Skip to content

K
Kernel

openeuler / Kernel
1 年多 前同步成功

通知 8
Star 0
Fork 0
K
Kernel
切换分支/标签
  1. 27 3月, 2019 1 次提交
    • P
      srcu: Remove cleanup_srcu_struct_quiesced() · f5ad3991
      由 Paul E. McKenney 提交于 
      The cleanup_srcu_struct_quiesced() function was added because NVME
used WQ_MEM_RECLAIM workqueues and SRCU did not, which meant that
NVME workqueues waiting on SRCU workqueues could result in deadlocks
during low-memory conditions.  However, SRCU now also has WQ_MEM_RECLAIM
workqueues, so there is no longer a potential for deadlock.  Furthermore,
it turns out to be extremely hard to use cleanup_srcu_struct_quiesced()
correctly due to the fact that SRCU callback invocation accesses the
srcu_struct structure's per-CPU data area just after callbacks are
invoked.  Therefore, the usual practice of using srcu_barrier() to wait
for callbacks to be invoked before invoking cleanup_srcu_struct_quiesced()
fails because SRCU's callback-invocation workqueue handler might be
delayed, which can result in cleanup_srcu_struct_quiesced() being invoked
(and thus freeing the per-CPU data) before the SRCU's callback-invocation
workqueue handler is finished using that per-CPU data.  Nor is this a
theoretical problem: KASAN emitted use-after-free warnings because of
this problem on actual runs.

In short, NVME can now safely invoke cleanup_srcu_struct(), which
avoids the use-after-free scenario.  And cleanup_srcu_struct_quiesced()
is quite difficult to use safely.  This commit therefore removes
cleanup_srcu_struct_quiesced(), switching its sole user back to
cleanup_srcu_struct().  This effectively reverts the following pair
of commits:

f7194ac3 ("srcu: Add cleanup_srcu_struct_quiesced()")
4317228a ("nvme: Avoid flush dependency in delete controller flow")
Reported-by: NBart Van Assche <bvanassche@acm.org>
Signed-off-by: NPaul E. McKenney <paulmck@linux.ibm.com>
Reviewed-by: NBart Van Assche <bvanassche@acm.org>
Tested-by: NBart Van Assche <bvanassche@acm.org>
      f5ad3991
  3. 14 3月, 2019 13 次提交
  5. 21 2月, 2019 1 次提交
  7. 20 2月, 2019 13 次提交
  9. 18 2月, 2019 2 次提交
    • M
      nvme-pci: Simplify interrupt allocation · 612b7286
      由 Ming Lei 提交于 
      The NVME PCI driver contains a tedious mechanism for interrupt
allocation, which is necessary to adjust the number and size of interrupt
sets to the maximum available number of interrupts which depends on the
underlying PCI capabilities and the available CPU resources.

It works around the former short comings of the PCI and core interrupt
allocation mechanims in combination with interrupt sets.

The PCI interrupt allocation function allows to provide a maximum and a
minimum number of interrupts to be allocated and tries to allocate as
many as possible. This worked without driver interaction as long as there
was only a single set of interrupts to handle.

With the addition of support for multiple interrupt sets in the generic
affinity spreading logic, which is invoked from the PCI interrupt
allocation, the adaptive loop in the PCI interrupt allocation did not
work for multiple interrupt sets. The reason is that depending on the
total number of interrupts which the PCI allocation adaptive loop tries
to allocate in each step, the number and the size of the interrupt sets
need to be adapted as well. Due to the way the interrupt sets support was
implemented there was no way for the PCI interrupt allocation code or the
core affinity spreading mechanism to invoke a driver specific function
for adapting the interrupt sets configuration.

As a consequence the driver had to implement another adaptive loop around
the PCI interrupt allocation function and calling that with maximum and
minimum interrupts set to the same value. This ensured that the
allocation either succeeded or immediately failed without any attempt to
adjust the number of interrupts in the PCI code.

The core code now allows drivers to provide a callback to recalculate the
number and the size of interrupt sets during PCI interrupt allocation,
which in turn allows the PCI interrupt allocation function to be called
in the same way as with a single set of interrupts. The PCI code handles
the adaptive loop and the interrupt affinity spreading mechanism invokes
the driver callback to adapt the interrupt set configuration to the
current loop value. This replaces the adaptive loop in the driver
completely.

Implement the NVME specific callback which adjusts the interrupt sets
configuration and remove the adaptive allocation loop.

[ tglx: Simplify the callback further and restore the dropped adjustment of
  	number of sets ]
Signed-off-by: NMing Lei <ming.lei@redhat.com>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: NMarc Zyngier <marc.zyngier@arm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Bjorn Helgaas <helgaas@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org
Cc: Sagi Grimberg <sagi@grimberg.me>
Cc: linux-nvme@lists.infradead.org
Cc: linux-pci@vger.kernel.org
Cc: Keith Busch <keith.busch@intel.com>
Cc: Sumit Saxena <sumit.saxena@broadcom.com>
Cc: Kashyap Desai <kashyap.desai@broadcom.com>
Cc: Shivasharan Srikanteshwara <shivasharan.srikanteshwara@broadcom.com>
Link: https://lkml.kernel.org/r/20190216172228.602546658@linutronix.de
      612b7286
    • M
      genirq/affinity: Store interrupt sets size in struct irq_affinity · 9cfef55b
      由 Ming Lei 提交于 
      The interrupt affinity spreading mechanism supports to spread out
affinities for one or more interrupt sets. A interrupt set contains one
or more interrupts. Each set is mapped to a specific functionality of a
device, e.g. general I/O queues and read I/O queus of multiqueue block
devices.

The number of interrupts per set is defined by the driver. It depends on
the total number of available interrupts for the device, which is
determined by the PCI capabilites and the availability of underlying CPU
resources, and the number of queues which the device provides and the
driver wants to instantiate.

The driver passes initial configuration for the interrupt allocation via
a pointer to struct irq_affinity.

Right now the allocation mechanism is complex as it requires to have a
loop in the driver to determine the maximum number of interrupts which
are provided by the PCI capabilities and the underlying CPU resources.
This loop would have to be replicated in every driver which wants to
utilize this mechanism. That's unwanted code duplication and error
prone.

In order to move this into generic facilities it is required to have a
mechanism, which allows the recalculation of the interrupt sets and
their size, in the core code. As the core code does not have any
knowledge about the underlying device, a driver specific callback will
be added to struct affinity_desc, which will be invoked by the core
code. The callback will get the number of available interupts as an
argument, so the driver can calculate the corresponding number and size
of interrupt sets.

To support this, two modifications for the handling of struct irq_affinity
are required:

1) The (optional) interrupt sets size information is contained in a
   separate array of integers and struct irq_affinity contains a
   pointer to it.

   This is cumbersome and as the maximum number of interrupt sets is small,
   there is no reason to have separate storage. Moving the size array into
   struct affinity_desc avoids indirections and makes the code simpler.

2) At the moment the struct irq_affinity pointer which is handed in from
   the driver and passed through to several core functions is marked
   'const'.

   With the upcoming callback to recalculate the number and size of
   interrupt sets, it's necessary to remove the 'const'
   qualifier. Otherwise the callback would not be able to update the data.

Implement #1 and store the interrupt sets size in 'struct irq_affinity'.

No functional change.

[ tglx: Fixed the memcpy() size so it won't copy beyond the size of the
  	source. Fixed the kernel doc comments for struct irq_affinity and
  	de-'This patch'-ed the changelog ]
Signed-off-by: NMing Lei <ming.lei@redhat.com>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Acked-by: NMarc Zyngier <marc.zyngier@arm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Bjorn Helgaas <helgaas@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org
Cc: Sagi Grimberg <sagi@grimberg.me>
Cc: linux-nvme@lists.infradead.org
Cc: linux-pci@vger.kernel.org
Cc: Keith Busch <keith.busch@intel.com>
Cc: Sumit Saxena <sumit.saxena@broadcom.com>
Cc: Kashyap Desai <kashyap.desai@broadcom.com>
Cc: Shivasharan Srikanteshwara <shivasharan.srikanteshwara@broadcom.com>
Link: https://lkml.kernel.org/r/20190216172228.423723127@linutronix.de
      9cfef55b
  11. 12 2月, 2019 1 次提交
  13. 06 2月, 2019 2 次提交
  15. 04 2月, 2019 2 次提交
  17. 24 1月, 2019 4 次提交
    • H
      nvme-multipath: drop optimization for static ANA group IDs · 78a61cd4
      由 Hannes Reinecke 提交于 
      Bit 6 in the ANACAP field is used to indicate that the ANA group ID
doesn't change while the namespace is attached to the controller.
There is an optimisation in the code to only allocate space
for the ANA group header, as the namespace list won't change and
hence would not need to be refreshed.
However, this optimisation was never carried over to the actual
workflow, which always assumes that the buffer is large enough
to hold the ANA header _and_ the namespace list.
So drop this optimisation and always allocate enough space.
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NHannes Reinecke <hare@suse.com>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
Signed-off-by: NJens Axboe <axboe@kernel.dk>
      78a61cd4
    • S
      nvme-rdma: rework queue maps handling · b1064d3e
      由 Sagi Grimberg 提交于 
      If the device supports less queues than provided (if the device has less
completion vectors), we might hit a bug due to the fact that we ignore
that in nvme_rdma_map_queues (we override the maps nr_queues with user
opts).

Instead, keep track of how many default/read/poll queues we actually
allocated (rather than asked by the user) and use that to assign our
queue mappings.

Fixes: b65bb777 (" nvme-rdma: support separate queue maps for read and write")
Reported-by: NSaleem, Shiraz <shiraz.saleem@intel.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
Signed-off-by: NJens Axboe <axboe@kernel.dk>
      b1064d3e
    • S
      nvme-tcp: fix timeout handler · 39d57757
      由 Sagi Grimberg 提交于 
      Currently, we have several problems with the timeout
handler:
1. If we timeout on the controller establishment flow, we will hang
because we don't execute the error recovery (and we shouldn't because
the create_ctrl flow needs to fail and cleanup on its own)
2. We might also hang if we get a disconnet on a queue while the
controller is already deleting. This racy flow can cause the controller
disable/shutdown admin command to hang.

We cannot complete a timed out request from the timeout handler without
mutual exclusion from the teardown flow (e.g. nvme_rdma_error_recovery_work).
So we serialize it in the timeout handler and teardown io and admin
queues to guarantee that no one races with us from completing the
request.
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
Signed-off-by: NJens Axboe <axboe@kernel.dk>
      39d57757
    • S
      nvme-rdma: fix timeout handler · 4c174e63
      由 Sagi Grimberg 提交于 
      Currently, we have several problems with the timeout
handler:
1. If we timeout on the controller establishment flow, we will hang
because we don't execute the error recovery (and we shouldn't because
the create_ctrl flow needs to fail and cleanup on its own)
2. We might also hang if we get a disconnet on a queue while the
controller is already deleting. This racy flow can cause the controller
disable/shutdown admin command to hang.

We cannot complete a timed out request from the timeout handler without
mutual exclusion from the teardown flow (e.g. nvme_rdma_error_recovery_work).
So we serialize it in the timeout handler and teardown io and admin
queues to guarantee that no one races with us from completing the
request.
Reported-by: NJaesoo Lee <jalee@purestorage.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NSagi Grimberg <sagi@grimberg.me>
Signed-off-by: NJens Axboe <axboe@kernel.dk>
      4c174e63
  19. 17 1月, 2019 1 次提交
    • M
      nvme-pci: fix nvme_setup_irqs() · c45b1fa2
      由 Ming Lei 提交于 
      When -ENOSPC is returned from pci_alloc_irq_vectors_affinity(),
we still try to allocate multiple irq vectors again, so irq queues
covers the admin queue actually. But we don't consider that, then
number of the allocated irq vector may be same with sum of
io_queues[HCTX_TYPE_DEFAULT] and io_queues[HCTX_TYPE_READ], this way
is obviously wrong, and finally breaks nvme_pci_map_queues(), and
warning from pci_irq_get_affinity() is triggered.

IRQ queues should cover admin queues, this patch makes this
point explicitely in nvme_calc_io_queues().

We got severl boot failure internal report on aarch64, so please
consider to fix it in v4.20.

Fixes: 6451fe73 ("nvme: fix irq vs io_queue calculations")
Signed-off-by: NMing Lei <ming.lei@redhat.com>
Reviewed-by: NKeith Busch <keith.busch@intel.com>
Tested-by: Nfin4478 <fin4478@hotmail.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>
      c45b1fa2