Merge tag 'powerpc-3.19-1' of git://git.kernel.org/pub/scm/linux/kernel/git/mpe/linux

Pull powerpc updates from Michael Ellerman:
 "Some nice cleanups like removing bootmem, and removal of
  __get_cpu_var().

  There is one patch to mm/gup.c.  This is the generic GUP
  implementation, but is only used by us and arm(64).  We have an ack
  from Steve Capper, and although we didn't get an ack from Andrew he
  told us to take the patch through the powerpc tree.

  There's one cxl patch.  This is in drivers/misc, but Greg said he was
  happy for us to manage fixes for it.

  There is an infrastructure patch to support an IPMI driver for OPAL.

  There is also an RTC driver for OPAL.  We weren't able to get any
  response from the RTC maintainer, Alessandro Zummo, so in the end we
  just merged the driver.

  The usual batch of Freescale updates from Scott"

* tag 'powerpc-3.19-1' of git://git.kernel.org/pub/scm/linux/kernel/git/mpe/linux: (101 commits)
  powerpc/powernv: Return to cpu offline loop when finished in KVM guest
  powerpc/book3s: Fix partial invalidation of TLBs in MCE code.
  powerpc/mm: don't do tlbie for updatepp request with NO HPTE fault
  powerpc/xmon: Cleanup the breakpoint flags
  powerpc/xmon: Enable HW instruction breakpoint on POWER8
  powerpc/mm/thp: Use tlbiel if possible
  powerpc/mm/thp: Remove code duplication
  powerpc/mm/hugetlb: Sanity check gigantic hugepage count
  powerpc/oprofile: Disable pagefaults during user stack read
  powerpc/mm: Check for matching hpte without taking hpte lock
  powerpc: Drop useless warning in eeh_init()
  powerpc/powernv: Cleanup unused MCE definitions/declarations.
  powerpc/eeh: Dump PHB diag-data early
  powerpc/eeh: Recover EEH error on ownership change for BCM5719
  powerpc/eeh: Set EEH_PE_RESET on PE reset
  powerpc/eeh: Refactor eeh_reset_pe()
  powerpc: Remove more traces of bootmem
  powerpc/pseries: Initialise nvram_pstore_info's buf_lock
  cxl: Name interrupts in /proc/interrupt
  cxl: Return error to PSL if IRQ demultiplexing fails & print clearer warning
  ...

1 files changed, 73 insertions, 8 deletions

diff --git a/mm/gup.c b/mm/gup.c
index cd62c8c90d4a..0ca1df9075ab 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -3,7 +3,6 @@
 #include <linux/err.h>
 #include <linux/spinlock.h>
 
-#include <linux/hugetlb.h>
 #include <linux/mm.h>
 #include <linux/pagemap.h>
 #include <linux/rmap.h>
@@ -12,6 +11,7 @@
 
 #include <linux/sched.h>
 #include <linux/rwsem.h>
+#include <linux/hugetlb.h>
 #include <asm/pgtable.h>
 
 #include "internal.h"
@@ -875,6 +875,49 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
 	return 1;
 }
 
+static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
+			unsigned long end, int write,
+			struct page **pages, int *nr)
+{
+	int refs;
+	struct page *head, *page, *tail;
+
+	if (write && !pgd_write(orig))
+		return 0;
+
+	refs = 0;
+	head = pgd_page(orig);
+	page = head + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT);
+	tail = page;
+	do {
+		VM_BUG_ON_PAGE(compound_head(page) != head, page);
+		pages[*nr] = page;
+		(*nr)++;
+		page++;
+		refs++;
+	} while (addr += PAGE_SIZE, addr != end);
+
+	if (!page_cache_add_speculative(head, refs)) {
+		*nr -= refs;
+		return 0;
+	}
+
+	if (unlikely(pgd_val(orig) != pgd_val(*pgdp))) {
+		*nr -= refs;
+		while (refs--)
+			put_page(head);
+		return 0;
+	}
+
+	while (refs--) {
+		if (PageTail(tail))
+			get_huge_page_tail(tail);
+		tail++;
+	}
+
+	return 1;
+}
+
 static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 		int write, struct page **pages, int *nr)
 {
@@ -902,6 +945,14 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 				pages, nr))
 				return 0;
 
+		} else if (unlikely(is_hugepd(__hugepd(pmd_val(pmd))))) {
+			/*
+			 * architecture have different format for hugetlbfs
+			 * pmd format and THP pmd format
+			 */
+			if (!gup_huge_pd(__hugepd(pmd_val(pmd)), addr,
+					 PMD_SHIFT, next, write, pages, nr))
+				return 0;
 		} else if (!gup_pte_range(pmd, addr, next, write, pages, nr))
 				return 0;
 	} while (pmdp++, addr = next, addr != end);
@@ -909,22 +960,26 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 	return 1;
 }
 
-static int gup_pud_range(pgd_t *pgdp, unsigned long addr, unsigned long end,
-		int write, struct page **pages, int *nr)
+static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
+			 int write, struct page **pages, int *nr)
 {
 	unsigned long next;
 	pud_t *pudp;
 
-	pudp = pud_offset(pgdp, addr);
+	pudp = pud_offset(&pgd, addr);
 	do {
 		pud_t pud = ACCESS_ONCE(*pudp);
 
 		next = pud_addr_end(addr, end);
 		if (pud_none(pud))
 			return 0;
-		if (pud_huge(pud)) {
+		if (unlikely(pud_huge(pud))) {
 			if (!gup_huge_pud(pud, pudp, addr, next, write,
-					pages, nr))
+					  pages, nr))
+				return 0;
+		} else if (unlikely(is_hugepd(__hugepd(pud_val(pud))))) {
+			if (!gup_huge_pd(__hugepd(pud_val(pud)), addr,
+					 PUD_SHIFT, next, write, pages, nr))
 				return 0;
 		} else if (!gup_pmd_range(pud, addr, next, write, pages, nr))
 			return 0;
@@ -970,10 +1025,20 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
 	local_irq_save(flags);
 	pgdp = pgd_offset(mm, addr);
 	do {
+		pgd_t pgd = ACCESS_ONCE(*pgdp);
+
 		next = pgd_addr_end(addr, end);
-		if (pgd_none(*pgdp))
+		if (pgd_none(pgd))
 			break;
-		else if (!gup_pud_range(pgdp, addr, next, write, pages, &nr))
+		if (unlikely(pgd_huge(pgd))) {
+			if (!gup_huge_pgd(pgd, pgdp, addr, next, write,
+					  pages, &nr))
+				break;
+		} else if (unlikely(is_hugepd(__hugepd(pgd_val(pgd))))) {
+			if (!gup_huge_pd(__hugepd(pgd_val(pgd)), addr,
+					 PGDIR_SHIFT, next, write, pages, &nr))
+				break;
+		} else if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
 			break;
 	} while (pgdp++, addr = next, addr != end);
 	local_irq_restore(flags);