From: Will Deacon will.deacon@arm.com
[ Upstream commit 6460d32014717686d3b7963595950ba2c6d1bb5e ]
A relatively standard idiom for ensuring that a pair of MMIO writes to a device arrive at that device with a specified minimum delay between them is as follows:
writel_relaxed(42, dev_base + CTL1); readl(dev_base + CTL1); udelay(10); writel_relaxed(42, dev_base + CTL2);
the intention being that the read-back from the device will push the prior write to CTL1, and the udelay will hold up the write to CTL1 until at least 10us have elapsed.
Unfortunately, on arm64 where the underlying delay loop is implemented as a read of the architected counter, the CPU does not guarantee ordering from the readl() to the delay loop and therefore the delay loop could in theory be speculated and not provide the desired interval between the two writes.
Fix this in a similar manner to PowerPC by introducing a dummy control dependency on the output of readX() which, combined with the ISB in the read of the architected counter, guarantees that a subsequent delay loop can not be executed until the readX() has returned its result.
Cc: Benjamin Herrenschmidt benh@kernel.crashing.org Cc: Arnd Bergmann arnd@arndb.de Signed-off-by: Will Deacon will.deacon@arm.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/include/asm/io.h | 31 +++++++++++++++++++++++-------- 1 file changed, 23 insertions(+), 8 deletions(-)
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h index 9f8b915af3a7..d42d00d8d5b6 100644 --- a/arch/arm64/include/asm/io.h +++ b/arch/arm64/include/asm/io.h @@ -104,7 +104,22 @@ static inline u64 __raw_readq(const volatile void __iomem *addr) }
/* IO barriers */ -#define __iormb() rmb() +#define __iormb(v) \ +({ \ + unsigned long tmp; \ + \ + rmb(); \ + \ + /* \ + * Create a dummy control dependency from the IO read to any \ + * later instructions. This ensures that a subsequent call to \ + * udelay() will be ordered due to the ISB in get_cycles(). \ + */ \ + asm volatile("eor %0, %1, %1\n" \ + "cbnz %0, ." \ + : "=r" (tmp) : "r" (v) : "memory"); \ +}) + #define __iowmb() wmb()
#define mmiowb() do { } while (0) @@ -129,10 +144,10 @@ static inline u64 __raw_readq(const volatile void __iomem *addr) * following Normal memory access. Writes are ordered relative to any prior * Normal memory access. */ -#define readb(c) ({ u8 __v = readb_relaxed(c); __iormb(); __v; }) -#define readw(c) ({ u16 __v = readw_relaxed(c); __iormb(); __v; }) -#define readl(c) ({ u32 __v = readl_relaxed(c); __iormb(); __v; }) -#define readq(c) ({ u64 __v = readq_relaxed(c); __iormb(); __v; }) +#define readb(c) ({ u8 __v = readb_relaxed(c); __iormb(__v); __v; }) +#define readw(c) ({ u16 __v = readw_relaxed(c); __iormb(__v); __v; }) +#define readl(c) ({ u32 __v = readl_relaxed(c); __iormb(__v); __v; }) +#define readq(c) ({ u64 __v = readq_relaxed(c); __iormb(__v); __v; })
#define writeb(v,c) ({ __iowmb(); writeb_relaxed((v),(c)); }) #define writew(v,c) ({ __iowmb(); writew_relaxed((v),(c)); }) @@ -183,9 +198,9 @@ extern void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size); /* * io{read,write}{16,32,64}be() macros */ -#define ioread16be(p) ({ __u16 __v = be16_to_cpu((__force __be16)__raw_readw(p)); __iormb(); __v; }) -#define ioread32be(p) ({ __u32 __v = be32_to_cpu((__force __be32)__raw_readl(p)); __iormb(); __v; }) -#define ioread64be(p) ({ __u64 __v = be64_to_cpu((__force __be64)__raw_readq(p)); __iormb(); __v; }) +#define ioread16be(p) ({ __u16 __v = be16_to_cpu((__force __be16)__raw_readw(p)); __iormb(__v); __v; }) +#define ioread32be(p) ({ __u32 __v = be32_to_cpu((__force __be32)__raw_readl(p)); __iormb(__v); __v; }) +#define ioread64be(p) ({ __u64 __v = be64_to_cpu((__force __be64)__raw_readq(p)); __iormb(__v); __v; })
#define iowrite16be(v,p) ({ __iowmb(); __raw_writew((__force __u16)cpu_to_be16(v), p); }) #define iowrite32be(v,p) ({ __iowmb(); __raw_writel((__force __u32)cpu_to_be32(v), p); })