1 ==============================================
2 Ordering I/O writes to memory-mapped addresses
3 ==============================================
5 On some platforms, so-called memory-mapped I/O is weakly ordered. On such
6 platforms, driver writers are responsible for ensuring that I/O writes to
7 memory-mapped addresses on their device arrive in the order intended. This is
8 typically done by reading a 'safe' device or bridge register, causing the I/O
9 chipset to flush pending writes to the device before any reads are posted. A
10 driver would usually use this technique immediately prior to the exit of a
11 critical section of code protected by spinlocks. This would ensure that
12 subsequent writes to I/O space arrived only after all prior writes (much like a
13 memory barrier op, mb(), only with respect to I/O).
15 A more concrete example from a hypothetical device driver::
18 CPU A: spin_lock_irqsave(&dev_lock, flags)
19 CPU A: val = readl(my_status);
21 CPU A: writel(newval, ring_ptr);
22 CPU A: spin_unlock_irqrestore(&dev_lock, flags)
24 CPU B: spin_lock_irqsave(&dev_lock, flags)
25 CPU B: val = readl(my_status);
27 CPU B: writel(newval2, ring_ptr);
28 CPU B: spin_unlock_irqrestore(&dev_lock, flags)
31 In the case above, the device may receive newval2 before it receives newval,
32 which could cause problems. Fixing it is easy enough though::
35 CPU A: spin_lock_irqsave(&dev_lock, flags)
36 CPU A: val = readl(my_status);
38 CPU A: writel(newval, ring_ptr);
39 CPU A: (void)readl(safe_register); /* maybe a config register? */
40 CPU A: spin_unlock_irqrestore(&dev_lock, flags)
42 CPU B: spin_lock_irqsave(&dev_lock, flags)
43 CPU B: val = readl(my_status);
45 CPU B: writel(newval2, ring_ptr);
46 CPU B: (void)readl(safe_register); /* maybe a config register? */
47 CPU B: spin_unlock_irqrestore(&dev_lock, flags)
49 Here, the reads from safe_register will cause the I/O chipset to flush any
50 pending writes before actually posting the read to the chipset, preventing
51 possible data corruption.