[PATCH v3 0/4] arm64: Add AT_HWCAP3

[PATCH v3 0/4] arm64: Add AT_HWCAP3

[Mark Brown]

Currently for arm64 we expose hwcaps to userspace using the low 32 bits
of AT_HWCAP and AT_HWCAP2. Due to the ever expanding capabilties of the
architecture we have now allocated all the available bits in this scheme
so we need to expand, either using the higher bits or adding a new
AT_HWCAP3. Discussions with glibc developers suggested that AT_HWCAP3
would be cleaner for them so the series adopts that approach.

The final patch adds an initial value in AT_HWCAP3 reporting the
presence of FEAT_EBF16, this will conflict with my series converting
ID_AA64ISAR1_EL1 to be generated. I've got a version based on top of
that which I can send if that's convenient.

v3:
 - Expand comment on CPU_FEATURES_PER_HWCAP.
v2:
 - Rebase onto v5.19-rc3.

Mark Brown (4):
  arm64/cpufeature: Store elf_hwcaps as an array rather than unsigned
    long
  elf: Allow architectures to provide AT_HWCAP3
  arm64/cpufeature: Support AT_HWCAP3
  arm64/hwcap: Support FEAT_EBF16

 Documentation/arm64/elf_hwcaps.rst  | 10 +++++++---
 arch/arm64/include/asm/cpufeature.h |  9 ++++++++-
 arch/arm64/include/asm/hwcap.h      | 17 ++++++++++++-----
 arch/arm64/include/uapi/asm/hwcap.h |  5 +++++
 arch/arm64/kernel/cpufeature.c      | 28 +++++++++++++++++++++-------
 arch/arm64/kernel/cpuinfo.c         |  1 +
 fs/binfmt_elf.c                     |  3 +++
 include/uapi/linux/auxvec.h         |  1 +
 8 files changed, 58 insertions(+), 16 deletions(-)


base-commit: a111daf0c53ae91e71fd2bfe7497862d14132e3e
-- 
2.30.2


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH v3 1/4] arm64/cpufeature: Store elf_hwcaps as an array rather than unsigned long

[Mark Brown]

When we added support for AT_HWCAP2 we took advantage of the fact that we
have limited hwcaps to the low 32 bits and stored it along with AT_HWCAP
in a single unsigned integer. Thanks to the ever expanding capabilities of
the architecture we have now allocated all 64 of the bits in an unsigned
long so in preparation for adding more hwcaps convert elf_hwcap to be an
array instead. There should be no functional change from this patch.

Signed-off-by: Mark Brown <broonie@kernel.org>
---
 arch/arm64/include/asm/cpufeature.h |  6 ++++++
 arch/arm64/include/asm/hwcap.h      |  4 +++-
 arch/arm64/kernel/cpufeature.c      | 22 +++++++++++++++-------
 3 files changed, 24 insertions(+), 8 deletions(-)

diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 14a8f3d93add..6c0284ca703e 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -11,6 +11,12 @@
 #include <asm/hwcap.h>
 #include <asm/sysreg.h>
 
+/*
+ * To support potential future 32 bit only ABIs and/or libc usage we
+ * currently only allocate the bottom 32 bits. Bits 62 and 63 of
+ * AT_HWCAP are reserved for glibc.
+ */
+#define CPU_FEATURES_PER_HWCAP	32
 #define MAX_CPU_FEATURES	64
 #define cpu_feature(x)		KERNEL_HWCAP_ ## x
 
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index aa443d8f8cfb..e0054c7b3a98 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -41,6 +41,8 @@
 #ifndef __ASSEMBLY__
 #include <linux/log2.h>
 
+#define KHWCAP_OFFSET(n)		((n - 1) * CPU_FEATURES_PER_HWCAP)
+
 /*
  * For userspace we represent hwcaps as a collection of HWCAP{,2}_x bitfields
  * as described in uapi/asm/hwcap.h. For the kernel we represent hwcaps as
@@ -85,7 +87,7 @@
 #define KERNEL_HWCAP_PACA		__khwcap_feature(PACA)
 #define KERNEL_HWCAP_PACG		__khwcap_feature(PACG)
 
-#define __khwcap2_feature(x)		(const_ilog2(HWCAP2_ ## x) + 32)
+#define __khwcap2_feature(x)		(const_ilog2(HWCAP2_ ## x) + KHWCAP_OFFSET(2))
 #define KERNEL_HWCAP_DCPODP		__khwcap2_feature(DCPODP)
 #define KERNEL_HWCAP_SVE2		__khwcap2_feature(SVE2)
 #define KERNEL_HWCAP_SVEAES		__khwcap2_feature(SVEAES)
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 8d88433de81d..1a8f60a6661e 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -91,7 +91,7 @@
 #include <asm/virt.h>
 
 /* Kernel representation of AT_HWCAP and AT_HWCAP2 */
-static unsigned long elf_hwcap __read_mostly;
+static unsigned long elf_hwcap[MAX_CPU_FEATURES / CPU_FEATURES_PER_HWCAP] __read_mostly;
 
 #ifdef CONFIG_COMPAT
 #define COMPAT_ELF_HWCAP_DEFAULT	\
@@ -3098,14 +3098,22 @@ static bool __maybe_unused __system_matches_cap(unsigned int n)
 
 void cpu_set_feature(unsigned int num)
 {
-	WARN_ON(num >= MAX_CPU_FEATURES);
-	elf_hwcap |= BIT(num);
+	int i = num / CPU_FEATURES_PER_HWCAP;
+	int bit = num % CPU_FEATURES_PER_HWCAP;
+
+	WARN_ON(i >= ARRAY_SIZE(elf_hwcap));
+
+	elf_hwcap[i] |= BIT(bit);
 }
 
 bool cpu_have_feature(unsigned int num)
 {
-	WARN_ON(num >= MAX_CPU_FEATURES);
-	return elf_hwcap & BIT(num);
+	int i = num / CPU_FEATURES_PER_HWCAP;
+	int bit = num % CPU_FEATURES_PER_HWCAP;
+
+	WARN_ON(i >= ARRAY_SIZE(elf_hwcap));
+
+	return elf_hwcap[i] & BIT(bit);
 }
 EXPORT_SYMBOL_GPL(cpu_have_feature);
 
@@ -3116,12 +3124,12 @@ unsigned long cpu_get_elf_hwcap(void)
 	 * note that for userspace compatibility we guarantee that bits 62
 	 * and 63 will always be returned as 0.
 	 */
-	return lower_32_bits(elf_hwcap);
+	return elf_hwcap[0];
 }
 
 unsigned long cpu_get_elf_hwcap2(void)
 {
-	return upper_32_bits(elf_hwcap);
+	return elf_hwcap[1];
 }
 
 static void __init setup_system_capabilities(void)
-- 
2.30.2


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH v3 2/4] elf: Allow architectures to provide AT_HWCAP3

[Mark Brown]

In order to provide for architectures which have filled both AT_HWCAP and
AT_HWCAP2 add support for AT_HWCAP3.

Signed-off-by: Mark Brown <broonie@kernel.org>
---
 fs/binfmt_elf.c             | 3 +++
 include/uapi/linux/auxvec.h | 1 +
 2 files changed, 4 insertions(+)

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 63c7ebb0da89..59d937dddc09 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -275,6 +275,9 @@ create_elf_tables(struct linux_binprm *bprm, const struct elfhdr *exec,
 	NEW_AUX_ENT(AT_RANDOM, (elf_addr_t)(unsigned long)u_rand_bytes);
 #ifdef ELF_HWCAP2
 	NEW_AUX_ENT(AT_HWCAP2, ELF_HWCAP2);
+#endif
+#ifdef ELF_HWCAP3
+	NEW_AUX_ENT(AT_HWCAP3, ELF_HWCAP3);
 #endif
 	NEW_AUX_ENT(AT_EXECFN, bprm->exec);
 	if (k_platform) {
diff --git a/include/uapi/linux/auxvec.h b/include/uapi/linux/auxvec.h
index c7e502bf5a6f..76631c7f9e8f 100644
--- a/include/uapi/linux/auxvec.h
+++ b/include/uapi/linux/auxvec.h
@@ -30,6 +30,7 @@
 				 * differ from AT_PLATFORM. */
 #define AT_RANDOM 25	/* address of 16 random bytes */
 #define AT_HWCAP2 26	/* extension of AT_HWCAP */
+#define AT_HWCAP3 27	/* further extension of AT_HWCAP */
 
 #define AT_EXECFN  31	/* filename of program */
 
-- 
2.30.2


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH v3 3/4] arm64/cpufeature: Support AT_HWCAP3

[Mark Brown]

We have filled the low 32 bits of both AT_HWCAP and AT_HWCAP2 so in order
to support further architecture features we must either start allocating
from the upper 32 bits or add a new AT_HWCAP3. Feedback from the glibc
developers was that AT_HWCAP3 would be cleaner so go with that.

This patch merely adds the glue required for AT_HWCAP3, meaning that we
start providing AT_HWCAP3 for ELF executables but no bits will be set in
it.

Signed-off-by: Mark Brown <broonie@kernel.org>
---
 Documentation/arm64/elf_hwcaps.rst  |  6 +++---
 arch/arm64/include/asm/cpufeature.h |  3 ++-
 arch/arm64/include/asm/hwcap.h      | 12 ++++++++----
 arch/arm64/include/uapi/asm/hwcap.h |  4 ++++
 arch/arm64/kernel/cpufeature.c      |  5 +++++
 5 files changed, 22 insertions(+), 8 deletions(-)

diff --git a/Documentation/arm64/elf_hwcaps.rst b/Documentation/arm64/elf_hwcaps.rst
index 3d116fb536c5..5f4d89c4afe2 100644
--- a/Documentation/arm64/elf_hwcaps.rst
+++ b/Documentation/arm64/elf_hwcaps.rst
@@ -16,9 +16,9 @@ architected discovery mechanism available to userspace code at EL0. The
 kernel exposes the presence of these features to userspace through a set
 of flags called hwcaps, exposed in the auxilliary vector.
 
-Userspace software can test for features by acquiring the AT_HWCAP or
-AT_HWCAP2 entry of the auxiliary vector, and testing whether the relevant
-flags are set, e.g.::
+Userspace software can test for features by acquiring the AT_HWCAP,
+AT_HWCAP2 or AT_HWCAP3 entry of the auxiliary vector, and testing
+whether the relevant flags are set, e.g.::
 
 	bool floating_point_is_present(void)
 	{
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 6c0284ca703e..b03a0819834f 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -17,7 +17,7 @@
  * AT_HWCAP are reserved for glibc.
  */
 #define CPU_FEATURES_PER_HWCAP	32
-#define MAX_CPU_FEATURES	64
+#define MAX_CPU_FEATURES	96
 #define cpu_feature(x)		KERNEL_HWCAP_ ## x
 
 #ifndef __ASSEMBLY__
@@ -440,6 +440,7 @@ void cpu_set_feature(unsigned int num);
 bool cpu_have_feature(unsigned int num);
 unsigned long cpu_get_elf_hwcap(void);
 unsigned long cpu_get_elf_hwcap2(void);
+unsigned long cpu_get_elf_hwcap3(void);
 
 #define cpu_set_named_feature(name) cpu_set_feature(cpu_feature(name))
 #define cpu_have_named_feature(name) cpu_have_feature(cpu_feature(name))
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index e0054c7b3a98..1ef208ab6895 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -44,10 +44,11 @@
 #define KHWCAP_OFFSET(n)		((n - 1) * CPU_FEATURES_PER_HWCAP)
 
 /*
- * For userspace we represent hwcaps as a collection of HWCAP{,2}_x bitfields
- * as described in uapi/asm/hwcap.h. For the kernel we represent hwcaps as
- * natural numbers (in a single range of size MAX_CPU_FEATURES) defined here
- * with prefix KERNEL_HWCAP_ mapped to their HWCAP{,2}_x counterpart.
+ * For userspace we represent hwcaps as a collection of HWCAP{,[23]}_x
+ * bitfields as described in uapi/asm/hwcap.h. For the kernel we
+ * represent hwcaps as natural numbers (in a single range of size
+ * MAX_CPU_FEATURES) defined here with prefix KERNEL_HWCAP_ mapped to
+ * their HWCAP{,2}_x counterpart.
  *
  * Hwcaps should be set and tested within the kernel via the
  * cpu_{set,have}_named_feature(feature) where feature is the unique suffix
@@ -121,12 +122,15 @@
 #define KERNEL_HWCAP_SME_FA64		__khwcap2_feature(SME_FA64)
 #define KERNEL_HWCAP_WFXT		__khwcap2_feature(WFXT)
 
+#define __khwcap3_feature(x)		(const_ilog2(HWCAP3_ ## x) + KHWCAP_OFFSET(3))
+
 /*
  * This yields a mask that user programs can use to figure out what
  * instruction set this cpu supports.
  */
 #define ELF_HWCAP		cpu_get_elf_hwcap()
 #define ELF_HWCAP2		cpu_get_elf_hwcap2()
+#define ELF_HWCAP3		cpu_get_elf_hwcap3()
 
 #ifdef CONFIG_COMPAT
 #define COMPAT_ELF_HWCAP	(compat_elf_hwcap)
diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h
index 4bb2cc8ac446..7b818f8fc01b 100644
--- a/arch/arm64/include/uapi/asm/hwcap.h
+++ b/arch/arm64/include/uapi/asm/hwcap.h
@@ -89,4 +89,8 @@
 #define HWCAP2_SME_FA64		(1 << 30)
 #define HWCAP2_WFXT		(1UL << 31)
 
+/*
+ * HWCAP3 flags - for AT_HWCAP3
+ */
+
 #endif /* _UAPI__ASM_HWCAP_H */
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 1a8f60a6661e..7605b213d9db 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -3132,6 +3132,11 @@ unsigned long cpu_get_elf_hwcap2(void)
 	return elf_hwcap[1];
 }
 
+unsigned long cpu_get_elf_hwcap3(void)
+{
+	return elf_hwcap[2];
+}
+
 static void __init setup_system_capabilities(void)
 {
 	/*
-- 
2.30.2


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH v3 4/4] arm64/hwcap: Support FEAT_EBF16

[Mark Brown]

The v9.2 feature FEAT_EBF16 provides support for an extended BFloat16 mode.
Allow userspace to discover system support for this feature by adding a
hwcap for it.

Signed-off-by: Mark Brown <broonie@kernel.org>
---
 Documentation/arm64/elf_hwcaps.rst  | 4 ++++
 arch/arm64/include/asm/hwcap.h      | 1 +
 arch/arm64/include/uapi/asm/hwcap.h | 1 +
 arch/arm64/kernel/cpufeature.c      | 1 +
 arch/arm64/kernel/cpuinfo.c         | 1 +
 5 files changed, 8 insertions(+)

diff --git a/Documentation/arm64/elf_hwcaps.rst b/Documentation/arm64/elf_hwcaps.rst
index 5f4d89c4afe2..4dab74a70cc1 100644
--- a/Documentation/arm64/elf_hwcaps.rst
+++ b/Documentation/arm64/elf_hwcaps.rst
@@ -301,6 +301,10 @@ HWCAP2_WFXT
 
     Functionality implied by ID_AA64ISAR2_EL1.WFXT == 0b0010.
 
+HWCAP3_EBF16
+
+    Functionality implied by ID_AA64ISAR1_EL1.BF16 == 0b0010.
+
 4. Unused AT_HWCAP bits
 -----------------------
 
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index 1ef208ab6895..cf670e4afc16 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -123,6 +123,7 @@
 #define KERNEL_HWCAP_WFXT		__khwcap2_feature(WFXT)
 
 #define __khwcap3_feature(x)		(const_ilog2(HWCAP3_ ## x) + KHWCAP_OFFSET(3))
+#define KERNEL_HWCAP_EBF16		__khwcap3_feature(EBF16)
 
 /*
  * This yields a mask that user programs can use to figure out what
diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h
index 7b818f8fc01b..3b6644f0c07f 100644
--- a/arch/arm64/include/uapi/asm/hwcap.h
+++ b/arch/arm64/include/uapi/asm/hwcap.h
@@ -92,5 +92,6 @@
 /*
  * HWCAP3 flags - for AT_HWCAP3
  */
+#define HWCAP3_EBF16		(1 << 0)
 
 #endif /* _UAPI__ASM_HWCAP_H */
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 7605b213d9db..79850a0cd563 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -2623,6 +2623,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_FRINTTS_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FRINT),
 	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_SB_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SB),
 	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_BF16_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_BF16),
+	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_BF16_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_EBF16),
 	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_DGH_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_DGH),
 	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_I8MM_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_I8MM),
 	HWCAP_CAP(SYS_ID_AA64MMFR2_EL1, ID_AA64MMFR2_AT_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_USCAT),
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 8eff0a34ffd4..2ca131243c30 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -107,6 +107,7 @@ static const char *const hwcap_str[] = {
 	[KERNEL_HWCAP_SME_F32F32]	= "smef32f32",
 	[KERNEL_HWCAP_SME_FA64]		= "smefa64",
 	[KERNEL_HWCAP_WFXT]		= "wfxt",
+	[KERNEL_HWCAP_EBF16]		= "ebf16",
 };
 
 #ifdef CONFIG_COMPAT
-- 
2.30.2


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel