Merge patch series "RISC-V: Apply Zicboz to clear_page"

Andrew Jones <ajones@ventanamicro.com> says:

When the Zicboz extension is available we can more rapidly zero naturally
aligned Zicboz block sized chunks of memory. As pages are always page
aligned and are larger than any Zicboz block size will be, then
clear_page() appears to be a good candidate for the extension. While cycle
count and energy consumption should also be considered, we can be pretty
certain that implementing clear_page() with the Zicboz extension is a win
by comparing the new dynamic instruction count with its current count[1].
Doing so we see that the new count is just over a quarter of the old count
(see patch6's commit message for more details).

For those of you who reviewed v1[2], you may be looking for the memset()
patches. As pointed out in v1, and a couple follow-up emails, it's not
clear that patching memset() is a win yet. When I get a chance to test
on real hardware with a comprehensive benchmark collection then I can
post the memset() patches separately (assuming the benchmarks show it's
worthwhile).

* b4-shazam-merge:
  RISC-V: KVM: Expose Zicboz to the guest
  RISC-V: KVM: Provide UAPI for Zicboz block size
  RISC-V: Use Zicboz in clear_page when available
  RISC-V: cpufeatures: Put the upper 16 bits of patch ID to work
  RISC-V: Add Zicboz detection and block size parsing
  dt-bindings: riscv: Document cboz-block-size
  RISC-V: Factor out body of riscv_init_cbom_blocksize loop
  RISC-V: alternatives: Support patching multiple insns in assembly

Link: https://lore.kernel.org/r/20230224162631.405473-1-ajones@ventanamicro.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

1 files changed, 54 insertions, 4 deletions

diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index 4f805c7c5a22..00d7cd2c9043 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -74,6 +74,15 @@ static bool riscv_isa_extension_check(int id)
 			return false;
 		}
 		return true;
+	case RISCV_ISA_EXT_ZICBOZ:
+		if (!riscv_cboz_block_size) {
+			pr_err("Zicboz detected in ISA string, but no cboz-block-size found\n");
+			return false;
+		} else if (!is_power_of_2(riscv_cboz_block_size)) {
+			pr_err("cboz-block-size present, but is not a power-of-2\n");
+			return false;
+		}
+		return true;
 	}
 
 	return true;
@@ -223,6 +232,7 @@ void __init riscv_fill_hwcap(void)
 				SET_ISA_EXT_MAP("svpbmt", RISCV_ISA_EXT_SVPBMT);
 				SET_ISA_EXT_MAP("zbb", RISCV_ISA_EXT_ZBB);
 				SET_ISA_EXT_MAP("zicbom", RISCV_ISA_EXT_ZICBOM);
+				SET_ISA_EXT_MAP("zicboz", RISCV_ISA_EXT_ZICBOZ);
 				SET_ISA_EXT_MAP("zihintpause", RISCV_ISA_EXT_ZIHINTPAUSE);
 			}
 #undef SET_ISA_EXT_MAP
@@ -265,12 +275,46 @@ void __init riscv_fill_hwcap(void)
 }
 
 #ifdef CONFIG_RISCV_ALTERNATIVE
+/*
+ * Alternative patch sites consider 48 bits when determining when to patch
+ * the old instruction sequence with the new. These bits are broken into a
+ * 16-bit vendor ID and a 32-bit patch ID. A non-zero vendor ID means the
+ * patch site is for an erratum, identified by the 32-bit patch ID. When
+ * the vendor ID is zero, the patch site is for a cpufeature. cpufeatures
+ * further break down patch ID into two 16-bit numbers. The lower 16 bits
+ * are the cpufeature ID and the upper 16 bits are used for a value specific
+ * to the cpufeature and patch site. If the upper 16 bits are zero, then it
+ * implies no specific value is specified. cpufeatures that want to control
+ * patching on a per-site basis will provide non-zero values and implement
+ * checks here. The checks return true when patching should be done, and
+ * false otherwise.
+ */
+static bool riscv_cpufeature_patch_check(u16 id, u16 value)
+{
+	if (!value)
+		return true;
+
+	switch (id) {
+	case RISCV_ISA_EXT_ZICBOZ:
+		/*
+		 * Zicboz alternative applications provide the maximum
+		 * supported block size order, or zero when it doesn't
+		 * matter. If the current block size exceeds the maximum,
+		 * then the alternative cannot be applied.
+		 */
+		return riscv_cboz_block_size <= (1U << value);
+	}
+
+	return false;
+}
+
 void __init_or_module riscv_cpufeature_patch_func(struct alt_entry *begin,
 						  struct alt_entry *end,
 						  unsigned int stage)
 {
 	struct alt_entry *alt;
 	void *oldptr, *altptr;
+	u16 id, value;
 
 	if (stage == RISCV_ALTERNATIVES_EARLY_BOOT)
 		return;
@@ -278,13 +322,19 @@ void __init_or_module riscv_cpufeature_patch_func(struct alt_entry *begin,
 	for (alt = begin; alt < end; alt++) {
 		if (alt->vendor_id != 0)
 			continue;
-		if (alt->patch_id >= RISCV_ISA_EXT_MAX) {
-			WARN(1, "This extension id:%d is not in ISA extension list",
-				alt->patch_id);
+
+		id = PATCH_ID_CPUFEATURE_ID(alt->patch_id);
+
+		if (id >= RISCV_ISA_EXT_MAX) {
+			WARN(1, "This extension id:%d is not in ISA extension list", id);
 			continue;
 		}
 
-		if (!__riscv_isa_extension_available(NULL, alt->patch_id))
+		if (!__riscv_isa_extension_available(NULL, id))
+			continue;
+
+		value = PATCH_ID_CPUFEATURE_VALUE(alt->patch_id);
+		if (!riscv_cpufeature_patch_check(id, value))
 			continue;
 
 		oldptr = ALT_OLD_PTR(alt);