[PATCH 1/2] mm: Introduce flush_cache_vmap_early() and its riscv implementation

[Alexandre Ghiti]

The pcpu setup when using the page allocator sets up a new vmalloc
mapping very early in the boot process, so early that it cannot use the
flush_cache_vmap() function which may depend on structures not yet
initialized (for example in riscv, we currently send an IPI to flush
other cpus TLB).

But on some architectures, we must call flush_cache_vmap(): for example,
in riscv, some uarchs can cache invalid TLB entries so we need to flush
the new established mapping to avoid taking an exception.

So fix this by introducing a new function flush_cache_vmap_early() which
is called right after setting the new page table entry and before
accessing this new mapping. This new function implements a local flush
tlb on riscv and is no-op for other architectures (same as today).

Signed-off-by: Alexandre Ghiti <alexghiti at rivosinc.com>
---
 arch/riscv/include/asm/cacheflush.h | 3 ++-
 arch/riscv/include/asm/tlbflush.h   | 2 ++
 arch/riscv/mm/tlbflush.c            | 5 +++++
 include/asm-generic/cacheflush.h    | 6 ++++++
 mm/percpu.c                         | 8 +-------
 5 files changed, 16 insertions(+), 8 deletions(-)

diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h
index 3cb53c4df27c..a129dac4521d 100644
--- a/arch/riscv/include/asm/cacheflush.h
+++ b/arch/riscv/include/asm/cacheflush.h
@@ -37,7 +37,8 @@ static inline void flush_dcache_page(struct page *page)
 	flush_icache_mm(vma->vm_mm, 0)
 
 #ifdef CONFIG_64BIT
-#define flush_cache_vmap(start, end)	flush_tlb_kernel_range(start, end)
+#define flush_cache_vmap(start, end)		flush_tlb_kernel_range(start, end)
+#define flush_cache_vmap_early(start, end)	local_flush_tlb_kernel_range(start, end)
 #endif
 
 #ifndef CONFIG_SMP
diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h
index 8f3418c5f172..f0d6328076b6 100644
--- a/arch/riscv/include/asm/tlbflush.h
+++ b/arch/riscv/include/asm/tlbflush.h
@@ -41,6 +41,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr);
 void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 		     unsigned long end);
 void flush_tlb_kernel_range(unsigned long start, unsigned long end);
+void local_flush_tlb_kernel_range(unsigned long start, unsigned long end);
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
 void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
@@ -64,6 +65,7 @@ static inline void flush_tlb_kernel_range(unsigned long start,
 	local_flush_tlb_all();
 }
 
+#define local_flush_tlb_kernel_range(start, end) flush_tlb_kernel_range(start, end)
 #define flush_tlb_mm(mm) flush_tlb_all()
 #define flush_tlb_mm_range(mm, start, end, page_size) flush_tlb_all()
 #endif /* !CONFIG_SMP || !CONFIG_MMU */
diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
index e6659d7368b3..8aadc5f71c93 100644
--- a/arch/riscv/mm/tlbflush.c
+++ b/arch/riscv/mm/tlbflush.c
@@ -66,6 +66,11 @@ static inline void local_flush_tlb_range_asid(unsigned long start,
 		local_flush_tlb_range_threshold_asid(start, size, stride, asid);
 }
 
+void local_flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+	local_flush_tlb_range_asid(start, end, PAGE_SIZE, FLUSH_TLB_NO_ASID);
+}
+
 static void __ipi_flush_tlb_all(void *info)
 {
 	local_flush_tlb_all();
diff --git a/include/asm-generic/cacheflush.h b/include/asm-generic/cacheflush.h
index 84ec53ccc450..7ee8a179d103 100644
--- a/include/asm-generic/cacheflush.h
+++ b/include/asm-generic/cacheflush.h
@@ -91,6 +91,12 @@ static inline void flush_cache_vmap(unsigned long start, unsigned long end)
 }
 #endif
 
+#ifndef flush_cache_vmap_early
+static inline void flush_cache_vmap_early(unsigned long start, unsigned long end)
+{
+}
+#endif
+
 #ifndef flush_cache_vunmap
 static inline void flush_cache_vunmap(unsigned long start, unsigned long end)
 {
diff --git a/mm/percpu.c b/mm/percpu.c
index a7665de8485f..d287cebd58ca 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -3306,13 +3306,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_cpu_to_node_fn_t
 		if (rc < 0)
 			panic("failed to map percpu area, err=%d\n", rc);
 
-		/*
-		 * FIXME: Archs with virtual cache should flush local
-		 * cache for the linear mapping here - something
-		 * equivalent to flush_cache_vmap() on the local cpu.
-		 * flush_cache_vmap() can't be used as most supporting
-		 * data structures are not set up yet.
-		 */
+		flush_cache_vmap_early(unit_addr, unit_addr + ai->unit_size);
 
 		/* copy static data */
 		memcpy((void *)unit_addr, __per_cpu_load, ai->static_size);
-- 
2.39.2