Documentation: Kill all references to mmiowb()

The guarantees provided by mmiowb() are now provided implicitly by
spin_unlock(), so remove all references to this most confusing of
barriers from our Documentation.

Good riddance.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
This commit is contained in:
Will Deacon 2019-02-22 16:17:54 +00:00
parent b012980d1c
commit 915530396c
3 changed files with 4 additions and 148 deletions

View File

@ -103,51 +103,6 @@ continuing execution::
ha->flags.ints_enabled = 0;
}
In addition to write posting, on some large multiprocessing systems
(e.g. SGI Challenge, Origin and Altix machines) posted writes won't be
strongly ordered coming from different CPUs. Thus it's important to
properly protect parts of your driver that do memory-mapped writes with
locks and use the :c:func:`mmiowb()` to make sure they arrive in the
order intended. Issuing a regular readX() will also ensure write ordering,
but should only be used when the
driver has to be sure that the write has actually arrived at the device
(not that it's simply ordered with respect to other writes), since a
full readX() is a relatively expensive operation.
Generally, one should use :c:func:`mmiowb()` prior to releasing a spinlock
that protects regions using :c:func:`writeb()` or similar functions that
aren't surrounded by readb() calls, which will ensure ordering
and flushing. The following pseudocode illustrates what might occur if
write ordering isn't guaranteed via :c:func:`mmiowb()` or one of the
readX() functions::
CPU A: spin_lock_irqsave(&dev_lock, flags)
CPU A: ...
CPU A: writel(newval, ring_ptr);
CPU A: spin_unlock_irqrestore(&dev_lock, flags)
...
CPU B: spin_lock_irqsave(&dev_lock, flags)
CPU B: writel(newval2, ring_ptr);
CPU B: ...
CPU B: spin_unlock_irqrestore(&dev_lock, flags)
In the case above, newval2 could be written to ring_ptr before newval.
Fixing it is easy though::
CPU A: spin_lock_irqsave(&dev_lock, flags)
CPU A: ...
CPU A: writel(newval, ring_ptr);
CPU A: mmiowb(); /* ensure no other writes beat us to the device */
CPU A: spin_unlock_irqrestore(&dev_lock, flags)
...
CPU B: spin_lock_irqsave(&dev_lock, flags)
CPU B: writel(newval2, ring_ptr);
CPU B: ...
CPU B: mmiowb();
CPU B: spin_unlock_irqrestore(&dev_lock, flags)
See tg3.c for a real world example of how to use :c:func:`mmiowb()`
PCI ordering rules also guarantee that PIO read responses arrive after any
outstanding DMA writes from that bus, since for some devices the result of
a readb() call may signal to the driver that a DMA transaction is

View File

@ -132,10 +132,6 @@ precludes passing these pages to userspace.
P2P memory is also technically IO memory but should never have any side
effects behind it. Thus, the order of loads and stores should not be important
and ioreadX(), iowriteX() and friends should not be necessary.
However, as the memory is not cache coherent, if access ever needs to
be protected by a spinlock then :c:func:`mmiowb()` must be used before
unlocking the lock. (See ACQUIRES VS I/O ACCESSES in
Documentation/memory-barriers.txt)
P2P DMA Support Library

View File

@ -1937,21 +1937,6 @@ There are some more advanced barrier functions:
information on consistent memory.
MMIO WRITE BARRIER
------------------
The Linux kernel also has a special barrier for use with memory-mapped I/O
writes:
mmiowb();
This is a variation on the mandatory write barrier that causes writes to weakly
ordered I/O regions to be partially ordered. Its effects may go beyond the
CPU->Hardware interface and actually affect the hardware at some level.
See the subsection "Acquires vs I/O accesses" for more information.
===============================
IMPLICIT KERNEL MEMORY BARRIERS
===============================
@ -2317,75 +2302,6 @@ But it won't see any of:
*E, *F or *G following RELEASE Q
ACQUIRES VS I/O ACCESSES
------------------------
Under certain circumstances (especially involving NUMA), I/O accesses within
two spinlocked sections on two different CPUs may be seen as interleaved by the
PCI bridge, because the PCI bridge does not necessarily participate in the
cache-coherence protocol, and is therefore incapable of issuing the required
read memory barriers.
For example:
CPU 1 CPU 2
=============================== ===============================
spin_lock(Q)
writel(0, ADDR)
writel(1, DATA);
spin_unlock(Q);
spin_lock(Q);
writel(4, ADDR);
writel(5, DATA);
spin_unlock(Q);
may be seen by the PCI bridge as follows:
STORE *ADDR = 0, STORE *ADDR = 4, STORE *DATA = 1, STORE *DATA = 5
which would probably cause the hardware to malfunction.
What is necessary here is to intervene with an mmiowb() before dropping the
spinlock, for example:
CPU 1 CPU 2
=============================== ===============================
spin_lock(Q)
writel(0, ADDR)
writel(1, DATA);
mmiowb();
spin_unlock(Q);
spin_lock(Q);
writel(4, ADDR);
writel(5, DATA);
mmiowb();
spin_unlock(Q);
this will ensure that the two stores issued on CPU 1 appear at the PCI bridge
before either of the stores issued on CPU 2.
Furthermore, following a store by a load from the same device obviates the need
for the mmiowb(), because the load forces the store to complete before the load
is performed:
CPU 1 CPU 2
=============================== ===============================
spin_lock(Q)
writel(0, ADDR)
a = readl(DATA);
spin_unlock(Q);
spin_lock(Q);
writel(4, ADDR);
b = readl(DATA);
spin_unlock(Q);
See Documentation/driver-api/device-io.rst for more information.
=================================
WHERE ARE MEMORY BARRIERS NEEDED?
=================================
@ -2532,16 +2448,9 @@ the device to malfunction.
Inside of the Linux kernel, I/O should be done through the appropriate accessor
routines - such as inb() or writel() - which know how to make such accesses
appropriately sequential. While this, for the most part, renders the explicit
use of memory barriers unnecessary, there are a couple of situations where they
might be needed:
(1) On some systems, I/O stores are not strongly ordered across all CPUs, and
so for _all_ general drivers locks should be used and mmiowb() must be
issued prior to unlocking the critical section.
(2) If the accessor functions are used to refer to an I/O memory window with
relaxed memory access properties, then _mandatory_ memory barriers are
required to enforce ordering.
use of memory barriers unnecessary, if the accessor functions are used to refer
to an I/O memory window with relaxed memory access properties, then _mandatory_
memory barriers are required to enforce ordering.
See Documentation/driver-api/device-io.rst for more information.
@ -2586,8 +2495,7 @@ explicit barriers are used.
Normally this won't be a problem because the I/O accesses done inside such
sections will include synchronous load operations on strictly ordered I/O
registers that form implicit I/O barriers. If this isn't sufficient then an
mmiowb() may need to be used explicitly.
registers that form implicit I/O barriers.
A similar situation may occur between an interrupt routine and two routines
@ -2687,9 +2595,6 @@ guarantees:
All of these accessors assume that the underlying peripheral is little-endian,
and will therefore perform byte-swapping operations on big-endian architectures.
Composing I/O ordering barriers with SMP ordering barriers and LOCK/UNLOCK
operations is a dangerous sport which may require the use of mmiowb(). See the
subsection "Acquires vs I/O accesses" for more information.
========================================
ASSUMED MINIMUM EXECUTION ORDERING MODEL