x86/boot/e820: Move the memblock_find_dma_reserve() function and rename it to membloc...

We introduced memblock_find_dma_reserve() in this commit:

   6f2a75369e75 x86, memblock: Use memblock_memory_size()/memblock_free_memory_size() to get correct dma_reserve

But there's several problems with it:

 - The changelog is full of typos and is incomprehensible in general, and
   the comments in the code are not much better either.

 - The function was inexplicably placed into e820.c, while it has very
   little connection to the E820 table: when we call
   memblock_find_dma_reserve() then memblock is already set up and we
   are not using the E820 table anymore.

 - The function is a wrapper around set_dma_reserve(), but changed the 'set'
   name to 'find' - actively misleading about its primary purpose, which is
   still to set the DMA-reserve value.

 - The function is limited to 64-bit systems, but neither the changelog nor
   the comments explain why. The change would appear to be relevant to
   32-bit systems as well, as the ISA DMA zone is the first 16 MB of RAM.

So address some of these problems:

 - Move it into arch/x86/mm/init.c, next to the other zone setup related
   functions.

 - Clean up the code flow and names of local variables a bit.

 - Rename it to memblock_set_dma_reserve()

 - Improve the comments.

No change in functionality. Enabling it for 32-bit systems is left
for a separate patch.

Cc: Alex Thorlton <athorlton@sgi.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Huang, Ying <ying.huang@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul Jackson <pj@sgi.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rafael J. Wysocki <rjw@sisk.pl>
Cc: Tejun Heo <tj@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Wei Yang <richard.weiyang@gmail.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/include/asm/e820/api.h b/arch/x86/include/asm/e820/api.h
index 01698548fbc8b1a83d9a1616dd2e064eff16589a..7c9e4bb84059c60adb2a40441ed9753447a4c3c2 100644 (file)
--- a/arch/x86/include/asm/e820/api.h
+++ b/arch/x86/include/asm/e820/api.h
@@ -22,7 +22,6 @@ extern unsigned long e820_end_of_ram_pfn(void);
 extern unsigned long e820_end_of_low_ram_pfn(void);
 extern u64  early_reserve_e820(u64 sizet, u64 align);
 extern void e820__memblock_setup(void);
-extern void memblock_find_dma_reserve(void);
 extern void finish_e820_parsing(void);
 extern void e820_reserve_resources(void);
 extern void e820_reserve_resources_late(void);

diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index ffaefb24891cd54eb8bea85a6b68800234862255..2d8116136f3eb591c2b7e1896eaaeab6f9d4f64f 100644 (file)
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -733,6 +733,7 @@ static inline int pgd_none(pgd_t pgd)
 extern int direct_gbpages;
 void init_mem_mapping(void);
 void early_alloc_pgt_buf(void);
+extern void memblock_find_dma_reserve(void);
 
 #ifdef CONFIG_X86_64
 /* Realmode trampoline initialization. */

diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 4a8d905226c99622f4079e7f381721aef43c58b0..5f8ba898e29d2a47712eeee0c37398f54efd32b5 100644 (file)
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1172,34 +1172,3 @@ void __init e820__memblock_setup(void)
 
        memblock_dump_all();
 }
-
-void __init memblock_find_dma_reserve(void)
-{
-#ifdef CONFIG_X86_64
-       u64 nr_pages = 0, nr_free_pages = 0;
-       unsigned long start_pfn, end_pfn;
-       phys_addr_t start, end;
-       int i;
-       u64 u;
-
-       /*
-        * need to find out used area below MAX_DMA_PFN
-        * need to use memblock to get free size in [0, MAX_DMA_PFN]
-        * at first, and assume boot_mem will not take below MAX_DMA_PFN
-        */
-       for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) {
-               start_pfn = min(start_pfn, MAX_DMA_PFN);
-               end_pfn = min(end_pfn, MAX_DMA_PFN);
-               nr_pages += end_pfn - start_pfn;
-       }
-
-       for_each_free_mem_range(u, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end, NULL) {
-               start_pfn = min_t(unsigned long, PFN_UP(start), MAX_DMA_PFN);
-               end_pfn = min_t(unsigned long, PFN_DOWN(end), MAX_DMA_PFN);
-               if (start_pfn < end_pfn)
-                       nr_free_pages += end_pfn - start_pfn;
-       }
-
-       set_dma_reserve(nr_pages - nr_free_pages);
-#endif
-}

diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index b7b4ad569d1394985e2207006c746543c40712ec..922671d3af8568ff30cda854a6d2338aaea6e68f 100644 (file)
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -724,6 +724,53 @@ void __init free_initrd_mem(unsigned long start, unsigned long end)
 }
 #endif
 
+/*
+ * Calculate the precise size of the DMA zone (first 16 MB of RAM),
+ * and pass it to the MM layer - to help it set zone watermarks more
+ * accurately.
+ *
+ * Done on 64-bit systems only for the time being, although 32-bit systems
+ * might benefit from this as well.
+ */
+void __init memblock_find_dma_reserve(void)
+{
+#ifdef CONFIG_X86_64
+       u64 nr_pages = 0, nr_free_pages = 0;
+       unsigned long start_pfn, end_pfn;
+       phys_addr_t start_addr, end_addr;
+       int i;
+       u64 u;
+
+       /*
+        * Iterate over all memory ranges (free and reserved ones alike),
+        * to calculate the total number of pages in the first 16 MB of RAM:
+        */
+       nr_pages = 0;
+       for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) {
+               start_pfn = min(start_pfn, MAX_DMA_PFN);
+               end_pfn   = min(end_pfn,   MAX_DMA_PFN);
+
+               nr_pages += end_pfn - start_pfn;
+       }
+
+       /*
+        * Iterate over free memory ranges to calculate the number of free
+        * pages in the DMA zone, while not counting potential partial
+        * pages at the beginning or the end of the range:
+        */
+       nr_free_pages = 0;
+       for_each_free_mem_range(u, NUMA_NO_NODE, MEMBLOCK_NONE, &start_addr, &end_addr, NULL) {
+               start_pfn = min_t(unsigned long, PFN_UP(start_addr), MAX_DMA_PFN);
+               end_pfn   = min_t(unsigned long, PFN_DOWN(end_addr), MAX_DMA_PFN);
+
+               if (start_pfn < end_pfn)
+                       nr_free_pages += end_pfn - start_pfn;
+       }
+
+       set_dma_reserve(nr_pages - nr_free_pages);
+#endif
+}
+
 void __init zone_sizes_init(void)
 {
        unsigned long max_zone_pfns[MAX_NR_ZONES];