xen/pdx: Make CONFIG_PDX_COMPRESSION a common Kconfig option

Adds a new compile-time flag to allow disabling PDX compression and
compiles out compression-related code/data. It also shorts the pdx<->pfn
conversion macros and creates stubs for masking functions.

While at it, removes the old arch-defined CONFIG_HAS_PDX flag.  Despite the
illusion of choice, it was not optional.

There are ARM and PPC platforms with sparse RAM banks - leave compression
active by default there.  However, there are no known production x86 systems
with sparse RAM banks, so disable compression.  RISC-V platforms are unknown
right now.  These decisions can be revisited if our understanding changes.

Signed-off-by: Alejandro Vallejo <alejandro.vallejo@cloud.com>
Reviewed-by: Julien Grall <jgrall@amazon.com>
Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Roger Pau Monné <roger.pau@citrix.com>
Release-acked-by: Henry Wang <Henry.Wang@arm.com>

xen/arch/arm/Kconfig

@@ -14,7 +14,6 @@ config ARM
 	select HAS_ALTERNATIVE
 	select HAS_DEVICE_TREE
 	select HAS_PASSTHROUGH
-	select HAS_PDX
 	select HAS_PMAP
 	select HAS_UBSAN
 	select IOMMU_FORCE_PT_SHARE

xen/arch/ppc/Kconfig

@@ -1,7 +1,6 @@
 config PPC
 	def_bool y
 	select HAS_DEVICE_TREE
-	select HAS_PDX
 
 config PPC64
 	def_bool y

xen/arch/x86/Kconfig

@@ -24,7 +24,6 @@ config X86
 	select HAS_PASSTHROUGH
 	select HAS_PCI
 	select HAS_PCI_MSI
-	select HAS_PDX
 	select HAS_SCHED_GRANULARITY
 	select HAS_UBSAN
 	select HAS_VPCI if HVM

xen/arch/x86/domain.c

@@ -458,7 +458,7 @@ void domain_cpu_policy_changed(struct domain *d)
     }
 }
 
-#ifndef CONFIG_BIGMEM
+#if !defined(CONFIG_BIGMEM) && defined(CONFIG_PDX_COMPRESSION)
 /*
  * The hole may be at or above the 44-bit boundary, so we need to determine
  * the total bit count until reaching 32 significant (not squashed out) bits
@@ -485,13 +485,20 @@ static unsigned int __init noinline _domain_struct_bits(void)
 struct domain *alloc_domain_struct(void)
 {
     struct domain *d;
-#ifdef CONFIG_BIGMEM
-    const unsigned int bits = 0;
-#else
+
     /*
-     * We pack the PDX of the domain structure into a 32-bit field within
-     * the page_info structure. Hence the MEMF_bits() restriction.
+     * Without CONFIG_BIGMEM, we pack the PDX of the domain structure into
+     * a 32-bit field within the page_info structure. Hence the MEMF_bits()
+     * restriction. With PDX compression in place the number of bits must
+     * be calculated at runtime, but it's fixed otherwise.
+     *
+     * On systems with CONFIG_BIGMEM there's no packing, and so there's no
+     * such restriction.
      */
+#if defined(CONFIG_BIGMEM) || !defined(CONFIG_PDX_COMPRESSION)
+    const unsigned int bits = IS_ENABLED(CONFIG_BIGMEM) ? 0 :
+                                                          32 + PAGE_SHIFT;
+#else
     static unsigned int __read_mostly bits;
 
     if ( unlikely(!bits) )

xen/common/Kconfig

@@ -23,6 +23,21 @@ config GRANT_TABLE
 
 	  If unsure, say Y.
 
+config PDX_COMPRESSION
+	bool "PDX (Page inDeX) compression" if EXPERT && !X86 && !RISCV
+	default ARM || PPC
+	help
+	  PDX compression is a technique designed to reduce the memory
+	  overhead of physical memory management on platforms with sparse RAM
+	  banks.
+
+	  If your platform does have sparse RAM banks, enabling PDX
+	  compression may reduce the memory overhead of Xen, but does carry a
+	  runtime performance cost.
+
+	  If your platform does not have sparse RAM banks, do not enable PDX
+	  compression.
+
 config ALTERNATIVE_CALL
 	bool
 
@@ -53,9 +68,6 @@ config HAS_IOPORTS
 config HAS_KEXEC
 	bool
 
-config HAS_PDX
-	bool
-
 config HAS_PMAP
 	bool
 

xen/common/Makefile

@@ -30,7 +30,7 @@ obj-y += multicall.o
 obj-y += notifier.o
 obj-$(CONFIG_NUMA) += numa.o
 obj-y += page_alloc.o
-obj-$(CONFIG_HAS_PDX) += pdx.o
+obj-y += pdx.o
 obj-$(CONFIG_PERF_COUNTERS) += perfc.o
 obj-bin-$(CONFIG_HAS_PMAP) += pmap.init.o
 obj-y += preempt.o

xen/common/pdx.c

@@ -31,11 +31,16 @@ unsigned long __read_mostly pdx_group_valid[BITS_TO_LONGS(
 
 bool __mfn_valid(unsigned long mfn)
 {
-    if ( unlikely(evaluate_nospec(mfn >= max_page)) )
+    bool invalid = mfn >= max_page;
+
+#ifdef CONFIG_PDX_COMPRESSION
+    invalid |= mfn & pfn_hole_mask;
+#endif
+
+    if ( unlikely(evaluate_nospec(invalid)) )
         return false;
-    return likely(!(mfn & pfn_hole_mask)) &&
-           likely(test_bit(pfn_to_pdx(mfn) / PDX_GROUP_COUNT,
-                           pdx_group_valid));
+
+    return test_bit(pfn_to_pdx(mfn) / PDX_GROUP_COUNT, pdx_group_valid);
 }
 
 void set_pdx_range(unsigned long smfn, unsigned long emfn)
@@ -49,6 +54,8 @@ void set_pdx_range(unsigned long smfn, unsigned long emfn)
         __set_bit(idx, pdx_group_valid);
 }
 
+#ifdef CONFIG_PDX_COMPRESSION
+
 /*
  * Diagram to make sense of the following variables. The masks and shifts
  * are done on mfn values in order to convert to/from pdx:
@@ -176,6 +183,7 @@ void __init pfn_pdx_hole_setup(unsigned long mask)
     ma_top_mask         = pfn_top_mask << PAGE_SHIFT;
 }
 
+#endif /* CONFIG_PDX_COMPRESSION */
 
 /*
  * Local variables:

xen/include/xen/pdx.h

@@ -67,8 +67,6 @@
  * region involved.
  */
 
-#ifdef CONFIG_HAS_PDX
-
 extern unsigned long max_pdx;
 
 #define PDX_GROUP_COUNT ((1 << PDX_GROUP_SHIFT) / \
@@ -100,6 +98,8 @@ bool __mfn_valid(unsigned long mfn);
 #define mfn_to_pdx(mfn) pfn_to_pdx(mfn_x(mfn))
 #define pdx_to_mfn(pdx) _mfn(pdx_to_pfn(pdx))
 
+#ifdef CONFIG_PDX_COMPRESSION
+
 extern unsigned long pfn_pdx_bottom_mask, ma_va_bottom_mask;
 extern unsigned int pfn_pdx_hole_shift;
 extern unsigned long pfn_hole_mask;
@@ -206,7 +206,39 @@ static inline paddr_t directmapoff_to_maddr(unsigned long offset)
  */
 void pfn_pdx_hole_setup(unsigned long mask);
 
-#endif /* HAS_PDX */
+#else /* !CONFIG_PDX_COMPRESSION */
+
+/* Without PDX compression we can skip some computations */
+
+/* pdx<->pfn == identity */
+#define pdx_to_pfn(x) (x)
+#define pfn_to_pdx(x) (x)
+
+/* directmap is indexed by by maddr */
+#define maddr_to_directmapoff(x) (x)
+#define directmapoff_to_maddr(x) (x)
+
+static inline bool pdx_is_region_compressible(paddr_t base,
+                                              unsigned long npages)
+{
+    return true;
+}
+
+static inline uint64_t pdx_init_mask(uint64_t base_addr)
+{
+    return 0;
+}
+
+static inline uint64_t pdx_region_mask(uint64_t base, uint64_t len)
+{
+    return 0;
+}
+
+static inline void pfn_pdx_hole_setup(unsigned long mask)
+{
+}
+
+#endif /* CONFIG_PDX_COMPRESSION */
 #endif /* __XEN_PDX_H__ */
 
 /*