1880085f]
pci 0000:00:0a.0: BAR 2: assigned [io 0x18800860-0x1880087f]
00:00.0 Non-VGA unclassified device: Integrated Device Technology,
Inc. Device 0000
Subsystem: Device 0214:011d
Flags: bus master, 66MHz, medium devsel, latency 60, IRQ 140
Memory at <unassigned> (32-bit, prefetchable)
I/O ports at <ignored>
I/O ports at <ignored>
00:02.0 Ethernet controller: VIA Technologies, Inc. VT6105/VT6106S
[Rhine-III] (rev 86)
Subsystem: AST Research Inc Device 086c
Flags: bus master, stepping, medium devsel, latency 64, IRQ 142
I/O ports at 18800000 [size=256]
Memory at 50014000 (32-bit, non-prefetchable) [size=256]
Capabilities: [40] Power Management version 2
Kernel driver in use: via-rhine
00:03.0 Ethernet controller: VIA Technologies, Inc. VT6105/VT6106S
[Rhine-III] (rev 86)
Subsystem: AST Research Inc Device 086c
Flags: bus master, stepping, medium devsel, latency 64, IRQ 143
I/O ports at 18800400 [size=256]
Memory at 50014100 (32-bit, non-prefetchable) [size=256]
Capabilities: [40] Power Management version 2
Kernel driver in use: via-rhine
00:04.0 Network controller: Atheros Communications Inc. Device 0029 (rev 01)
Subsystem: Atheros Communications Inc. Device 2091
Flags: bus master, 66MHz, medium devsel, latency 168, IRQ 142
Memory at 50000000 (32-bit, non-prefetchable) [size=64K]
Capabilities: [44] Power Management version 2
Kernel driver in use: ath9k
00:05.0 Serial controller: Oxford Semiconductor Ltd OX16PCI954 (Quad
16950 UART) function 0 (Uart) (rev 01) (prog-if 06 [)
Subsystem: Oxford Semiconductor Ltd Device 0000
Flags: medium devsel, IRQ 143
I/O ports at 18800800 [size=32]
Memory at 50010000 (32-bit, non-prefetchable) [size=4K]
I/O ports at 18800820 [size=32]
Memory at 50011000 (32-bit, non-prefetchable) [size=4K]
Capabilities: [40] Power Management version 2
Kernel driver in use: serial
00:05.1 Non-VGA unclassified device: Oxford Semiconductor Ltd
OX16PCI954 (Quad 16950 UART) function 0 (Disabled) (rev 01)
Subsystem: Oxford Semiconductor Ltd Device 0000
Flags: medium devsel, IRQ 143
I/O ports at <unassigned> [disabled]
I/O ports at <unassigned> [disabled]
I/O ports at <unassigned> [disabled]
Capabilities: [40] Power Management version 2
00:0a.0 Serial controller: Oxford Semiconductor Ltd OX16PCI954 (Quad
16950 UART) function 0 (Uart) (rev 01) (prog-if 06 [)
Subsystem: Oxford Semiconductor Ltd Device 0000
Flags: medium devsel, IRQ 140
I/O ports at 18800840 [size=32]
Memory at 50012000 (32-bit, non-prefetchable) [size=4K]
I/O ports at 18800860 [size=32]
Memory at 50013000 (32-bit, non-prefetchable) [size=4K]
Capabilities: [40] Power Management version 2
Kernel driver in use: serial
00:0a.1 Non-VGA unclassified device: Oxford Semiconductor Ltd
OX16PCI954 (Quad 16950 UART) function 0 (Disabled) (rev 01)
Subsystem: Oxford Semiconductor Ltd Device 0000
Flags: medium devsel, IRQ 140
I/O ports at <unassigned> [disabled]
I/O ports at <unassigned> [disabled]
I/O ports at <unassigned> [disabled]
Capabilities: [40] Power Management version 2
hi guys
I have a couple of miniPCI Oxford Semiconductor Ltd OX16PCI954 cards
installed, and the dmesg looks weird
espeially these lines
pci_bus 0000:00: root bus resource [mem 0x50000000-0x5fffffff]
pci_bus 0000:00: root bus resource [io 0x18800000-0x188fffff]
pci_bus 0000:00: root bus resource [??? 0x00000000 flags 0x0]
pci_bus 0000:00: No busn resource found for root bus, will use [bus 00-ff]
pci 0000:00:00.0: [Firmware Bug]: reg 0x14: invalid BAR (can't size)
pci 0000:00:00.0: [Firmware Bug]: reg 0x18: invalid BAR (can't size)
besides, I am experimenting crashes happening in burn-in tests, and I
do suspect it's something related to the newly added cards
any enlightenment?
^ permalink raw reply [flat|nested] 35+ messages in thread* Re: Oxford Semiconductor Ltd OX16PCI954 - weird dmesg
2019-10-25 14:33 ` Oxford Semiconductor Ltd OX16PCI954 - weird dmesg Carlo Pisani
@ 2019-10-25 16:37 ` Bjorn Helgaas
0 siblings, 0 replies; 35+ messages in thread
From: Bjorn Helgaas @ 2019-10-25 16:37 UTC (permalink / raw)
To: Carlo Pisani; +Cc: linux-pci, linuxppc-dev, linux
On Fri, Oct 25, 2019 at 04:33:13PM +0200, Carlo Pisani wrote:
> pci_bus 0000:00: root bus resource [mem 0x50000000-0x5fffffff]
> pci_bus 0000:00: root bus resource [io 0x18800000-0x188fffff]
> pci_bus 0000:00: root bus resource [??? 0x00000000 flags 0x0]
> pci_bus 0000:00: No busn resource found for root bus, will use [bus 00-ff]
> pci 0000:00:00.0: [Firmware Bug]: reg 0x14: invalid BAR (can't size)
> pci 0000:00:00.0: [Firmware Bug]: reg 0x18: invalid BAR (can't size)
> pci 0000:00:04.0: BAR 0: assigned [mem 0x50000000-0x5000ffff]
> pci 0000:00:05.0: BAR 1: assigned [mem 0x50010000-0x50010fff]
> pci 0000:00:05.0: BAR 3: assigned [mem 0x50011000-0x50011fff]
> pci 0000:00:0a.0: BAR 1: assigned [mem 0x50012000-0x50012fff]
> pci 0000:00:0a.0: BAR 3: assigned [mem 0x50013000-0x50013fff]
> pci 0000:00:02.0: BAR 0: assigned [io 0x18800000-0x188000ff]
> pci 0000:00:02.0: BAR 1: assigned [mem 0x50014000-0x500140ff]
> pci 0000:00:03.0: BAR 0: assigned [io 0x18800400-0x188004ff]
> pci 0000:00:03.0: BAR 1: assigned [mem 0x50014100-0x500141ff]
> pci 0000:00:05.0: BAR 0: assigned [io 0x18800800-0x1880081f]
> pci 0000:00:05.0: BAR 2: assigned [io 0x18800820-0x1880083f]
> pci 0000:00:0a.0: BAR 0: assigned [io 0x18800840-0x1880085f]
> pci 0000:00:0a.0: BAR 2: assigned [io 0x18800860-0x1880087f]
>
>
> 00:00.0 Non-VGA unclassified device: Integrated Device Technology,
> Inc. Device 0000
> Subsystem: Device 0214:011d
> Flags: bus master, 66MHz, medium devsel, latency 60, IRQ 140
> Memory at <unassigned> (32-bit, prefetchable)
> I/O ports at <ignored>
> I/O ports at <ignored>
>
> 00:02.0 Ethernet controller: VIA Technologies, Inc. VT6105/VT6106S
> [Rhine-III] (rev 86)
> Subsystem: AST Research Inc Device 086c
> Flags: bus master, stepping, medium devsel, latency 64, IRQ 142
> I/O ports at 18800000 [size=256]
> Memory at 50014000 (32-bit, non-prefetchable) [size=256]
> Capabilities: [40] Power Management version 2
> Kernel driver in use: via-rhine
>
> 00:03.0 Ethernet controller: VIA Technologies, Inc. VT6105/VT6106S
> [Rhine-III] (rev 86)
> Subsystem: AST Research Inc Device 086c
> Flags: bus master, stepping, medium devsel, latency 64, IRQ 143
> I/O ports at 18800400 [size=256]
> Memory at 50014100 (32-bit, non-prefetchable) [size=256]
> Capabilities: [40] Power Management version 2
> Kernel driver in use: via-rhine
>
> 00:04.0 Network controller: Atheros Communications Inc. Device 0029 (rev 01)
> Subsystem: Atheros Communications Inc. Device 2091
> Flags: bus master, 66MHz, medium devsel, latency 168, IRQ 142
> Memory at 50000000 (32-bit, non-prefetchable) [size=64K]
> Capabilities: [44] Power Management version 2
> Kernel driver in use: ath9k
>
> 00:05.0 Serial controller: Oxford Semiconductor Ltd OX16PCI954 (Quad
> 16950 UART) function 0 (Uart) (rev 01) (prog-if 06 [)
> Subsystem: Oxford Semiconductor Ltd Device 0000
> Flags: medium devsel, IRQ 143
> I/O ports at 18800800 [size=32]
> Memory at 50010000 (32-bit, non-prefetchable) [size=4K]
> I/O ports at 18800820 [size=32]
> Memory at 50011000 (32-bit, non-prefetchable) [size=4K]
> Capabilities: [40] Power Management version 2
> Kernel driver in use: serial
>
> 00:05.1 Non-VGA unclassified device: Oxford Semiconductor Ltd
> OX16PCI954 (Quad 16950 UART) function 0 (Disabled) (rev 01)
> Subsystem: Oxford Semiconductor Ltd Device 0000
> Flags: medium devsel, IRQ 143
> I/O ports at <unassigned> [disabled]
> I/O ports at <unassigned> [disabled]
> I/O ports at <unassigned> [disabled]
> Capabilities: [40] Power Management version 2
>
> 00:0a.0 Serial controller: Oxford Semiconductor Ltd OX16PCI954 (Quad
> 16950 UART) function 0 (Uart) (rev 01) (prog-if 06 [)
> Subsystem: Oxford Semiconductor Ltd Device 0000
> Flags: medium devsel, IRQ 140
> I/O ports at 18800840 [size=32]
> Memory at 50012000 (32-bit, non-prefetchable) [size=4K]
> I/O ports at 18800860 [size=32]
> Memory at 50013000 (32-bit, non-prefetchable) [size=4K]
> Capabilities: [40] Power Management version 2
> Kernel driver in use: serial
>
> 00:0a.1 Non-VGA unclassified device: Oxford Semiconductor Ltd
> OX16PCI954 (Quad 16950 UART) function 0 (Disabled) (rev 01)
> Subsystem: Oxford Semiconductor Ltd Device 0000
> Flags: medium devsel, IRQ 140
> I/O ports at <unassigned> [disabled]
> I/O ports at <unassigned> [disabled]
> I/O ports at <unassigned> [disabled]
> Capabilities: [40] Power Management version 2
>
>
> hi guys
> I have a couple of miniPCI Oxford Semiconductor Ltd OX16PCI954 cards
> installed, and the dmesg looks weird
>
> espeially these lines
> pci_bus 0000:00: root bus resource [mem 0x50000000-0x5fffffff]
> pci_bus 0000:00: root bus resource [io 0x18800000-0x188fffff]
> pci_bus 0000:00: root bus resource [??? 0x00000000 flags 0x0]
> pci_bus 0000:00: No busn resource found for root bus, will use [bus 00-ff]
These resources are supplied to the PCI core, probably from DT. A
complete dmesg log would show more.
> pci 0000:00:00.0: [Firmware Bug]: reg 0x14: invalid BAR (can't size)
> pci 0000:00:00.0: [Firmware Bug]: reg 0x18: invalid BAR (can't size)
> besides, I am experimenting crashes happening in burn-in tests, and I
> do suspect it's something related to the newly added cards
If you take the cards out do the lines you mention above change?
What sort of crashes do you see? I assume it doesn't crash without
the cards?
It *looks* like the miniPCI cards should be these devices:
00:05.0 Serial controller: Oxford Semiconductor Ltd OX16PCI954 (Quad 16950 UART) function 0 (Uart) (rev 01) (prog-if 06 [)
00:0a.0 Serial controller: Oxford Semiconductor Ltd OX16PCI954 (Quad 16950 UART) function 0 (Uart) (rev 01) (prog-if 06 [)
which are unrelated to the 00:00.0 device with the broken BAR.
^ permalink raw reply [flat|nested] 35+ messages in thread
* [PATCH v6 02/30] PCI: Enable bridge's I/O and MEM access for hotplugged devices
2019-10-24 17:11 [PATCH v6 00/30] PCI: Allow BAR movement during hotplug Sergey Miroshnichenko
2019-10-24 17:11 ` [PATCH v6 01/30] PCI: Fix race condition in pci_enable/disable_device() Sergey Miroshnichenko
@ 2019-10-24 17:12 ` Sergey Miroshnichenko
2019-10-24 17:12 ` [PATCH v6 03/30] PCI: hotplug: Add a flag for the movable BARs feature Sergey Miroshnichenko
` (27 subsequent siblings)
29 siblings, 0 replies; 35+ messages in thread
From: Sergey Miroshnichenko @ 2019-10-24 17:12 UTC (permalink / raw)
To: linux-pci, linuxppc-dev; +Cc: Bjorn Helgaas, linux, Sergey Miroshnichenko
The PCI_COMMAND_IO and PCI_COMMAND_MEMORY bits of the bridge must be
updated not only when enabling the bridge for the first time, but also if a
hotplugged device requests these types of resources.
Originally these bits were set by the pci_enable_device_flags() only, which
exits early if the bridge is already pci_is_enabled(). So if the bridge was
empty initially (an edge case), then hotplugged devices fail to IO/MEM.
Signed-off-by: Sergey Miroshnichenko <s.miroshnichenko@yadro.com>
---
drivers/pci/pci.c | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 44d0d12c80cf..e85dc63c73fd 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -1650,6 +1650,14 @@ static void pci_enable_bridge(struct pci_dev *dev)
pci_enable_bridge(bridge);
if (pci_is_enabled(dev)) {
+ int i, bars = 0;
+
+ for (i = PCI_BRIDGE_RESOURCES; i < DEVICE_COUNT_RESOURCE; i++) {
+ if (dev->resource[i].flags & (IORESOURCE_MEM | IORESOURCE_IO))
+ bars |= (1 << i);
+ }
+ do_pci_enable_device(dev, bars);
+
if (!dev->is_busmaster)
pci_set_master(dev);
mutex_unlock(&dev->enable_mutex);
--
2.23.0
^ permalink raw reply related [flat|nested] 35+ messages in thread* [PATCH v6 03/30] PCI: hotplug: Add a flag for the movable BARs feature
2019-10-24 17:11 [PATCH v6 00/30] PCI: Allow BAR movement during hotplug Sergey Miroshnichenko
2019-10-24 17:11 ` [PATCH v6 01/30] PCI: Fix race condition in pci_enable/disable_device() Sergey Miroshnichenko
2019-10-24 17:12 ` [PATCH v6 02/30] PCI: Enable bridge's I/O and MEM access for hotplugged devices Sergey Miroshnichenko
@ 2019-10-24 17:12 ` Sergey Miroshnichenko
2019-10-24 17:12 ` [PATCH v6 04/30] PCI: Define PCI-specific version of the release_child_resources() Sergey Miroshnichenko
` (26 subsequent siblings)
29 siblings, 0 replies; 35+ messages in thread
From: Sergey Miroshnichenko @ 2019-10-24 17:12 UTC (permalink / raw)
To: linux-pci, linuxppc-dev
Cc: Bjorn Helgaas, linux, Sergey Miroshnichenko, Sam Bobroff,
Rajat Jain, Lukas Wunner, Oliver O'Halloran, David Laight
When hot-adding a device, the bridge may have windows not big enough (or
fragmented too much) for newly requested BARs to fit in. And expanding
these bridge windows may be impossible because blocked by "neighboring"
BARs and bridge windows.
Still, it may be possible to allocate a memory region for new BARs with the
following procedure:
1) notify all the drivers which support movable BARs to pause and release
the BARs; the rest of the drivers are guaranteed that their devices will
not get BARs moved;
2) release all the bridge windows and movable BARs;
3) try to recalculate new bridge windows that will fit all the BAR types:
- fixed;
- immovable;
- movable;
- newly requested by hot-added devices;
4) if the previous step fails, disable BARs for one of the hot-added
devices and retry from step 3;
5) notify the drivers, so they remap BARs and resume.
If bridge calculation and BAR assignment fails with a hot-added devices,
BARs of these devices will be disabled, falling back to the same amount and
size of BARs as they were before the hotplug event. The kernel succeeded in
assigning then, so the same algorithm will provide the same results again.
This makes the prior reservation of memory by BIOS/bootloader/firmware not
required anymore for the PCI hotplug.
Drivers indicate their support of movable BARs by implementing the new
.rescan_prepare() and .rescan_done() hooks in the struct pci_driver. All
device's activity must be paused during a rescan, and iounmap()+ioremap()
must be applied to every used BAR.
If a device is not bound to a driver, its BARs are considered movable.
For a higher probability of the successful BAR reassignment, all the BARs
and bridge windows should be released before the rescan, not only those
with higher addresses.
One example when it is needed, BAR(I) is moved to free a gap for the new
BAR(II):
Before:
==================== parent bridge window ===============
---- hotplug bridge window ----
| BAR(I) | fixed BAR | fixed BAR | fixed BAR |
^
|
new BAR(II)
After:
==================== parent bridge window =========================
----------- hotplug bridge window -----------
| new BAR(II) | fixed BAR | fixed BAR | fixed BAR | BAR(I) |
Another example is a fragmented bridge window jammed between fixed BARs:
Before:
===================== parent bridge window ========================
---------- hotplug bridge window ----------
| fixed BAR | | BAR(I) | | BAR(II) | | BAR(III) | fixed BAR |
^
|
new BAR(IV)
After:
==================== parent bridge window =========================
---------- hotplug bridge window ----------
| fixed BAR | BAR(I) | BAR(II) | BAR(III) | new BAR(IV) | fixed BAR |
This patch is a preparation for future patches with actual implementation,
and for now it just does the following:
- declares the feature;
- defines the bool pci_can_move_bars and bool pci_dev_bar_movable(dev);
- invokes the .rescan_prepare() and .rescan_done() driver notifiers;
- disables the feature for the powerpc/pseries.
The feature is disabled by default until the final patch of the series.
It can be overridden per-arch using the pci_can_move_bars=false flag or by
the following command line option:
pci=no_movable_bars
CC: Sam Bobroff <sbobroff@linux.ibm.com>
CC: Rajat Jain <rajatja@google.com>
CC: Lukas Wunner <lukas@wunner.de>
CC: Oliver O'Halloran <oohall@gmail.com>
CC: David Laight <David.Laight@ACULAB.COM>
Signed-off-by: Sergey Miroshnichenko <s.miroshnichenko@yadro.com>
---
.../admin-guide/kernel-parameters.txt | 1 +
arch/powerpc/platforms/pseries/setup.c | 2 +
drivers/pci/pci.c | 4 +
drivers/pci/pci.h | 2 +
drivers/pci/probe.c | 85 ++++++++++++++++++-
include/linux/pci.h | 4 +
6 files changed, 96 insertions(+), 2 deletions(-)
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index a84a83f8881e..c6243aaed0c9 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -3528,6 +3528,7 @@
may put more devices in an IOMMU group.
force_floating [S390] Force usage of floating interrupts.
nomio [S390] Do not use MIO instructions.
+ no_movable_bars Don't allow BARs to be moved during hotplug
pcie_aspm= [PCIE] Forcibly enable or disable PCIe Active State Power
Management.
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 0a40201f315f..7cd12c5a2deb 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -920,6 +920,8 @@ static void __init pseries_init(void)
{
pr_debug(" -> pseries_init()\n");
+ pci_can_move_bars = false;
+
#ifdef CONFIG_HVC_CONSOLE
if (firmware_has_feature(FW_FEATURE_LPAR))
hvc_vio_init_early();
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index e85dc63c73fd..85014c6b2817 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -78,6 +78,8 @@ static void pci_dev_d3_sleep(struct pci_dev *dev)
int pci_domains_supported = 1;
#endif
+bool pci_can_move_bars;
+
#define DEFAULT_CARDBUS_IO_SIZE (256)
#define DEFAULT_CARDBUS_MEM_SIZE (64*1024*1024)
/* pci=cbmemsize=nnM,cbiosize=nn can override this */
@@ -6331,6 +6333,8 @@ static int __init pci_setup(char *str)
pci_add_flags(PCI_SCAN_ALL_PCIE_DEVS);
} else if (!strncmp(str, "disable_acs_redir=", 18)) {
disable_acs_redir_param = str + 18;
+ } else if (!strncmp(str, "no_movable_bars", 15)) {
+ pci_can_move_bars = false;
} else {
pr_err("PCI: Unknown option `%s'\n", str);
}
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 3f6947ee3324..19bc50597d12 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -286,6 +286,8 @@ void pci_disable_bridge_window(struct pci_dev *dev);
struct pci_bus *pci_bus_get(struct pci_bus *bus);
void pci_bus_put(struct pci_bus *bus);
+bool pci_dev_bar_movable(struct pci_dev *dev, struct resource *res);
+
/* PCIe link information */
#define PCIE_SPEED2STR(speed) \
((speed) == PCIE_SPEED_16_0GT ? "16 GT/s" : \
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index d4f21e413638..3d8c0f653378 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -3133,6 +3133,73 @@ unsigned int pci_rescan_bus_bridge_resize(struct pci_dev *bridge)
return max;
}
+static bool pci_dev_movable(struct pci_dev *dev, bool res_has_children)
+{
+ if (!pci_can_move_bars)
+ return false;
+
+ if (dev->driver && dev->driver->rescan_prepare)
+ return true;
+
+ if (!dev->driver && !res_has_children)
+ return true;
+
+ return false;
+}
+
+bool pci_dev_bar_movable(struct pci_dev *dev, struct resource *res)
+{
+ struct pci_bus_region region;
+
+ if (res->flags & IORESOURCE_PCI_FIXED)
+ return false;
+
+ /* Workaround for the legacy VGA memory 0xa0000-0xbffff */
+ pcibios_resource_to_bus(dev->bus, ®ion, res);
+ if (region.start == 0xa0000)
+ return false;
+
+ return pci_dev_movable(dev, res->child);
+}
+
+static void pci_bus_rescan_prepare(struct pci_bus *bus)
+{
+ struct pci_dev *dev;
+
+ if (bus->self)
+ pci_config_pm_runtime_get(bus->self);
+
+ list_for_each_entry(dev, &bus->devices, bus_list) {
+ struct pci_bus *child = dev->subordinate;
+
+ if (child)
+ pci_bus_rescan_prepare(child);
+
+ if (dev->driver &&
+ dev->driver->rescan_prepare)
+ dev->driver->rescan_prepare(dev);
+ }
+}
+
+static void pci_bus_rescan_done(struct pci_bus *bus)
+{
+ struct pci_dev *dev;
+
+ list_for_each_entry(dev, &bus->devices, bus_list) {
+ struct pci_bus *child = dev->subordinate;
+
+ if (dev->driver &&
+ dev->driver->rescan_done)
+ dev->driver->rescan_done(dev);
+
+ if (child)
+ pci_bus_rescan_done(child);
+ }
+
+ if (bus->self)
+ pci_config_pm_runtime_put(bus->self);
+}
+
/**
* pci_rescan_bus - Scan a PCI bus for devices
* @bus: PCI bus to scan
@@ -3145,9 +3212,23 @@ unsigned int pci_rescan_bus_bridge_resize(struct pci_dev *bridge)
unsigned int pci_rescan_bus(struct pci_bus *bus)
{
unsigned int max;
+ struct pci_bus *root = bus;
+
+ while (!pci_is_root_bus(root))
+ root = root->parent;
+
+ if (pci_can_move_bars) {
+ pci_bus_rescan_prepare(root);
+
+ max = pci_scan_child_bus(root);
+ pci_assign_unassigned_root_bus_resources(root);
+
+ pci_bus_rescan_done(root);
+ } else {
+ max = pci_scan_child_bus(bus);
+ pci_assign_unassigned_bus_resources(bus);
+ }
- max = pci_scan_child_bus(bus);
- pci_assign_unassigned_bus_resources(bus);
pci_bus_add_devices(bus);
return max;
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 525140e3a460..b981e67c8a13 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -835,6 +835,8 @@ struct pci_driver {
int (*resume)(struct pci_dev *dev); /* Device woken up */
void (*shutdown)(struct pci_dev *dev);
int (*sriov_configure)(struct pci_dev *dev, int num_vfs); /* On PF */
+ void (*rescan_prepare)(struct pci_dev *dev);
+ void (*rescan_done)(struct pci_dev *dev);
const struct pci_error_handlers *err_handler;
const struct attribute_group **groups;
struct device_driver driver;
@@ -1395,6 +1397,8 @@ void pci_setup_bridge(struct pci_bus *bus);
resource_size_t pcibios_window_alignment(struct pci_bus *bus,
unsigned long type);
+extern bool pci_can_move_bars;
+
#define PCI_VGA_STATE_CHANGE_BRIDGE (1 << 0)
#define PCI_VGA_STATE_CHANGE_DECODES (1 << 1)
--
2.23.0
^ permalink raw reply related [flat|nested] 35+ messages in thread* [PATCH v6 04/30] PCI: Define PCI-specific version of the release_child_resources()
2019-10-24 17:11 [PATCH v6 00/30] PCI: Allow BAR movement during hotplug Sergey Miroshnichenko
` (2 preceding siblings ...)
2019-10-24 17:12 ` [PATCH v6 03/30] PCI: hotplug: Add a flag for the movable BARs feature Sergey Miroshnichenko
@ 2019-10-24 17:12 ` Sergey Miroshnichenko
2019-10-24 17:12 ` [PATCH v6 05/30] PCI: hotplug: movable BARs: Fix reassigning the released bridge windows Sergey Miroshnichenko
` (25 subsequent siblings)
29 siblings, 0 replies; 35+ messages in thread
From: Sergey Miroshnichenko @ 2019-10-24 17:12 UTC (permalink / raw)
To: linux-pci, linuxppc-dev; +Cc: Bjorn Helgaas, linux, Sergey Miroshnichenko
If release the bridge resources with standard release_child_resources(), it
drops the .start field of children's BARs to zero, but with the STARTALIGN
flag remaining set, which makes the resource invalid for reassignment.
Some resources must preserve their offset and size: those marked with the
PCI_FIXED and the immovable ones - which are bound by drivers without
support of the movable BARs feature.
Add the pci_release_child_resources() to replace release_child_resources()
in handling the described PCI-specific cases.
Signed-off-by: Sergey Miroshnichenko <s.miroshnichenko@yadro.com>
---
drivers/pci/setup-bus.c | 54 ++++++++++++++++++++++++++++++++++++++++-
1 file changed, 53 insertions(+), 1 deletion(-)
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index e7dbe21705ba..2c02eb1acf5d 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -1482,6 +1482,54 @@ static void __pci_bridge_assign_resources(const struct pci_dev *bridge,
(IORESOURCE_IO | IORESOURCE_MEM | IORESOURCE_PREFETCH |\
IORESOURCE_MEM_64)
+/*
+ * Similar to generic release_child_resources(), but aware of immovable BARs and
+ * PCI_FIXED and STARTALIGN flags
+ */
+static void pci_release_child_resources(struct pci_bus *bus, struct resource *r)
+{
+ struct pci_dev *dev;
+
+ if (!bus || !r)
+ return;
+
+ if (r->flags & IORESOURCE_PCI_FIXED)
+ return;
+
+ r->child = NULL;
+
+ list_for_each_entry(dev, &bus->devices, bus_list) {
+ int i;
+
+ for (i = 0; i < PCI_NUM_RESOURCES; i++) {
+ struct resource *tmp = &dev->resource[i];
+ resource_size_t size = resource_size(tmp);
+
+ if (!tmp->flags || tmp->parent != r)
+ continue;
+
+ tmp->parent = NULL;
+ tmp->sibling = NULL;
+
+ pci_release_child_resources(dev->subordinate, tmp);
+
+ tmp->flags &= ~IORESOURCE_STARTALIGN;
+ tmp->flags |= IORESOURCE_SIZEALIGN;
+
+ if (!pci_dev_bar_movable(dev, tmp)) {
+ pci_dbg(dev, "release immovable %pR (%s), keep its flags, base and size\n",
+ tmp, tmp->name);
+ continue;
+ }
+
+ pci_dbg(dev, "release %pR (%s)\n", tmp, tmp->name);
+
+ tmp->start = 0;
+ tmp->end = size - 1;
+ }
+ }
+}
+
static void pci_bridge_release_resources(struct pci_bus *bus,
unsigned long type)
{
@@ -1522,7 +1570,11 @@ static void pci_bridge_release_resources(struct pci_bus *bus,
return;
/* If there are children, release them all */
- release_child_resources(r);
+ if (pci_can_move_bars)
+ pci_release_child_resources(bus, r);
+ else
+ release_child_resources(r);
+
if (!release_resource(r)) {
type = old_flags = r->flags & PCI_RES_TYPE_MASK;
pci_info(dev, "resource %d %pR released\n",
--
2.23.0
^ permalink raw reply related [flat|nested] 35+ messages in thread* [PATCH v6 05/30] PCI: hotplug: movable BARs: Fix reassigning the released bridge windows
2019-10-24 17:11 [PATCH v6 00/30] PCI: Allow BAR movement during hotplug Sergey Miroshnichenko
` (3 preceding siblings ...)
2019-10-24 17:12 ` [PATCH v6 04/30] PCI: Define PCI-specific version of the release_child_resources() Sergey Miroshnichenko
@ 2019-10-24 17:12 ` Sergey Miroshnichenko
2019-10-24 17:12 ` [PATCH v6 06/30] PCI: hotplug: movable BARs: Recalculate all bridge windows during rescan Sergey Miroshnichenko
` (24 subsequent siblings)
29 siblings, 0 replies; 35+ messages in thread
From: Sergey Miroshnichenko @ 2019-10-24 17:12 UTC (permalink / raw)
To: linux-pci, linuxppc-dev; +Cc: Bjorn Helgaas, linux, Sergey Miroshnichenko
When a bridge window is temporarily released during the rescan, its old
size is not relevant anymore - it will be recreated from pbus_size_*(), so
it's start value should be zero.
If such window can't be reassigned, don't apply reset_resource(), so the
next retry may succeed.
Signed-off-by: Sergey Miroshnichenko <s.miroshnichenko@yadro.com>
---
drivers/pci/setup-bus.c | 7 ++++---
1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index 2c02eb1acf5d..f2f02e6c9000 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -295,7 +295,8 @@ static void assign_requested_resources_sorted(struct list_head *head,
0 /* don't care */,
0 /* don't care */);
}
- reset_resource(res);
+ if (!pci_can_move_bars)
+ reset_resource(res);
}
}
}
@@ -1579,8 +1580,8 @@ static void pci_bridge_release_resources(struct pci_bus *bus,
type = old_flags = r->flags & PCI_RES_TYPE_MASK;
pci_info(dev, "resource %d %pR released\n",
PCI_BRIDGE_RESOURCES + idx, r);
- /* Keep the old size */
- r->end = resource_size(r) - 1;
+ /* Don't keep the old size if the bridge will be recalculated */
+ r->end = pci_can_move_bars ? 0 : (resource_size(r) - 1);
r->start = 0;
r->flags = 0;
--
2.23.0
^ permalink raw reply related [flat|nested] 35+ messages in thread* [PATCH v6 06/30] PCI: hotplug: movable BARs: Recalculate all bridge windows during rescan
2019-10-24 17:11 [PATCH v6 00/30] PCI: Allow BAR movement during hotplug Sergey Miroshnichenko
` (4 preceding siblings ...)
2019-10-24 17:12 ` [PATCH v6 05/30] PCI: hotplug: movable BARs: Fix reassigning the released bridge windows Sergey Miroshnichenko
@ 2019-10-24 17:12 ` Sergey Miroshnichenko
2019-10-24 17:12 ` [PATCH v6 07/30] PCI: hotplug: movable BARs: Don't disable the released bridge windows Sergey Miroshnichenko
` (23 subsequent siblings)
29 siblings, 0 replies; 35+ messages in thread
From: Sergey Miroshnichenko @ 2019-10-24 17:12 UTC (permalink / raw)
To: linux-pci, linuxppc-dev; +Cc: Bjorn Helgaas, linux, Sergey Miroshnichenko
When the movable BARs feature is enabled and a rescan has been requested,
release all the bridge windows and recalculate them from scratch, taking
into account all kinds for BARs: fixed, immovable, movable, new.
This increases the chances to find a memory space to fit BARs for newly
hotplugged devices, especially if no/not enough gaps were reserved by the
BIOS/bootloader/firmware.
The last step of writing the recalculated windows to the bridges is done
by the new pci_setup_bridges() function.
Signed-off-by: Sergey Miroshnichenko <s.miroshnichenko@yadro.com>
---
drivers/pci/pci.h | 1 +
drivers/pci/probe.c | 22 ++++++++++++++++++++++
drivers/pci/setup-bus.c | 16 ++++++++++++++++
3 files changed, 39 insertions(+)
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 19bc50597d12..4a3f2b69285b 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -280,6 +280,7 @@ void __pci_bus_assign_resources(const struct pci_bus *bus,
struct list_head *realloc_head,
struct list_head *fail_head);
bool pci_bus_clip_resource(struct pci_dev *dev, int idx);
+void pci_bus_release_root_bridge_resources(struct pci_bus *bus);
void pci_reassigndev_resource_alignment(struct pci_dev *dev);
void pci_disable_bridge_window(struct pci_dev *dev);
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 3d8c0f653378..d2dbec51c4df 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -3200,6 +3200,25 @@ static void pci_bus_rescan_done(struct pci_bus *bus)
pci_config_pm_runtime_put(bus->self);
}
+static void pci_setup_bridges(struct pci_bus *bus)
+{
+ struct pci_dev *dev;
+
+ list_for_each_entry(dev, &bus->devices, bus_list) {
+ struct pci_bus *child;
+
+ if (!pci_dev_is_added(dev))
+ continue;
+
+ child = dev->subordinate;
+ if (child)
+ pci_setup_bridges(child);
+ }
+
+ if (bus->self)
+ pci_setup_bridge(bus);
+}
+
/**
* pci_rescan_bus - Scan a PCI bus for devices
* @bus: PCI bus to scan
@@ -3221,8 +3240,11 @@ unsigned int pci_rescan_bus(struct pci_bus *bus)
pci_bus_rescan_prepare(root);
max = pci_scan_child_bus(root);
+
+ pci_bus_release_root_bridge_resources(root);
pci_assign_unassigned_root_bus_resources(root);
+ pci_setup_bridges(root);
pci_bus_rescan_done(root);
} else {
max = pci_scan_child_bus(bus);
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index f2f02e6c9000..075e8185b936 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -1635,6 +1635,22 @@ static void pci_bus_release_bridge_resources(struct pci_bus *bus,
pci_bridge_release_resources(bus, type);
}
+void pci_bus_release_root_bridge_resources(struct pci_bus *root_bus)
+{
+ int i;
+ struct resource *r;
+
+ pci_bus_release_bridge_resources(root_bus, IORESOURCE_IO, whole_subtree);
+ pci_bus_release_bridge_resources(root_bus, IORESOURCE_MEM, whole_subtree);
+ pci_bus_release_bridge_resources(root_bus,
+ IORESOURCE_MEM_64 | IORESOURCE_PREFETCH,
+ whole_subtree);
+
+ pci_bus_for_each_resource(root_bus, r, i) {
+ pci_release_child_resources(root_bus, r);
+ }
+}
+
static void pci_bus_dump_res(struct pci_bus *bus)
{
struct resource *res;
--
2.23.0
^ permalink raw reply related [flat|nested] 35+ messages in thread* [PATCH v6 07/30] PCI: hotplug: movable BARs: Don't disable the released bridge windows
2019-10-24 17:11 [PATCH v6 00/30] PCI: Allow BAR movement during hotplug Sergey Miroshnichenko
` (5 preceding siblings ...)
2019-10-24 17:12 ` [PATCH v6 06/30] PCI: hotplug: movable BARs: Recalculate all bridge windows during rescan Sergey Miroshnichenko
@ 2019-10-24 17:12 ` Sergey Miroshnichenko
2019-10-24 17:12 ` [PATCH v6 08/30] PCI: hotplug: movable BARs: Don't allow added devices to steal resources Sergey Miroshnichenko
` (22 subsequent siblings)
29 siblings, 0 replies; 35+ messages in thread
From: Sergey Miroshnichenko @ 2019-10-24 17:12 UTC (permalink / raw)
To: linux-pci, linuxppc-dev; +Cc: Bjorn Helgaas, linux, Sergey Miroshnichenko
On a hotplug event with enabled BAR movement, calculating the new bridge
windows takes some time. During this procedure, the structures that
represent these windows are released - marked for recalculation.
When new bridge windows are ready, they are written to the registers of
every bridge via pci_setup_bridges().
Currently, bridge's registers are updated immediately after releasing a
window to disable it. But if a driver doesn't yet support movable BARs, it
doesn't stop MEM transactions during the hotplug, so disabled bridge
windows will break them.
Let the bridge windows remain operating after releasing, as they will be
updated to the new values in the end of a hotplug event.
Signed-off-by: Sergey Miroshnichenko <s.miroshnichenko@yadro.com>
---
drivers/pci/setup-bus.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index 075e8185b936..381ce964cb20 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -1588,7 +1588,8 @@ static void pci_bridge_release_resources(struct pci_bus *bus,
/* Avoiding touch the one without PREF */
if (type & IORESOURCE_PREFETCH)
type = IORESOURCE_PREFETCH;
- __pci_setup_bridge(bus, type);
+ if (!pci_can_move_bars)
+ __pci_setup_bridge(bus, type);
/* For next child res under same bridge */
r->flags = old_flags;
}
--
2.23.0
^ permalink raw reply related [flat|nested] 35+ messages in thread* [PATCH v6 08/30] PCI: hotplug: movable BARs: Don't allow added devices to steal resources
2019-10-24 17:11 [PATCH v6 00/30] PCI: Allow BAR movement during hotplug Sergey Miroshnichenko
` (6 preceding siblings ...)
2019-10-24 17:12 ` [PATCH v6 07/30] PCI: hotplug: movable BARs: Don't disable the released bridge windows Sergey Miroshnichenko
@ 2019-10-24 17:12 ` Sergey Miroshnichenko
2019-10-24 17:12 ` [PATCH v6 09/30] PCI: Include fixed and immovable BARs into the bus size calculating Sergey Miroshnichenko
` (21 subsequent siblings)
29 siblings, 0 replies; 35+ messages in thread
From: Sergey Miroshnichenko @ 2019-10-24 17:12 UTC (permalink / raw)
To: linux-pci, linuxppc-dev; +Cc: Bjorn Helgaas, linux, Sergey Miroshnichenko
When movable BARs are enabled, the PCI subsystem at first releases all the
bridge windows and then attempts to assign resources both to previously
working devices and to the newly hotplugged ones, with the same priority.
If a hotplugged device gets its BARs first, this may lead to lack of space
for already working devices, which is unacceptable. If that happens, mark
one of the new devices with the newly introduced flag PCI_DEV_DISABLED_BARS
(if it is not yet marked) and retry the BAR recalculation.
The worst case would be no BARs for hotplugged devices, while all the rest
just continue working.
The algorithm is simple and it doesn't retry different subsets of hot-added
devices in case of a failure, e.g. if there are no space to allocate BARs
for both hotplugged devices A and B, but is enough for just A, the A will
be marked with PCI_DEV_DISABLED_BARS first, then (after the next failure) -
B. As a result, A will not get BARs while it could. This issue is only
relevant when hotplugging two and more devices simultaneously.
Add a new res_mask bitmask to the struct pci_dev for storing the indices of
assigned BARs.
Signed-off-by: Sergey Miroshnichenko <s.miroshnichenko@yadro.com>
---
drivers/pci/pci.h | 11 +++++
drivers/pci/probe.c | 102 ++++++++++++++++++++++++++++++++++++++--
drivers/pci/setup-bus.c | 15 ++++++
include/linux/pci.h | 1 +
4 files changed, 126 insertions(+), 3 deletions(-)
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 4a3f2b69285b..55344f2c55bf 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -403,6 +403,7 @@ static inline bool pci_dev_is_disconnected(const struct pci_dev *dev)
/* pci_dev priv_flags */
#define PCI_DEV_ADDED 0
+#define PCI_DEV_DISABLED_BARS 1
static inline void pci_dev_assign_added(struct pci_dev *dev, bool added)
{
@@ -414,6 +415,16 @@ static inline bool pci_dev_is_added(const struct pci_dev *dev)
return test_bit(PCI_DEV_ADDED, &dev->priv_flags);
}
+static inline void pci_dev_disable_bars(struct pci_dev *dev)
+{
+ assign_bit(PCI_DEV_DISABLED_BARS, &dev->priv_flags, true);
+}
+
+static inline bool pci_dev_bars_enabled(const struct pci_dev *dev)
+{
+ return !test_bit(PCI_DEV_DISABLED_BARS, &dev->priv_flags);
+}
+
#ifdef CONFIG_PCIEAER
#include <linux/aer.h>
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index d2dbec51c4df..2d1157493e6a 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -3162,6 +3162,23 @@ bool pci_dev_bar_movable(struct pci_dev *dev, struct resource *res)
return pci_dev_movable(dev, res->child);
}
+static unsigned int pci_dev_count_res_mask(struct pci_dev *dev)
+{
+ unsigned int res_mask = 0;
+ int i;
+
+ for (i = 0; i < PCI_BRIDGE_RESOURCES; i++) {
+ struct resource *r = &dev->resource[i];
+
+ if (!r->flags || (r->flags & IORESOURCE_UNSET) || !r->parent)
+ continue;
+
+ res_mask |= (1 << i);
+ }
+
+ return res_mask;
+}
+
static void pci_bus_rescan_prepare(struct pci_bus *bus)
{
struct pci_dev *dev;
@@ -3172,6 +3189,8 @@ static void pci_bus_rescan_prepare(struct pci_bus *bus)
list_for_each_entry(dev, &bus->devices, bus_list) {
struct pci_bus *child = dev->subordinate;
+ dev->res_mask = pci_dev_count_res_mask(dev);
+
if (child)
pci_bus_rescan_prepare(child);
@@ -3207,7 +3226,7 @@ static void pci_setup_bridges(struct pci_bus *bus)
list_for_each_entry(dev, &bus->devices, bus_list) {
struct pci_bus *child;
- if (!pci_dev_is_added(dev))
+ if (!pci_dev_is_added(dev) || !pci_dev_bars_enabled(dev))
continue;
child = dev->subordinate;
@@ -3219,6 +3238,83 @@ static void pci_setup_bridges(struct pci_bus *bus)
pci_setup_bridge(bus);
}
+static struct pci_dev *pci_find_next_new_device(struct pci_bus *bus)
+{
+ struct pci_dev *dev;
+
+ if (!bus)
+ return NULL;
+
+ list_for_each_entry(dev, &bus->devices, bus_list) {
+ struct pci_bus *child_bus = dev->subordinate;
+
+ if (!pci_dev_is_added(dev) && pci_dev_bars_enabled(dev))
+ return dev;
+
+ if (child_bus) {
+ struct pci_dev *next_new_dev;
+
+ next_new_dev = pci_find_next_new_device(child_bus);
+ if (next_new_dev)
+ return next_new_dev;
+ }
+ }
+
+ return NULL;
+}
+
+static bool pci_bus_check_all_bars_reassigned(struct pci_bus *bus)
+{
+ struct pci_dev *dev;
+ bool ret = true;
+
+ if (!bus)
+ return false;
+
+ list_for_each_entry(dev, &bus->devices, bus_list) {
+ struct pci_bus *child = dev->subordinate;
+ unsigned int res_mask = pci_dev_count_res_mask(dev);
+
+ if (!pci_dev_bars_enabled(dev))
+ continue;
+
+ if (dev->res_mask & ~res_mask) {
+ pci_err(dev, "Non-re-enabled resources found: 0x%x -> 0x%x\n",
+ dev->res_mask, res_mask);
+ ret = false;
+ }
+
+ if (child && !pci_bus_check_all_bars_reassigned(child))
+ ret = false;
+ }
+
+ return ret;
+}
+
+static void pci_reassign_root_bus_resources(struct pci_bus *root)
+{
+ do {
+ struct pci_dev *next_new_dev;
+
+ pci_assign_unassigned_root_bus_resources(root);
+
+ if (pci_bus_check_all_bars_reassigned(root))
+ break;
+
+ next_new_dev = pci_find_next_new_device(root);
+ if (!next_new_dev) {
+ dev_err(&root->dev, "failed to re-assign resources even after ignoring all the hotplugged devices\n");
+ break;
+ }
+
+ dev_warn(&root->dev, "failed to re-assign resources, disable the next hotplugged device %s and retry\n",
+ dev_name(&next_new_dev->dev));
+
+ pci_dev_disable_bars(next_new_dev);
+ pci_bus_release_root_bridge_resources(root);
+ } while (true);
+}
+
/**
* pci_rescan_bus - Scan a PCI bus for devices
* @bus: PCI bus to scan
@@ -3238,11 +3334,11 @@ unsigned int pci_rescan_bus(struct pci_bus *bus)
if (pci_can_move_bars) {
pci_bus_rescan_prepare(root);
+ pci_bus_release_root_bridge_resources(root);
max = pci_scan_child_bus(root);
- pci_bus_release_root_bridge_resources(root);
- pci_assign_unassigned_root_bus_resources(root);
+ pci_reassign_root_bus_resources(root);
pci_setup_bridges(root);
pci_bus_rescan_done(root);
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index 381ce964cb20..4b538d132958 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -128,6 +128,9 @@ static void pdev_sort_resources(struct pci_dev *dev, struct list_head *head)
{
int i;
+ if (!pci_dev_bars_enabled(dev))
+ return;
+
for (i = 0; i < PCI_NUM_RESOURCES; i++) {
struct resource *r;
struct pci_dev_resource *dev_res, *tmp;
@@ -177,6 +180,9 @@ static void __dev_sort_resources(struct pci_dev *dev, struct list_head *head)
{
u16 class = dev->class >> 8;
+ if (!pci_dev_bars_enabled(dev))
+ return;
+
/* Don't touch classless devices or host bridges or IOAPICs */
if (class == PCI_CLASS_NOT_DEFINED || class == PCI_CLASS_BRIDGE_HOST)
return;
@@ -278,6 +284,9 @@ static void assign_requested_resources_sorted(struct list_head *head,
int idx;
list_for_each_entry(dev_res, head, list) {
+ if (!pci_dev_bars_enabled(dev_res->dev))
+ continue;
+
res = dev_res->res;
idx = res - &dev_res->dev->resource[0];
if (resource_size(res) &&
@@ -995,6 +1004,9 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask,
list_for_each_entry(dev, &bus->devices, bus_list) {
int i;
+ if (!pci_dev_bars_enabled(dev))
+ continue;
+
for (i = 0; i < PCI_NUM_RESOURCES; i++) {
struct resource *r = &dev->resource[i];
resource_size_t r_size;
@@ -1349,6 +1361,9 @@ void __pci_bus_assign_resources(const struct pci_bus *bus,
pbus_assign_resources_sorted(bus, realloc_head, fail_head);
list_for_each_entry(dev, &bus->devices, bus_list) {
+ if (!pci_dev_bars_enabled(dev))
+ continue;
+
pdev_assign_fixed_resources(dev);
b = dev->subordinate;
diff --git a/include/linux/pci.h b/include/linux/pci.h
index b981e67c8a13..7f7f704df672 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -376,6 +376,7 @@ struct pci_dev {
*/
unsigned int irq;
struct resource resource[DEVICE_COUNT_RESOURCE]; /* I/O and memory regions + expansion ROMs */
+ unsigned int res_mask; /* Bitmask of assigned resources */
bool match_driver; /* Skip attaching driver */
--
2.23.0
^ permalink raw reply related [flat|nested] 35+ messages in thread* [PATCH v6 09/30] PCI: Include fixed and immovable BARs into the bus size calculating
2019-10-24 17:11 [PATCH v6 00/30] PCI: Allow BAR movement during hotplug Sergey Miroshnichenko
` (7 preceding siblings ...)
2019-10-24 17:12 ` [PATCH v6 08/30] PCI: hotplug: movable BARs: Don't allow added devices to steal resources Sergey Miroshnichenko
@ 2019-10-24 17:12 ` Sergey Miroshnichenko
2019-10-24 17:12 ` [PATCH v6 10/30] PCI: Prohibit assigning BARs and bridge windows to non-direct parents Sergey Miroshnichenko
` (20 subsequent siblings)
29 siblings, 0 replies; 35+ messages in thread
From: Sergey Miroshnichenko @ 2019-10-24 17:12 UTC (permalink / raw)
To: linux-pci, linuxppc-dev; +Cc: Bjorn Helgaas, linux, Sergey Miroshnichenko
The only difference between the fixed/immovable and movable BARs is a size
and offset preservation after they are released (the corresponding struct
resource* detached from a bridge window for a while during a bus rescan).
Include fixed/immovable BARs into result of pbus_size_mem() and prohibit
assigning them to non-direct parents.
Signed-off-by: Sergey Miroshnichenko <s.miroshnichenko@yadro.com>
---
drivers/pci/setup-bus.c | 10 +++++++++-
1 file changed, 9 insertions(+), 1 deletion(-)
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index 4b538d132958..ff33b47b1bb7 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -1011,12 +1011,20 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask,
struct resource *r = &dev->resource[i];
resource_size_t r_size;
- if (r->parent || (r->flags & IORESOURCE_PCI_FIXED) ||
+ if (r->parent ||
((r->flags & mask) != type &&
(r->flags & mask) != type2 &&
(r->flags & mask) != type3))
continue;
r_size = resource_size(r);
+
+ if (!pci_dev_bar_movable(dev, r)) {
+ if (pci_can_move_bars)
+ size += r_size;
+
+ continue;
+ }
+
#ifdef CONFIG_PCI_IOV
/* Put SRIOV requested res to the optional list */
if (realloc_head && i >= PCI_IOV_RESOURCES &&
--
2.23.0
^ permalink raw reply related [flat|nested] 35+ messages in thread* [PATCH v6 10/30] PCI: Prohibit assigning BARs and bridge windows to non-direct parents
2019-10-24 17:11 [PATCH v6 00/30] PCI: Allow BAR movement during hotplug Sergey Miroshnichenko
` (8 preceding siblings ...)
2019-10-24 17:12 ` [PATCH v6 09/30] PCI: Include fixed and immovable BARs into the bus size calculating Sergey Miroshnichenko
@ 2019-10-24 17:12 ` Sergey Miroshnichenko
2019-10-24 17:12 ` [PATCH v6 11/30] PCI: hotplug: movable BARs: Try to assign unassigned resources only once Sergey Miroshnichenko
` (19 subsequent siblings)
29 siblings, 0 replies; 35+ messages in thread
From: Sergey Miroshnichenko @ 2019-10-24 17:12 UTC (permalink / raw)
To: linux-pci, linuxppc-dev; +Cc: Bjorn Helgaas, linux, Sergey Miroshnichenko
When movable BARs are enabled, the feature of resource relocating from
commit 2bbc6942273b5 ("PCI : ability to relocate assigned pci-resources")
is not used. Instead, inability to assign a resource is used as a signal
to retry BAR assignment with other configuration of bridge windows.
Signed-off-by: Sergey Miroshnichenko <s.miroshnichenko@yadro.com>
---
drivers/pci/setup-bus.c | 2 ++
drivers/pci/setup-res.c | 12 ++++++++++++
2 files changed, 14 insertions(+)
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index ff33b47b1bb7..cf325daae1b1 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -1355,6 +1355,8 @@ static void pdev_assign_fixed_resources(struct pci_dev *dev)
while (b && !r->parent) {
assign_fixed_resource_on_bus(b, r);
b = b->parent;
+ if (!r->parent && pci_can_move_bars)
+ break;
}
}
}
diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c
index d8ca40a97693..a1657a8bf93d 100644
--- a/drivers/pci/setup-res.c
+++ b/drivers/pci/setup-res.c
@@ -298,6 +298,18 @@ static int _pci_assign_resource(struct pci_dev *dev, int resno,
bus = dev->bus;
while ((ret = __pci_assign_resource(bus, dev, resno, size, min_align))) {
+ if (pci_can_move_bars) {
+ if (resno >= PCI_BRIDGE_RESOURCES &&
+ resno <= PCI_BRIDGE_RESOURCE_END) {
+ struct resource *res = dev->resource + resno;
+
+ res->start = 0;
+ res->end = 0;
+ res->flags = 0;
+ }
+ break;
+ }
+
if (!bus->parent || !bus->self->transparent)
break;
bus = bus->parent;
--
2.23.0
^ permalink raw reply related [flat|nested] 35+ messages in thread* [PATCH v6 11/30] PCI: hotplug: movable BARs: Try to assign unassigned resources only once
2019-10-24 17:11 [PATCH v6 00/30] PCI: Allow BAR movement during hotplug Sergey Miroshnichenko
` (9 preceding siblings ...)
2019-10-24 17:12 ` [PATCH v6 10/30] PCI: Prohibit assigning BARs and bridge windows to non-direct parents Sergey Miroshnichenko
@ 2019-10-24 17:12 ` Sergey Miroshnichenko
2019-10-24 17:12 ` [PATCH v6 12/30] PCI: hotplug: movable BARs: Calculate immovable parts of bridge windows Sergey Miroshnichenko
` (18 subsequent siblings)
29 siblings, 0 replies; 35+ messages in thread
From: Sergey Miroshnichenko @ 2019-10-24 17:12 UTC (permalink / raw)
To: linux-pci, linuxppc-dev; +Cc: Bjorn Helgaas, linux, Sergey Miroshnichenko
With enabled BAR movement, BARs and bridge windows can only be assigned to
their direct parents, so there can be only one variant of resource tree,
thus every retry within the pci_assign_unassigned_root_bus_resources() will
result in the same tree, and it is enough to try just once.
In case of failures the pci_reassign_root_bus_resources() disables BARs for
one of the hotplugged devices and tries the assignment again.
Signed-off-by: Sergey Miroshnichenko <s.miroshnichenko@yadro.com>
---
drivers/pci/setup-bus.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index cf325daae1b1..3deb1c343e89 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -1819,6 +1819,13 @@ void pci_assign_unassigned_root_bus_resources(struct pci_bus *bus)
int pci_try_num = 1;
enum enable_type enable_local;
+ if (pci_can_move_bars) {
+ __pci_bus_size_bridges(bus, NULL);
+ __pci_bus_assign_resources(bus, NULL, NULL);
+
+ goto dump;
+ }
+
/* Don't realloc if asked to do so */
enable_local = pci_realloc_detect(bus, pci_realloc_enable);
if (pci_realloc_enabled(enable_local)) {
--
2.23.0
^ permalink raw reply related [flat|nested] 35+ messages in thread* [PATCH v6 12/30] PCI: hotplug: movable BARs: Calculate immovable parts of bridge windows
2019-10-24 17:11 [PATCH v6 00/30] PCI: Allow BAR movement during hotplug Sergey Miroshnichenko
` (10 preceding siblings ...)
2019-10-24 17:12 ` [PATCH v6 11/30] PCI: hotplug: movable BARs: Try to assign unassigned resources only once Sergey Miroshnichenko
@ 2019-10-24 17:12 ` Sergey Miroshnichenko
2019-10-24 17:12 ` [PATCH v6 13/30] PCI: hotplug: movable BARs: Compute limits for relocated " Sergey Miroshnichenko
` (17 subsequent siblings)
29 siblings, 0 replies; 35+ messages in thread
From: Sergey Miroshnichenko @ 2019-10-24 17:12 UTC (permalink / raw)
To: linux-pci, linuxppc-dev; +Cc: Bjorn Helgaas, linux, Sergey Miroshnichenko
When movable BARs are enabled, and if a bridge contains a device with fixed
(IORESOURCE_PCI_FIXED) or immovable BARs, the corresponing windows can't be
moved too far away from their original positions - they must still contain
all the fixed/immovable BARs, like that:
1) Window position before a bus rescan:
| <-- root bridge window --> |
| |
| | <-- bridge window --> | |
| | movable BARs | **fixed BAR** | |
2) Possible valid outcome after rescan and move:
| <-- root bridge window --> |
| |
| | <-- bridge window --> | |
| | **fixed BAR** | Movable BARs | |
An immovable area of a bridge (separare for IO, MEM and MEM64 window types)
is a range that covers all the fixed and immovable BARs of direct children,
and all the fixed area of children bridges:
| <-- root bridge window --> |
| |
| | <-- bridge window level 1 --> | |
| | ******** immovable area of this bridge window ******** | |
| | | |
| | **fixed BAR** | <-- bridge window level 2 --> | BARs | |
| | | ***** fixed area of this bridge ***** | | |
| | | | | |
| | | ***fixed BAR*** | | ***fixed BAR*** | | |
To store these areas, the .immovable_range field has been added to struct
pci_bus. It is filled recursively from leaves to the root before a rescan.
Also make pbus_size_io() and pbus_size_mem() return their usual result OR
the size of an immovable range of according type, depending on which one is
larger.
Signed-off-by: Sergey Miroshnichenko <s.miroshnichenko@yadro.com>
---
drivers/pci/pci.h | 14 +++++++
drivers/pci/probe.c | 88 +++++++++++++++++++++++++++++++++++++++++
drivers/pci/setup-bus.c | 17 ++++++++
include/linux/pci.h | 6 +++
4 files changed, 125 insertions(+)
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 55344f2c55bf..7cd108885598 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -401,6 +401,20 @@ static inline bool pci_dev_is_disconnected(const struct pci_dev *dev)
return dev->error_state == pci_channel_io_perm_failure;
}
+static inline int pci_get_bridge_resource_idx(struct resource *r)
+{
+ int idx = 1;
+
+ if (r->flags & IORESOURCE_IO)
+ idx = 0;
+ else if (!(r->flags & IORESOURCE_PREFETCH))
+ idx = 1;
+ else if (r->flags & IORESOURCE_MEM_64)
+ idx = 2;
+
+ return idx;
+}
+
/* pci_dev priv_flags */
#define PCI_DEV_ADDED 0
#define PCI_DEV_DISABLED_BARS 1
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 2d1157493e6a..d0d00cb3e965 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -545,6 +545,7 @@ void pci_read_bridge_bases(struct pci_bus *child)
static struct pci_bus *pci_alloc_bus(struct pci_bus *parent)
{
struct pci_bus *b;
+ int idx;
b = kzalloc(sizeof(*b), GFP_KERNEL);
if (!b)
@@ -561,6 +562,11 @@ static struct pci_bus *pci_alloc_bus(struct pci_bus *parent)
if (parent)
b->domain_nr = parent->domain_nr;
#endif
+ for (idx = 0; idx < PCI_BRIDGE_RESOURCE_NUM; ++idx) {
+ b->immovable_range[idx].start = 0;
+ b->immovable_range[idx].end = 0;
+ }
+
return b;
}
@@ -3238,6 +3244,87 @@ static void pci_setup_bridges(struct pci_bus *bus)
pci_setup_bridge(bus);
}
+static void pci_bus_update_immovable_range(struct pci_bus *bus)
+{
+ struct pci_dev *dev;
+ int idx;
+ resource_size_t start, end;
+
+ for (idx = 0; idx < PCI_BRIDGE_RESOURCE_NUM; ++idx) {
+ bus->immovable_range[idx].start = 0;
+ bus->immovable_range[idx].end = 0;
+ }
+
+ list_for_each_entry(dev, &bus->devices, bus_list)
+ if (dev->subordinate)
+ pci_bus_update_immovable_range(dev->subordinate);
+
+ list_for_each_entry(dev, &bus->devices, bus_list) {
+ int i;
+ struct pci_bus *child = dev->subordinate;
+
+ for (i = 0; i < PCI_BRIDGE_RESOURCES; ++i) {
+ struct resource *r = &dev->resource[i];
+
+ if (!r->flags || (r->flags & IORESOURCE_UNSET) || !r->parent)
+ continue;
+
+ if (!pci_dev_bar_movable(dev, r)) {
+ idx = pci_get_bridge_resource_idx(r);
+ start = bus->immovable_range[idx].start;
+ end = bus->immovable_range[idx].end;
+
+ if (!start || start > r->start)
+ start = r->start;
+ if (end < r->end)
+ end = r->end;
+
+ if (bus->immovable_range[idx].start != start ||
+ bus->immovable_range[idx].end != end) {
+ dev_dbg(&bus->dev, "Found fixed BAR%d 0x%llx-0x%llx in %s, expand the fixed bridge window %d to 0x%llx-0x%llx\n",
+ i,
+ (unsigned long long)r->start,
+ (unsigned long long)r->end,
+ dev_name(&dev->dev), idx,
+ (unsigned long long)start,
+ (unsigned long long)end);
+ bus->immovable_range[idx].start = start;
+ bus->immovable_range[idx].end = end;
+ }
+ }
+ }
+
+ if (child) {
+ for (idx = 0; idx < PCI_BRIDGE_RESOURCE_NUM; ++idx) {
+ struct resource *child_immovable_range =
+ &child->immovable_range[idx];
+
+ if (child_immovable_range->start >=
+ child_immovable_range->end)
+ continue;
+
+ start = bus->immovable_range[idx].start;
+ end = bus->immovable_range[idx].end;
+
+ if (!start || start > child_immovable_range->start)
+ start = child_immovable_range->start;
+ if (end < child_immovable_range->end)
+ end = child_immovable_range->end;
+
+ if (start < bus->immovable_range[idx].start ||
+ end > bus->immovable_range[idx].end) {
+ dev_dbg(&bus->dev, "Expand the fixed bridge window %d from %s to 0x%llx-0x%llx\n",
+ idx, dev_name(&child->dev),
+ (unsigned long long)start,
+ (unsigned long long)end);
+ bus->immovable_range[idx].start = start;
+ bus->immovable_range[idx].end = end;
+ }
+ }
+ }
+ }
+}
+
static struct pci_dev *pci_find_next_new_device(struct pci_bus *bus)
{
struct pci_dev *dev;
@@ -3334,6 +3421,7 @@ unsigned int pci_rescan_bus(struct pci_bus *bus)
if (pci_can_move_bars) {
pci_bus_rescan_prepare(root);
+ pci_bus_update_immovable_range(root);
pci_bus_release_root_bridge_resources(root);
max = pci_scan_child_bus(root);
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index 3deb1c343e89..a7546e02ea7c 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -882,9 +882,17 @@ static void pbus_size_io(struct pci_bus *bus, resource_size_t min_size,
resource_size_t children_add_size = 0;
resource_size_t min_align, align;
+ resource_size_t fixed_start = bus->immovable_range[0].start;
+ resource_size_t fixed_end = bus->immovable_range[0].end;
+ resource_size_t fixed_size = (fixed_start < fixed_end) ?
+ (fixed_end - fixed_start + 1) : 0;
+
if (!b_res)
return;
+ if (min_size < fixed_size)
+ min_size = fixed_size;
+
min_align = window_alignment(bus, IORESOURCE_IO);
list_for_each_entry(dev, &bus->devices, bus_list) {
int i;
@@ -993,6 +1001,15 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask,
resource_size_t children_add_size = 0;
resource_size_t children_add_align = 0;
resource_size_t add_align = 0;
+ bool is_mem64 = (mask & IORESOURCE_MEM_64);
+
+ resource_size_t fixed_start = bus->immovable_range[is_mem64 ? 2 : 1].start;
+ resource_size_t fixed_end = bus->immovable_range[is_mem64 ? 2 : 1].end;
+ resource_size_t fixed_size = (fixed_start < fixed_end) ?
+ (fixed_end - fixed_start + 1) : 0;
+
+ if (min_size < fixed_size)
+ min_size = fixed_size;
if (!b_res)
return -ENOSPC;
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 7f7f704df672..ef41be0ce082 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -581,6 +581,12 @@ struct pci_bus {
struct list_head resources; /* Address space routed to this bus */
struct resource busn_res; /* Bus numbers routed to this bus */
+ /*
+ * If there are fixed or immovable resources in the bridge window, this range
+ * contains the lowest start address and highest end address of them.
+ */
+ struct resource immovable_range[PCI_BRIDGE_RESOURCE_NUM];
+
struct pci_ops *ops; /* Configuration access functions */
struct msi_controller *msi; /* MSI controller */
void *sysdata; /* Hook for sys-specific extension */
--
2.23.0
^ permalink raw reply related [flat|nested] 35+ messages in thread* [PATCH v6 13/30] PCI: hotplug: movable BARs: Compute limits for relocated bridge windows
2019-10-24 17:11 [PATCH v6 00/30] PCI: Allow BAR movement during hotplug Sergey Miroshnichenko
` (11 preceding siblings ...)
2019-10-24 17:12 ` [PATCH v6 12/30] PCI: hotplug: movable BARs: Calculate immovable parts of bridge windows Sergey Miroshnichenko
@ 2019-10-24 17:12 ` Sergey Miroshnichenko
2019-10-24 17:12 ` [PATCH v6 14/30] PCI: Make sure bridge windows include their fixed BARs Sergey Miroshnichenko
` (16 subsequent siblings)
29 siblings, 0 replies; 35+ messages in thread
From: Sergey Miroshnichenko @ 2019-10-24 17:12 UTC (permalink / raw)
To: linux-pci, linuxppc-dev; +Cc: Bjorn Helgaas, linux, Sergey Miroshnichenko
With enabled movable BARs, bridge windows are recalculated during each pci
rescan. Some of the BARs below the bridge may be fixed/immovable: these
areas are represented by the .immovable_range field in struct pci_bus.
If a bridge window size is equal to its immovable range, it can only be
assigned to the start of this range. But if a bridge window size is larger,
and this difference in size is denoted as "delta", the window can start
from (immovable_range.start - delta) to (immovable_range.start), and it can
end from (immovable_range.end) to (immovable_range.end + delta). This range
(the new .realloc_range field in struct pci_bus) must then be compared with
immovable ranges of neighbouring bridges to guarantee no intersections.
This patch only calculates valid ranges for reallocated bridges during pci
rescan, and the next one will make use of these values during allocation.
Signed-off-by: Sergey Miroshnichenko <s.miroshnichenko@yadro.com>
---
drivers/pci/setup-bus.c | 67 +++++++++++++++++++++++++++++++++++++++++
include/linux/pci.h | 6 ++++
2 files changed, 73 insertions(+)
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index a7546e02ea7c..653ba4d5f191 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -1819,6 +1819,72 @@ static enum enable_type pci_realloc_detect(struct pci_bus *bus,
}
#endif
+/*
+ * Calculate the address margins where the bridge windows may be allocated to fit all
+ * the fixed and immovable BARs beneath.
+ */
+static void pci_bus_update_realloc_range(struct pci_bus *bus)
+{
+ struct pci_dev *dev;
+ struct pci_bus *parent = bus->parent;
+ int idx;
+
+ list_for_each_entry(dev, &bus->devices, bus_list)
+ if (dev->subordinate)
+ pci_bus_update_realloc_range(dev->subordinate);
+
+ if (!parent || !bus->self)
+ return;
+
+ for (idx = 0; idx < PCI_BRIDGE_RESOURCE_NUM; ++idx) {
+ struct resource *immovable_range = &bus->immovable_range[idx];
+ resource_size_t window_size = resource_size(bus->resource[idx]);
+ resource_size_t realloc_start, realloc_end;
+
+ bus->realloc_range[idx].start = 0;
+ bus->realloc_range[idx].end = 0;
+
+ /* Check if there any immovable BARs under the bridge */
+ if (immovable_range->start >= immovable_range->end)
+ continue;
+
+ /* The lowest possible address where the bridge window can start */
+ realloc_start = immovable_range->end - window_size + 1;
+ /* The highest possible address where the bridge window can end */
+ realloc_end = immovable_range->start + window_size - 1;
+
+ if (realloc_start > immovable_range->start)
+ realloc_start = immovable_range->start;
+
+ if (realloc_end < immovable_range->end)
+ realloc_end = immovable_range->end;
+
+ /*
+ * Check that realloc range doesn't intersect with hard fixed ranges
+ * of neighboring bridges
+ */
+ list_for_each_entry(dev, &parent->devices, bus_list) {
+ struct pci_bus *neighbor = dev->subordinate;
+ struct resource *n_imm_range;
+
+ if (!neighbor || neighbor == bus)
+ continue;
+
+ n_imm_range = &neighbor->immovable_range[idx];
+
+ if (n_imm_range->start >= n_imm_range->end)
+ continue;
+
+ if (n_imm_range->end < immovable_range->start &&
+ n_imm_range->end > realloc_start)
+ realloc_start = n_imm_range->end;
+ }
+
+ bus->realloc_range[idx].start = realloc_start;
+ bus->realloc_range[idx].end = realloc_end;
+ }
+}
+
/*
* First try will not touch PCI bridge res.
* Second and later try will clear small leaf bridge res.
@@ -1838,6 +1904,7 @@ void pci_assign_unassigned_root_bus_resources(struct pci_bus *bus)
if (pci_can_move_bars) {
__pci_bus_size_bridges(bus, NULL);
+ pci_bus_update_realloc_range(bus);
__pci_bus_assign_resources(bus, NULL, NULL);
goto dump;
diff --git a/include/linux/pci.h b/include/linux/pci.h
index ef41be0ce082..e1edcb3fad31 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -587,6 +587,12 @@ struct pci_bus {
*/
struct resource immovable_range[PCI_BRIDGE_RESOURCE_NUM];
+ /*
+ * Acceptable address range, where the bridge window may reside, considering its
+ * size, so it will cover all the fixed and immovable BARs below.
+ */
+ struct resource realloc_range[PCI_BRIDGE_RESOURCE_NUM];
+
struct pci_ops *ops; /* Configuration access functions */
struct msi_controller *msi; /* MSI controller */
void *sysdata; /* Hook for sys-specific extension */
--
2.23.0
^ permalink raw reply related [flat|nested] 35+ messages in thread* [PATCH v6 14/30] PCI: Make sure bridge windows include their fixed BARs
2019-10-24 17:11 [PATCH v6 00/30] PCI: Allow BAR movement during hotplug Sergey Miroshnichenko
` (12 preceding siblings ...)
2019-10-24 17:12 ` [PATCH v6 13/30] PCI: hotplug: movable BARs: Compute limits for relocated " Sergey Miroshnichenko
@ 2019-10-24 17:12 ` Sergey Miroshnichenko
2019-10-24 17:12 ` [PATCH v6 15/30] PCI: Fix assigning the fixed prefetchable resources Sergey Miroshnichenko
` (15 subsequent siblings)
29 siblings, 0 replies; 35+ messages in thread
From: Sergey Miroshnichenko @ 2019-10-24 17:12 UTC (permalink / raw)
To: linux-pci, linuxppc-dev; +Cc: Bjorn Helgaas, linux, Sergey Miroshnichenko
When the time comes to select a start address for the bridge window during
the root bus rescan, it should be not just a lowest possible address: this
window must cover all the underlying fixed and immovable BARs. The lowest
address that satisfies this requirement is the .realloc_range field of
struct pci_bus, which is calculated during the preparation to the rescan.
Signed-off-by: Sergey Miroshnichenko <s.miroshnichenko@yadro.com>
---
drivers/pci/bus.c | 2 +-
drivers/pci/setup-res.c | 31 +++++++++++++++++++++++++++++--
2 files changed, 30 insertions(+), 3 deletions(-)
diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index 8e40b3e6da77..a1efa87e31b9 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -192,7 +192,7 @@ static int pci_bus_alloc_from_region(struct pci_bus *bus, struct resource *res,
* this is an already-configured bridge window, its start
* overrides "min".
*/
- if (avail.start)
+ if (min_used < avail.start)
min_used = avail.start;
max = avail.end;
diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c
index a1657a8bf93d..1570bbd620cd 100644
--- a/drivers/pci/setup-res.c
+++ b/drivers/pci/setup-res.c
@@ -248,9 +248,23 @@ static int __pci_assign_resource(struct pci_bus *bus, struct pci_dev *dev,
struct resource *res = dev->resource + resno;
resource_size_t min;
int ret;
+ resource_size_t start = (resource_size_t)-1;
+ resource_size_t end = 0;
min = (res->flags & IORESOURCE_IO) ? PCIBIOS_MIN_IO : PCIBIOS_MIN_MEM;
+ if (dev->subordinate && resno >= PCI_BRIDGE_RESOURCES) {
+ struct pci_bus *child_bus = dev->subordinate;
+ int b_resno = resno - PCI_BRIDGE_RESOURCES;
+ struct resource *immovable_range = &child_bus->immovable_range[b_resno];
+
+ if (immovable_range->start < immovable_range->end) {
+ start = immovable_range->start;
+ end = immovable_range->end;
+ min = child_bus->realloc_range[b_resno].start;
+ }
+ }
+
/*
* First, try exact prefetching match. Even if a 64-bit
* prefetchable bridge window is below 4GB, we can't put a 32-bit
@@ -262,7 +276,7 @@ static int __pci_assign_resource(struct pci_bus *bus, struct pci_dev *dev,
IORESOURCE_PREFETCH | IORESOURCE_MEM_64,
pcibios_align_resource, dev);
if (ret == 0)
- return 0;
+ goto check_fixed;
/*
* If the prefetchable window is only 32 bits wide, we can put
@@ -274,7 +288,7 @@ static int __pci_assign_resource(struct pci_bus *bus, struct pci_dev *dev,
IORESOURCE_PREFETCH,
pcibios_align_resource, dev);
if (ret == 0)
- return 0;
+ goto check_fixed;
}
/*
@@ -287,6 +301,19 @@ static int __pci_assign_resource(struct pci_bus *bus, struct pci_dev *dev,
ret = pci_bus_alloc_resource(bus, res, size, align, min, 0,
pcibios_align_resource, dev);
+check_fixed:
+ if (ret == 0 && start < end) {
+ if (res->start > start || res->end < end) {
+ dev_err(&bus->dev, "fixed area 0x%llx-0x%llx for %s doesn't fit in the allocated %pR (0x%llx-0x%llx)",
+ (unsigned long long)start, (unsigned long long)end,
+ dev_name(&dev->dev),
+ res, (unsigned long long)res->start,
+ (unsigned long long)res->end);
+ release_resource(res);
+ return -1;
+ }
+ }
+
return ret;
}
--
2.23.0
^ permalink raw reply related [flat|nested] 35+ messages in thread* [PATCH v6 15/30] PCI: Fix assigning the fixed prefetchable resources
2019-10-24 17:11 [PATCH v6 00/30] PCI: Allow BAR movement during hotplug Sergey Miroshnichenko
` (13 preceding siblings ...)
2019-10-24 17:12 ` [PATCH v6 14/30] PCI: Make sure bridge windows include their fixed BARs Sergey Miroshnichenko
@ 2019-10-24 17:12 ` Sergey Miroshnichenko
2019-10-24 17:12 ` [PATCH v6 16/30] PCI: hotplug: movable BARs: Assign fixed and immovable BARs before others Sergey Miroshnichenko
` (14 subsequent siblings)
29 siblings, 0 replies; 35+ messages in thread
From: Sergey Miroshnichenko @ 2019-10-24 17:12 UTC (permalink / raw)
To: linux-pci, linuxppc-dev; +Cc: Bjorn Helgaas, linux, Sergey Miroshnichenko
Allow matching IORESOURCE_PCI_FIXED prefetchable BARs to non-prefetchable
windows, so they follow the same rules as immovable BARs.
Signed-off-by: Sergey Miroshnichenko <s.miroshnichenko@yadro.com>
---
drivers/pci/setup-bus.c | 13 +++++++++----
1 file changed, 9 insertions(+), 4 deletions(-)
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index 653ba4d5f191..c7365998fbd6 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -1339,15 +1339,20 @@ static void assign_fixed_resource_on_bus(struct pci_bus *b, struct resource *r)
{
int i;
struct resource *parent_r;
- unsigned long mask = IORESOURCE_IO | IORESOURCE_MEM |
- IORESOURCE_PREFETCH;
+ unsigned long mask = IORESOURCE_TYPE_BITS;
pci_bus_for_each_resource(b, parent_r, i) {
if (!parent_r)
continue;
- if ((r->flags & mask) == (parent_r->flags & mask) &&
- resource_contains(parent_r, r))
+ if ((r->flags & mask) != (parent_r->flags & mask))
+ continue;
+
+ if (parent_r->flags & IORESOURCE_PREFETCH &&
+ !(r->flags & IORESOURCE_PREFETCH))
+ continue;
+
+ if (resource_contains(parent_r, r))
request_resource(parent_r, r);
}
}
--
2.23.0
^ permalink raw reply related [flat|nested] 35+ messages in thread* [PATCH v6 16/30] PCI: hotplug: movable BARs: Assign fixed and immovable BARs before others
2019-10-24 17:11 [PATCH v6 00/30] PCI: Allow BAR movement during hotplug Sergey Miroshnichenko
` (14 preceding siblings ...)
2019-10-24 17:12 ` [PATCH v6 15/30] PCI: Fix assigning the fixed prefetchable resources Sergey Miroshnichenko
@ 2019-10-24 17:12 ` Sergey Miroshnichenko
2019-10-24 17:12 ` [PATCH v6 17/30] PCI: hotplug: movable BARs: Don't reserve IO/mem bus space Sergey Miroshnichenko
` (13 subsequent siblings)
29 siblings, 0 replies; 35+ messages in thread
From: Sergey Miroshnichenko @ 2019-10-24 17:12 UTC (permalink / raw)
To: linux-pci, linuxppc-dev; +Cc: Bjorn Helgaas, linux, Sergey Miroshnichenko
Reassign resources during rescan in two steps: first the fixed/immovable
BARs and bridge windows that have fixed areas, so the movable ones will not
steal these reserved areas; then the rest - so the movable BARs will divide
the rest of the space.
With this change, pci_assign_resource() is now able to assign all types of
BARs, so the pdev_assign_fixed_resources() became unused and thus removed.
Signed-off-by: Sergey Miroshnichenko <s.miroshnichenko@yadro.com>
---
drivers/pci/pci.h | 2 ++
drivers/pci/setup-bus.c | 78 ++++++++++++++++++++++++-----------------
drivers/pci/setup-res.c | 7 ++--
3 files changed, 53 insertions(+), 34 deletions(-)
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 7cd108885598..9b5164d10499 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -289,6 +289,8 @@ void pci_bus_put(struct pci_bus *bus);
bool pci_dev_bar_movable(struct pci_dev *dev, struct resource *res);
+int assign_fixed_resource_on_bus(struct pci_bus *b, struct resource *r);
+
/* PCIe link information */
#define PCIE_SPEED2STR(speed) \
((speed) == PCIE_SPEED_16_0GT ? "16 GT/s" : \
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index c7365998fbd6..675a612236d7 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -38,6 +38,15 @@ struct pci_dev_resource {
unsigned long flags;
};
+enum assign_step {
+ assign_fixed_resources,
+ assign_float_resources,
+};
+
+static void _assign_requested_resources_sorted(struct list_head *head,
+ struct list_head *fail_head,
+ enum assign_step step);
+
static void free_list(struct list_head *head)
{
struct pci_dev_resource *dev_res, *tmp;
@@ -278,19 +287,47 @@ static void reassign_resources_sorted(struct list_head *realloc_head,
*/
static void assign_requested_resources_sorted(struct list_head *head,
struct list_head *fail_head)
+{
+ _assign_requested_resources_sorted(head, fail_head, assign_fixed_resources);
+ _assign_requested_resources_sorted(head, fail_head, assign_float_resources);
+}
+
+static void _assign_requested_resources_sorted(struct list_head *head,
+ struct list_head *fail_head,
+ enum assign_step step)
{
struct resource *res;
struct pci_dev_resource *dev_res;
int idx;
list_for_each_entry(dev_res, head, list) {
+ bool is_fixed = false;
+
if (!pci_dev_bars_enabled(dev_res->dev))
continue;
res = dev_res->res;
+ if (!resource_size(res))
+ continue;
+
idx = res - &dev_res->dev->resource[0];
- if (resource_size(res) &&
- pci_assign_resource(dev_res->dev, idx)) {
+
+ if (idx < PCI_BRIDGE_RESOURCES) {
+ is_fixed = !pci_dev_bar_movable(dev_res->dev, res);
+ } else {
+ int b_res_idx = pci_get_bridge_resource_idx(res);
+ struct resource *fixed_res =
+ &dev_res->dev->subordinate->immovable_range[b_res_idx];
+
+ is_fixed = (fixed_res->start < fixed_res->end);
+ }
+
+ if (assign_fixed_resources == step && !is_fixed)
+ continue;
+ else if (assign_float_resources == step && is_fixed)
+ continue;
+
+ if (pci_assign_resource(dev_res->dev, idx)) {
if (fail_head) {
/*
* If the failed resource is a ROM BAR and
@@ -1335,7 +1372,7 @@ void pci_bus_size_bridges(struct pci_bus *bus)
}
EXPORT_SYMBOL(pci_bus_size_bridges);
-static void assign_fixed_resource_on_bus(struct pci_bus *b, struct resource *r)
+int assign_fixed_resource_on_bus(struct pci_bus *b, struct resource *r)
{
int i;
struct resource *parent_r;
@@ -1352,35 +1389,14 @@ static void assign_fixed_resource_on_bus(struct pci_bus *b, struct resource *r)
!(r->flags & IORESOURCE_PREFETCH))
continue;
- if (resource_contains(parent_r, r))
- request_resource(parent_r, r);
- }
-}
-
-/*
- * Try to assign any resources marked as IORESOURCE_PCI_FIXED, as they are
- * skipped by pbus_assign_resources_sorted().
- */
-static void pdev_assign_fixed_resources(struct pci_dev *dev)
-{
- int i;
-
- for (i = 0; i < PCI_NUM_RESOURCES; i++) {
- struct pci_bus *b;
- struct resource *r = &dev->resource[i];
-
- if (r->parent || !(r->flags & IORESOURCE_PCI_FIXED) ||
- !(r->flags & (IORESOURCE_IO | IORESOURCE_MEM)))
- continue;
-
- b = dev->bus;
- while (b && !r->parent) {
- assign_fixed_resource_on_bus(b, r);
- b = b->parent;
- if (!r->parent && pci_can_move_bars)
- break;
+ if (resource_contains(parent_r, r)) {
+ if (!request_resource(parent_r, r))
+ return 0;
}
}
+
+ dev_err(&b->dev, "failed to assign immovable %pR\n", r);
+ return -EBUSY;
}
void __pci_bus_assign_resources(const struct pci_bus *bus,
@@ -1396,8 +1412,6 @@ void __pci_bus_assign_resources(const struct pci_bus *bus,
if (!pci_dev_bars_enabled(dev))
continue;
- pdev_assign_fixed_resources(dev);
-
b = dev->subordinate;
if (!b)
continue;
diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c
index 1570bbd620cd..924ea8241061 100644
--- a/drivers/pci/setup-res.c
+++ b/drivers/pci/setup-res.c
@@ -351,8 +351,11 @@ int pci_assign_resource(struct pci_dev *dev, int resno)
resource_size_t align, size;
int ret;
- if (res->flags & IORESOURCE_PCI_FIXED)
- return 0;
+ if (resno < PCI_BRIDGE_RESOURCES &&
+ !pci_dev_bar_movable(dev, res) &&
+ res->start) {
+ return assign_fixed_resource_on_bus(dev->bus, res);
+ }
res->flags |= IORESOURCE_UNSET;
align = pci_resource_alignment(dev, res);
--
2.23.0
^ permalink raw reply related [flat|nested] 35+ messages in thread* [PATCH v6 17/30] PCI: hotplug: movable BARs: Don't reserve IO/mem bus space
2019-10-24 17:11 [PATCH v6 00/30] PCI: Allow BAR movement during hotplug Sergey Miroshnichenko
` (15 preceding siblings ...)
2019-10-24 17:12 ` [PATCH v6 16/30] PCI: hotplug: movable BARs: Assign fixed and immovable BARs before others Sergey Miroshnichenko
@ 2019-10-24 17:12 ` Sergey Miroshnichenko
2019-10-24 17:12 ` [PATCH v6 18/30] PCI: hotplug: Configure MPS for hot-added bridges during bus rescan Sergey Miroshnichenko
` (12 subsequent siblings)
29 siblings, 0 replies; 35+ messages in thread
From: Sergey Miroshnichenko @ 2019-10-24 17:12 UTC (permalink / raw)
To: linux-pci, linuxppc-dev; +Cc: Bjorn Helgaas, linux, Sergey Miroshnichenko
A hotplugged bridge with many hotplug-capable ports may request
reserving more IO space than the machine has. This could be overridden
with the "hpiosize=" kernel argument though.
But when BARs are movable, there are no need to reserve space anymore:
new BARs are allocated not from reserved gaps, but via rearranging the
existing BARs. Requesting a precise amount of space for bridge windows
increases the chances of adding the new bridge successfully.
Signed-off-by: Sergey Miroshnichenko <s.miroshnichenko@yadro.com>
---
drivers/pci/setup-bus.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index 675a612236d7..a68ec726010e 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -1285,7 +1285,7 @@ void __pci_bus_size_bridges(struct pci_bus *bus, struct list_head *realloc_head)
case PCI_HEADER_TYPE_BRIDGE:
pci_bridge_check_ranges(bus);
- if (bus->self->is_hotplug_bridge) {
+ if (bus->self->is_hotplug_bridge && !pci_can_move_bars) {
additional_io_size = pci_hotplug_io_size;
additional_mem_size = pci_hotplug_mem_size;
}
--
2.23.0
^ permalink raw reply related [flat|nested] 35+ messages in thread* [PATCH v6 18/30] PCI: hotplug: Configure MPS for hot-added bridges during bus rescan
2019-10-24 17:11 [PATCH v6 00/30] PCI: Allow BAR movement during hotplug Sergey Miroshnichenko
` (16 preceding siblings ...)
2019-10-24 17:12 ` [PATCH v6 17/30] PCI: hotplug: movable BARs: Don't reserve IO/mem bus space Sergey Miroshnichenko
@ 2019-10-24 17:12 ` Sergey Miroshnichenko
2019-10-24 17:12 ` [PATCH v6 19/30] PCI: hotplug: movable BARs: Ignore the MEM BAR offsets from bootloader Sergey Miroshnichenko
` (11 subsequent siblings)
29 siblings, 0 replies; 35+ messages in thread
From: Sergey Miroshnichenko @ 2019-10-24 17:12 UTC (permalink / raw)
To: linux-pci, linuxppc-dev; +Cc: Bjorn Helgaas, linux, Sergey Miroshnichenko
Assure that MPS settings are set up for bridges which are discovered during
manually triggered rescan via sysfs. This sequence of bridge init (using
pci_rescan_bus()) will be used for pciehp hot-add events when BARs are
movable.
Signed-off-by: Sergey Miroshnichenko <s.miroshnichenko@yadro.com>
---
drivers/pci/probe.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index d0d00cb3e965..94bbdf9b9dc1 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -3414,7 +3414,7 @@ static void pci_reassign_root_bus_resources(struct pci_bus *root)
unsigned int pci_rescan_bus(struct pci_bus *bus)
{
unsigned int max;
- struct pci_bus *root = bus;
+ struct pci_bus *root = bus, *child;
while (!pci_is_root_bus(root))
root = root->parent;
@@ -3435,6 +3435,9 @@ unsigned int pci_rescan_bus(struct pci_bus *bus)
pci_assign_unassigned_bus_resources(bus);
}
+ list_for_each_entry(child, &root->children, node)
+ pcie_bus_configure_settings(child);
+
pci_bus_add_devices(bus);
return max;
--
2.23.0
^ permalink raw reply related [flat|nested] 35+ messages in thread* [PATCH v6 19/30] PCI: hotplug: movable BARs: Ignore the MEM BAR offsets from bootloader
2019-10-24 17:11 [PATCH v6 00/30] PCI: Allow BAR movement during hotplug Sergey Miroshnichenko
` (17 preceding siblings ...)
2019-10-24 17:12 ` [PATCH v6 18/30] PCI: hotplug: Configure MPS for hot-added bridges during bus rescan Sergey Miroshnichenko
@ 2019-10-24 17:12 ` Sergey Miroshnichenko
2019-10-24 17:12 ` [PATCH v6 20/30] powerpc/pci: Fix crash with enabled movable BARs Sergey Miroshnichenko
` (10 subsequent siblings)
29 siblings, 0 replies; 35+ messages in thread
From: Sergey Miroshnichenko @ 2019-10-24 17:12 UTC (permalink / raw)
To: linux-pci, linuxppc-dev; +Cc: Bjorn Helgaas, linux, Sergey Miroshnichenko
BAR allocation by BIOS/UEFI/bootloader/firmware may be non-optimal and
it may even clash with the kernel's BAR assignment algorithm.
For example, if no space was reserved for SR-IOV BARs, and this bridge
window is packed between immovable BARs (so it is unable to extend),
and if this window can't be moved, the next PCI rescan will fail, as
the kernel tries to find a space for all the BARs, including SR-IOV.
With this patch the kernel will use its own methods of BAR allocating
when possible, increasing the chances of successful hotplug.
Also add a workaround for implicitly used video BARs on x86.
Signed-off-by: Sergey Miroshnichenko <s.miroshnichenko@yadro.com>
---
drivers/pci/probe.c | 10 ++++++++++
1 file changed, 10 insertions(+)
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 94bbdf9b9dc1..73452aa81417 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -305,6 +305,16 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
pos, (unsigned long long)region.start);
}
+ if (pci_can_move_bars &&
+ !(res->flags & IORESOURCE_IO) &&
+ (dev->class >> 8) != PCI_CLASS_DISPLAY_VGA) {
+ pci_warn(dev, "ignore the current offset of BAR %llx-%llx\n",
+ l64, l64 + sz64 - 1);
+ res->start = 0;
+ res->end = sz64 - 1;
+ res->flags |= IORESOURCE_SIZEALIGN;
+ }
+
goto out;
--
2.23.0
^ permalink raw reply related [flat|nested] 35+ messages in thread* [PATCH v6 20/30] powerpc/pci: Fix crash with enabled movable BARs
2019-10-24 17:11 [PATCH v6 00/30] PCI: Allow BAR movement during hotplug Sergey Miroshnichenko
` (18 preceding siblings ...)
2019-10-24 17:12 ` [PATCH v6 19/30] PCI: hotplug: movable BARs: Ignore the MEM BAR offsets from bootloader Sergey Miroshnichenko
@ 2019-10-24 17:12 ` Sergey Miroshnichenko
2019-10-25 1:22 ` Alexey Kardashevskiy
2019-10-24 17:12 ` [PATCH v6 21/30] powerpc/pci: Access PCI config space directly w/o pci_dn Sergey Miroshnichenko
` (9 subsequent siblings)
29 siblings, 1 reply; 35+ messages in thread
From: Sergey Miroshnichenko @ 2019-10-24 17:12 UTC (permalink / raw)
To: linux-pci, linuxppc-dev
Cc: Bjorn Helgaas, linux, Sergey Miroshnichenko,
Alexey Kardashevskiy, Oliver O'Halloran, Sam Bobroff
Add a check for the UNSET resource flag to skip the released BARs
CC: Alexey Kardashevskiy <aik@ozlabs.ru>
CC: Oliver O'Halloran <oohall@gmail.com>
CC: Sam Bobroff <sbobroff@linux.ibm.com>
Signed-off-by: Sergey Miroshnichenko <s.miroshnichenko@yadro.com>
---
arch/powerpc/platforms/powernv/pci-ioda.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index c28d0d9b7ee0..33d5ed8c258f 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -2976,7 +2976,8 @@ static void pnv_ioda_setup_pe_res(struct pnv_ioda_pe *pe,
int index;
int64_t rc;
- if (!res || !res->flags || res->start > res->end)
+ if (!res || !res->flags || res->start > res->end ||
+ (res->flags & IORESOURCE_UNSET))
return;
if (res->flags & IORESOURCE_IO) {
--
2.23.0
^ permalink raw reply related [flat|nested] 35+ messages in thread* Re: [PATCH v6 20/30] powerpc/pci: Fix crash with enabled movable BARs
2019-10-24 17:12 ` [PATCH v6 20/30] powerpc/pci: Fix crash with enabled movable BARs Sergey Miroshnichenko
@ 2019-10-25 1:22 ` Alexey Kardashevskiy
0 siblings, 0 replies; 35+ messages in thread
From: Alexey Kardashevskiy @ 2019-10-25 1:22 UTC (permalink / raw)
To: Sergey Miroshnichenko, linux-pci, linuxppc-dev
Cc: Bjorn Helgaas, linux, Oliver O'Halloran, Sam Bobroff
On 25/10/2019 04:12, Sergey Miroshnichenko wrote:
> Add a check for the UNSET resource flag to skip the released BARs
Where/why does it crash exactly? It is not extremely clear from the code. Thanks,
>
> CC: Alexey Kardashevskiy <aik@ozlabs.ru>
> CC: Oliver O'Halloran <oohall@gmail.com>
> CC: Sam Bobroff <sbobroff@linux.ibm.com>
> Signed-off-by: Sergey Miroshnichenko <s.miroshnichenko@yadro.com>
> ---
> arch/powerpc/platforms/powernv/pci-ioda.c | 3 ++-
> 1 file changed, 2 insertions(+), 1 deletion(-)
>
> diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
> index c28d0d9b7ee0..33d5ed8c258f 100644
> --- a/arch/powerpc/platforms/powernv/pci-ioda.c
> +++ b/arch/powerpc/platforms/powernv/pci-ioda.c
> @@ -2976,7 +2976,8 @@ static void pnv_ioda_setup_pe_res(struct pnv_ioda_pe *pe,
> int index;
> int64_t rc;
>
> - if (!res || !res->flags || res->start > res->end)
> + if (!res || !res->flags || res->start > res->end ||
> + (res->flags & IORESOURCE_UNSET))
> return;
>
> if (res->flags & IORESOURCE_IO) {
>
--
Alexey
^ permalink raw reply [flat|nested] 35+ messages in thread
* [PATCH v6 21/30] powerpc/pci: Access PCI config space directly w/o pci_dn
2019-10-24 17:11 [PATCH v6 00/30] PCI: Allow BAR movement during hotplug Sergey Miroshnichenko
` (19 preceding siblings ...)
2019-10-24 17:12 ` [PATCH v6 20/30] powerpc/pci: Fix crash with enabled movable BARs Sergey Miroshnichenko
@ 2019-10-24 17:12 ` Sergey Miroshnichenko
2019-10-24 17:12 ` [PATCH v6 22/30] powerpc/pci: Create pci_dn on demand Sergey Miroshnichenko
` (8 subsequent siblings)
29 siblings, 0 replies; 35+ messages in thread
From: Sergey Miroshnichenko @ 2019-10-24 17:12 UTC (permalink / raw)
To: linux-pci, linuxppc-dev
Cc: Bjorn Helgaas, linux, Sergey Miroshnichenko, Oliver O'Halloran
To fetch an updated DT for the newly hotplugged device, OS must explicitly
request it from the firmware via the pnv_php driver.
If pnv_php wasn't triggered/loaded, it is still possible to discover new
devices if PCIe I/O will not stop in absence of the pci_dn structure.
Reviewed-by: Oliver O'Halloran <oohall@gmail.com>
Signed-off-by: Sergey Miroshnichenko <s.miroshnichenko@yadro.com>
---
arch/powerpc/kernel/rtas_pci.c | 97 +++++++++++++++++++---------
arch/powerpc/platforms/powernv/pci.c | 64 ++++++++++++------
2 files changed, 109 insertions(+), 52 deletions(-)
diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c
index ae5e43eaca48..912da28b3737 100644
--- a/arch/powerpc/kernel/rtas_pci.c
+++ b/arch/powerpc/kernel/rtas_pci.c
@@ -42,10 +42,26 @@ static inline int config_access_valid(struct pci_dn *dn, int where)
return 0;
}
-int rtas_read_config(struct pci_dn *pdn, int where, int size, u32 *val)
+static int rtas_read_raw_config(unsigned long buid, int busno, unsigned int devfn,
+ int where, int size, u32 *val)
{
int returnval = -1;
- unsigned long buid, addr;
+ unsigned long addr = rtas_config_addr(busno, devfn, where);
+ int ret;
+
+ if (buid) {
+ ret = rtas_call(ibm_read_pci_config, 4, 2, &returnval,
+ addr, BUID_HI(buid), BUID_LO(buid), size);
+ } else {
+ ret = rtas_call(read_pci_config, 2, 2, &returnval, addr, size);
+ }
+ *val = returnval;
+
+ return ret;
+}
+
+int rtas_read_config(struct pci_dn *pdn, int where, int size, u32 *val)
+{
int ret;
if (!pdn)
@@ -58,16 +74,8 @@ int rtas_read_config(struct pci_dn *pdn, int where, int size, u32 *val)
return PCIBIOS_SET_FAILED;
#endif
- addr = rtas_config_addr(pdn->busno, pdn->devfn, where);
- buid = pdn->phb->buid;
- if (buid) {
- ret = rtas_call(ibm_read_pci_config, 4, 2, &returnval,
- addr, BUID_HI(buid), BUID_LO(buid), size);
- } else {
- ret = rtas_call(read_pci_config, 2, 2, &returnval, addr, size);
- }
- *val = returnval;
-
+ ret = rtas_read_raw_config(pdn->phb->buid, pdn->busno, pdn->devfn,
+ where, size, val);
if (ret)
return PCIBIOS_DEVICE_NOT_FOUND;
@@ -85,18 +93,44 @@ static int rtas_pci_read_config(struct pci_bus *bus,
pdn = pci_get_pdn_by_devfn(bus, devfn);
- /* Validity of pdn is checked in here */
- ret = rtas_read_config(pdn, where, size, val);
- if (*val == EEH_IO_ERROR_VALUE(size) &&
- eeh_dev_check_failure(pdn_to_eeh_dev(pdn)))
- return PCIBIOS_DEVICE_NOT_FOUND;
+ if (pdn) {
+ /* Validity of pdn is checked in here */
+ ret = rtas_read_config(pdn, where, size, val);
+
+ if (*val == EEH_IO_ERROR_VALUE(size) &&
+ eeh_dev_check_failure(pdn_to_eeh_dev(pdn)))
+ ret = PCIBIOS_DEVICE_NOT_FOUND;
+ } else {
+ struct pci_controller *phb = pci_bus_to_host(bus);
+
+ ret = rtas_read_raw_config(phb->buid, bus->number, devfn,
+ where, size, val);
+ }
return ret;
}
+static int rtas_write_raw_config(unsigned long buid, int busno, unsigned int devfn,
+ int where, int size, u32 val)
+{
+ unsigned long addr = rtas_config_addr(busno, devfn, where);
+ int ret;
+
+ if (buid) {
+ ret = rtas_call(ibm_write_pci_config, 5, 1, NULL, addr,
+ BUID_HI(buid), BUID_LO(buid), size, (ulong)val);
+ } else {
+ ret = rtas_call(write_pci_config, 3, 1, NULL, addr, size, (ulong)val);
+ }
+
+ if (ret)
+ return PCIBIOS_DEVICE_NOT_FOUND;
+
+ return PCIBIOS_SUCCESSFUL;
+}
+
int rtas_write_config(struct pci_dn *pdn, int where, int size, u32 val)
{
- unsigned long buid, addr;
int ret;
if (!pdn)
@@ -109,15 +143,8 @@ int rtas_write_config(struct pci_dn *pdn, int where, int size, u32 val)
return PCIBIOS_SET_FAILED;
#endif
- addr = rtas_config_addr(pdn->busno, pdn->devfn, where);
- buid = pdn->phb->buid;
- if (buid) {
- ret = rtas_call(ibm_write_pci_config, 5, 1, NULL, addr,
- BUID_HI(buid), BUID_LO(buid), size, (ulong) val);
- } else {
- ret = rtas_call(write_pci_config, 3, 1, NULL, addr, size, (ulong)val);
- }
-
+ ret = rtas_write_raw_config(pdn->phb->buid, pdn->busno, pdn->devfn,
+ where, size, val);
if (ret)
return PCIBIOS_DEVICE_NOT_FOUND;
@@ -128,12 +155,20 @@ static int rtas_pci_write_config(struct pci_bus *bus,
unsigned int devfn,
int where, int size, u32 val)
{
- struct pci_dn *pdn;
+ struct pci_dn *pdn = pci_get_pdn_by_devfn(bus, devfn);
+ int ret;
- pdn = pci_get_pdn_by_devfn(bus, devfn);
+ if (pdn) {
+ /* Validity of pdn is checked in here. */
+ ret = rtas_write_config(pdn, where, size, val);
+ } else {
+ struct pci_controller *phb = pci_bus_to_host(bus);
- /* Validity of pdn is checked in here. */
- return rtas_write_config(pdn, where, size, val);
+ ret = rtas_write_raw_config(phb->buid, bus->number, devfn,
+ where, size, val);
+ }
+
+ return ret;
}
static struct pci_ops rtas_pci_ops = {
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 2825d004dece..ffd546cf9204 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -648,30 +648,29 @@ static void pnv_pci_config_check_eeh(struct pci_dn *pdn)
}
}
-int pnv_pci_cfg_read(struct pci_dn *pdn,
- int where, int size, u32 *val)
+static int pnv_pci_cfg_read_raw(u64 phb_id, int busno, unsigned int devfn,
+ int where, int size, u32 *val)
{
- struct pnv_phb *phb = pdn->phb->private_data;
- u32 bdfn = (pdn->busno << 8) | pdn->devfn;
+ u32 bdfn = (busno << 8) | devfn;
s64 rc;
switch (size) {
case 1: {
u8 v8;
- rc = opal_pci_config_read_byte(phb->opal_id, bdfn, where, &v8);
+ rc = opal_pci_config_read_byte(phb_id, bdfn, where, &v8);
*val = (rc == OPAL_SUCCESS) ? v8 : 0xff;
break;
}
case 2: {
__be16 v16;
- rc = opal_pci_config_read_half_word(phb->opal_id, bdfn, where,
- &v16);
+ rc = opal_pci_config_read_half_word(phb_id, bdfn, where,
+ &v16);
*val = (rc == OPAL_SUCCESS) ? be16_to_cpu(v16) : 0xffff;
break;
}
case 4: {
__be32 v32;
- rc = opal_pci_config_read_word(phb->opal_id, bdfn, where, &v32);
+ rc = opal_pci_config_read_word(phb_id, bdfn, where, &v32);
*val = (rc == OPAL_SUCCESS) ? be32_to_cpu(v32) : 0xffffffff;
break;
}
@@ -680,27 +679,28 @@ int pnv_pci_cfg_read(struct pci_dn *pdn,
}
pr_devel("%s: bus: %x devfn: %x +%x/%x -> %08x\n",
- __func__, pdn->busno, pdn->devfn, where, size, *val);
+ __func__, busno, devfn, where, size, *val);
+
return PCIBIOS_SUCCESSFUL;
}
-int pnv_pci_cfg_write(struct pci_dn *pdn,
- int where, int size, u32 val)
+static int pnv_pci_cfg_write_raw(u64 phb_id, int busno, unsigned int devfn,
+ int where, int size, u32 val)
{
- struct pnv_phb *phb = pdn->phb->private_data;
- u32 bdfn = (pdn->busno << 8) | pdn->devfn;
+ u32 bdfn = (busno << 8) | devfn;
pr_devel("%s: bus: %x devfn: %x +%x/%x -> %08x\n",
- __func__, pdn->busno, pdn->devfn, where, size, val);
+ __func__, busno, devfn, where, size, val);
+
switch (size) {
case 1:
- opal_pci_config_write_byte(phb->opal_id, bdfn, where, val);
+ opal_pci_config_write_byte(phb_id, bdfn, where, val);
break;
case 2:
- opal_pci_config_write_half_word(phb->opal_id, bdfn, where, val);
+ opal_pci_config_write_half_word(phb_id, bdfn, where, val);
break;
case 4:
- opal_pci_config_write_word(phb->opal_id, bdfn, where, val);
+ opal_pci_config_write_word(phb_id, bdfn, where, val);
break;
default:
return PCIBIOS_FUNC_NOT_SUPPORTED;
@@ -709,6 +709,24 @@ int pnv_pci_cfg_write(struct pci_dn *pdn,
return PCIBIOS_SUCCESSFUL;
}
+int pnv_pci_cfg_read(struct pci_dn *pdn,
+ int where, int size, u32 *val)
+{
+ struct pnv_phb *phb = pdn->phb->private_data;
+
+ return pnv_pci_cfg_read_raw(phb->opal_id, pdn->busno, pdn->devfn,
+ where, size, val);
+}
+
+int pnv_pci_cfg_write(struct pci_dn *pdn,
+ int where, int size, u32 val)
+{
+ struct pnv_phb *phb = pdn->phb->private_data;
+
+ return pnv_pci_cfg_write_raw(phb->opal_id, pdn->busno, pdn->devfn,
+ where, size, val);
+}
+
#if CONFIG_EEH
static bool pnv_pci_cfg_check(struct pci_dn *pdn)
{
@@ -744,13 +762,15 @@ static int pnv_pci_read_config(struct pci_bus *bus,
int where, int size, u32 *val)
{
struct pci_dn *pdn;
- struct pnv_phb *phb;
+ struct pci_controller *hose = pci_bus_to_host(bus);
+ struct pnv_phb *phb = hose->private_data;
int ret;
*val = 0xFFFFFFFF;
pdn = pci_get_pdn_by_devfn(bus, devfn);
if (!pdn)
- return PCIBIOS_DEVICE_NOT_FOUND;
+ return pnv_pci_cfg_read_raw(phb->opal_id, bus->number, devfn,
+ where, size, val);
if (!pnv_pci_cfg_check(pdn))
return PCIBIOS_DEVICE_NOT_FOUND;
@@ -773,12 +793,14 @@ static int pnv_pci_write_config(struct pci_bus *bus,
int where, int size, u32 val)
{
struct pci_dn *pdn;
- struct pnv_phb *phb;
+ struct pci_controller *hose = pci_bus_to_host(bus);
+ struct pnv_phb *phb = hose->private_data;
int ret;
pdn = pci_get_pdn_by_devfn(bus, devfn);
if (!pdn)
- return PCIBIOS_DEVICE_NOT_FOUND;
+ return pnv_pci_cfg_write_raw(phb->opal_id, bus->number, devfn,
+ where, size, val);
if (!pnv_pci_cfg_check(pdn))
return PCIBIOS_DEVICE_NOT_FOUND;
--
2.23.0
^ permalink raw reply related [flat|nested] 35+ messages in thread* [PATCH v6 22/30] powerpc/pci: Create pci_dn on demand
2019-10-24 17:11 [PATCH v6 00/30] PCI: Allow BAR movement during hotplug Sergey Miroshnichenko
` (20 preceding siblings ...)
2019-10-24 17:12 ` [PATCH v6 21/30] powerpc/pci: Access PCI config space directly w/o pci_dn Sergey Miroshnichenko
@ 2019-10-24 17:12 ` Sergey Miroshnichenko
2019-10-24 17:12 ` [PATCH v6 23/30] powerpc/pci: hotplug: Add support for movable BARs Sergey Miroshnichenko
` (7 subsequent siblings)
29 siblings, 0 replies; 35+ messages in thread
From: Sergey Miroshnichenko @ 2019-10-24 17:12 UTC (permalink / raw)
To: linux-pci, linuxppc-dev
Cc: Bjorn Helgaas, linux, Sergey Miroshnichenko,
Oliver O'Halloran, Sam Bobroff
If a struct pci_dn hasn't yet been created for the PCIe device (there was
no DT node for it), allocate this structure and fill with info read from
the device directly.
CC: Oliver O'Halloran <oohall@gmail.com>
CC: Sam Bobroff <sbobroff@linux.ibm.com>
Signed-off-by: Sergey Miroshnichenko <s.miroshnichenko@yadro.com>
---
arch/powerpc/kernel/pci_dn.c | 88 ++++++++++++++++++++++++++++++------
1 file changed, 74 insertions(+), 14 deletions(-)
diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c
index 9524009ca1ae..ad0ecf48e943 100644
--- a/arch/powerpc/kernel/pci_dn.c
+++ b/arch/powerpc/kernel/pci_dn.c
@@ -20,6 +20,9 @@
#include <asm/firmware.h>
#include <asm/eeh.h>
+static struct pci_dn *pci_create_pdn_from_dev(struct pci_dev *pdev,
+ struct pci_dn *parent);
+
/*
* The function is used to find the firmware data of one
* specific PCI device, which is attached to the indicated
@@ -52,6 +55,9 @@ static struct pci_dn *pci_bus_to_pdn(struct pci_bus *bus)
dn = pci_bus_to_OF_node(pbus);
pdn = dn ? PCI_DN(dn) : NULL;
+ if (!pdn && pbus->self)
+ pdn = pbus->self->dev.archdata.pci_data;
+
return pdn;
}
@@ -61,10 +67,13 @@ struct pci_dn *pci_get_pdn_by_devfn(struct pci_bus *bus,
struct device_node *dn = NULL;
struct pci_dn *parent, *pdn;
struct pci_dev *pdev = NULL;
+ bool pdev_found = false;
/* Fast path: fetch from PCI device */
list_for_each_entry(pdev, &bus->devices, bus_list) {
if (pdev->devfn == devfn) {
+ pdev_found = true;
+
if (pdev->dev.archdata.pci_data)
return pdev->dev.archdata.pci_data;
@@ -73,6 +82,9 @@ struct pci_dn *pci_get_pdn_by_devfn(struct pci_bus *bus,
}
}
+ if (!pdev_found)
+ pdev = NULL;
+
/* Fast path: fetch from device node */
pdn = dn ? PCI_DN(dn) : NULL;
if (pdn)
@@ -85,9 +97,12 @@ struct pci_dn *pci_get_pdn_by_devfn(struct pci_bus *bus,
list_for_each_entry(pdn, &parent->child_list, list) {
if (pdn->busno == bus->number &&
- pdn->devfn == devfn)
- return pdn;
- }
+ pdn->devfn == devfn) {
+ if (pdev)
+ pdev->dev.archdata.pci_data = pdn;
+ return pdn;
+ }
+ }
return NULL;
}
@@ -117,17 +132,17 @@ struct pci_dn *pci_get_pdn(struct pci_dev *pdev)
list_for_each_entry(pdn, &parent->child_list, list) {
if (pdn->busno == pdev->bus->number &&
- pdn->devfn == pdev->devfn)
+ pdn->devfn == pdev->devfn) {
+ pdev->dev.archdata.pci_data = pdn;
return pdn;
+ }
}
- return NULL;
+ return pci_create_pdn_from_dev(pdev, parent);
}
-#ifdef CONFIG_PCI_IOV
-static struct pci_dn *add_one_dev_pci_data(struct pci_dn *parent,
- int vf_index,
- int busno, int devfn)
+static struct pci_dn *pci_alloc_pdn(struct pci_dn *parent,
+ int busno, int devfn)
{
struct pci_dn *pdn;
@@ -143,7 +158,6 @@ static struct pci_dn *add_one_dev_pci_data(struct pci_dn *parent,
pdn->parent = parent;
pdn->busno = busno;
pdn->devfn = devfn;
- pdn->vf_index = vf_index;
pdn->pe_number = IODA_INVALID_PE;
INIT_LIST_HEAD(&pdn->child_list);
INIT_LIST_HEAD(&pdn->list);
@@ -151,7 +165,51 @@ static struct pci_dn *add_one_dev_pci_data(struct pci_dn *parent,
return pdn;
}
-#endif
+
+static struct pci_dn *pci_create_pdn_from_dev(struct pci_dev *pdev,
+ struct pci_dn *parent)
+{
+ struct pci_dn *pdn = NULL;
+ u32 class_code;
+ u16 device_id;
+ u16 vendor_id;
+
+ if (!parent)
+ return NULL;
+
+ pdn = pci_alloc_pdn(parent, pdev->bus->busn_res.start, pdev->devfn);
+ pci_info(pdev, "Create a new pdn for devfn %2x\n", pdev->devfn / 8);
+
+ if (!pdn) {
+ pci_err(pdev, "%s: Failed to allocate pdn\n", __func__);
+ return NULL;
+ }
+
+ #ifdef CONFIG_EEH
+ if (!eeh_dev_init(pdn)) {
+ kfree(pdn);
+ pci_err(pdev, "%s: Failed to allocate edev\n", __func__);
+ return NULL;
+ }
+ #endif /* CONFIG_EEH */
+
+ pci_bus_read_config_word(pdev->bus, pdev->devfn,
+ PCI_VENDOR_ID, &vendor_id);
+ pdn->vendor_id = vendor_id;
+
+ pci_bus_read_config_word(pdev->bus, pdev->devfn,
+ PCI_DEVICE_ID, &device_id);
+ pdn->device_id = device_id;
+
+ pci_bus_read_config_dword(pdev->bus, pdev->devfn,
+ PCI_CLASS_REVISION, &class_code);
+ class_code >>= 8;
+ pdn->class_code = class_code;
+
+ pdev->dev.archdata.pci_data = pdn;
+
+ return pdn;
+}
struct pci_dn *add_dev_pci_data(struct pci_dev *pdev)
{
@@ -176,15 +234,17 @@ struct pci_dn *add_dev_pci_data(struct pci_dev *pdev)
for (i = 0; i < pci_sriov_get_totalvfs(pdev); i++) {
struct eeh_dev *edev __maybe_unused;
- pdn = add_one_dev_pci_data(parent, i,
- pci_iov_virtfn_bus(pdev, i),
- pci_iov_virtfn_devfn(pdev, i));
+ pdn = pci_alloc_pdn(parent,
+ pci_iov_virtfn_bus(pdev, i),
+ pci_iov_virtfn_devfn(pdev, i));
if (!pdn) {
dev_warn(&pdev->dev, "%s: Cannot create firmware data for VF#%d\n",
__func__, i);
return NULL;
}
+ pdn->vf_index = i;
+
#ifdef CONFIG_EEH
/* Create the EEH device for the VF */
edev = eeh_dev_init(pdn);
--
2.23.0
^ permalink raw reply related [flat|nested] 35+ messages in thread* [PATCH v6 23/30] powerpc/pci: hotplug: Add support for movable BARs
2019-10-24 17:11 [PATCH v6 00/30] PCI: Allow BAR movement during hotplug Sergey Miroshnichenko
` (21 preceding siblings ...)
2019-10-24 17:12 ` [PATCH v6 22/30] powerpc/pci: Create pci_dn on demand Sergey Miroshnichenko
@ 2019-10-24 17:12 ` Sergey Miroshnichenko
2019-10-24 17:12 ` [PATCH v6 24/30] powerpc/powernv/pci: Suppress an EEH error when reading an empty slot Sergey Miroshnichenko
` (6 subsequent siblings)
29 siblings, 0 replies; 35+ messages in thread
From: Sergey Miroshnichenko @ 2019-10-24 17:12 UTC (permalink / raw)
To: linux-pci, linuxppc-dev
Cc: Bjorn Helgaas, linux, Sergey Miroshnichenko,
Oliver O'Halloran, Sam Bobroff
Add pcibios_root_bus_rescan_prepare()/_done() hooks for the powerpc, so it
can reassign the PE numbers (which depend on BAR sizes and locations) and
update the EEH address cache during a PCI rescan.
New PE numbers are assigned during pci_setup_bridges(root) after the rescan
is done.
CC: Oliver O'Halloran <oohall@gmail.com>
CC: Sam Bobroff <sbobroff@linux.ibm.com>
Signed-off-by: Sergey Miroshnichenko <s.miroshnichenko@yadro.com>
---
arch/powerpc/kernel/pci-hotplug.c | 43 +++++++++++++++++++++++++++++++
drivers/pci/probe.c | 10 +++++++
include/linux/pci.h | 3 +++
3 files changed, 56 insertions(+)
diff --git a/arch/powerpc/kernel/pci-hotplug.c b/arch/powerpc/kernel/pci-hotplug.c
index fc62c4bc47b1..42847f5b0f08 100644
--- a/arch/powerpc/kernel/pci-hotplug.c
+++ b/arch/powerpc/kernel/pci-hotplug.c
@@ -16,6 +16,7 @@
#include <asm/ppc-pci.h>
#include <asm/firmware.h>
#include <asm/eeh.h>
+#include <asm/iommu.h>
static struct pci_bus *find_bus_among_children(struct pci_bus *bus,
struct device_node *dn)
@@ -151,3 +152,45 @@ void pci_hp_add_devices(struct pci_bus *bus)
pcibios_finish_adding_to_bus(bus);
}
EXPORT_SYMBOL_GPL(pci_hp_add_devices);
+
+static void pci_hp_bus_rescan_prepare(struct pci_bus *bus)
+{
+ struct pci_dev *dev;
+
+ list_for_each_entry(dev, &bus->devices, bus_list) {
+ struct pci_bus *child = dev->subordinate;
+
+ if (child)
+ pci_hp_bus_rescan_prepare(child);
+
+ iommu_del_device(&dev->dev);
+ }
+
+ list_for_each_entry(dev, &bus->devices, bus_list) {
+ pcibios_release_device(dev);
+ }
+}
+
+static void pci_hp_bus_rescan_done(struct pci_bus *bus)
+{
+ struct pci_dev *dev;
+
+ list_for_each_entry(dev, &bus->devices, bus_list) {
+ struct pci_bus *child = dev->subordinate;
+
+ pcibios_bus_add_device(dev);
+
+ if (child)
+ pci_hp_bus_rescan_done(child);
+ }
+}
+
+void pcibios_root_bus_rescan_prepare(struct pci_bus *root)
+{
+ pci_hp_bus_rescan_prepare(root);
+}
+
+void pcibios_root_bus_rescan_done(struct pci_bus *root)
+{
+ pci_hp_bus_rescan_done(root);
+}
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 73452aa81417..539f5d39bb6d 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -3235,6 +3235,14 @@ static void pci_bus_rescan_done(struct pci_bus *bus)
pci_config_pm_runtime_put(bus->self);
}
+void __weak pcibios_root_bus_rescan_prepare(struct pci_bus *root)
+{
+}
+
+void __weak pcibios_root_bus_rescan_done(struct pci_bus *root)
+{
+}
+
static void pci_setup_bridges(struct pci_bus *bus)
{
struct pci_dev *dev;
@@ -3430,6 +3438,7 @@ unsigned int pci_rescan_bus(struct pci_bus *bus)
root = root->parent;
if (pci_can_move_bars) {
+ pcibios_root_bus_rescan_prepare(root);
pci_bus_rescan_prepare(root);
pci_bus_update_immovable_range(root);
pci_bus_release_root_bridge_resources(root);
@@ -3440,6 +3449,7 @@ unsigned int pci_rescan_bus(struct pci_bus *bus)
pci_setup_bridges(root);
pci_bus_rescan_done(root);
+ pcibios_root_bus_rescan_done(root);
} else {
max = pci_scan_child_bus(bus);
pci_assign_unassigned_bus_resources(bus);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index e1edcb3fad31..b5821134bdae 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1275,6 +1275,9 @@ unsigned int pci_rescan_bus(struct pci_bus *bus);
void pci_lock_rescan_remove(void);
void pci_unlock_rescan_remove(void);
+void pcibios_root_bus_rescan_prepare(struct pci_bus *root);
+void pcibios_root_bus_rescan_done(struct pci_bus *root);
+
/* Vital Product Data routines */
ssize_t pci_read_vpd(struct pci_dev *dev, loff_t pos, size_t count, void *buf);
ssize_t pci_write_vpd(struct pci_dev *dev, loff_t pos, size_t count, const void *buf);
--
2.23.0
^ permalink raw reply related [flat|nested] 35+ messages in thread* [PATCH v6 24/30] powerpc/powernv/pci: Suppress an EEH error when reading an empty slot
2019-10-24 17:11 [PATCH v6 00/30] PCI: Allow BAR movement during hotplug Sergey Miroshnichenko
` (22 preceding siblings ...)
2019-10-24 17:12 ` [PATCH v6 23/30] powerpc/pci: hotplug: Add support for movable BARs Sergey Miroshnichenko
@ 2019-10-24 17:12 ` Sergey Miroshnichenko
2019-10-24 17:12 ` [PATCH v6 25/30] PNP: Don't reserve BARs for PCI when enabled movable BARs Sergey Miroshnichenko
` (5 subsequent siblings)
29 siblings, 0 replies; 35+ messages in thread
From: Sergey Miroshnichenko @ 2019-10-24 17:12 UTC (permalink / raw)
To: linux-pci, linuxppc-dev
Cc: Bjorn Helgaas, linux, Sergey Miroshnichenko,
Oliver O'Halloran, Sam Bobroff
Reading an empty slot returns all ones, which triggers a false EEH
error event on PowerNV. A rescan is performed after all the PEs have
been unmapped, so the reserved PE index is used for unfreezing.
CC: Oliver O'Halloran <oohall@gmail.com>
CC: Sam Bobroff <sbobroff@linux.ibm.com>
Signed-off-by: Sergey Miroshnichenko <s.miroshnichenko@yadro.com>
---
arch/powerpc/platforms/powernv/pci.c | 13 ++++++++++---
1 file changed, 10 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index ffd546cf9204..e1b45dc96474 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -768,9 +768,16 @@ static int pnv_pci_read_config(struct pci_bus *bus,
*val = 0xFFFFFFFF;
pdn = pci_get_pdn_by_devfn(bus, devfn);
- if (!pdn)
- return pnv_pci_cfg_read_raw(phb->opal_id, bus->number, devfn,
- where, size, val);
+ if (!pdn) {
+ ret = pnv_pci_cfg_read_raw(phb->opal_id, bus->number, devfn,
+ where, size, val);
+
+ if (!ret && (*val == EEH_IO_ERROR_VALUE(size)) && phb->unfreeze_pe)
+ phb->unfreeze_pe(phb, phb->ioda.reserved_pe_idx,
+ OPAL_EEH_ACTION_CLEAR_FREEZE_ALL);
+
+ return ret;
+ }
if (!pnv_pci_cfg_check(pdn))
return PCIBIOS_DEVICE_NOT_FOUND;
--
2.23.0
^ permalink raw reply related [flat|nested] 35+ messages in thread* [PATCH v6 25/30] PNP: Don't reserve BARs for PCI when enabled movable BARs
2019-10-24 17:11 [PATCH v6 00/30] PCI: Allow BAR movement during hotplug Sergey Miroshnichenko
` (23 preceding siblings ...)
2019-10-24 17:12 ` [PATCH v6 24/30] powerpc/powernv/pci: Suppress an EEH error when reading an empty slot Sergey Miroshnichenko
@ 2019-10-24 17:12 ` Sergey Miroshnichenko
2019-10-27 17:40 ` kbuild test robot
2019-10-24 17:12 ` [PATCH v6 26/30] PCI: hotplug: movable BARs: Enable the feature by default Sergey Miroshnichenko
` (4 subsequent siblings)
29 siblings, 1 reply; 35+ messages in thread
From: Sergey Miroshnichenko @ 2019-10-24 17:12 UTC (permalink / raw)
To: linux-pci, linuxppc-dev
Cc: Bjorn Helgaas, linux, Sergey Miroshnichenko, Rafael J . Wysocki
When the Movable BARs feature is supported, the PCI subsystem is able to
distribute existing BARs and allocate the new ones itself, without need to
reserve gaps by BIOS.
CC: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Sergey Miroshnichenko <s.miroshnichenko@yadro.com>
---
drivers/pnp/system.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/drivers/pnp/system.c b/drivers/pnp/system.c
index 6950503741eb..5977bd11f4d4 100644
--- a/drivers/pnp/system.c
+++ b/drivers/pnp/system.c
@@ -12,6 +12,7 @@
#include <linux/device.h>
#include <linux/init.h>
#include <linux/slab.h>
+#include <linux/pci.h>
#include <linux/kernel.h>
#include <linux/ioport.h>
@@ -58,6 +59,9 @@ static void reserve_resources_of_dev(struct pnp_dev *dev)
struct resource *res;
int i;
+ if (pci_can_move_bars)
+ return;
+
for (i = 0; (res = pnp_get_resource(dev, IORESOURCE_IO, i)); i++) {
if (res->flags & IORESOURCE_DISABLED)
continue;
--
2.23.0
^ permalink raw reply related [flat|nested] 35+ messages in thread* Re: [PATCH v6 25/30] PNP: Don't reserve BARs for PCI when enabled movable BARs
2019-10-24 17:12 ` [PATCH v6 25/30] PNP: Don't reserve BARs for PCI when enabled movable BARs Sergey Miroshnichenko
@ 2019-10-27 17:40 ` kbuild test robot
0 siblings, 0 replies; 35+ messages in thread
From: kbuild test robot @ 2019-10-27 17:40 UTC (permalink / raw)
To: Sergey Miroshnichenko
Cc: kbuild-all, linux-pci, linuxppc-dev, Bjorn Helgaas, linux,
Sergey Miroshnichenko, Rafael J . Wysocki
[-- Attachment #1: Type: text/plain, Size: 2599 bytes --]
Hi Sergey,
Thank you for the patch! Yet something to improve:
[auto build test ERROR on pci/next]
[also build test ERROR on v5.4-rc4 next-20191025]
[if your patch is applied to the wrong git tree, please drop us a note to help
improve the system. BTW, we also suggest to use '--base' option to specify the
base tree in git format-patch, please see https://stackoverflow.com/a/37406982]
url: https://github.com/0day-ci/linux/commits/Sergey-Miroshnichenko/PCI-Allow-BAR-movement-during-hotplug/20191028-002741
base: https://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci.git next
config: i386-alldefconfig (attached as .config)
compiler: gcc-7 (Debian 7.4.0-14) 7.4.0
reproduce:
# save the attached .config to linux build tree
make ARCH=i386
If you fix the issue, kindly add following tag
Reported-by: kbuild test robot <lkp@intel.com>
All errors (new ones prefixed by >>):
drivers/pnp/system.c: In function 'reserve_resources_of_dev':
>> drivers/pnp/system.c:62:6: error: 'pci_can_move_bars' undeclared (first use in this function); did you mean 'pci_cap_saved_data'?
if (pci_can_move_bars)
^~~~~~~~~~~~~~~~~
pci_cap_saved_data
drivers/pnp/system.c:62:6: note: each undeclared identifier is reported only once for each function it appears in
vim +62 drivers/pnp/system.c
56
57 static void reserve_resources_of_dev(struct pnp_dev *dev)
58 {
59 struct resource *res;
60 int i;
61
> 62 if (pci_can_move_bars)
63 return;
64
65 for (i = 0; (res = pnp_get_resource(dev, IORESOURCE_IO, i)); i++) {
66 if (res->flags & IORESOURCE_DISABLED)
67 continue;
68 if (res->start == 0)
69 continue; /* disabled */
70 if (res->start < 0x100)
71 /*
72 * Below 0x100 is only standard PC hardware
73 * (pics, kbd, timer, dma, ...)
74 * We should not get resource conflicts there,
75 * and the kernel reserves these anyway
76 * (see arch/i386/kernel/setup.c).
77 * So, do nothing
78 */
79 continue;
80 if (res->end < res->start)
81 continue; /* invalid */
82
83 reserve_range(dev, res, 1);
84 }
85
86 for (i = 0; (res = pnp_get_resource(dev, IORESOURCE_MEM, i)); i++) {
87 if (res->flags & IORESOURCE_DISABLED)
88 continue;
89
90 reserve_range(dev, res, 0);
91 }
92 }
93
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 10514 bytes --]
^ permalink raw reply [flat|nested] 35+ messages in thread
* [PATCH v6 26/30] PCI: hotplug: movable BARs: Enable the feature by default
2019-10-24 17:11 [PATCH v6 00/30] PCI: Allow BAR movement during hotplug Sergey Miroshnichenko
` (24 preceding siblings ...)
2019-10-24 17:12 ` [PATCH v6 25/30] PNP: Don't reserve BARs for PCI when enabled movable BARs Sergey Miroshnichenko
@ 2019-10-24 17:12 ` Sergey Miroshnichenko
2019-10-24 17:12 ` [PATCH v6 27/30] nvme-pci: Handle movable BARs Sergey Miroshnichenko
` (3 subsequent siblings)
29 siblings, 0 replies; 35+ messages in thread
From: Sergey Miroshnichenko @ 2019-10-24 17:12 UTC (permalink / raw)
To: linux-pci, linuxppc-dev
Cc: Bjorn Helgaas, linux, Sergey Miroshnichenko, Oliver O'Halloran
This is the last patch in the series which implements the essentials of the
Movable BARs feature, so it is turned by default now. Tested on:
- x86_64 with "pci=realloc,pcie_bus_peer2peer" command line argument;
- POWER8 PowerNV+PHB3 ppc64le with "pci=realloc,pcie_bus_peer2peer".
In case of problems it is still can be overridden by the following command
line option:
pcie_movable_bars=off
CC: Oliver O'Halloran <oohall@gmail.com>
Signed-off-by: Sergey Miroshnichenko <s.miroshnichenko@yadro.com>
---
drivers/pci/pci.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 85014c6b2817..6ec1b70e4a96 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -78,7 +78,7 @@ static void pci_dev_d3_sleep(struct pci_dev *dev)
int pci_domains_supported = 1;
#endif
-bool pci_can_move_bars;
+bool pci_can_move_bars = true;
#define DEFAULT_CARDBUS_IO_SIZE (256)
#define DEFAULT_CARDBUS_MEM_SIZE (64*1024*1024)
--
2.23.0
^ permalink raw reply related [flat|nested] 35+ messages in thread* [PATCH v6 27/30] nvme-pci: Handle movable BARs
2019-10-24 17:11 [PATCH v6 00/30] PCI: Allow BAR movement during hotplug Sergey Miroshnichenko
` (25 preceding siblings ...)
2019-10-24 17:12 ` [PATCH v6 26/30] PCI: hotplug: movable BARs: Enable the feature by default Sergey Miroshnichenko
@ 2019-10-24 17:12 ` Sergey Miroshnichenko
2019-10-24 17:12 ` [PATCH v6 28/30] PCI/portdrv: Declare support of " Sergey Miroshnichenko
` (2 subsequent siblings)
29 siblings, 0 replies; 35+ messages in thread
From: Sergey Miroshnichenko @ 2019-10-24 17:12 UTC (permalink / raw)
To: linux-pci, linuxppc-dev
Cc: Bjorn Helgaas, linux, Sergey Miroshnichenko, linux-nvme,
Christoph Hellwig
Hotplugged devices can affect the existing ones by moving their BARs. The
PCI subsystem will inform the NVME driver about this by invoking the
.rescan_prepare() and .rescan_done() hooks, so the BARs can by re-mapped.
Tested under the "randrw" mode of the fio tool. Before the hotplugging:
% sudo cat /proc/iomem
...
3fe800000000-3fe8007fffff : PCI Bus 0020:0b
3fe800000000-3fe8007fffff : PCI Bus 0020:18
3fe800000000-3fe8000fffff : 0020:18:00.0
3fe800000000-3fe8000fffff : nvme
3fe800100000-3fe80017ffff : 0020:18:00.0
...
, then another NVME drive was hot-added, so BARs of the 0020:18:00.0 are
moved:
% sudo cat /proc/iomem
...
3fe800000000-3fe800ffffff : PCI Bus 0020:0b
3fe800000000-3fe8007fffff : PCI Bus 0020:10
3fe800000000-3fe800003fff : 0020:10:00.0
3fe800000000-3fe800003fff : nvme
3fe800010000-3fe80001ffff : 0020:10:00.0
3fe800800000-3fe800ffffff : PCI Bus 0020:18
3fe800800000-3fe8008fffff : 0020:18:00.0
3fe800800000-3fe8008fffff : nvme
3fe800900000-3fe80097ffff : 0020:18:00.0
...
During the rescanning, both READ and WRITE speeds drop to zero for a while
due to driver's pause, then restore.
Also tested with an NVME as a system drive.
Cc: linux-nvme@lists.infradead.org
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sergey Miroshnichenko <s.miroshnichenko@yadro.com>
---
drivers/nvme/host/pci.c | 21 ++++++++++++++++++++-
1 file changed, 20 insertions(+), 1 deletion(-)
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 869f462e6b6e..5f162ea5a5f1 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1650,7 +1650,7 @@ static int nvme_remap_bar(struct nvme_dev *dev, unsigned long size)
{
struct pci_dev *pdev = to_pci_dev(dev->dev);
- if (size <= dev->bar_mapped_size)
+ if (dev->bar && size <= dev->bar_mapped_size)
return 0;
if (size > pci_resource_len(pdev, 0))
return -ENOMEM;
@@ -3059,6 +3059,23 @@ static void nvme_error_resume(struct pci_dev *pdev)
flush_work(&dev->ctrl.reset_work);
}
+static void nvme_rescan_prepare(struct pci_dev *pdev)
+{
+ struct nvme_dev *dev = pci_get_drvdata(pdev);
+
+ nvme_dev_disable(dev, false);
+ nvme_dev_unmap(dev);
+ dev->bar = NULL;
+}
+
+static void nvme_rescan_done(struct pci_dev *pdev)
+{
+ struct nvme_dev *dev = pci_get_drvdata(pdev);
+
+ nvme_dev_map(dev);
+ nvme_reset_ctrl_sync(&dev->ctrl);
+}
+
static const struct pci_error_handlers nvme_err_handler = {
.error_detected = nvme_error_detected,
.slot_reset = nvme_slot_reset,
@@ -3135,6 +3152,8 @@ static struct pci_driver nvme_driver = {
#endif
.sriov_configure = pci_sriov_configure_simple,
.err_handler = &nvme_err_handler,
+ .rescan_prepare = nvme_rescan_prepare,
+ .rescan_done = nvme_rescan_done,
};
static int __init nvme_init(void)
--
2.23.0
^ permalink raw reply related [flat|nested] 35+ messages in thread* [PATCH v6 28/30] PCI/portdrv: Declare support of movable BARs
2019-10-24 17:11 [PATCH v6 00/30] PCI: Allow BAR movement during hotplug Sergey Miroshnichenko
` (26 preceding siblings ...)
2019-10-24 17:12 ` [PATCH v6 27/30] nvme-pci: Handle movable BARs Sergey Miroshnichenko
@ 2019-10-24 17:12 ` Sergey Miroshnichenko
2019-10-24 17:12 ` [PATCH v6 29/30] PCI: pciehp: movable BARs: Trigger a domain rescan on hp events Sergey Miroshnichenko
2019-10-24 17:12 ` [PATCH v6 30/30] Revert "powerpc/powernv/pci: Work around races in PCI bridge enabling" Sergey Miroshnichenko
29 siblings, 0 replies; 35+ messages in thread
From: Sergey Miroshnichenko @ 2019-10-24 17:12 UTC (permalink / raw)
To: linux-pci, linuxppc-dev; +Cc: Bjorn Helgaas, linux, Sergey Miroshnichenko
Switch's BARs are not used by the portdrv driver, but they are still
considered as immovable until the .rescan_prepare() and .rescan_done()
hooks are added. Add these hooks to increase chances to allocate new BARs.
Signed-off-by: Sergey Miroshnichenko <s.miroshnichenko@yadro.com>
---
drivers/pci/pcie/portdrv_pci.c | 11 +++++++++++
1 file changed, 11 insertions(+)
diff --git a/drivers/pci/pcie/portdrv_pci.c b/drivers/pci/pcie/portdrv_pci.c
index 0a87091a0800..9dbddc7faaa7 100644
--- a/drivers/pci/pcie/portdrv_pci.c
+++ b/drivers/pci/pcie/portdrv_pci.c
@@ -197,6 +197,14 @@ static const struct pci_error_handlers pcie_portdrv_err_handler = {
.resume = pcie_portdrv_err_resume,
};
+static void pcie_portdrv_rescan_prepare(struct pci_dev *pdev)
+{
+}
+
+static void pcie_portdrv_rescan_done(struct pci_dev *pdev)
+{
+}
+
static struct pci_driver pcie_portdriver = {
.name = "pcieport",
.id_table = &port_pci_ids[0],
@@ -207,6 +215,9 @@ static struct pci_driver pcie_portdriver = {
.err_handler = &pcie_portdrv_err_handler,
+ .rescan_prepare = pcie_portdrv_rescan_prepare,
+ .rescan_done = pcie_portdrv_rescan_done,
+
.driver.pm = PCIE_PORTDRV_PM_OPS,
};
--
2.23.0
^ permalink raw reply related [flat|nested] 35+ messages in thread* [PATCH v6 29/30] PCI: pciehp: movable BARs: Trigger a domain rescan on hp events
2019-10-24 17:11 [PATCH v6 00/30] PCI: Allow BAR movement during hotplug Sergey Miroshnichenko
` (27 preceding siblings ...)
2019-10-24 17:12 ` [PATCH v6 28/30] PCI/portdrv: Declare support of " Sergey Miroshnichenko
@ 2019-10-24 17:12 ` Sergey Miroshnichenko
2019-10-24 17:12 ` [PATCH v6 30/30] Revert "powerpc/powernv/pci: Work around races in PCI bridge enabling" Sergey Miroshnichenko
29 siblings, 0 replies; 35+ messages in thread
From: Sergey Miroshnichenko @ 2019-10-24 17:12 UTC (permalink / raw)
To: linux-pci, linuxppc-dev
Cc: Bjorn Helgaas, linux, Sergey Miroshnichenko, Lukas Wunner
With movable BARs, adding a hotplugged device is not local to its bridge
anymore, but it affects the whole domain: BARs, bridge windows and bus
numbers can be substantially rearranged. So instead of trying to fit the
new devices into preallocated reserved gaps, initiate a full domain rescan.
The pci_rescan_bus() covers all the operations of the replaced functions:
- assigning new bus numbers, as the pci_hp_add_bridge() does it;
- allocating BARs (pci_assign_unassigned_bridge_resources());
- cofiguring MPS settings (pcie_bus_configure_settings());
- binding devices to their drivers (pci_bus_add_devices()).
CC: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Sergey Miroshnichenko <s.miroshnichenko@yadro.com>
---
drivers/pci/hotplug/pciehp_pci.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/drivers/pci/hotplug/pciehp_pci.c b/drivers/pci/hotplug/pciehp_pci.c
index d17f3bf36f70..6d4c1ef38210 100644
--- a/drivers/pci/hotplug/pciehp_pci.c
+++ b/drivers/pci/hotplug/pciehp_pci.c
@@ -58,6 +58,11 @@ int pciehp_configure_device(struct controller *ctrl)
goto out;
}
+ if (pci_can_move_bars) {
+ pci_rescan_bus(parent);
+ goto out;
+ }
+
for_each_pci_bridge(dev, parent)
pci_hp_add_bridge(dev);
--
2.23.0
^ permalink raw reply related [flat|nested] 35+ messages in thread* [PATCH v6 30/30] Revert "powerpc/powernv/pci: Work around races in PCI bridge enabling"
2019-10-24 17:11 [PATCH v6 00/30] PCI: Allow BAR movement during hotplug Sergey Miroshnichenko
` (28 preceding siblings ...)
2019-10-24 17:12 ` [PATCH v6 29/30] PCI: pciehp: movable BARs: Trigger a domain rescan on hp events Sergey Miroshnichenko
@ 2019-10-24 17:12 ` Sergey Miroshnichenko
29 siblings, 0 replies; 35+ messages in thread
From: Sergey Miroshnichenko @ 2019-10-24 17:12 UTC (permalink / raw)
To: linux-pci, linuxppc-dev
Cc: Bjorn Helgaas, linux, Sergey Miroshnichenko, Benjamin Herrenschmidt
This reverts commit db2173198b9513f7add8009f225afa1f1c79bcc6.
The root cause of this bug is fixed by the following two commits:
1. "PCI: Fix race condition in pci_enable/disable_device()"
2. "PCI: Enable bridge's I/O and MEM access for hotplugged devices"
The x86 is also affected by this bug if a PCIe bridge has been hotplugged
without pre-enabling by the BIOS.
CC: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Sergey Miroshnichenko <s.miroshnichenko@yadro.com>
---
arch/powerpc/platforms/powernv/pci-ioda.c | 37 -----------------------
1 file changed, 37 deletions(-)
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 33d5ed8c258f..f12f3a49d3bb 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -3119,49 +3119,12 @@ static void pnv_pci_ioda_create_dbgfs(void)
#endif /* CONFIG_DEBUG_FS */
}
-static void pnv_pci_enable_bridge(struct pci_bus *bus)
-{
- struct pci_dev *dev = bus->self;
- struct pci_bus *child;
-
- /* Empty bus ? bail */
- if (list_empty(&bus->devices))
- return;
-
- /*
- * If there's a bridge associated with that bus enable it. This works
- * around races in the generic code if the enabling is done during
- * parallel probing. This can be removed once those races have been
- * fixed.
- */
- if (dev) {
- int rc = pci_enable_device(dev);
- if (rc)
- pci_err(dev, "Error enabling bridge (%d)\n", rc);
- pci_set_master(dev);
- }
-
- /* Perform the same to child busses */
- list_for_each_entry(child, &bus->children, node)
- pnv_pci_enable_bridge(child);
-}
-
-static void pnv_pci_enable_bridges(void)
-{
- struct pci_controller *hose;
-
- list_for_each_entry(hose, &hose_list, list_node)
- pnv_pci_enable_bridge(hose->bus);
-}
-
static void pnv_pci_ioda_fixup(void)
{
pnv_pci_ioda_setup_PEs();
pnv_pci_ioda_setup_iommu_api();
pnv_pci_ioda_create_dbgfs();
- pnv_pci_enable_bridges();
-
#ifdef CONFIG_EEH
pnv_eeh_post_init();
#endif
--
2.23.0
^ permalink raw reply related [flat|nested] 35+ messages in thread