Merge patch series "riscv: ASID-related and UP-related TLB flush enhancements"

Samuel Holland <samuel.holland@sifive.com> says:

This series converts uniprocessor kernel builds to use the same TLB
flushing code as SMP builds, to take advantage of batching and existing
range- and ASID-based TLB flush optimizations. It optimizes out IPIs and
SBI calls based on the online CPU count, which also covers the scenario
where SMP was enabled at build time but only one CPU is present/online.
A final optimization is to use single-ASID flushes wherever possible, to
avoid unnecessary TLB misses for kernel mappings.

This series has a semantic conflict with the AIA patches that are in
linux-next due to the removal of the third parameter of
riscv_ipi_set_virq_range(), which is called from imsic_ipi_domain_init()
in drivers/irqchip/irq-riscv-imsic-early.c. The resolution is to remove
the extra argument from the call site.

Here are some numbers from D1 which show the performance impact:

v6.9-rc1:
 System Benchmarks Partial Index              BASELINE       RESULT    INDEX
 Execl Throughput                                 43.0        198.5     46.2
 File Copy 1024 bufsize 2000 maxblocks          3960.0      73934.4    186.7
 File Copy 256 bufsize 500 maxblocks            1655.0      20242.6    122.3
 File Copy 4096 bufsize 8000 maxblocks          5800.0     197706.4    340.9
 Pipe Throughput                               12440.0     176974.2    142.3
 Pipe-based Context Switching                   4000.0      23626.8     59.1
 Process Creation                                126.0        449.9     35.7
 Shell Scripts (1 concurrent)                     42.4        544.4    128.4
 Shell Scripts (16 concurrent)                     ---         35.3      ---
 Shell Scripts (8 concurrent)                      6.0         71.6    119.3
 System Call Overhead                          15000.0     248072.6    165.4
                                                                    ========
 System Benchmarks Index Score (Partial Only)                          110.6

v6.9-rc1 + this patch series:
 System Benchmarks Partial Index              BASELINE       RESULT    INDEX
 Execl Throughput                                 43.0        196.8     45.8
 File Copy 1024 bufsize 2000 maxblocks          3960.0      71782.2    181.3
 File Copy 256 bufsize 500 maxblocks            1655.0      21269.4    128.5
 File Copy 4096 bufsize 8000 maxblocks          5800.0     199424.0    343.8
 Pipe Throughput                               12440.0     196468.6    157.9
 Pipe-based Context Switching                   4000.0      24261.8     60.7
 Process Creation                                126.0        459.0     36.4
 Shell Scripts (1 concurrent)                     42.4        543.8    128.2
 Shell Scripts (16 concurrent)                     ---         35.5      ---
 Shell Scripts (8 concurrent)                      6.0         71.7    119.6
 System Call Overhead                          15000.0     259415.2    172.9
                                                                    ========
 System Benchmarks Index Score (Partial Only)                          113.0

* b4-shazam-lts:
  riscv: mm: Always use an ASID to flush mm contexts
  riscv: mm: Preserve global TLB entries when switching contexts
  riscv: mm: Make asid_bits a local variable
  riscv: mm: Use a fixed layout for the MM context ID
  riscv: mm: Introduce cntx2asid/cntx2version helper macros
  riscv: Avoid TLB flush loops when affected by SiFive CIP-1200
  riscv: Apply SiFive CIP-1200 workaround to single-ASID sfence.vma
  riscv: mm: Combine the SMP and UP TLB flush code
  riscv: Only send remote fences when some other CPU is online
  riscv: mm: Broadcast kernel TLB flushes only when needed
  riscv: Use IPIs for remote cache/TLB flushes by default
  riscv: Factor out page table TLB synchronization
  riscv: Flush the instruction cache during SMP bringup

Link: https://lore.kernel.org/r/20240327045035.368512-1-samuel.holland@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

3 files changed, 15 insertions, 14 deletions

diff --git a/arch/riscv/kernel/sbi-ipi.c b/arch/riscv/kernel/sbi-ipi.c
index a4559695ce62..1026e22955cc 100644
--- a/arch/riscv/kernel/sbi-ipi.c
+++ b/arch/riscv/kernel/sbi-ipi.c
@@ -13,6 +13,9 @@
 #include <linux/irqdomain.h>
 #include <asm/sbi.h>
 
+DEFINE_STATIC_KEY_FALSE(riscv_sbi_for_rfence);
+EXPORT_SYMBOL_GPL(riscv_sbi_for_rfence);
+
 static int sbi_ipi_virq;
 
 static void sbi_ipi_handle(struct irq_desc *desc)
@@ -72,6 +75,12 @@ void __init sbi_ipi_init(void)
 			  "irqchip/sbi-ipi:starting",
 			  sbi_ipi_starting_cpu, NULL);
 
-	riscv_ipi_set_virq_range(virq, BITS_PER_BYTE, false);
+	riscv_ipi_set_virq_range(virq, BITS_PER_BYTE);
 	pr_info("providing IPIs using SBI IPI extension\n");
+
+	/*
+	 * Use the SBI remote fence extension to avoid
+	 * the extra context switch needed to handle IPIs.
+	 */
+	static_branch_enable(&riscv_sbi_for_rfence);
 }
diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c
index 45dd4035416e..8e6eb64459af 100644
--- a/arch/riscv/kernel/smp.c
+++ b/arch/riscv/kernel/smp.c
@@ -171,10 +171,7 @@ bool riscv_ipi_have_virq_range(void)
 	return (ipi_virq_base) ? true : false;
 }
 
-DEFINE_STATIC_KEY_FALSE(riscv_ipi_for_rfence);
-EXPORT_SYMBOL_GPL(riscv_ipi_for_rfence);
-
-void riscv_ipi_set_virq_range(int virq, int nr, bool use_for_rfence)
+void riscv_ipi_set_virq_range(int virq, int nr)
 {
 	int i, err;
 
@@ -197,12 +194,6 @@ void riscv_ipi_set_virq_range(int virq, int nr, bool use_for_rfence)
 
 	/* Enabled IPIs for boot CPU immediately */
 	riscv_ipi_enable();
-
-	/* Update RFENCE static key */
-	if (use_for_rfence)
-		static_branch_enable(&riscv_ipi_for_rfence);
-	else
-		static_branch_disable(&riscv_ipi_for_rfence);
 }
 
 static const char * const ipi_names[] = {
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
index d41090fc3203..4b3c50da48ba 100644
--- a/arch/riscv/kernel/smpboot.c
+++ b/arch/riscv/kernel/smpboot.c
@@ -26,7 +26,7 @@
 #include <linux/sched/task_stack.h>
 #include <linux/sched/mm.h>
 
-#include <asm/cpufeature.h>
+#include <asm/cacheflush.h>
 #include <asm/cpu_ops.h>
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
@@ -234,9 +234,10 @@ asmlinkage __visible void smp_callin(void)
 	riscv_user_isa_enable();
 
 	/*
-	 * Remote TLB flushes are ignored while the CPU is offline, so emit
-	 * a local TLB flush right now just in case.
+	 * Remote cache and TLB flushes are ignored while the CPU is offline,
+	 * so flush them both right now just in case.
 	 */
+	local_flush_icache_all();
 	local_flush_tlb_all();
 	complete(&cpu_running);
 	/*