[Xen-devel] [PATCH v2 5/6] xen/arm: read cacheline size when needed

[Stefano Stabellini <sstabellini@xxxxxxxxxx>]

On big.LITTLE systems the cacheline size might differ between big and
LITTLE cores. Instead of reading the cacheline size once at boot,
read it as needed from the system registers.

Suggested-by: Julien Grall <julien.grall@xxxxxxx>
Signed-off-by: Stefano Stabellini <sstabellini@xxxxxxxxxx>
---
 xen/arch/arm/arm32/head.S  |  9 +++++++--
 xen/arch/arm/arm64/head.S  | 10 ++++++++--
 xen/arch/arm/setup.c       | 17 -----------------
 xen/include/asm-arm/page.h | 17 +++++++++++++++--
 4 files changed, 30 insertions(+), 23 deletions(-)

diff --git a/xen/arch/arm/arm32/head.S b/xen/arch/arm/arm32/head.S
index 43374e7..db470ad 100644
--- a/xen/arch/arm/arm32/head.S
+++ b/xen/arch/arm/arm32/head.S
@@ -504,8 +504,13 @@ ENTRY(relocate_xen)
         dsb        /* So the CPU issues all writes to the range */
 
         mov   r5, r4
-        ldr   r6, =cacheline_bytes /* r6 := step */
-        ldr   r6, [r6]
+        mov   r6, #0
+        mcr   CP32(r6, CSSELR_EL1)
+        mrc   CP32(r6, CSSELR_EL1)
+        and   r6, r6, #0x7
+        add   r6, r6, #4
+        mov   r7, #1
+        lsl   r6, r7, r6
         mov   r7, r3
 
 1:      mcr   CP32(r7, DCCMVAC)
diff --git a/xen/arch/arm/arm64/head.S b/xen/arch/arm/arm64/head.S
index fa0ef70..edea300 100644
--- a/xen/arch/arm/arm64/head.S
+++ b/xen/arch/arm/arm64/head.S
@@ -631,8 +631,14 @@ ENTRY(relocate_xen)
         dsb   sy        /* So the CPU issues all writes to the range */
 
         mov   x9, x3
-        ldr   x10, =cacheline_bytes /* x10 := step */
-        ldr   x10, [x10]
+
+        mov   x10, #0
+        msr   CSSELR_EL1, x10
+        mrs   x10, CSSELR_EL1
+        and   x10, x10, #0x7
+        add   x10, x10, #4
+        mov   x11, #1
+        lsl   x10, x11, x10
         mov   x11, x2
 
 1:      dc    cvac, x11
diff --git a/xen/arch/arm/setup.c b/xen/arch/arm/setup.c
index 032a6a8..4754c95 100644
--- a/xen/arch/arm/setup.c
+++ b/xen/arch/arm/setup.c
@@ -680,21 +680,6 @@ static void __init setup_mm(unsigned long dtb_paddr, 
size_t dtb_size)
 }
 #endif
 
-size_t __read_mostly cacheline_bytes;
-
-/* Very early check of the CPU cache properties */
-void __init setup_cache(void)
-{
-    uint32_t ccsid;
-
-    /* Read the cache size ID register for the level-0 data cache */
-    WRITE_SYSREG32(0, CSSELR_EL1);
-    ccsid = READ_SYSREG32(CCSIDR_EL1);
-
-    /* Low 3 bits are log2(cacheline size in words) - 2. */
-    cacheline_bytes = 1U << (4 + (ccsid & 0x7));
-}
-
 /* C entry point for boot CPU */
 void __init start_xen(unsigned long boot_phys_offset,
                       unsigned long fdt_paddr,
@@ -708,8 +693,6 @@ void __init start_xen(unsigned long boot_phys_offset,
     struct domain *dom0;
     struct xen_arch_domainconfig config;
 
-    setup_cache();
-
     percpu_init_areas();
     set_processor_id(0); /* needed early, for smp_processor_id() */
 
diff --git a/xen/include/asm-arm/page.h b/xen/include/asm-arm/page.h
index d948250..791e22e 100644
--- a/xen/include/asm-arm/page.h
+++ b/xen/include/asm-arm/page.h
@@ -133,8 +133,6 @@
 
 /* Architectural minimum cacheline size is 4 32-bit words. */
 #define MIN_CACHELINE_BYTES 16
-/* Actual cacheline size on the boot CPU. */
-extern size_t cacheline_bytes;
 
 #define copy_page(dp, sp) memcpy(dp, sp, PAGE_SIZE)
 
@@ -142,9 +140,22 @@ extern size_t cacheline_bytes;
  * if 'range' is large enough we might want to use model-specific
  * full-cache flushes. */
 
+static inline size_t read_cacheline_size(void)
+{
+    uint32_t ccsid;
+
+    /* Read the cache size ID register for the level-0 data cache */
+    WRITE_SYSREG32(0, CSSELR_EL1);
+    ccsid = READ_SYSREG32(CCSIDR_EL1);
+
+    /* Low 3 bits are log2(cacheline size in words) - 2. */
+    return (size_t) (1U << (4 + (ccsid & 0x7)));
+}
+
 static inline int invalidate_dcache_va_range(const void *p, unsigned long size)
 {
     const void *end = p + size;
+    size_t cacheline_bytes = read_cacheline_size();
     size_t cacheline_mask = cacheline_bytes - 1;
 
     dsb(sy);           /* So the CPU issues all writes to the range */
@@ -171,6 +182,7 @@ static inline int invalidate_dcache_va_range(const void *p, 
unsigned long size)
 
 static inline int clean_dcache_va_range(const void *p, unsigned long size)
 {
+    size_t cacheline_bytes = read_cacheline_size();
     const void *end = p + size;
     dsb(sy);           /* So the CPU issues all writes to the range */
     p = (void *)((uintptr_t)p & ~(cacheline_bytes - 1));
@@ -184,6 +196,7 @@ static inline int clean_dcache_va_range(const void *p, 
unsigned long size)
 static inline int clean_and_invalidate_dcache_va_range
     (const void *p, unsigned long size)
 {
+    size_t cacheline_bytes = read_cacheline_size();
     const void *end = p + size;
     dsb(sy);         /* So the CPU issues all writes to the range */
     p = (void *)((uintptr_t)p & ~(cacheline_bytes - 1));
-- 
1.9.1


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxxx
https://lists.xenproject.org/mailman/listinfo/xen-devel