Merge patch series "riscv: Allow userspace to directly access perf counters"

Alexandre Ghiti <alexghiti@rivosinc.com> says:

riscv used to allow direct access to cycle/time/instret counters,
bypassing the perf framework, this patchset intends to allow the user to
mmap any counter when accessed through perf.

**Important**: The default mode is now user access through perf only, not
the legacy so some applications will break. However, we introduce a sysctl
perf_user_access like arm64 does, which will allow to switch to the legacy
mode described above.

This version needs openSBI v1.3 *and* a kernel fix that went upstream lately
(https://lore.kernel.org/lkml/20230616114831.3186980-1-maz@kernel.org/T/).

* b4-shazam-merge:
  perf: tests: Adapt mmap-basic.c for riscv
  tools: lib: perf: Implement riscv mmap support
  Documentation: admin-guide: Add riscv sysctl_perf_user_access
  drivers: perf: Implement perf event mmap support in the SBI backend
  drivers: perf: Implement perf event mmap support in the legacy backend
  riscv: Prepare for user-space perf event mmap support
  drivers: perf: Rename riscv pmu sbi driver
  riscv: Make legacy counter enum match the HW numbering
  include: riscv: Fix wrong include guard in riscv_pmu.h
  perf: Fix wrong comment about default event_idx

Link: https://lore.kernel.org/r/20230802080328.1213905-1-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

2 files changed, 70 insertions, 2 deletions

diff --git a/tools/lib/perf/mmap.c b/tools/lib/perf/mmap.c
index 0d1634cedf44..2184814b37dd 100644
--- a/tools/lib/perf/mmap.c
+++ b/tools/lib/perf/mmap.c
@@ -392,6 +392,72 @@ static u64 read_perf_counter(unsigned int counter)
 
 static u64 read_timestamp(void) { return read_sysreg(cntvct_el0); }
 
+/* __riscv_xlen contains the witdh of the native base integer, here 64-bit */
+#elif defined(__riscv) && __riscv_xlen == 64
+
+/* TODO: implement rv32 support */
+
+#define CSR_CYCLE	0xc00
+#define CSR_TIME	0xc01
+
+#define csr_read(csr)						\
+({								\
+	register unsigned long __v;				\
+		__asm__ __volatile__ ("csrr %0, %1"		\
+		 : "=r" (__v)					\
+		 : "i" (csr) : );				\
+		 __v;						\
+})
+
+static unsigned long csr_read_num(int csr_num)
+{
+#define switchcase_csr_read(__csr_num, __val)           {\
+	case __csr_num:                                 \
+		__val = csr_read(__csr_num);            \
+		break; }
+#define switchcase_csr_read_2(__csr_num, __val)         {\
+	switchcase_csr_read(__csr_num + 0, __val)        \
+	switchcase_csr_read(__csr_num + 1, __val)}
+#define switchcase_csr_read_4(__csr_num, __val)         {\
+	switchcase_csr_read_2(__csr_num + 0, __val)      \
+	switchcase_csr_read_2(__csr_num + 2, __val)}
+#define switchcase_csr_read_8(__csr_num, __val)         {\
+	switchcase_csr_read_4(__csr_num + 0, __val)      \
+	switchcase_csr_read_4(__csr_num + 4, __val)}
+#define switchcase_csr_read_16(__csr_num, __val)        {\
+	switchcase_csr_read_8(__csr_num + 0, __val)      \
+	switchcase_csr_read_8(__csr_num + 8, __val)}
+#define switchcase_csr_read_32(__csr_num, __val)        {\
+	switchcase_csr_read_16(__csr_num + 0, __val)     \
+	switchcase_csr_read_16(__csr_num + 16, __val)}
+
+	unsigned long ret = 0;
+
+	switch (csr_num) {
+	switchcase_csr_read_32(CSR_CYCLE, ret)
+	default:
+		break;
+	}
+
+	return ret;
+#undef switchcase_csr_read_32
+#undef switchcase_csr_read_16
+#undef switchcase_csr_read_8
+#undef switchcase_csr_read_4
+#undef switchcase_csr_read_2
+#undef switchcase_csr_read
+}
+
+static u64 read_perf_counter(unsigned int counter)
+{
+	return csr_read_num(CSR_CYCLE + counter);
+}
+
+static u64 read_timestamp(void)
+{
+	return csr_read_num(CSR_TIME);
+}
+
 #else
 static u64 read_perf_counter(unsigned int counter __maybe_unused) { return 0; }
 static u64 read_timestamp(void) { return 0; }
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index e68ca6229756..886a13a77a16 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -284,7 +284,8 @@ static struct test_case tests__basic_mmap[] = {
 			 "permissions"),
 	TEST_CASE_REASON("User space counter reading of instructions",
 			 mmap_user_read_instr,
-#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__)
+#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__) || \
+			 (defined(__riscv) && __riscv_xlen == 64)
 			 "permissions"
 #else
 			 "unsupported"
@@ -292,7 +293,8 @@ static struct test_case tests__basic_mmap[] = {
 		),
 	TEST_CASE_REASON("User space counter reading of cycles",
 			 mmap_user_read_cycles,
-#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__)
+#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__) || \
+			 (defined(__riscv) && __riscv_xlen == 64)
 			 "permissions"
 #else
 			 "unsupported"