Merge patch series "riscv: support fast gup"

Jisheng Zhang <jszhang@kernel.org> says:

This series adds fast gup support to riscv.

The First patch fixes a bug in __p*d_free_tlb(). Per the riscv
privileged spec, if non-leaf PTEs I.E pmd, pud or p4d is modified, a
sfence.vma is a must.

The 2nd patch is a preparation patch.

The last two patches do the real work:
In order to implement fast gup we need to ensure that the page
table walker is protected from page table pages being freed from
under it.

riscv situation is more complicated than other architectures: some
riscv platforms may use IPI to perform TLB shootdown, for example,
those platforms which support AIA, usually the riscv_ipi_for_rfence is
true on these platforms; some riscv platforms may rely on the SBI to
perform TLB shootdown, usually the riscv_ipi_for_rfence is false on
these platforms. To keep software pagetable walkers safe in this case
we switch to RCU based table free (MMU_GATHER_RCU_TABLE_FREE). See the
comment below 'ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE' in
include/asm-generic/tlb.h for more details.

This patch enables MMU_GATHER_RCU_TABLE_FREE, then use

*tlb_remove_page_ptdesc() for those platforms which use IPI to perform
TLB shootdown;

*tlb_remove_ptdesc() for those platforms which use SBI to perform TLB
shootdown;

Both case mean that disabling interrupts will block the free and
protect the fast gup page walker.

So after the 3rd patch, everything is well prepared, let's select
HAVE_FAST_GUP if MMU.

* b4-shazam-merge:
  riscv: enable HAVE_FAST_GUP if MMU
  riscv: enable MMU_GATHER_RCU_TABLE_FREE for SMP && MMU
  riscv: tlb: convert __p*d_free_tlb() to inline functions
  riscv: tlb: fix __p*d_free_tlb()

Link: https://lore.kernel.org/r/20231219175046.2496-1-jszhang@kernel.orgSigned-off-by: Palmer Dabbelt <palmer@rivosinc.com>

arch/riscv/Kconfig

@@ -127,6 +127,7 @@ config RISCV
 	select HAVE_FUNCTION_GRAPH_RETVAL if HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACER if !XIP_KERNEL && !PREEMPTION
 	select HAVE_EBPF_JIT if MMU
+	select HAVE_FAST_GUP if MMU
 	select HAVE_FUNCTION_ARG_ACCESS_API
 	select HAVE_FUNCTION_ERROR_INJECTION
 	select HAVE_GCC_PLUGINS
@@ -157,6 +158,7 @@ config RISCV
 	select IRQ_FORCED_THREADING
 	select KASAN_VMALLOC if KASAN
 	select LOCK_MM_AND_FIND_VMA
+	select MMU_GATHER_RCU_TABLE_FREE if SMP && MMU
 	select MODULES_USE_ELF_RELA if MODULES
 	select MODULE_SECTIONS if MODULES
 	select OF

arch/riscv/include/asm/pgalloc.h

@@ -95,7 +95,19 @@ static inline void pud_free(struct mm_struct *mm, pud_t *pud)
 		__pud_free(mm, pud);
 }
 
-#define __pud_free_tlb(tlb, pud, addr)  pud_free((tlb)->mm, pud)
+static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
+				  unsigned long addr)
+{
+	if (pgtable_l4_enabled) {
+		struct ptdesc *ptdesc = virt_to_ptdesc(pud);
+
+		pagetable_pud_dtor(ptdesc);
+		if (riscv_use_ipi_for_rfence())
+			tlb_remove_page_ptdesc(tlb, ptdesc);
+		else
+			tlb_remove_ptdesc(tlb, ptdesc);
+	}
+}
 
 #define p4d_alloc_one p4d_alloc_one
 static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long addr)
@@ -124,7 +136,16 @@ static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d)
 		__p4d_free(mm, p4d);
 }
 
-#define __p4d_free_tlb(tlb, p4d, addr)  p4d_free((tlb)->mm, p4d)
+static inline void __p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d,
+				  unsigned long addr)
+{
+	if (pgtable_l5_enabled) {
+		if (riscv_use_ipi_for_rfence())
+			tlb_remove_page_ptdesc(tlb, virt_to_ptdesc(p4d));
+		else
+			tlb_remove_ptdesc(tlb, virt_to_ptdesc(p4d));
+	}
+}
 #endif /* __PAGETABLE_PMD_FOLDED */
 
 static inline void sync_kernel_mappings(pgd_t *pgd)
@@ -149,15 +170,31 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 
 #ifndef __PAGETABLE_PMD_FOLDED
 
-#define __pmd_free_tlb(tlb, pmd, addr)  pmd_free((tlb)->mm, pmd)
+static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
+				  unsigned long addr)
+{
+	struct ptdesc *ptdesc = virt_to_ptdesc(pmd);
+
+	pagetable_pmd_dtor(ptdesc);
+	if (riscv_use_ipi_for_rfence())
+		tlb_remove_page_ptdesc(tlb, ptdesc);
+	else
+		tlb_remove_ptdesc(tlb, ptdesc);
+}
 
 #endif /* __PAGETABLE_PMD_FOLDED */
 
-#define __pte_free_tlb(tlb, pte, buf)			\
-do {							\
-	pagetable_pte_dtor(page_ptdesc(pte));		\
-	tlb_remove_page_ptdesc((tlb), page_ptdesc(pte));\
-} while (0)
+static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
+				  unsigned long addr)
+{
+	struct ptdesc *ptdesc = page_ptdesc(pte);
+
+	pagetable_pte_dtor(ptdesc);
+	if (riscv_use_ipi_for_rfence())
+		tlb_remove_page_ptdesc(tlb, ptdesc);
+	else
+		tlb_remove_ptdesc(tlb, ptdesc);
+}
 #endif /* CONFIG_MMU */
 
 #endif /* _ASM_RISCV_PGALLOC_H */

arch/riscv/include/asm/pgtable.h

@@ -656,6 +656,12 @@ static inline int pmd_write(pmd_t pmd)
 	return pte_write(pmd_pte(pmd));
 }
 
+#define pud_write pud_write
+static inline int pud_write(pud_t pud)
+{
+	return pte_write(pud_pte(pud));
+}
+
 #define pmd_dirty pmd_dirty
 static inline int pmd_dirty(pmd_t pmd)
 {

arch/riscv/include/asm/tlb.h

@@ -10,6 +10,24 @@ struct mmu_gather;
 
 static void tlb_flush(struct mmu_gather *tlb);
 
+#ifdef CONFIG_MMU
+#include <linux/swap.h>
+
+/*
+ * While riscv platforms with riscv_ipi_for_rfence as true require an IPI to
+ * perform TLB shootdown, some platforms with riscv_ipi_for_rfence as false use
+ * SBI to perform TLB shootdown. To keep software pagetable walkers safe in this
+ * case we switch to RCU based table free (MMU_GATHER_RCU_TABLE_FREE). See the
+ * comment below 'ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE' in include/asm-generic/tlb.h
+ * for more details.
+ */
+static inline void __tlb_remove_table(void *table)
+{
+	free_page_and_swap_cache(table);
+}
+
+#endif /* CONFIG_MMU */
+
 #define tlb_flush tlb_flush
 #include <asm-generic/tlb.h>