Merge branch 'asm-generic-mmiotrace' into asm-generic

A patch series from Sai Prakash Ranjan, who explains:

Generic MMIO read/write i.e., __raw_{read,write}{b,l,w,q} accessors
are typically used to read/write from/to memory mapped registers
and can cause hangs or some undefined behaviour in following cases,

* If the access to the register space is unclocked, for example: if
  there is an access to multimedia(MM) block registers without MM
  clocks.

* If the register space is protected and not set to be accessible from
  non-secure world, for example: only EL3 (EL: Exception level) access
  is allowed and any EL2/EL1 access is forbidden.

* If xPU(memory/register protection units) is controlling access to
  certain memory/register space for specific clients.

and more...

Such cases usually results in instant reboot/SErrors/NOC or interconnect
hangs and tracing these register accesses can be very helpful to debug
such issues during initial development stages and also in later stages.

So use ftrace trace events to log such MMIO register accesses which
provides rich feature set such as early enablement of trace events,
filtering capability, dumping ftrace logs on console and many more.

Sample output:

rwmmio_write: __qcom_geni_serial_console_write+0x160/0x1e0 width=32 val=0xa0d5d addr=0xfffffbfffdbff700
rwmmio_post_write: __qcom_geni_serial_console_write+0x160/0x1e0 width=32 val=0xa0d5d addr=0xfffffbfffdbff700
rwmmio_read: qcom_geni_serial_poll_bit+0x94/0x138 width=32 addr=0xfffffbfffdbff610
rwmmio_post_read: qcom_geni_serial_poll_bit+0x94/0x138 width=32 val=0x0 addr=0xfffffbfffdbff610

This series is a follow-up for the series [1] and a recent series [2] making use
of both.

[1] https://lore.kernel.org/lkml/cover.1536430404.git.saiprakash.ranjan@codeaurora.org/
[2] https://lore.kernel.org/lkml/1604631386-178312-1-git-send-email-psodagud@codeaurora.org/

Note in v4 version, Arnd suggested to benchmark and compare size with callback
based implementation, please see [3] for more details on that with brief comparison below.

**Inline version with CONFIG_FTRACE=y and CONFIG_TRACE_MMIO_ACCESS=y**
$ size vmlinux
   text           data             bss     dec             hex         filename
 23884219        14284468         532568 38701255        24e88c7        vmlinux

**Callback version with CONFIG_FTRACE=y and CONFIG_TRACE_MMIO_ACCESS=y**
$ size vmlinux
    text          data             bss     dec             hex        filename
 24108179        14279596         532568 38920343        251e097       vmlinux

$ ./scripts/bloat-o-meter inline-vmlinux callback-vmlinux
add/remove: 8/3 grow/shrink: 4889/89 up/down: 242244/-11564 (230680)
Total: Before=25812612, After=26043292, chg +0.89%

[3] https://lore.kernel.org/lkml/466449a1-36da-aaa9-7e4f-477f36b52c9e@quicinc.com/

Link: https://lore.kernel.org/lkml/cover.1652891705.git.quic_saipraka@quicinc.com/

* asm-generic-mmiotrace:
  soc: qcom: geni: Disable MMIO tracing for GENI SE
  serial: qcom_geni_serial: Disable MMIO tracing for geni serial
  asm-generic/io: Add logging support for MMIO accessors
  KVM: arm64: Add a flag to disable MMIO trace for nVHE KVM
  lib: Add register read/write tracing support
  drm/meson: Fix overflow implicit truncation warnings
  irqchip/tegra: Fix overflow implicit truncation warnings
  coresight: etm4x: Use asm-generic IO memory barriers
  arm64: io: Use asm-generic high level MMIO accessors
  arch/*: Disable softirq stacks on PREEMPT_RT.

2 files changed, 88 insertions, 5 deletions

diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h
index 7ce93aaf69f8..9c5114335a2d 100644
--- a/include/asm-generic/io.h
+++ b/include/asm-generic/io.h
@@ -10,6 +10,7 @@
 #include <asm/page.h> /* I/O is all done through memory accesses */
 #include <linux/string.h> /* for memset() and memcpy() */
 #include <linux/types.h>
+#include <linux/instruction_pointer.h>
 
 #ifdef CONFIG_GENERIC_IOMAP
 #include <asm-generic/iomap.h>
@@ -61,6 +62,44 @@
 #define __io_par(v)     __io_ar(v)
 #endif
 
+/*
+ * "__DISABLE_TRACE_MMIO__" flag can be used to disable MMIO tracing for
+ * specific kernel drivers in case of excessive/unwanted logging.
+ *
+ * Usage: Add a #define flag at the beginning of the driver file.
+ * Ex: #define __DISABLE_TRACE_MMIO__
+ *     #include <...>
+ *     ...
+ */
+#if IS_ENABLED(CONFIG_TRACE_MMIO_ACCESS) && !(defined(__DISABLE_TRACE_MMIO__))
+#include <linux/tracepoint-defs.h>
+
+DECLARE_TRACEPOINT(rwmmio_write);
+DECLARE_TRACEPOINT(rwmmio_post_write);
+DECLARE_TRACEPOINT(rwmmio_read);
+DECLARE_TRACEPOINT(rwmmio_post_read);
+
+void log_write_mmio(u64 val, u8 width, volatile void __iomem *addr,
+		    unsigned long caller_addr);
+void log_post_write_mmio(u64 val, u8 width, volatile void __iomem *addr,
+			 unsigned long caller_addr);
+void log_read_mmio(u8 width, const volatile void __iomem *addr,
+		   unsigned long caller_addr);
+void log_post_read_mmio(u64 val, u8 width, const volatile void __iomem *addr,
+			unsigned long caller_addr);
+
+#else
+
+static inline void log_write_mmio(u64 val, u8 width, volatile void __iomem *addr,
+				  unsigned long caller_addr) {}
+static inline void log_post_write_mmio(u64 val, u8 width, volatile void __iomem *addr,
+				       unsigned long caller_addr) {}
+static inline void log_read_mmio(u8 width, const volatile void __iomem *addr,
+				 unsigned long caller_addr) {}
+static inline void log_post_read_mmio(u64 val, u8 width, const volatile void __iomem *addr,
+				      unsigned long caller_addr) {}
+
+#endif /* CONFIG_TRACE_MMIO_ACCESS */
 
 /*
  * __raw_{read,write}{b,w,l,q}() access memory in native endianness.
@@ -149,9 +188,11 @@ static inline u8 readb(const volatile void __iomem *addr)
 {
 	u8 val;
 
+	log_read_mmio(8, addr, _THIS_IP_);
 	__io_br();
 	val = __raw_readb(addr);
 	__io_ar(val);
+	log_post_read_mmio(val, 8, addr, _THIS_IP_);
 	return val;
 }
 #endif
@@ -162,9 +203,11 @@ static inline u16 readw(const volatile void __iomem *addr)
 {
 	u16 val;
 
+	log_read_mmio(16, addr, _THIS_IP_);
 	__io_br();
 	val = __le16_to_cpu((__le16 __force)__raw_readw(addr));
 	__io_ar(val);
+	log_post_read_mmio(val, 16, addr, _THIS_IP_);
 	return val;
 }
 #endif
@@ -175,9 +218,11 @@ static inline u32 readl(const volatile void __iomem *addr)
 {
 	u32 val;
 
+	log_read_mmio(32, addr, _THIS_IP_);
 	__io_br();
 	val = __le32_to_cpu((__le32 __force)__raw_readl(addr));
 	__io_ar(val);
+	log_post_read_mmio(val, 32, addr, _THIS_IP_);
 	return val;
 }
 #endif
@@ -189,9 +234,11 @@ static inline u64 readq(const volatile void __iomem *addr)
 {
 	u64 val;
 
+	log_read_mmio(64, addr, _THIS_IP_);
 	__io_br();
 	val = __le64_to_cpu(__raw_readq(addr));
 	__io_ar(val);
+	log_post_read_mmio(val, 64, addr, _THIS_IP_);
 	return val;
 }
 #endif
@@ -201,9 +248,11 @@ static inline u64 readq(const volatile void __iomem *addr)
 #define writeb writeb
 static inline void writeb(u8 value, volatile void __iomem *addr)
 {
+	log_write_mmio(value, 8, addr, _THIS_IP_);
 	__io_bw();
 	__raw_writeb(value, addr);
 	__io_aw();
+	log_post_write_mmio(value, 8, addr, _THIS_IP_);
 }
 #endif
 
@@ -211,9 +260,11 @@ static inline void writeb(u8 value, volatile void __iomem *addr)
 #define writew writew
 static inline void writew(u16 value, volatile void __iomem *addr)
 {
+	log_write_mmio(value, 16, addr, _THIS_IP_);
 	__io_bw();
 	__raw_writew((u16 __force)cpu_to_le16(value), addr);
 	__io_aw();
+	log_post_write_mmio(value, 16, addr, _THIS_IP_);
 }
 #endif
 
@@ -221,9 +272,11 @@ static inline void writew(u16 value, volatile void __iomem *addr)
 #define writel writel
 static inline void writel(u32 value, volatile void __iomem *addr)
 {
+	log_write_mmio(value, 32, addr, _THIS_IP_);
 	__io_bw();
 	__raw_writel((u32 __force)__cpu_to_le32(value), addr);
 	__io_aw();
+	log_post_write_mmio(value, 32, addr, _THIS_IP_);
 }
 #endif
 
@@ -232,9 +285,11 @@ static inline void writel(u32 value, volatile void __iomem *addr)
 #define writeq writeq
 static inline void writeq(u64 value, volatile void __iomem *addr)
 {
+	log_write_mmio(value, 64, addr, _THIS_IP_);
 	__io_bw();
 	__raw_writeq(__cpu_to_le64(value), addr);
 	__io_aw();
+	log_post_write_mmio(value, 64, addr, _THIS_IP_);
 }
 #endif
 #endif /* CONFIG_64BIT */
@@ -248,7 +303,12 @@ static inline void writeq(u64 value, volatile void __iomem *addr)
 #define readb_relaxed readb_relaxed
 static inline u8 readb_relaxed(const volatile void __iomem *addr)
 {
-	return __raw_readb(addr);
+	u8 val;
+
+	log_read_mmio(8, addr, _THIS_IP_);
+	val = __raw_readb(addr);
+	log_post_read_mmio(val, 8, addr, _THIS_IP_);
+	return val;
 }
 #endif
 
@@ -256,7 +316,12 @@ static inline u8 readb_relaxed(const volatile void __iomem *addr)
 #define readw_relaxed readw_relaxed
 static inline u16 readw_relaxed(const volatile void __iomem *addr)
 {
-	return __le16_to_cpu(__raw_readw(addr));
+	u16 val;
+
+	log_read_mmio(16, addr, _THIS_IP_);
+	val = __le16_to_cpu(__raw_readw(addr));
+	log_post_read_mmio(val, 16, addr, _THIS_IP_);
+	return val;
 }
 #endif
 
@@ -264,7 +329,12 @@ static inline u16 readw_relaxed(const volatile void __iomem *addr)
 #define readl_relaxed readl_relaxed
 static inline u32 readl_relaxed(const volatile void __iomem *addr)
 {
-	return __le32_to_cpu(__raw_readl(addr));
+	u32 val;
+
+	log_read_mmio(32, addr, _THIS_IP_);
+	val = __le32_to_cpu(__raw_readl(addr));
+	log_post_read_mmio(val, 32, addr, _THIS_IP_);
+	return val;
 }
 #endif
 
@@ -272,7 +342,12 @@ static inline u32 readl_relaxed(const volatile void __iomem *addr)
 #define readq_relaxed readq_relaxed
 static inline u64 readq_relaxed(const volatile void __iomem *addr)
 {
-	return __le64_to_cpu(__raw_readq(addr));
+	u64 val;
+
+	log_read_mmio(64, addr, _THIS_IP_);
+	val = __le64_to_cpu(__raw_readq(addr));
+	log_post_read_mmio(val, 64, addr, _THIS_IP_);
+	return val;
 }
 #endif
 
@@ -280,7 +355,9 @@ static inline u64 readq_relaxed(const volatile void __iomem *addr)
 #define writeb_relaxed writeb_relaxed
 static inline void writeb_relaxed(u8 value, volatile void __iomem *addr)
 {
+	log_write_mmio(value, 8, addr, _THIS_IP_);
 	__raw_writeb(value, addr);
+	log_post_write_mmio(value, 8, addr, _THIS_IP_);
 }
 #endif
 
@@ -288,7 +365,9 @@ static inline void writeb_relaxed(u8 value, volatile void __iomem *addr)
 #define writew_relaxed writew_relaxed
 static inline void writew_relaxed(u16 value, volatile void __iomem *addr)
 {
+	log_write_mmio(value, 16, addr, _THIS_IP_);
 	__raw_writew(cpu_to_le16(value), addr);
+	log_post_write_mmio(value, 16, addr, _THIS_IP_);
 }
 #endif
 
@@ -296,7 +375,9 @@ static inline void writew_relaxed(u16 value, volatile void __iomem *addr)
 #define writel_relaxed writel_relaxed
 static inline void writel_relaxed(u32 value, volatile void __iomem *addr)
 {
+	log_write_mmio(value, 32, addr, _THIS_IP_);
 	__raw_writel(__cpu_to_le32(value), addr);
+	log_post_write_mmio(value, 32, addr, _THIS_IP_);
 }
 #endif
 
@@ -304,7 +385,9 @@ static inline void writel_relaxed(u32 value, volatile void __iomem *addr)
 #define writeq_relaxed writeq_relaxed
 static inline void writeq_relaxed(u64 value, volatile void __iomem *addr)
 {
+	log_write_mmio(value, 64, addr, _THIS_IP_);
 	__raw_writeq(__cpu_to_le64(value), addr);
+	log_post_write_mmio(value, 64, addr, _THIS_IP_);
 }
 #endif
 
diff --git a/include/asm-generic/softirq_stack.h b/include/asm-generic/softirq_stack.h
index eceeecf6a5bd..d3e2d81656e0 100644
--- a/include/asm-generic/softirq_stack.h
+++ b/include/asm-generic/softirq_stack.h
@@ -2,7 +2,7 @@
 #ifndef __ASM_GENERIC_SOFTIRQ_STACK_H
 #define __ASM_GENERIC_SOFTIRQ_STACK_H
 
-#ifdef CONFIG_HAVE_SOFTIRQ_ON_OWN_STACK
+#if defined(CONFIG_HAVE_SOFTIRQ_ON_OWN_STACK) && !defined(CONFIG_PREEMPT_RT)
 void do_softirq_own_stack(void);
 #else
 static inline void do_softirq_own_stack(void)