From dafcc4380deec21d160c31411f33c8813f67f517 Mon Sep 17 00:00:00 2001 From: Eliezer Tamir Date: Fri, 14 Jun 2013 16:33:57 +0300 Subject: net: add socket option for low latency polling adds a socket option for low latency polling. This allows overriding the global sysctl value with a per-socket one. Unexport sysctl_net_ll_poll since for now it's not needed in modules. Signed-off-by: Eliezer Tamir Signed-off-by: David S. Miller --- arch/s390/include/uapi/asm/socket.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/s390') diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h index 2dacb306835..0c5105fbaaf 100644 --- a/arch/s390/include/uapi/asm/socket.h +++ b/arch/s390/include/uapi/asm/socket.h @@ -80,4 +80,6 @@ #define SO_SELECT_ERR_QUEUE 45 +#define SO_LL 46 + #endif /* _ASM_SOCKET_H */ -- cgit v1.2.3-70-g09d2 From 6b0b50b0617fad5f2af3b928596a25f7de8dbf50 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 5 Jun 2013 17:14:02 -0700 Subject: mm/THP: add pmd args to pgtable deposit and withdraw APIs This will be later used by powerpc THP support. In powerpc we want to use pgtable for storing the hash index values. So instead of adding them to mm_context list, we would like to store them in the second half of pmd Signed-off-by: Aneesh Kumar K.V Reviewed-by: Andrea Arcangeli Reviewed-by: David Gibson Cc: Benjamin Herrenschmidt Signed-off-by: Andrew Morton Signed-off-by: Benjamin Herrenschmidt --- arch/s390/include/asm/pgtable.h | 5 +++-- arch/s390/mm/pgtable.c | 5 +++-- arch/sparc/include/asm/pgtable_64.h | 5 +++-- arch/sparc/mm/tlb.c | 5 +++-- include/asm-generic/pgtable.h | 5 +++-- mm/huge_memory.c | 18 +++++++++--------- mm/pgtable-generic.c | 5 +++-- 7 files changed, 27 insertions(+), 21 deletions(-) (limited to 'arch/s390') diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index e8b6e5b8932..2080dfeba64 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1370,10 +1370,11 @@ static inline pmd_t pmd_mkwrite(pmd_t pmd) #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_PGTABLE_DEPOSIT -extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable); +extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, + pgtable_t pgtable); #define __HAVE_ARCH_PGTABLE_WITHDRAW -extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm); +extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp); static inline int pmd_trans_splitting(pmd_t pmd) { diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index a938b548f07..1ccbffecc4d 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -1117,7 +1117,8 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address, } } -void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable) +void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, + pgtable_t pgtable) { struct list_head *lh = (struct list_head *) pgtable; @@ -1131,7 +1132,7 @@ void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable) mm->pmd_huge_pte = pgtable; } -pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm) +pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp) { struct list_head *lh; pgtable_t pgtable; diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h index 7619f2f792a..d22b92d6784 100644 --- a/arch/sparc/include/asm/pgtable_64.h +++ b/arch/sparc/include/asm/pgtable_64.h @@ -853,10 +853,11 @@ extern void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd); #define __HAVE_ARCH_PGTABLE_DEPOSIT -extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable); +extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, + pgtable_t pgtable); #define __HAVE_ARCH_PGTABLE_WITHDRAW -extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm); +extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp); #endif /* Encode and de-code a swap entry */ diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c index 83d89bcb44a..f828dd33551 100644 --- a/arch/sparc/mm/tlb.c +++ b/arch/sparc/mm/tlb.c @@ -188,7 +188,8 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr, } } -void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable) +void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, + pgtable_t pgtable) { struct list_head *lh = (struct list_head *) pgtable; @@ -202,7 +203,7 @@ void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable) mm->pmd_huge_pte = pgtable; } -pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm) +pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp) { struct list_head *lh; pgtable_t pgtable; diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index a59ff51b016..18e27c21071 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -173,11 +173,12 @@ extern void pmdp_splitting_flush(struct vm_area_struct *vma, #endif #ifndef __HAVE_ARCH_PGTABLE_DEPOSIT -extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable); +extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, + pgtable_t pgtable); #endif #ifndef __HAVE_ARCH_PGTABLE_WITHDRAW -extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm); +extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp); #endif #ifndef __HAVE_ARCH_PMDP_INVALIDATE diff --git a/mm/huge_memory.c b/mm/huge_memory.c index dab90fd6729..6b785e17b67 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -730,7 +730,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, entry = mk_huge_pmd(page, vma); page_add_new_anon_rmap(page, vma, haddr); set_pmd_at(mm, haddr, pmd, entry); - pgtable_trans_huge_deposit(mm, pgtable); + pgtable_trans_huge_deposit(mm, pmd, pgtable); add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR); mm->nr_ptes++; spin_unlock(&mm->page_table_lock); @@ -772,7 +772,7 @@ static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm, entry = pmd_wrprotect(entry); entry = pmd_mkhuge(entry); set_pmd_at(mm, haddr, pmd, entry); - pgtable_trans_huge_deposit(mm, pgtable); + pgtable_trans_huge_deposit(mm, pmd, pgtable); mm->nr_ptes++; return true; } @@ -917,7 +917,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmdp_set_wrprotect(src_mm, addr, src_pmd); pmd = pmd_mkold(pmd_wrprotect(pmd)); set_pmd_at(dst_mm, addr, dst_pmd, pmd); - pgtable_trans_huge_deposit(dst_mm, pgtable); + pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable); dst_mm->nr_ptes++; ret = 0; @@ -987,7 +987,7 @@ static int do_huge_pmd_wp_zero_page_fallback(struct mm_struct *mm, pmdp_clear_flush(vma, haddr, pmd); /* leave pmd empty until pte is filled */ - pgtable = pgtable_trans_huge_withdraw(mm); + pgtable = pgtable_trans_huge_withdraw(mm, pmd); pmd_populate(mm, &_pmd, pgtable); for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) { @@ -1085,7 +1085,7 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, pmdp_clear_flush(vma, haddr, pmd); /* leave pmd empty until pte is filled */ - pgtable = pgtable_trans_huge_withdraw(mm); + pgtable = pgtable_trans_huge_withdraw(mm, pmd); pmd_populate(mm, &_pmd, pgtable); for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) { @@ -1360,7 +1360,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, struct page *page; pgtable_t pgtable; pmd_t orig_pmd; - pgtable = pgtable_trans_huge_withdraw(tlb->mm); + pgtable = pgtable_trans_huge_withdraw(tlb->mm, pmd); orig_pmd = pmdp_get_and_clear(tlb->mm, addr, pmd); tlb_remove_pmd_tlb_entry(tlb, pmd, addr); if (is_huge_zero_pmd(orig_pmd)) { @@ -1693,7 +1693,7 @@ static int __split_huge_page_map(struct page *page, pmd = page_check_address_pmd(page, mm, address, PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG); if (pmd) { - pgtable = pgtable_trans_huge_withdraw(mm); + pgtable = pgtable_trans_huge_withdraw(mm, pmd); pmd_populate(mm, &_pmd, pgtable); haddr = address; @@ -2363,7 +2363,7 @@ static void collapse_huge_page(struct mm_struct *mm, page_add_new_anon_rmap(new_page, vma, address); set_pmd_at(mm, address, pmd, _pmd); update_mmu_cache_pmd(vma, address, pmd); - pgtable_trans_huge_deposit(mm, pgtable); + pgtable_trans_huge_deposit(mm, pmd, pgtable); spin_unlock(&mm->page_table_lock); *hpage = NULL; @@ -2669,7 +2669,7 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma, pmdp_clear_flush(vma, haddr, pmd); /* leave pmd empty until pte is filled */ - pgtable = pgtable_trans_huge_withdraw(mm); + pgtable = pgtable_trans_huge_withdraw(mm, pmd); pmd_populate(mm, &_pmd, pgtable); for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) { diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index 0c8323fe6c8..e1a6e4fab01 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -124,7 +124,8 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address, #ifndef __HAVE_ARCH_PGTABLE_DEPOSIT #ifdef CONFIG_TRANSPARENT_HUGEPAGE -void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable) +void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, + pgtable_t pgtable) { assert_spin_locked(&mm->page_table_lock); @@ -141,7 +142,7 @@ void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable) #ifndef __HAVE_ARCH_PGTABLE_WITHDRAW #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* no "address" argument so destroys page coloring of some arch */ -pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm) +pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp) { pgtable_t pgtable; -- cgit v1.2.3-70-g09d2 From 11199692d83dd3fe1511203024fb9853d176ec4c Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Wed, 3 Jul 2013 15:02:48 -0700 Subject: mm: change signature of free_reserved_area() to fix building warnings Change signature of free_reserved_area() according to Russell King's suggestion to fix following build warnings: arch/arm/mm/init.c: In function 'mem_init': arch/arm/mm/init.c:603:2: warning: passing argument 1 of 'free_reserved_area' makes integer from pointer without a cast [enabled by default] free_reserved_area(__va(PHYS_PFN_OFFSET), swapper_pg_dir, 0, NULL); ^ In file included from include/linux/mman.h:4:0, from arch/arm/mm/init.c:15: include/linux/mm.h:1301:22: note: expected 'long unsigned int' but argument is of type 'void *' extern unsigned long free_reserved_area(unsigned long start, unsigned long end, mm/page_alloc.c: In function 'free_reserved_area': >> mm/page_alloc.c:5134:3: warning: passing argument 1 of 'virt_to_phys' makes pointer from integer without a cast [enabled by default] In file included from arch/mips/include/asm/page.h:49:0, from include/linux/mmzone.h:20, from include/linux/gfp.h:4, from include/linux/mm.h:8, from mm/page_alloc.c:18: arch/mips/include/asm/io.h:119:29: note: expected 'const volatile void *' but argument is of type 'long unsigned int' mm/page_alloc.c: In function 'free_area_init_nodes': mm/page_alloc.c:5030:34: warning: array subscript is below array bounds [-Warray-bounds] Also address some minor code review comments. Signed-off-by: Jiang Liu Reported-by: Arnd Bergmann Cc: "H. Peter Anvin" Cc: "Michael S. Tsirkin" Cc: Cc: Catalin Marinas Cc: Chris Metcalf Cc: David Howells Cc: Geert Uytterhoeven Cc: Ingo Molnar Cc: Jeremy Fitzhardinge Cc: Jianguo Wu Cc: Joonsoo Kim Cc: Kamezawa Hiroyuki Cc: Konrad Rzeszutek Wilk Cc: Marek Szyprowski Cc: Mel Gorman Cc: Michel Lespinasse Cc: Minchan Kim Cc: Rik van Riel Cc: Rusty Russell Cc: Tang Chen Cc: Tejun Heo Cc: Thomas Gleixner Cc: Wen Congyang Cc: Will Deacon Cc: Yasuaki Ishimatsu Cc: Yinghai Lu Cc: Russell King Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/kernel/sys_nautilus.c | 4 ++-- arch/alpha/mm/init.c | 2 +- arch/arc/mm/init.c | 2 +- arch/arm/mm/init.c | 2 +- arch/arm64/mm/init.c | 2 +- arch/avr32/mm/init.c | 2 +- arch/blackfin/mm/init.c | 2 +- arch/c6x/mm/init.c | 2 +- arch/frv/mm/init.c | 2 +- arch/h8300/mm/init.c | 2 +- arch/ia64/mm/init.c | 3 +-- arch/m32r/mm/init.c | 2 +- arch/m68k/mm/init.c | 2 +- arch/metag/mm/init.c | 3 ++- arch/microblaze/mm/init.c | 2 +- arch/mips/mm/init.c | 3 ++- arch/mn10300/mm/init.c | 3 ++- arch/openrisc/mm/init.c | 2 +- arch/parisc/mm/init.c | 3 ++- arch/powerpc/kernel/kvm.c | 2 +- arch/powerpc/mm/mem.c | 2 +- arch/s390/mm/init.c | 3 ++- arch/score/mm/init.c | 3 ++- arch/sh/mm/init.c | 2 +- arch/sparc/mm/init_32.c | 4 ++-- arch/sparc/mm/init_64.c | 4 ++-- arch/um/kernel/mem.c | 2 +- arch/unicore32/mm/init.c | 2 +- arch/xtensa/mm/init.c | 2 +- include/linux/mm.h | 5 ++--- mm/page_alloc.c | 19 ++++++++++--------- 31 files changed, 50 insertions(+), 45 deletions(-) (limited to 'arch/s390') diff --git a/arch/alpha/kernel/sys_nautilus.c b/arch/alpha/kernel/sys_nautilus.c index 1d4aabfcf9a..891bd274ccb 100644 --- a/arch/alpha/kernel/sys_nautilus.c +++ b/arch/alpha/kernel/sys_nautilus.c @@ -238,8 +238,8 @@ nautilus_init_pci(void) if (pci_mem < memtop) memtop = pci_mem; if (memtop > alpha_mv.min_mem_address) { - free_reserved_area((unsigned long)__va(alpha_mv.min_mem_address), - (unsigned long)__va(memtop), 0, NULL); + free_reserved_area(__va(alpha_mv.min_mem_address), + __va(memtop), 0, NULL); printk("nautilus_init_pci: %ldk freed\n", (memtop - alpha_mv.min_mem_address) >> 10); } diff --git a/arch/alpha/mm/init.c b/arch/alpha/mm/init.c index 0ba85ee4a46..d54848d4e46 100644 --- a/arch/alpha/mm/init.c +++ b/arch/alpha/mm/init.c @@ -326,6 +326,6 @@ free_initmem(void) void free_initrd_mem(unsigned long start, unsigned long end) { - free_reserved_area(start, end, 0, "initrd"); + free_reserved_area((void *)start, (void *)end, 0, "initrd"); } #endif diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c index 4a177365b2c..dce02e4716a 100644 --- a/arch/arc/mm/init.c +++ b/arch/arc/mm/init.c @@ -152,7 +152,7 @@ void __init_refok free_initmem(void) #ifdef CONFIG_BLK_DEV_INITRD void __init free_initrd_mem(unsigned long start, unsigned long end) { - free_reserved_area(start, end, 0, "initrd"); + free_reserved_area((void *)start, (void *)end, 0, "initrd"); } #endif diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 2ffee02d1d5..7fae391caf8 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -745,7 +745,7 @@ void free_initrd_mem(unsigned long start, unsigned long end) { if (!keep_initrd) { poison_init_mem((void *)start, PAGE_ALIGN(end) - start); - free_reserved_area(start, end, 0, "initrd"); + free_reserved_area((void *)start, (void *)end, 0, "initrd"); } } diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index f497ca77925..6041e4008a8 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -398,7 +398,7 @@ void free_initrd_mem(unsigned long start, unsigned long end) { if (!keep_initrd) { poison_init_mem((void *)start, PAGE_ALIGN(end) - start); - free_reserved_area(start, end, 0, "initrd"); + free_reserved_area((void *)start, (void *)end, 0, "initrd"); } } diff --git a/arch/avr32/mm/init.c b/arch/avr32/mm/init.c index e66e8406f99..5a79fa08cb3 100644 --- a/arch/avr32/mm/init.c +++ b/arch/avr32/mm/init.c @@ -154,6 +154,6 @@ void free_initmem(void) #ifdef CONFIG_BLK_DEV_INITRD void free_initrd_mem(unsigned long start, unsigned long end) { - free_reserved_area(start, end, 0, "initrd"); + free_reserved_area((void *)start, (void *)end, 0, "initrd"); } #endif diff --git a/arch/blackfin/mm/init.c b/arch/blackfin/mm/init.c index 82d01a71207..8e9eab27281 100644 --- a/arch/blackfin/mm/init.c +++ b/arch/blackfin/mm/init.c @@ -133,7 +133,7 @@ void __init mem_init(void) void __init free_initrd_mem(unsigned long start, unsigned long end) { #ifndef CONFIG_MPU - free_reserved_area(start, end, 0, "initrd"); + free_reserved_area((void *)start, (void *)end, 0, "initrd"); #endif } #endif diff --git a/arch/c6x/mm/init.c b/arch/c6x/mm/init.c index b74ccb5a769..07bfcc98a3b 100644 --- a/arch/c6x/mm/init.c +++ b/arch/c6x/mm/init.c @@ -78,7 +78,7 @@ void __init mem_init(void) #ifdef CONFIG_BLK_DEV_INITRD void __init free_initrd_mem(unsigned long start, unsigned long end) { - free_reserved_area(start, end, 0, "initrd"); + free_reserved_area((void *)start, (void *)end, 0, "initrd"); } #endif diff --git a/arch/frv/mm/init.c b/arch/frv/mm/init.c index dee354fa6b6..a67f3a5897b 100644 --- a/arch/frv/mm/init.c +++ b/arch/frv/mm/init.c @@ -173,6 +173,6 @@ void free_initmem(void) #ifdef CONFIG_BLK_DEV_INITRD void __init free_initrd_mem(unsigned long start, unsigned long end) { - free_reserved_area(start, end, 0, "initrd"); + free_reserved_area((void *)start, (void *)end, 0, "initrd"); } /* end free_initrd_mem() */ #endif diff --git a/arch/h8300/mm/init.c b/arch/h8300/mm/init.c index ff349d70a29..57e03c59861 100644 --- a/arch/h8300/mm/init.c +++ b/arch/h8300/mm/init.c @@ -161,7 +161,7 @@ void __init mem_init(void) #ifdef CONFIG_BLK_DEV_INITRD void free_initrd_mem(unsigned long start, unsigned long end) { - free_reserved_area(start, end, 0, "initrd"); + free_reserved_area((void *)start, (void *)end, 0, "initrd"); } #endif diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index d1fe4b40260..da568c2e839 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -154,8 +154,7 @@ ia64_init_addr_space (void) void free_initmem (void) { - free_reserved_area((unsigned long)ia64_imva(__init_begin), - (unsigned long)ia64_imva(__init_end), + free_reserved_area(ia64_imva(__init_begin), ia64_imva(__init_end), 0, "unused kernel"); } diff --git a/arch/m32r/mm/init.c b/arch/m32r/mm/init.c index ab4cbce91a9..d80412d0c14 100644 --- a/arch/m32r/mm/init.c +++ b/arch/m32r/mm/init.c @@ -191,6 +191,6 @@ void free_initmem(void) *======================================================================*/ void free_initrd_mem(unsigned long start, unsigned long end) { - free_reserved_area(start, end, 0, "initrd"); + free_reserved_area((void *)start, (void *)end, 0, "initrd"); } #endif diff --git a/arch/m68k/mm/init.c b/arch/m68k/mm/init.c index 1af2ca3411f..95de725534e 100644 --- a/arch/m68k/mm/init.c +++ b/arch/m68k/mm/init.c @@ -202,6 +202,6 @@ void __init mem_init(void) #ifdef CONFIG_BLK_DEV_INITRD void free_initrd_mem(unsigned long start, unsigned long end) { - free_reserved_area(start, end, 0, "initrd"); + free_reserved_area((void *)start, (void *)end, 0, "initrd"); } #endif diff --git a/arch/metag/mm/init.c b/arch/metag/mm/init.c index d05b8455c44..5e2238dd72e 100644 --- a/arch/metag/mm/init.c +++ b/arch/metag/mm/init.c @@ -414,7 +414,8 @@ void free_initmem(void) #ifdef CONFIG_BLK_DEV_INITRD void free_initrd_mem(unsigned long start, unsigned long end) { - free_reserved_area(start, end, POISON_FREE_INITMEM, "initrd"); + free_reserved_area((void *)start, (void *)end, POISON_FREE_INITMEM, + "initrd"); } #endif diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c index b38ae3acfeb..d7b8ada9345 100644 --- a/arch/microblaze/mm/init.c +++ b/arch/microblaze/mm/init.c @@ -235,7 +235,7 @@ void __init setup_memory(void) #ifdef CONFIG_BLK_DEV_INITRD void free_initrd_mem(unsigned long start, unsigned long end) { - free_reserved_area(start, end, 0, "initrd"); + free_reserved_area((void *)start, (void *)end, 0, "initrd"); } #endif diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index 9b973e0af9c..268f2a94031 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -440,7 +440,8 @@ void free_init_pages(const char *what, unsigned long begin, unsigned long end) #ifdef CONFIG_BLK_DEV_INITRD void free_initrd_mem(unsigned long start, unsigned long end) { - free_reserved_area(start, end, POISON_FREE_INITMEM, "initrd"); + free_reserved_area((void *)start, (void *)end, POISON_FREE_INITMEM, + "initrd"); } #endif diff --git a/arch/mn10300/mm/init.c b/arch/mn10300/mm/init.c index 5a8ace63a6b..e19049d1f2b 100644 --- a/arch/mn10300/mm/init.c +++ b/arch/mn10300/mm/init.c @@ -152,6 +152,7 @@ void free_initmem(void) #ifdef CONFIG_BLK_DEV_INITRD void free_initrd_mem(unsigned long start, unsigned long end) { - free_reserved_area(start, end, POISON_FREE_INITMEM, "initrd"); + free_reserved_area((void *)start, (void *)end, POISON_FREE_INITMEM, + "initrd"); } #endif diff --git a/arch/openrisc/mm/init.c b/arch/openrisc/mm/init.c index b3cbc670383..ab113325dc4 100644 --- a/arch/openrisc/mm/init.c +++ b/arch/openrisc/mm/init.c @@ -261,7 +261,7 @@ void __init mem_init(void) #ifdef CONFIG_BLK_DEV_INITRD void free_initrd_mem(unsigned long start, unsigned long end) { - free_reserved_area(start, end, 0, "initrd"); + free_reserved_area((void *)start, (void *)end, 0, "initrd"); } #endif diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c index 505b56c6b9b..3223d5e4a37 100644 --- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -1101,6 +1101,7 @@ void flush_tlb_all(void) #ifdef CONFIG_BLK_DEV_INITRD void free_initrd_mem(unsigned long start, unsigned long end) { - num_physpages += free_reserved_area(start, end, 0, "initrd"); + num_physpages += free_reserved_area((void *)start, (void *)end, 0, + "initrd"); } #endif diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c index 6782221d49b..5e4830a33c0 100644 --- a/arch/powerpc/kernel/kvm.c +++ b/arch/powerpc/kernel/kvm.c @@ -756,7 +756,7 @@ static __init void kvm_free_tmp(void) end = (ulong)&kvm_tmp[ARRAY_SIZE(kvm_tmp)] & PAGE_MASK; /* Free the tmp space we don't need */ - free_reserved_area(start, end, 0, NULL); + free_reserved_area((void *)start, (void *)end, 0, NULL); } static int __init kvm_guest_init(void) diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 0988a26e041..347c5b1bbd6 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -407,7 +407,7 @@ void free_initmem(void) #ifdef CONFIG_BLK_DEV_INITRD void __init free_initrd_mem(unsigned long start, unsigned long end) { - free_reserved_area(start, end, 0, "initrd"); + free_reserved_area((void *)start, (void *)end, 0, "initrd"); } #endif diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index 89ebae4008f..0878c89fe7d 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -172,7 +172,8 @@ void free_initmem(void) #ifdef CONFIG_BLK_DEV_INITRD void __init free_initrd_mem(unsigned long start, unsigned long end) { - free_reserved_area(start, end, POISON_FREE_INITMEM, "initrd"); + free_reserved_area((void *)start, (void *)end, POISON_FREE_INITMEM, + "initrd"); } #endif diff --git a/arch/score/mm/init.c b/arch/score/mm/init.c index 0940682ab38..f5dd61eb454 100644 --- a/arch/score/mm/init.c +++ b/arch/score/mm/init.c @@ -108,7 +108,8 @@ void __init mem_init(void) #ifdef CONFIG_BLK_DEV_INITRD void free_initrd_mem(unsigned long start, unsigned long end) { - free_reserved_area(start, end, POISON_FREE_INITMEM, "initrd"); + free_reserved_area((void *)start, (void *)end, POISON_FREE_INITMEM, + "initrd"); } #endif diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index 20f9ead650d..b892a9b7d7e 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -505,7 +505,7 @@ void free_initmem(void) #ifdef CONFIG_BLK_DEV_INITRD void free_initrd_mem(unsigned long start, unsigned long end) { - free_reserved_area(start, end, 0, "initrd"); + free_reserved_area((void *)start, (void *)end, 0, "initrd"); } #endif diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c index af472cf7c69..d5f9c023826 100644 --- a/arch/sparc/mm/init_32.c +++ b/arch/sparc/mm/init_32.c @@ -372,8 +372,8 @@ void free_initmem (void) #ifdef CONFIG_BLK_DEV_INITRD void free_initrd_mem(unsigned long start, unsigned long end) { - num_physpages += free_reserved_area(start, end, POISON_FREE_INITMEM, - "initrd"); + num_physpages += free_reserved_area((void *)start, (void *)end, + POISON_FREE_INITMEM, "initrd"); } #endif diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 04fd55a6e46..8269deb84ed 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -2131,8 +2131,8 @@ void free_initmem(void) #ifdef CONFIG_BLK_DEV_INITRD void free_initrd_mem(unsigned long start, unsigned long end) { - num_physpages += free_reserved_area(start, end, POISON_FREE_INITMEM, - "initrd"); + num_physpages += free_reserved_area((void *)start, (void *)end, + POISON_FREE_INITMEM, "initrd"); } #endif diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c index 9df292b270a..2aa7a2448d5 100644 --- a/arch/um/kernel/mem.c +++ b/arch/um/kernel/mem.c @@ -244,7 +244,7 @@ void free_initmem(void) #ifdef CONFIG_BLK_DEV_INITRD void free_initrd_mem(unsigned long start, unsigned long end) { - free_reserved_area(start, end, 0, "initrd"); + free_reserved_area((void *)start, (void *)end, 0, "initrd"); } #endif diff --git a/arch/unicore32/mm/init.c b/arch/unicore32/mm/init.c index 63df12d71ce..220755cc970 100644 --- a/arch/unicore32/mm/init.c +++ b/arch/unicore32/mm/init.c @@ -486,7 +486,7 @@ static int keep_initrd; void free_initrd_mem(unsigned long start, unsigned long end) { if (!keep_initrd) - free_reserved_area(start, end, 0, "initrd"); + free_reserved_area((void *)start, (void *)end, 0, "initrd"); } static int __init keepinitrd_setup(char *__unused) diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c index bba125b4bb0..4d658efc328 100644 --- a/arch/xtensa/mm/init.c +++ b/arch/xtensa/mm/init.c @@ -214,7 +214,7 @@ extern int initrd_is_mapped; void free_initrd_mem(unsigned long start, unsigned long end) { if (initrd_is_mapped) - free_reserved_area(start, end, 0, "initrd"); + free_reserved_area((void *)start, (void *)end, 0, "initrd"); } #endif diff --git a/include/linux/mm.h b/include/linux/mm.h index 949bd703589..be1b96ce065 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1311,7 +1311,7 @@ extern void free_initmem(void); * "poison" if it's non-zero. * Return pages freed into the buddy system. */ -extern unsigned long free_reserved_area(unsigned long start, unsigned long end, +extern unsigned long free_reserved_area(void *start, void *end, int poison, char *s); #ifdef CONFIG_HIGHMEM /* @@ -1355,8 +1355,7 @@ static inline unsigned long free_initmem_default(int poison) { extern char __init_begin[], __init_end[]; - return free_reserved_area(PAGE_ALIGN((unsigned long)&__init_begin) , - ((unsigned long)&__init_end) & PAGE_MASK, + return free_reserved_area(&__init_begin, &__init_end, poison, "unused kernel"); } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index d711dcdda36..be18ccd017b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5206,25 +5206,26 @@ early_param("movablecore", cmdline_parse_movablecore); #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ -unsigned long free_reserved_area(unsigned long start, unsigned long end, - int poison, char *s) +unsigned long free_reserved_area(void *start, void *end, int poison, char *s) { - unsigned long pages, pos; + void *pos; + unsigned long pages = 0; - pos = start = PAGE_ALIGN(start); - end &= PAGE_MASK; - for (pages = 0; pos < end; pos += PAGE_SIZE, pages++) { + start = (void *)PAGE_ALIGN((unsigned long)start); + end = (void *)((unsigned long)end & PAGE_MASK); + for (pos = start; pos < end; pos += PAGE_SIZE, pages++) { if (poison) - memset((void *)pos, poison, PAGE_SIZE); - free_reserved_page(virt_to_page((void *)pos)); + memset(pos, poison, PAGE_SIZE); + free_reserved_page(virt_to_page(pos)); } if (pages && s) - pr_info("Freeing %s memory: %ldK (%lx - %lx)\n", + pr_info("Freeing %s memory: %ldK (%p - %p)\n", s, pages << (PAGE_SHIFT - 10), start, end); return pages; } +EXPORT_SYMBOL(free_reserved_area); #ifdef CONFIG_HIGHMEM void free_highmem_page(struct page *page) -- cgit v1.2.3-70-g09d2 From dbe67df4ba78c79db547c7864e1120981c144c97 Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Wed, 3 Jul 2013 15:02:51 -0700 Subject: mm: enhance free_reserved_area() to support poisoning memory with zero Address more review comments from last round of code review. 1) Enhance free_reserved_area() to support poisoning freed memory with pattern '0'. This could be used to get rid of poison_init_mem() on ARM64. 2) A previous patch has disabled memory poison for initmem on s390 by mistake, so restore to the original behavior. 3) Remove redundant PAGE_ALIGN() when calling free_reserved_area(). Signed-off-by: Jiang Liu Cc: Geert Uytterhoeven Cc: "H. Peter Anvin" Cc: "Michael S. Tsirkin" Cc: Cc: Arnd Bergmann Cc: Catalin Marinas Cc: Chris Metcalf Cc: David Howells Cc: Ingo Molnar Cc: Jeremy Fitzhardinge Cc: Jianguo Wu Cc: Joonsoo Kim Cc: Kamezawa Hiroyuki Cc: Konrad Rzeszutek Wilk Cc: Marek Szyprowski Cc: Mel Gorman Cc: Michel Lespinasse Cc: Minchan Kim Cc: Rik van Riel Cc: Rusty Russell Cc: Tang Chen Cc: Tejun Heo Cc: Thomas Gleixner Cc: Wen Congyang Cc: Will Deacon Cc: Yasuaki Ishimatsu Cc: Yinghai Lu Cc: Russell King Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/kernel/sys_nautilus.c | 2 +- arch/alpha/mm/init.c | 4 ++-- arch/arc/mm/init.c | 4 ++-- arch/arm/mm/init.c | 8 ++++---- arch/arm64/mm/init.c | 4 ++-- arch/avr32/mm/init.c | 4 ++-- arch/blackfin/mm/init.c | 4 ++-- arch/c6x/mm/init.c | 4 ++-- arch/cris/mm/init.c | 2 +- arch/frv/mm/init.c | 4 ++-- arch/h8300/mm/init.c | 4 ++-- arch/ia64/mm/init.c | 2 +- arch/m32r/mm/init.c | 4 ++-- arch/m68k/mm/init.c | 4 ++-- arch/microblaze/mm/init.c | 4 ++-- arch/openrisc/mm/init.c | 4 ++-- arch/parisc/mm/init.c | 4 ++-- arch/powerpc/kernel/kvm.c | 9 ++------- arch/powerpc/mm/mem.c | 2 +- arch/s390/mm/init.c | 2 +- arch/sh/mm/init.c | 4 ++-- arch/um/kernel/mem.c | 2 +- arch/unicore32/mm/init.c | 4 ++-- arch/xtensa/mm/init.c | 4 ++-- include/linux/mm.h | 7 ++++--- mm/page_alloc.c | 2 +- 26 files changed, 49 insertions(+), 53 deletions(-) (limited to 'arch/s390') diff --git a/arch/alpha/kernel/sys_nautilus.c b/arch/alpha/kernel/sys_nautilus.c index 891bd274ccb..837c0fa5831 100644 --- a/arch/alpha/kernel/sys_nautilus.c +++ b/arch/alpha/kernel/sys_nautilus.c @@ -239,7 +239,7 @@ nautilus_init_pci(void) memtop = pci_mem; if (memtop > alpha_mv.min_mem_address) { free_reserved_area(__va(alpha_mv.min_mem_address), - __va(memtop), 0, NULL); + __va(memtop), -1, NULL); printk("nautilus_init_pci: %ldk freed\n", (memtop - alpha_mv.min_mem_address) >> 10); } diff --git a/arch/alpha/mm/init.c b/arch/alpha/mm/init.c index d54848d4e46..218c29c14bb 100644 --- a/arch/alpha/mm/init.c +++ b/arch/alpha/mm/init.c @@ -319,13 +319,13 @@ mem_init(void) void free_initmem(void) { - free_initmem_default(0); + free_initmem_default(-1); } #ifdef CONFIG_BLK_DEV_INITRD void free_initrd_mem(unsigned long start, unsigned long end) { - free_reserved_area((void *)start, (void *)end, 0, "initrd"); + free_reserved_area((void *)start, (void *)end, -1, "initrd"); } #endif diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c index dce02e4716a..f9c70771209 100644 --- a/arch/arc/mm/init.c +++ b/arch/arc/mm/init.c @@ -146,13 +146,13 @@ void __init mem_init(void) */ void __init_refok free_initmem(void) { - free_initmem_default(0); + free_initmem_default(-1); } #ifdef CONFIG_BLK_DEV_INITRD void __init free_initrd_mem(unsigned long start, unsigned long end) { - free_reserved_area((void *)start, (void *)end, 0, "initrd"); + free_reserved_area((void *)start, (void *)end, -1, "initrd"); } #endif diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 7fae391caf8..2070651c1bb 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -601,7 +601,7 @@ void __init mem_init(void) #ifdef CONFIG_SA1111 /* now that our DMA memory is actually so designated, we can free it */ - free_reserved_area(__va(PHYS_PFN_OFFSET), swapper_pg_dir, 0, NULL); + free_reserved_area(__va(PHYS_PFN_OFFSET), swapper_pg_dir, -1, NULL); #endif free_highpages(); @@ -729,12 +729,12 @@ void free_initmem(void) extern char __tcm_start, __tcm_end; poison_init_mem(&__tcm_start, &__tcm_end - &__tcm_start); - free_reserved_area(&__tcm_start, &__tcm_end, 0, "TCM link"); + free_reserved_area(&__tcm_start, &__tcm_end, -1, "TCM link"); #endif poison_init_mem(__init_begin, __init_end - __init_begin); if (!machine_is_integrator() && !machine_is_cintegrator()) - free_initmem_default(0); + free_initmem_default(-1); } #ifdef CONFIG_BLK_DEV_INITRD @@ -745,7 +745,7 @@ void free_initrd_mem(unsigned long start, unsigned long end) { if (!keep_initrd) { poison_init_mem((void *)start, PAGE_ALIGN(end) - start); - free_reserved_area((void *)start, (void *)end, 0, "initrd"); + free_reserved_area((void *)start, (void *)end, -1, "initrd"); } } diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 6041e4008a8..997c6345cdd 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -387,7 +387,7 @@ void __init mem_init(void) void free_initmem(void) { poison_init_mem(__init_begin, __init_end - __init_begin); - free_initmem_default(0); + free_initmem_default(-1); } #ifdef CONFIG_BLK_DEV_INITRD @@ -398,7 +398,7 @@ void free_initrd_mem(unsigned long start, unsigned long end) { if (!keep_initrd) { poison_init_mem((void *)start, PAGE_ALIGN(end) - start); - free_reserved_area((void *)start, (void *)end, 0, "initrd"); + free_reserved_area((void *)start, (void *)end, -1, "initrd"); } } diff --git a/arch/avr32/mm/init.c b/arch/avr32/mm/init.c index 5a79fa08cb3..b079e04f695 100644 --- a/arch/avr32/mm/init.c +++ b/arch/avr32/mm/init.c @@ -148,12 +148,12 @@ void __init mem_init(void) void free_initmem(void) { - free_initmem_default(0); + free_initmem_default(-1); } #ifdef CONFIG_BLK_DEV_INITRD void free_initrd_mem(unsigned long start, unsigned long end) { - free_reserved_area((void *)start, (void *)end, 0, "initrd"); + free_reserved_area((void *)start, (void *)end, -1, "initrd"); } #endif diff --git a/arch/blackfin/mm/init.c b/arch/blackfin/mm/init.c index 8e9eab27281..fa241f5a7dc 100644 --- a/arch/blackfin/mm/init.c +++ b/arch/blackfin/mm/init.c @@ -133,7 +133,7 @@ void __init mem_init(void) void __init free_initrd_mem(unsigned long start, unsigned long end) { #ifndef CONFIG_MPU - free_reserved_area((void *)start, (void *)end, 0, "initrd"); + free_reserved_area((void *)start, (void *)end, -1, "initrd"); #endif } #endif @@ -141,7 +141,7 @@ void __init free_initrd_mem(unsigned long start, unsigned long end) void __init_refok free_initmem(void) { #if defined CONFIG_RAMKERNEL && !defined CONFIG_MPU - free_initmem_default(0); + free_initmem_default(-1); if (memory_start == (unsigned long)(&__init_end)) memory_start = (unsigned long)(&__init_begin); #endif diff --git a/arch/c6x/mm/init.c b/arch/c6x/mm/init.c index 07bfcc98a3b..3987a20fdee 100644 --- a/arch/c6x/mm/init.c +++ b/arch/c6x/mm/init.c @@ -78,11 +78,11 @@ void __init mem_init(void) #ifdef CONFIG_BLK_DEV_INITRD void __init free_initrd_mem(unsigned long start, unsigned long end) { - free_reserved_area((void *)start, (void *)end, 0, "initrd"); + free_reserved_area((void *)start, (void *)end, -1, "initrd"); } #endif void __init free_initmem(void) { - free_initmem_default(0); + free_initmem_default(-1); } diff --git a/arch/cris/mm/init.c b/arch/cris/mm/init.c index 9ac80946dad..8fec26392ae 100644 --- a/arch/cris/mm/init.c +++ b/arch/cris/mm/init.c @@ -65,5 +65,5 @@ mem_init(void) void free_initmem(void) { - free_initmem_default(0); + free_initmem_default(-1); } diff --git a/arch/frv/mm/init.c b/arch/frv/mm/init.c index a67f3a5897b..8ba9d22d0d9 100644 --- a/arch/frv/mm/init.c +++ b/arch/frv/mm/init.c @@ -162,7 +162,7 @@ void __init mem_init(void) void free_initmem(void) { #if defined(CONFIG_RAMKERNEL) && !defined(CONFIG_PROTECT_KERNEL) - free_initmem_default(0); + free_initmem_default(-1); #endif } /* end free_initmem() */ @@ -173,6 +173,6 @@ void free_initmem(void) #ifdef CONFIG_BLK_DEV_INITRD void __init free_initrd_mem(unsigned long start, unsigned long end) { - free_reserved_area((void *)start, (void *)end, 0, "initrd"); + free_reserved_area((void *)start, (void *)end, -1, "initrd"); } /* end free_initrd_mem() */ #endif diff --git a/arch/h8300/mm/init.c b/arch/h8300/mm/init.c index 57e03c59861..c831f1dba13 100644 --- a/arch/h8300/mm/init.c +++ b/arch/h8300/mm/init.c @@ -161,7 +161,7 @@ void __init mem_init(void) #ifdef CONFIG_BLK_DEV_INITRD void free_initrd_mem(unsigned long start, unsigned long end) { - free_reserved_area((void *)start, (void *)end, 0, "initrd"); + free_reserved_area((void *)start, (void *)end, -1, "initrd"); } #endif @@ -169,7 +169,7 @@ void free_initmem(void) { #ifdef CONFIG_RAMKERNEL - free_initmem_default(0); + free_initmem_default(-1); #endif } diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index da568c2e839..f8a4f38b0ad 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -155,7 +155,7 @@ void free_initmem (void) { free_reserved_area(ia64_imva(__init_begin), ia64_imva(__init_end), - 0, "unused kernel"); + -1, "unused kernel"); } void __init diff --git a/arch/m32r/mm/init.c b/arch/m32r/mm/init.c index d80412d0c14..cca87d91843 100644 --- a/arch/m32r/mm/init.c +++ b/arch/m32r/mm/init.c @@ -181,7 +181,7 @@ void __init mem_init(void) *======================================================================*/ void free_initmem(void) { - free_initmem_default(0); + free_initmem_default(-1); } #ifdef CONFIG_BLK_DEV_INITRD @@ -191,6 +191,6 @@ void free_initmem(void) *======================================================================*/ void free_initrd_mem(unsigned long start, unsigned long end) { - free_reserved_area((void *)start, (void *)end, 0, "initrd"); + free_reserved_area((void *)start, (void *)end, -1, "initrd"); } #endif diff --git a/arch/m68k/mm/init.c b/arch/m68k/mm/init.c index 95de725534e..ab0b54ca5d8 100644 --- a/arch/m68k/mm/init.c +++ b/arch/m68k/mm/init.c @@ -110,7 +110,7 @@ void __init paging_init(void) void free_initmem(void) { #ifndef CONFIG_MMU_SUN3 - free_initmem_default(0); + free_initmem_default(-1); #endif /* CONFIG_MMU_SUN3 */ } @@ -202,6 +202,6 @@ void __init mem_init(void) #ifdef CONFIG_BLK_DEV_INITRD void free_initrd_mem(unsigned long start, unsigned long end) { - free_reserved_area((void *)start, (void *)end, 0, "initrd"); + free_reserved_area((void *)start, (void *)end, -1, "initrd"); } #endif diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c index d7b8ada9345..d149e0ebb76 100644 --- a/arch/microblaze/mm/init.c +++ b/arch/microblaze/mm/init.c @@ -235,13 +235,13 @@ void __init setup_memory(void) #ifdef CONFIG_BLK_DEV_INITRD void free_initrd_mem(unsigned long start, unsigned long end) { - free_reserved_area((void *)start, (void *)end, 0, "initrd"); + free_reserved_area((void *)start, (void *)end, -1, "initrd"); } #endif void free_initmem(void) { - free_initmem_default(0); + free_initmem_default(-1); } void __init mem_init(void) diff --git a/arch/openrisc/mm/init.c b/arch/openrisc/mm/init.c index ab113325dc4..c371e4a0fca 100644 --- a/arch/openrisc/mm/init.c +++ b/arch/openrisc/mm/init.c @@ -261,11 +261,11 @@ void __init mem_init(void) #ifdef CONFIG_BLK_DEV_INITRD void free_initrd_mem(unsigned long start, unsigned long end) { - free_reserved_area((void *)start, (void *)end, 0, "initrd"); + free_reserved_area((void *)start, (void *)end, -1, "initrd"); } #endif void free_initmem(void) { - free_initmem_default(0); + free_initmem_default(-1); } diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c index 3223d5e4a37..ebac7bd76b5 100644 --- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -532,7 +532,7 @@ void free_initmem(void) * pages are no-longer executable */ flush_icache_range(init_begin, init_end); - num_physpages += free_initmem_default(0); + num_physpages += free_initmem_default(-1); /* set up a new led state on systems shipped LED State panel */ pdc_chassis_send_status(PDC_CHASSIS_DIRECT_BCOMPLETE); @@ -1101,7 +1101,7 @@ void flush_tlb_all(void) #ifdef CONFIG_BLK_DEV_INITRD void free_initrd_mem(unsigned long start, unsigned long end) { - num_physpages += free_reserved_area((void *)start, (void *)end, 0, + num_physpages += free_reserved_area((void *)start, (void *)end, -1, "initrd"); } #endif diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c index 5e4830a33c0..db28032e320 100644 --- a/arch/powerpc/kernel/kvm.c +++ b/arch/powerpc/kernel/kvm.c @@ -750,13 +750,8 @@ EXPORT_SYMBOL_GPL(kvm_hypercall); static __init void kvm_free_tmp(void) { - unsigned long start, end; - - start = (ulong)&kvm_tmp[kvm_tmp_index + (PAGE_SIZE - 1)] & PAGE_MASK; - end = (ulong)&kvm_tmp[ARRAY_SIZE(kvm_tmp)] & PAGE_MASK; - - /* Free the tmp space we don't need */ - free_reserved_area((void *)start, (void *)end, 0, NULL); + free_reserved_area(&kvm_tmp[kvm_tmp_index], + &kvm_tmp[ARRAY_SIZE(kvm_tmp)], -1, NULL); } static int __init kvm_guest_init(void) diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 347c5b1bbd6..7f47a05f55a 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -407,7 +407,7 @@ void free_initmem(void) #ifdef CONFIG_BLK_DEV_INITRD void __init free_initrd_mem(unsigned long start, unsigned long end) { - free_reserved_area((void *)start, (void *)end, 0, "initrd"); + free_reserved_area((void *)start, (void *)end, -1, "initrd"); } #endif diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index 0878c89fe7d..bf01d18422e 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -166,7 +166,7 @@ void __init mem_init(void) void free_initmem(void) { - free_initmem_default(0); + free_initmem_default(POISON_FREE_INITMEM); } #ifdef CONFIG_BLK_DEV_INITRD diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index b892a9b7d7e..d3af56b7a09 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -499,13 +499,13 @@ void __init mem_init(void) void free_initmem(void) { - free_initmem_default(0); + free_initmem_default(-1); } #ifdef CONFIG_BLK_DEV_INITRD void free_initrd_mem(unsigned long start, unsigned long end) { - free_reserved_area((void *)start, (void *)end, 0, "initrd"); + free_reserved_area((void *)start, (void *)end, -1, "initrd"); } #endif diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c index 2aa7a2448d5..8ff0b7ae8ec 100644 --- a/arch/um/kernel/mem.c +++ b/arch/um/kernel/mem.c @@ -244,7 +244,7 @@ void free_initmem(void) #ifdef CONFIG_BLK_DEV_INITRD void free_initrd_mem(unsigned long start, unsigned long end) { - free_reserved_area((void *)start, (void *)end, 0, "initrd"); + free_reserved_area((void *)start, (void *)end, -1, "initrd"); } #endif diff --git a/arch/unicore32/mm/init.c b/arch/unicore32/mm/init.c index 220755cc970..df9b8abcb6a 100644 --- a/arch/unicore32/mm/init.c +++ b/arch/unicore32/mm/init.c @@ -476,7 +476,7 @@ void __init mem_init(void) void free_initmem(void) { - free_initmem_default(0); + free_initmem_default(-1); } #ifdef CONFIG_BLK_DEV_INITRD @@ -486,7 +486,7 @@ static int keep_initrd; void free_initrd_mem(unsigned long start, unsigned long end) { if (!keep_initrd) - free_reserved_area((void *)start, (void *)end, 0, "initrd"); + free_reserved_area((void *)start, (void *)end, -1, "initrd"); } static int __init keepinitrd_setup(char *__unused) diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c index 4d658efc328..026d29bee30 100644 --- a/arch/xtensa/mm/init.c +++ b/arch/xtensa/mm/init.c @@ -214,11 +214,11 @@ extern int initrd_is_mapped; void free_initrd_mem(unsigned long start, unsigned long end) { if (initrd_is_mapped) - free_reserved_area((void *)start, (void *)end, 0, "initrd"); + free_reserved_area((void *)start, (void *)end, -1, "initrd"); } #endif void free_initmem(void) { - free_initmem_default(0); + free_initmem_default(-1); } diff --git a/include/linux/mm.h b/include/linux/mm.h index be1b96ce065..083cc0ba238 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1308,7 +1308,7 @@ extern void free_initmem(void); /* * Free reserved pages within range [PAGE_ALIGN(start), end & PAGE_MASK) * into the buddy system. The freed pages will be poisoned with pattern - * "poison" if it's non-zero. + * "poison" if it's within range [0, UCHAR_MAX]. * Return pages freed into the buddy system. */ extern unsigned long free_reserved_area(void *start, void *end, @@ -1348,8 +1348,9 @@ static inline void mark_page_reserved(struct page *page) /* * Default method to free all the __init memory into the buddy system. - * The freed pages will be poisoned with pattern "poison" if it is - * non-zero. Return pages freed into the buddy system. + * The freed pages will be poisoned with pattern "poison" if it's within + * range [0, UCHAR_MAX]. + * Return pages freed into the buddy system. */ static inline unsigned long free_initmem_default(int poison) { diff --git a/mm/page_alloc.c b/mm/page_alloc.c index be18ccd017b..6780b2e18aa 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5214,7 +5214,7 @@ unsigned long free_reserved_area(void *start, void *end, int poison, char *s) start = (void *)PAGE_ALIGN((unsigned long)start); end = (void *)((unsigned long)end & PAGE_MASK); for (pos = start; pos < end; pos += PAGE_SIZE, pages++) { - if (poison) + if ((unsigned int)poison <= 0xFF) memset(pos, poison, PAGE_SIZE); free_reserved_page(virt_to_page(pos)); } -- cgit v1.2.3-70-g09d2 From 0c988534737a358fdff42fcce78f0ff1a12dbfc5 Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Wed, 3 Jul 2013 15:03:24 -0700 Subject: mm: concentrate modification of totalram_pages into the mm core Concentrate code to modify totalram_pages into the mm core, so the arch memory initialized code doesn't need to take care of it. With these changes applied, only following functions from mm core modify global variable totalram_pages: free_bootmem_late(), free_all_bootmem(), free_all_bootmem_node(), adjust_managed_page_count(). With this patch applied, it will be much more easier for us to keep totalram_pages and zone->managed_pages in consistence. Signed-off-by: Jiang Liu Acked-by: David Howells Cc: "H. Peter Anvin" Cc: "Michael S. Tsirkin" Cc: Cc: Arnd Bergmann Cc: Catalin Marinas Cc: Chris Metcalf Cc: Geert Uytterhoeven Cc: Ingo Molnar Cc: Jeremy Fitzhardinge Cc: Jianguo Wu Cc: Joonsoo Kim Cc: Kamezawa Hiroyuki Cc: Konrad Rzeszutek Wilk Cc: Marek Szyprowski Cc: Mel Gorman Cc: Michel Lespinasse Cc: Minchan Kim Cc: Rik van Riel Cc: Rusty Russell Cc: Tang Chen Cc: Tejun Heo Cc: Thomas Gleixner Cc: Wen Congyang Cc: Will Deacon Cc: Yasuaki Ishimatsu Cc: Yinghai Lu Cc: Russell King Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/mm/init.c | 2 +- arch/alpha/mm/numa.c | 2 +- arch/arc/mm/init.c | 2 +- arch/arm/mm/init.c | 3 +-- arch/arm64/mm/init.c | 2 +- arch/avr32/mm/init.c | 2 -- arch/blackfin/mm/init.c | 2 +- arch/c6x/mm/init.c | 2 +- arch/cris/mm/init.c | 2 +- arch/frv/mm/init.c | 2 +- arch/h8300/mm/init.c | 2 +- arch/hexagon/mm/init.c | 2 +- arch/ia64/mm/init.c | 2 +- arch/m32r/mm/init.c | 2 +- arch/m68k/mm/init.c | 4 ++-- arch/metag/mm/init.c | 5 +---- arch/microblaze/mm/init.c | 2 +- arch/mips/mm/init.c | 2 +- arch/mips/sgi-ip27/ip27-memory.c | 2 +- arch/mn10300/mm/init.c | 2 +- arch/openrisc/mm/init.c | 2 +- arch/parisc/mm/init.c | 4 ++-- arch/powerpc/mm/mem.c | 5 ++--- arch/s390/mm/init.c | 2 +- arch/score/mm/init.c | 2 +- arch/sh/mm/init.c | 2 +- arch/sparc/mm/init_32.c | 3 +-- arch/sparc/mm/init_64.c | 2 +- arch/tile/mm/init.c | 2 +- arch/um/kernel/mem.c | 2 +- arch/unicore32/mm/init.c | 2 +- arch/x86/mm/init_32.c | 2 +- arch/x86/mm/init_64.c | 2 +- arch/xtensa/mm/init.c | 2 +- mm/bootmem.c | 9 ++++++++- mm/nobootmem.c | 7 ++++++- 36 files changed, 50 insertions(+), 46 deletions(-) (limited to 'arch/s390') diff --git a/arch/alpha/mm/init.c b/arch/alpha/mm/init.c index 218c29c14bb..eee47a453d7 100644 --- a/arch/alpha/mm/init.c +++ b/arch/alpha/mm/init.c @@ -309,7 +309,7 @@ void __init mem_init(void) { max_mapnr = num_physpages = max_low_pfn; - totalram_pages += free_all_bootmem(); + free_all_bootmem(); high_memory = (void *) __va(max_low_pfn * PAGE_SIZE); printk_memory_info(); diff --git a/arch/alpha/mm/numa.c b/arch/alpha/mm/numa.c index 33885048fa3..857452c13c4 100644 --- a/arch/alpha/mm/numa.c +++ b/arch/alpha/mm/numa.c @@ -334,7 +334,7 @@ void __init mem_init(void) /* * This will free up the bootmem, ie, slot 0 memory */ - totalram_pages += free_all_bootmem_node(NODE_DATA(nid)); + free_all_bootmem_node(NODE_DATA(nid)); pfn = NODE_DATA(nid)->node_start_pfn; for (i = 0; i < node_spanned_pages(nid); i++, pfn++) diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c index f9c70771209..c668a600f65 100644 --- a/arch/arc/mm/init.c +++ b/arch/arc/mm/init.c @@ -111,7 +111,7 @@ void __init mem_init(void) high_memory = (void *)(CONFIG_LINUX_LINK_BASE + arc_mem_sz); - totalram_pages = free_all_bootmem(); + free_all_bootmem(); /* count all reserved pages [kernel code/data/mem_map..] */ reserved_pages = 0; diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 2070651c1bb..06e9ce17d1d 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -596,8 +596,7 @@ void __init mem_init(void) /* this will put all unused low memory onto the freelists */ free_unused_memmap(&meminfo); - - totalram_pages += free_all_bootmem(); + free_all_bootmem(); #ifdef CONFIG_SA1111 /* now that our DMA memory is actually so designated, we can free it */ diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index a398eb9018b..93de98afedd 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -284,7 +284,7 @@ void __init mem_init(void) free_unused_memmap(); #endif - totalram_pages += free_all_bootmem(); + free_all_bootmem(); reserved_pages = free_pages = 0; diff --git a/arch/avr32/mm/init.c b/arch/avr32/mm/init.c index b079e04f695..af6890fd731 100644 --- a/arch/avr32/mm/init.c +++ b/arch/avr32/mm/init.c @@ -117,8 +117,6 @@ void __init mem_init(void) if (pgdat->node_spanned_pages != 0) node_pages = free_all_bootmem_node(pgdat); - totalram_pages += node_pages; - for (i = 0; i < node_pages; i++) if (PageReserved(pgdat->node_mem_map + i)) reservedpages++; diff --git a/arch/blackfin/mm/init.c b/arch/blackfin/mm/init.c index fa241f5a7dc..c73d80ef564 100644 --- a/arch/blackfin/mm/init.c +++ b/arch/blackfin/mm/init.c @@ -104,7 +104,7 @@ void __init mem_init(void) printk(KERN_DEBUG "Kernel managed physical pages: %lu\n", num_physpages); /* This will put all low memory onto the freelists. */ - totalram_pages = free_all_bootmem(); + free_all_bootmem(); reservedpages = 0; for (tmp = ARCH_PFN_OFFSET; tmp < max_mapnr; tmp++) diff --git a/arch/c6x/mm/init.c b/arch/c6x/mm/init.c index 3987a20fdee..c9ae8ce731d 100644 --- a/arch/c6x/mm/init.c +++ b/arch/c6x/mm/init.c @@ -65,7 +65,7 @@ void __init mem_init(void) high_memory = (void *)(memory_end & PAGE_MASK); /* this will put all memory onto the freelists */ - totalram_pages = free_all_bootmem(); + free_all_bootmem(); codek = (_etext - _stext) >> 10; datak = (_end - _sdata) >> 10; diff --git a/arch/cris/mm/init.c b/arch/cris/mm/init.c index 8fec26392ae..52b8b56ae30 100644 --- a/arch/cris/mm/init.c +++ b/arch/cris/mm/init.c @@ -33,7 +33,7 @@ mem_init(void) max_mapnr = num_physpages = max_low_pfn - min_low_pfn; /* this will put all memory onto the freelists */ - totalram_pages = free_all_bootmem(); + free_all_bootmem(); reservedpages = 0; for (tmp = 0; tmp < max_mapnr; tmp++) { diff --git a/arch/frv/mm/init.c b/arch/frv/mm/init.c index 8ba9d22d0d9..3dcc88803a4 100644 --- a/arch/frv/mm/init.c +++ b/arch/frv/mm/init.c @@ -123,7 +123,7 @@ void __init mem_init(void) int codek = 0, datak = 0; /* this will put all low memory onto the freelists */ - totalram_pages = free_all_bootmem(); + free_all_bootmem(); #ifdef CONFIG_MMU for (loop = 0 ; loop < npages ; loop++) diff --git a/arch/h8300/mm/init.c b/arch/h8300/mm/init.c index c831f1dba13..a506dd4724e 100644 --- a/arch/h8300/mm/init.c +++ b/arch/h8300/mm/init.c @@ -140,7 +140,7 @@ void __init mem_init(void) max_mapnr = num_physpages = MAP_NR(high_memory); /* this will put all low memory onto the freelists */ - totalram_pages = free_all_bootmem(); + free_all_bootmem(); codek = (_etext - _stext) >> 10; datak = (__bss_stop - _sdata) >> 10; diff --git a/arch/hexagon/mm/init.c b/arch/hexagon/mm/init.c index 2561d259a29..0ab5b4350e9 100644 --- a/arch/hexagon/mm/init.c +++ b/arch/hexagon/mm/init.c @@ -70,7 +70,7 @@ unsigned long long kmap_generation; void __init mem_init(void) { /* No idea where this is actually declared. Seems to evade LXR. */ - totalram_pages += free_all_bootmem(); + free_all_bootmem(); num_physpages = bootmem_lastpg-ARCH_PFN_OFFSET; printk(KERN_INFO "totalram_pages = %ld\n", totalram_pages); diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index f8a4f38b0ad..d141f7ea0be 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -622,7 +622,7 @@ mem_init (void) for_each_online_pgdat(pgdat) if (pgdat->bdata->node_bootmem_map) - totalram_pages += free_all_bootmem_node(pgdat); + free_all_bootmem_node(pgdat); reserved_pages = 0; efi_memmap_walk(count_reserved_pages, &reserved_pages); diff --git a/arch/m32r/mm/init.c b/arch/m32r/mm/init.c index cca87d91843..a501838233a 100644 --- a/arch/m32r/mm/init.c +++ b/arch/m32r/mm/init.c @@ -158,7 +158,7 @@ void __init mem_init(void) /* this will put all low memory onto the freelists */ for_each_online_node(nid) - totalram_pages += free_all_bootmem_node(NODE_DATA(nid)); + free_all_bootmem_node(NODE_DATA(nid)); reservedpages = reservedpages_count() - hole_pages; codesize = (unsigned long) &_etext - (unsigned long)&_text; diff --git a/arch/m68k/mm/init.c b/arch/m68k/mm/init.c index ab0b54ca5d8..614c60a0445 100644 --- a/arch/m68k/mm/init.c +++ b/arch/m68k/mm/init.c @@ -155,11 +155,11 @@ void __init mem_init(void) int i; /* this will put all memory onto the freelists */ - totalram_pages = num_physpages = 0; + num_physpages = 0; for_each_online_pgdat(pgdat) { num_physpages += pgdat->node_present_pages; - totalram_pages += free_all_bootmem_node(pgdat); + free_all_bootmem_node(pgdat); for (i = 0; i < pgdat->node_spanned_pages; i++) { struct page *page = pgdat->node_mem_map + i; char *addr = page_to_virt(page); diff --git a/arch/metag/mm/init.c b/arch/metag/mm/init.c index d7595f58fad..ce81d7c4398 100644 --- a/arch/metag/mm/init.c +++ b/arch/metag/mm/init.c @@ -393,14 +393,11 @@ void __init mem_init(void) for_each_online_node(nid) { pg_data_t *pgdat = NODE_DATA(nid); - unsigned long node_pages = 0; num_physpages += pgdat->node_present_pages; if (pgdat->node_spanned_pages) - node_pages = free_all_bootmem_node(pgdat); - - totalram_pages += node_pages; + free_all_bootmem_node(pgdat); } pr_info("Memory: %luk/%luk available\n", diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c index d149e0ebb76..b384cbc2c8f 100644 --- a/arch/microblaze/mm/init.c +++ b/arch/microblaze/mm/init.c @@ -252,7 +252,7 @@ void __init mem_init(void) high_memory = (void *)__va(memory_start + lowmem_size - 1); /* this will put all memory onto the freelists */ - totalram_pages += free_all_bootmem(); + free_all_bootmem(); for_each_online_pgdat(pgdat) { unsigned long i; diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index 268f2a94031..e7333f15b1b 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -374,7 +374,7 @@ void __init mem_init(void) #endif high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT); - totalram_pages += free_all_bootmem(); + free_all_bootmem(); setup_zero_pages(); /* Setup zeroed pages. */ reservedpages = ram = 0; diff --git a/arch/mips/sgi-ip27/ip27-memory.c b/arch/mips/sgi-ip27/ip27-memory.c index 1230f56429d..aecac4a0836 100644 --- a/arch/mips/sgi-ip27/ip27-memory.c +++ b/arch/mips/sgi-ip27/ip27-memory.c @@ -489,7 +489,7 @@ void __init mem_init(void) /* * This will free up the bootmem, ie, slot 0 memory. */ - totalram_pages += free_all_bootmem_node(NODE_DATA(node)); + free_all_bootmem_node(NODE_DATA(node)); } setup_zero_pages(); /* This comes from node 0 */ diff --git a/arch/mn10300/mm/init.c b/arch/mn10300/mm/init.c index e19049d1f2b..7590d91627f 100644 --- a/arch/mn10300/mm/init.c +++ b/arch/mn10300/mm/init.c @@ -114,7 +114,7 @@ void __init mem_init(void) memset(empty_zero_page, 0, PAGE_SIZE); /* this will put all low memory onto the freelists */ - totalram_pages += free_all_bootmem(); + free_all_bootmem(); reservedpages = 0; for (tmp = 0; tmp < num_physpages; tmp++) diff --git a/arch/openrisc/mm/init.c b/arch/openrisc/mm/init.c index c371e4a0fca..16c1e135cf3 100644 --- a/arch/openrisc/mm/init.c +++ b/arch/openrisc/mm/init.c @@ -207,7 +207,7 @@ static int __init free_pages_init(void) int reservedpages, pfn; /* this will put all low memory onto the freelists */ - totalram_pages = free_all_bootmem(); + free_all_bootmem(); reservedpages = 0; for (pfn = 0; pfn < max_low_pfn; pfn++) { diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c index ebac7bd76b5..d8aaaf06ede 100644 --- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -593,13 +593,13 @@ void __init mem_init(void) #ifndef CONFIG_DISCONTIGMEM max_mapnr = page_to_pfn(virt_to_page(high_memory - 1)) + 1; - totalram_pages += free_all_bootmem(); + free_all_bootmem(); #else { int i; for (i = 0; i < npmem_ranges; i++) - totalram_pages += free_all_bootmem_node(NODE_DATA(i)); + free_all_bootmem_node(NODE_DATA(i)); } #endif diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 7f47a05f55a..3bcfc0d0d32 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -318,13 +318,12 @@ void __init mem_init(void) for_each_online_node(nid) { if (NODE_DATA(nid)->node_spanned_pages != 0) { printk("freeing bootmem node %d\n", nid); - totalram_pages += - free_all_bootmem_node(NODE_DATA(nid)); + free_all_bootmem_node(NODE_DATA(nid)); } } #else max_mapnr = max_pfn; - totalram_pages += free_all_bootmem(); + free_all_bootmem(); #endif for_each_online_pgdat(pgdat) { for (i = 0; i < pgdat->node_spanned_pages; i++) { diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index bf01d18422e..a2aafe1b230 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -144,7 +144,7 @@ void __init mem_init(void) cmma_init(); /* this will put all low memory onto the freelists */ - totalram_pages += free_all_bootmem(); + free_all_bootmem(); setup_zero_pages(); /* Setup zeroed pages. */ reservedpages = 0; diff --git a/arch/score/mm/init.c b/arch/score/mm/init.c index f5dd61eb454..a8b917742de 100644 --- a/arch/score/mm/init.c +++ b/arch/score/mm/init.c @@ -79,7 +79,7 @@ void __init mem_init(void) unsigned long tmp, ram = 0; high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT); - totalram_pages += free_all_bootmem(); + free_all_bootmem(); setup_zero_page(); /* Setup zeroed pages. */ reservedpages = 0; diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index d3af56b7a09..fc0c8e1c32a 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -422,7 +422,7 @@ void __init mem_init(void) num_physpages += pgdat->node_present_pages; if (pgdat->node_spanned_pages) - totalram_pages += free_all_bootmem_node(pgdat); + free_all_bootmem_node(pgdat); node_high_memory = (void *)__va((pgdat->node_start_pfn + diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c index d5f9c023826..a438abb5495 100644 --- a/arch/sparc/mm/init_32.c +++ b/arch/sparc/mm/init_32.c @@ -323,8 +323,7 @@ void __init mem_init(void) max_mapnr = last_valid_pfn - pfn_base; high_memory = __va(max_low_pfn << PAGE_SHIFT); - - totalram_pages = free_all_bootmem(); + free_all_bootmem(); for (i = 0; sp_banks[i].num_bytes != 0; i++) { unsigned long start_pfn = sp_banks[i].base_addr >> PAGE_SHIFT; diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 8269deb84ed..752d73837f9 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -2061,7 +2061,7 @@ void __init mem_init(void) high_memory = __va(last_valid_pfn << PAGE_SHIFT); register_page_bootmem_info(); - totalram_pages = free_all_bootmem(); + free_all_bootmem(); /* We subtract one to account for the mem_map_zero page * allocated below. diff --git a/arch/tile/mm/init.c b/arch/tile/mm/init.c index ccfeb3f2e76..45ce26d4e47 100644 --- a/arch/tile/mm/init.c +++ b/arch/tile/mm/init.c @@ -846,7 +846,7 @@ void __init mem_init(void) set_max_mapnr_init(); /* this will put all bootmem onto the freelists */ - totalram_pages += free_all_bootmem(); + free_all_bootmem(); #ifndef CONFIG_64BIT /* count all remaining LOWMEM and give all HIGHMEM to page allocator */ diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c index 8ff0b7ae8ec..b0c763094ff 100644 --- a/arch/um/kernel/mem.c +++ b/arch/um/kernel/mem.c @@ -65,7 +65,7 @@ void __init mem_init(void) uml_reserved = brk_end; /* this will put all low memory onto the freelists */ - totalram_pages = free_all_bootmem(); + free_all_bootmem(); max_low_pfn = totalram_pages; #ifdef CONFIG_HIGHMEM setup_highmem(end_iomem, highmem); diff --git a/arch/unicore32/mm/init.c b/arch/unicore32/mm/init.c index df9b8abcb6a..7d1356c466b 100644 --- a/arch/unicore32/mm/init.c +++ b/arch/unicore32/mm/init.c @@ -392,7 +392,7 @@ void __init mem_init(void) free_unused_memmap(&meminfo); /* this will put all unused low memory onto the freelists */ - totalram_pages += free_all_bootmem(); + free_all_bootmem(); reserved_pages = free_pages = 0; diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 3ac7e319918..9fa46baada2 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -759,7 +759,7 @@ void __init mem_init(void) set_highmem_pages_init(); /* this will put all low memory onto the freelists */ - totalram_pages += free_all_bootmem(); + free_all_bootmem(); reservedpages = 0; for (tmp = 0; tmp < max_low_pfn; tmp++) diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index ec312a92b13..9577638f3ea 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1054,7 +1054,7 @@ void __init mem_init(void) register_page_bootmem_info(); /* this will put all memory onto the freelists */ - totalram_pages = free_all_bootmem(); + free_all_bootmem(); absent_pages = absent_pages_in_range(0, max_pfn); reservedpages = max_pfn - totalram_pages - absent_pages; diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c index 026d29bee30..663c1619562 100644 --- a/arch/xtensa/mm/init.c +++ b/arch/xtensa/mm/init.c @@ -184,7 +184,7 @@ void __init mem_init(void) #error HIGHGMEM not implemented in init.c #endif - totalram_pages += free_all_bootmem(); + free_all_bootmem(); reservedpages = ram = 0; for (tmp = 0; tmp < max_mapnr; tmp++) { diff --git a/mm/bootmem.c b/mm/bootmem.c index eb792323187..58609bbf584 100644 --- a/mm/bootmem.c +++ b/mm/bootmem.c @@ -271,9 +271,14 @@ void __init reset_all_zones_managed_pages(void) */ unsigned long __init free_all_bootmem_node(pg_data_t *pgdat) { + unsigned long pages; + register_page_bootmem_info_node(pgdat); reset_node_managed_pages(pgdat); - return free_all_bootmem_core(pgdat->bdata); + pages = free_all_bootmem_core(pgdat->bdata); + totalram_pages += pages; + + return pages; } /** @@ -291,6 +296,8 @@ unsigned long __init free_all_bootmem(void) list_for_each_entry(bdata, &bdata_list, list) total_pages += free_all_bootmem_core(bdata); + totalram_pages += total_pages; + return total_pages; } diff --git a/mm/nobootmem.c b/mm/nobootmem.c index 0ae8d91365a..61107cf55bb 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -165,6 +165,8 @@ void __init reset_all_zones_managed_pages(void) */ unsigned long __init free_all_bootmem(void) { + unsigned long pages; + reset_all_zones_managed_pages(); /* @@ -172,7 +174,10 @@ unsigned long __init free_all_bootmem(void) * because in some case like Node0 doesn't have RAM installed * low ram will be on Node1 */ - return free_low_memory_core_early(); + pages = free_low_memory_core_early(); + totalram_pages += pages; + + return pages; } /** -- cgit v1.2.3-70-g09d2 From a18d0e2d7097937e9f51b83eda4bc750d93eb34d Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Wed, 3 Jul 2013 15:04:10 -0700 Subject: mm/s390: prepare for removing num_physpages and simplify mem_init() Prepare for removing num_physpages and simplify mem_init(). Signed-off-by: Jiang Liu Cc: Martin Schwidefsky Cc: Heiko Carstens Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/s390/mm/init.c | 17 ++--------------- 1 file changed, 2 insertions(+), 15 deletions(-) (limited to 'arch/s390') diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index a2aafe1b230..ce36ea80e4f 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -135,9 +135,7 @@ void __init paging_init(void) void __init mem_init(void) { - unsigned long codesize, reservedpages, datasize, initsize; - - max_mapnr = num_physpages = max_low_pfn; + max_mapnr = max_low_pfn; high_memory = (void *) __va(max_low_pfn * PAGE_SIZE); /* Setup guest page hinting */ @@ -147,18 +145,7 @@ void __init mem_init(void) free_all_bootmem(); setup_zero_pages(); /* Setup zeroed pages. */ - reservedpages = 0; - - codesize = (unsigned long) &_etext - (unsigned long) &_text; - datasize = (unsigned long) &_edata - (unsigned long) &_etext; - initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin; - printk("Memory: %luk/%luk available (%ldk kernel code, %ldk reserved, %ldk data, %ldk init)\n", - nr_free_pages() << (PAGE_SHIFT-10), - max_mapnr << (PAGE_SHIFT-10), - codesize >> 10, - reservedpages << (PAGE_SHIFT-10), - datasize >>10, - initsize >> 10); + mem_init_print_info(NULL); printk("Write protected kernel read-only data: %#lx - %#lx\n", (unsigned long)&_stext, PFN_ALIGN((unsigned long)&_eshared) - 1); -- cgit v1.2.3-70-g09d2 From 8bdc237ac113dd42a1c977c8cd3a65a82f774d5e Mon Sep 17 00:00:00 2001 From: Zhang Yanfei Date: Wed, 3 Jul 2013 15:08:45 -0700 Subject: s390: remove setting for saved_max_pfn The only user of saved_max_pfn in s390 is read_oldmem interface but we have removed that interface, so saved_max_pfn is now unneeded in s390, and we needn't set it anymore. Signed-off-by: Zhang Yanfei Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: Michael Holzheu Cc: "Eric W. Biederman" Cc: "H. Peter Anvin" Cc: Benjamin Herrenschmidt Cc: Dave Hansen Cc: Fenghua Yu Cc: Matt Fleming Cc: Paul Mackerras Cc: Ralf Baechle Cc: Tony Luck Cc: Vivek Goyal Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/s390/kernel/setup.c | 4 ---- 1 file changed, 4 deletions(-) (limited to 'arch/s390') diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 0a49095104c..497451ec5e2 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -719,10 +719,6 @@ static void reserve_oldmem(void) } create_mem_hole(memory_chunk, OLDMEM_BASE, OLDMEM_SIZE); create_mem_hole(memory_chunk, OLDMEM_SIZE, real_size - OLDMEM_SIZE); - if (OLDMEM_BASE + OLDMEM_SIZE == real_size) - saved_max_pfn = PFN_DOWN(OLDMEM_BASE) - 1; - else - saved_max_pfn = PFN_DOWN(real_size) - 1; #endif } -- cgit v1.2.3-70-g09d2 From 64b0dc517ea1b35d02565a779e6cb77ae9045685 Mon Sep 17 00:00:00 2001 From: Eliezer Tamir Date: Wed, 10 Jul 2013 17:13:36 +0300 Subject: net: rename busy poll socket op and globals Rename LL_SO to BUSY_POLL_SO Rename sysctl_net_ll_{read,poll} to sysctl_busy_{read,poll} Fix up users of these variables. Fix documentation for sysctl. a patch for the socket.7 man page will follow separately, because of limitations of my mail setup. Signed-off-by: Eliezer Tamir Signed-off-by: David S. Miller --- Documentation/sysctl/net.txt | 17 +++++++++-------- arch/alpha/include/uapi/asm/socket.h | 2 +- arch/avr32/include/uapi/asm/socket.h | 2 +- arch/cris/include/uapi/asm/socket.h | 2 +- arch/frv/include/uapi/asm/socket.h | 2 +- arch/h8300/include/uapi/asm/socket.h | 2 +- arch/ia64/include/uapi/asm/socket.h | 2 +- arch/m32r/include/uapi/asm/socket.h | 2 +- arch/mips/include/uapi/asm/socket.h | 2 +- arch/mn10300/include/uapi/asm/socket.h | 2 +- arch/parisc/include/uapi/asm/socket.h | 2 +- arch/powerpc/include/uapi/asm/socket.h | 2 +- arch/s390/include/uapi/asm/socket.h | 2 +- arch/sparc/include/uapi/asm/socket.h | 2 +- arch/xtensa/include/uapi/asm/socket.h | 2 +- include/net/busy_poll.h | 8 ++++---- include/uapi/asm-generic/socket.h | 2 +- net/core/sock.c | 6 +++--- net/core/sysctl_net_core.c | 8 ++++---- net/socket.c | 4 ++-- 20 files changed, 37 insertions(+), 36 deletions(-) (limited to 'arch/s390') diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt index d69e14c9002..1c15043aaee 100644 --- a/Documentation/sysctl/net.txt +++ b/Documentation/sysctl/net.txt @@ -50,26 +50,27 @@ The maximum number of packets that kernel can handle on a NAPI interrupt, it's a Per-CPU variable. Default: 64 -low_latency_read +busy_read ---------------- Low latency busy poll timeout for socket reads. (needs CONFIG_NET_LL_RX_POLL) Approximate time in us to busy loop waiting for packets on the device queue. -This sets the default value of the SO_LL socket option. -Can be set or overridden per socket by setting socket option SO_LL, which is -the preferred method of enabling. -If you need to enable the feature globally via sysctl, a value of 50 is recommended. +This sets the default value of the SO_BUSY_POLL socket option. +Can be set or overridden per socket by setting socket option SO_BUSY_POLL, +which is the preferred method of enabling. If you need to enable the feature +globally via sysctl, a value of 50 is recommended. Will increase power usage. Default: 0 (off) -low_latency_poll +busy_poll ---------------- Low latency busy poll timeout for poll and select. (needs CONFIG_NET_LL_RX_POLL) Approximate time in us to busy loop waiting for events. Recommended value depends on the number of sockets you poll on. For several sockets 50, for several hundreds 100. For more than that you probably want to use epoll. -Note that only sockets with SO_LL set will be busy polled, so you want to either -selectively set SO_LL on those sockets or set sysctl.net.low_latency_read globally. +Note that only sockets with SO_BUSY_POLL set will be busy polled, +so you want to either selectively set SO_BUSY_POLL on those sockets or set +sysctl.net.busy_read globally. Will increase power usage. Default: 0 (off) diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index 4885825e498..467de010ea7 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -81,6 +81,6 @@ #define SO_SELECT_ERR_QUEUE 45 -#define SO_LL 46 +#define SO_BUSY_POLL 46 #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/avr32/include/uapi/asm/socket.h b/arch/avr32/include/uapi/asm/socket.h index 79b61798ebf..11c4259c62f 100644 --- a/arch/avr32/include/uapi/asm/socket.h +++ b/arch/avr32/include/uapi/asm/socket.h @@ -74,6 +74,6 @@ #define SO_SELECT_ERR_QUEUE 45 -#define SO_LL 46 +#define SO_BUSY_POLL 46 #endif /* __ASM_AVR32_SOCKET_H */ diff --git a/arch/cris/include/uapi/asm/socket.h b/arch/cris/include/uapi/asm/socket.h index 47b1ec55092..eb723e51554 100644 --- a/arch/cris/include/uapi/asm/socket.h +++ b/arch/cris/include/uapi/asm/socket.h @@ -76,7 +76,7 @@ #define SO_SELECT_ERR_QUEUE 45 -#define SO_LL 46 +#define SO_BUSY_POLL 46 #endif /* _ASM_SOCKET_H */ diff --git a/arch/frv/include/uapi/asm/socket.h b/arch/frv/include/uapi/asm/socket.h index dbc08520f22..f0cb1c34116 100644 --- a/arch/frv/include/uapi/asm/socket.h +++ b/arch/frv/include/uapi/asm/socket.h @@ -74,7 +74,7 @@ #define SO_SELECT_ERR_QUEUE 45 -#define SO_LL 46 +#define SO_BUSY_POLL 46 #endif /* _ASM_SOCKET_H */ diff --git a/arch/h8300/include/uapi/asm/socket.h b/arch/h8300/include/uapi/asm/socket.h index a38d38a6520..9490758c5e2 100644 --- a/arch/h8300/include/uapi/asm/socket.h +++ b/arch/h8300/include/uapi/asm/socket.h @@ -74,6 +74,6 @@ #define SO_SELECT_ERR_QUEUE 45 -#define SO_LL 46 +#define SO_BUSY_POLL 46 #endif /* _ASM_SOCKET_H */ diff --git a/arch/ia64/include/uapi/asm/socket.h b/arch/ia64/include/uapi/asm/socket.h index d3358b76068..556d0701a15 100644 --- a/arch/ia64/include/uapi/asm/socket.h +++ b/arch/ia64/include/uapi/asm/socket.h @@ -83,6 +83,6 @@ #define SO_SELECT_ERR_QUEUE 45 -#define SO_LL 46 +#define SO_BUSY_POLL 46 #endif /* _ASM_IA64_SOCKET_H */ diff --git a/arch/m32r/include/uapi/asm/socket.h b/arch/m32r/include/uapi/asm/socket.h index 44aaf4639a4..24be7c8da86 100644 --- a/arch/m32r/include/uapi/asm/socket.h +++ b/arch/m32r/include/uapi/asm/socket.h @@ -74,6 +74,6 @@ #define SO_SELECT_ERR_QUEUE 45 -#define SO_LL 46 +#define SO_BUSY_POLL 46 #endif /* _ASM_M32R_SOCKET_H */ diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index 6a07992ba6c..61c01f054d1 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -92,6 +92,6 @@ #define SO_SELECT_ERR_QUEUE 45 -#define SO_LL 46 +#define SO_BUSY_POLL 46 #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/mn10300/include/uapi/asm/socket.h b/arch/mn10300/include/uapi/asm/socket.h index db80fd3e398..e2a2b203eb0 100644 --- a/arch/mn10300/include/uapi/asm/socket.h +++ b/arch/mn10300/include/uapi/asm/socket.h @@ -74,6 +74,6 @@ #define SO_SELECT_ERR_QUEUE 45 -#define SO_LL 46 +#define SO_BUSY_POLL 46 #endif /* _ASM_SOCKET_H */ diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index f866fff9a00..71700e636a8 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -73,7 +73,7 @@ #define SO_SELECT_ERR_QUEUE 0x4026 -#define SO_LL 0x4027 +#define SO_BUSY_POLL 0x4027 /* O_NONBLOCK clashes with the bits used for socket types. Therefore we * have to define SOCK_NONBLOCK to a different value here. diff --git a/arch/powerpc/include/uapi/asm/socket.h b/arch/powerpc/include/uapi/asm/socket.h index 405fb09bda9..a6d74467c9e 100644 --- a/arch/powerpc/include/uapi/asm/socket.h +++ b/arch/powerpc/include/uapi/asm/socket.h @@ -81,6 +81,6 @@ #define SO_SELECT_ERR_QUEUE 45 -#define SO_LL 46 +#define SO_BUSY_POLL 46 #endif /* _ASM_POWERPC_SOCKET_H */ diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h index 0c5105fbaaf..92494494692 100644 --- a/arch/s390/include/uapi/asm/socket.h +++ b/arch/s390/include/uapi/asm/socket.h @@ -80,6 +80,6 @@ #define SO_SELECT_ERR_QUEUE 45 -#define SO_LL 46 +#define SO_BUSY_POLL 46 #endif /* _ASM_SOCKET_H */ diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index b46c3fa0b26..4e1d66c3ce7 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -70,7 +70,7 @@ #define SO_SELECT_ERR_QUEUE 0x0029 -#define SO_LL 0x0030 +#define SO_BUSY_POLL 0x0030 /* Security levels - as per NRL IPv6 - don't actually do anything */ #define SO_SECURITY_AUTHENTICATION 0x5001 diff --git a/arch/xtensa/include/uapi/asm/socket.h b/arch/xtensa/include/uapi/asm/socket.h index b21ace4fc9b..c114483010c 100644 --- a/arch/xtensa/include/uapi/asm/socket.h +++ b/arch/xtensa/include/uapi/asm/socket.h @@ -85,6 +85,6 @@ #define SO_SELECT_ERR_QUEUE 45 -#define SO_LL 46 +#define SO_BUSY_POLL 46 #endif /* _XTENSA_SOCKET_H */ diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index 4ff71908fd4..a14339c2985 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -30,8 +30,8 @@ #ifdef CONFIG_NET_LL_RX_POLL struct napi_struct; -extern unsigned int sysctl_net_ll_read __read_mostly; -extern unsigned int sysctl_net_ll_poll __read_mostly; +extern unsigned int sysctl_net_busy_read __read_mostly; +extern unsigned int sysctl_net_busy_poll __read_mostly; /* return values from ndo_ll_poll */ #define LL_FLUSH_FAILED -1 @@ -39,7 +39,7 @@ extern unsigned int sysctl_net_ll_poll __read_mostly; static inline bool net_busy_loop_on(void) { - return sysctl_net_ll_poll; + return sysctl_net_busy_poll; } /* a wrapper to make debug_smp_processor_id() happy @@ -72,7 +72,7 @@ static inline unsigned long sk_busy_loop_end_time(struct sock *sk) /* in poll/select we use the global sysctl_net_ll_poll value */ static inline unsigned long busy_loop_end_time(void) { - return busy_loop_us_clock() + ACCESS_ONCE(sysctl_net_ll_poll); + return busy_loop_us_clock() + ACCESS_ONCE(sysctl_net_busy_poll); } static inline bool sk_can_busy_loop(struct sock *sk) diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index ca3a20d772a..f04b69b6abf 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -76,6 +76,6 @@ #define SO_SELECT_ERR_QUEUE 45 -#define SO_LL 46 +#define SO_BUSY_POLL 46 #endif /* __ASM_GENERIC_SOCKET_H */ diff --git a/net/core/sock.c b/net/core/sock.c index 9bfe83f4d67..548d716c5f6 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -901,7 +901,7 @@ set_rcvbuf: break; #ifdef CONFIG_NET_LL_RX_POLL - case SO_LL: + case SO_BUSY_POLL: /* allow unprivileged users to decrease the value */ if ((val > sk->sk_ll_usec) && !capable(CAP_NET_ADMIN)) ret = -EPERM; @@ -1171,7 +1171,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; #ifdef CONFIG_NET_LL_RX_POLL - case SO_LL: + case SO_BUSY_POLL: v.val = sk->sk_ll_usec; break; #endif @@ -2294,7 +2294,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) #ifdef CONFIG_NET_LL_RX_POLL sk->sk_napi_id = 0; - sk->sk_ll_usec = sysctl_net_ll_read; + sk->sk_ll_usec = sysctl_net_busy_read; #endif /* diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 1a298cb3dae..66096861663 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -300,15 +300,15 @@ static struct ctl_table net_core_table[] = { #endif /* CONFIG_NET_FLOW_LIMIT */ #ifdef CONFIG_NET_LL_RX_POLL { - .procname = "low_latency_poll", - .data = &sysctl_net_ll_poll, + .procname = "busy_poll", + .data = &sysctl_net_busy_poll, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec }, { - .procname = "low_latency_read", - .data = &sysctl_net_ll_read, + .procname = "busy_read", + .data = &sysctl_net_busy_read, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec diff --git a/net/socket.c b/net/socket.c index 6a3e9a3f50a..829b460acb8 100644 --- a/net/socket.c +++ b/net/socket.c @@ -107,8 +107,8 @@ #include #ifdef CONFIG_NET_LL_RX_POLL -unsigned int sysctl_net_ll_read __read_mostly; -unsigned int sysctl_net_ll_poll __read_mostly; +unsigned int sysctl_net_busy_read __read_mostly; +unsigned int sysctl_net_busy_poll __read_mostly; #endif static int sock_no_open(struct inode *irrelevant, struct file *dontcare); -- cgit v1.2.3-70-g09d2 From 98d1e64f95b177d0f14efbdf695a1b28e1428035 Mon Sep 17 00:00:00 2001 From: Michel Lespinasse Date: Wed, 10 Jul 2013 16:05:12 -0700 Subject: mm: remove free_area_cache Since all architectures have been converted to use vm_unmapped_area(), there is no remaining use for the free_area_cache. Signed-off-by: Michel Lespinasse Acked-by: Rik van Riel Cc: "James E.J. Bottomley" Cc: "Luck, Tony" Cc: Benjamin Herrenschmidt Cc: David Howells Cc: Helge Deller Cc: Ivan Kokshaysky Cc: Matt Turner Cc: Paul Mackerras Cc: Richard Henderson Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/mm/mmap.c | 2 -- arch/arm64/mm/mmap.c | 2 -- arch/mips/mm/mmap.c | 2 -- arch/powerpc/mm/mmap.c | 2 -- arch/s390/mm/mmap.c | 4 ---- arch/sparc/kernel/sys_sparc_64.c | 2 -- arch/tile/mm/mmap.c | 2 -- arch/x86/ia32/ia32_aout.c | 2 -- arch/x86/mm/mmap.c | 2 -- fs/binfmt_aout.c | 2 -- fs/binfmt_elf.c | 2 -- include/linux/mm_types.h | 3 --- include/linux/sched.h | 2 -- kernel/fork.c | 4 ---- mm/mmap.c | 28 ---------------------------- mm/nommu.c | 4 ---- mm/util.c | 1 - 17 files changed, 66 deletions(-) (limited to 'arch/s390') diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c index 10062ceadd1..0c6356255fe 100644 --- a/arch/arm/mm/mmap.c +++ b/arch/arm/mm/mmap.c @@ -181,11 +181,9 @@ void arch_pick_mmap_layout(struct mm_struct *mm) if (mmap_is_legacy()) { mm->mmap_base = TASK_UNMAPPED_BASE + random_factor; mm->get_unmapped_area = arch_get_unmapped_area; - mm->unmap_area = arch_unmap_area; } else { mm->mmap_base = mmap_base(random_factor); mm->get_unmapped_area = arch_get_unmapped_area_topdown; - mm->unmap_area = arch_unmap_area_topdown; } } diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c index 7c7be785563..8ed6cb1a900 100644 --- a/arch/arm64/mm/mmap.c +++ b/arch/arm64/mm/mmap.c @@ -90,11 +90,9 @@ void arch_pick_mmap_layout(struct mm_struct *mm) if (mmap_is_legacy()) { mm->mmap_base = TASK_UNMAPPED_BASE; mm->get_unmapped_area = arch_get_unmapped_area; - mm->unmap_area = arch_unmap_area; } else { mm->mmap_base = mmap_base(); mm->get_unmapped_area = arch_get_unmapped_area_topdown; - mm->unmap_area = arch_unmap_area_topdown; } } EXPORT_SYMBOL_GPL(arch_pick_mmap_layout); diff --git a/arch/mips/mm/mmap.c b/arch/mips/mm/mmap.c index 7e5fe2790d8..f1baadd56e8 100644 --- a/arch/mips/mm/mmap.c +++ b/arch/mips/mm/mmap.c @@ -158,11 +158,9 @@ void arch_pick_mmap_layout(struct mm_struct *mm) if (mmap_is_legacy()) { mm->mmap_base = TASK_UNMAPPED_BASE + random_factor; mm->get_unmapped_area = arch_get_unmapped_area; - mm->unmap_area = arch_unmap_area; } else { mm->mmap_base = mmap_base(random_factor); mm->get_unmapped_area = arch_get_unmapped_area_topdown; - mm->unmap_area = arch_unmap_area_topdown; } } diff --git a/arch/powerpc/mm/mmap.c b/arch/powerpc/mm/mmap.c index 67a42ed0d2f..cb8bdbe4972 100644 --- a/arch/powerpc/mm/mmap.c +++ b/arch/powerpc/mm/mmap.c @@ -92,10 +92,8 @@ void arch_pick_mmap_layout(struct mm_struct *mm) if (mmap_is_legacy()) { mm->mmap_base = TASK_UNMAPPED_BASE; mm->get_unmapped_area = arch_get_unmapped_area; - mm->unmap_area = arch_unmap_area; } else { mm->mmap_base = mmap_base(); mm->get_unmapped_area = arch_get_unmapped_area_topdown; - mm->unmap_area = arch_unmap_area_topdown; } } diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index 06bafec0027..40023290ee5 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -91,11 +91,9 @@ void arch_pick_mmap_layout(struct mm_struct *mm) if (mmap_is_legacy()) { mm->mmap_base = TASK_UNMAPPED_BASE; mm->get_unmapped_area = arch_get_unmapped_area; - mm->unmap_area = arch_unmap_area; } else { mm->mmap_base = mmap_base(); mm->get_unmapped_area = arch_get_unmapped_area_topdown; - mm->unmap_area = arch_unmap_area_topdown; } } @@ -176,11 +174,9 @@ void arch_pick_mmap_layout(struct mm_struct *mm) if (mmap_is_legacy()) { mm->mmap_base = TASK_UNMAPPED_BASE; mm->get_unmapped_area = s390_get_unmapped_area; - mm->unmap_area = arch_unmap_area; } else { mm->mmap_base = mmap_base(); mm->get_unmapped_area = s390_get_unmapped_area_topdown; - mm->unmap_area = arch_unmap_area_topdown; } } diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c index 2daaaa6eda2..51561b8b15b 100644 --- a/arch/sparc/kernel/sys_sparc_64.c +++ b/arch/sparc/kernel/sys_sparc_64.c @@ -290,7 +290,6 @@ void arch_pick_mmap_layout(struct mm_struct *mm) sysctl_legacy_va_layout) { mm->mmap_base = TASK_UNMAPPED_BASE + random_factor; mm->get_unmapped_area = arch_get_unmapped_area; - mm->unmap_area = arch_unmap_area; } else { /* We know it's 32-bit */ unsigned long task_size = STACK_TOP32; @@ -302,7 +301,6 @@ void arch_pick_mmap_layout(struct mm_struct *mm) mm->mmap_base = PAGE_ALIGN(task_size - gap - random_factor); mm->get_unmapped_area = arch_get_unmapped_area_topdown; - mm->unmap_area = arch_unmap_area_topdown; } } diff --git a/arch/tile/mm/mmap.c b/arch/tile/mm/mmap.c index f96f4cec602..d67d91ebf63 100644 --- a/arch/tile/mm/mmap.c +++ b/arch/tile/mm/mmap.c @@ -66,10 +66,8 @@ void arch_pick_mmap_layout(struct mm_struct *mm) if (!is_32bit || rlimit(RLIMIT_STACK) == RLIM_INFINITY) { mm->mmap_base = TASK_UNMAPPED_BASE; mm->get_unmapped_area = arch_get_unmapped_area; - mm->unmap_area = arch_unmap_area; } else { mm->mmap_base = mmap_base(mm); mm->get_unmapped_area = arch_get_unmapped_area_topdown; - mm->unmap_area = arch_unmap_area_topdown; } } diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c index 52ff81cce00..bae3aba95b1 100644 --- a/arch/x86/ia32/ia32_aout.c +++ b/arch/x86/ia32/ia32_aout.c @@ -308,8 +308,6 @@ static int load_aout_binary(struct linux_binprm *bprm) (current->mm->start_data = N_DATADDR(ex)); current->mm->brk = ex.a_bss + (current->mm->start_brk = N_BSSADDR(ex)); - current->mm->free_area_cache = TASK_UNMAPPED_BASE; - current->mm->cached_hole_size = 0; retval = setup_arg_pages(bprm, IA32_STACK_TOP, EXSTACK_DEFAULT); if (retval < 0) { diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 845df6835f9..62c29a5bfe2 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -115,10 +115,8 @@ void arch_pick_mmap_layout(struct mm_struct *mm) if (mmap_is_legacy()) { mm->mmap_base = mmap_legacy_base(); mm->get_unmapped_area = arch_get_unmapped_area; - mm->unmap_area = arch_unmap_area; } else { mm->mmap_base = mmap_base(); mm->get_unmapped_area = arch_get_unmapped_area_topdown; - mm->unmap_area = arch_unmap_area_topdown; } } diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c index bce87694f7b..89dec7f789a 100644 --- a/fs/binfmt_aout.c +++ b/fs/binfmt_aout.c @@ -255,8 +255,6 @@ static int load_aout_binary(struct linux_binprm * bprm) (current->mm->start_data = N_DATADDR(ex)); current->mm->brk = ex.a_bss + (current->mm->start_brk = N_BSSADDR(ex)); - current->mm->free_area_cache = current->mm->mmap_base; - current->mm->cached_hole_size = 0; retval = setup_arg_pages(bprm, STACK_TOP, EXSTACK_DEFAULT); if (retval < 0) { diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index f8a0b0efda4..100edcc5e31 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -738,8 +738,6 @@ static int load_elf_binary(struct linux_binprm *bprm) /* Do this so that we can load the interpreter, if need be. We will change some of these later */ - current->mm->free_area_cache = current->mm->mmap_base; - current->mm->cached_hole_size = 0; retval = setup_arg_pages(bprm, randomize_stack_top(STACK_TOP), executable_stack); if (retval < 0) { diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index ace9a5f01c6..fb425aa16c0 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -330,12 +330,9 @@ struct mm_struct { unsigned long (*get_unmapped_area) (struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); - void (*unmap_area) (struct mm_struct *mm, unsigned long addr); #endif unsigned long mmap_base; /* base of mmap area */ unsigned long task_size; /* size of task vm space */ - unsigned long cached_hole_size; /* if non-zero, the largest hole below free_area_cache */ - unsigned long free_area_cache; /* first hole of size cached_hole_size or larger */ unsigned long highest_vm_end; /* highest vma end address */ pgd_t * pgd; atomic_t mm_users; /* How many users with user space? */ diff --git a/include/linux/sched.h b/include/linux/sched.h index f99d57e0ae4..50d04b92ced 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -322,8 +322,6 @@ extern unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); -extern void arch_unmap_area(struct mm_struct *, unsigned long); -extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long); #else static inline void arch_pick_mmap_layout(struct mm_struct *mm) {} #endif diff --git a/kernel/fork.c b/kernel/fork.c index 6e6a1c11b3e..66635c80a81 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -365,8 +365,6 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) mm->locked_vm = 0; mm->mmap = NULL; mm->mmap_cache = NULL; - mm->free_area_cache = oldmm->mmap_base; - mm->cached_hole_size = ~0UL; mm->map_count = 0; cpumask_clear(mm_cpumask(mm)); mm->mm_rb = RB_ROOT; @@ -540,8 +538,6 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p) mm->nr_ptes = 0; memset(&mm->rss_stat, 0, sizeof(mm->rss_stat)); spin_lock_init(&mm->page_table_lock); - mm->free_area_cache = TASK_UNMAPPED_BASE; - mm->cached_hole_size = ~0UL; mm_init_aio(mm); mm_init_owner(mm, p); diff --git a/mm/mmap.c b/mm/mmap.c index f81311173b4..fbad7b09109 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1878,15 +1878,6 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, } #endif -void arch_unmap_area(struct mm_struct *mm, unsigned long addr) -{ - /* - * Is this a new hole at the lowest possible address? - */ - if (addr >= TASK_UNMAPPED_BASE && addr < mm->free_area_cache) - mm->free_area_cache = addr; -} - /* * This mmap-allocator allocates new areas top-down from below the * stack's low limit (the base): @@ -1943,19 +1934,6 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, } #endif -void arch_unmap_area_topdown(struct mm_struct *mm, unsigned long addr) -{ - /* - * Is this a new hole at the highest possible address? - */ - if (addr > mm->free_area_cache) - mm->free_area_cache = addr; - - /* dont allow allocations above current base */ - if (mm->free_area_cache > mm->mmap_base) - mm->free_area_cache = mm->mmap_base; -} - unsigned long get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) @@ -2376,7 +2354,6 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma, { struct vm_area_struct **insertion_point; struct vm_area_struct *tail_vma = NULL; - unsigned long addr; insertion_point = (prev ? &prev->vm_next : &mm->mmap); vma->vm_prev = NULL; @@ -2393,11 +2370,6 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma, } else mm->highest_vm_end = prev ? prev->vm_end : 0; tail_vma->vm_next = NULL; - if (mm->unmap_area == arch_unmap_area) - addr = prev ? prev->vm_end : mm->mmap_base; - else - addr = vma ? vma->vm_start : mm->mmap_base; - mm->unmap_area(mm, addr); mm->mmap_cache = NULL; /* Kill the cache. */ } diff --git a/mm/nommu.c b/mm/nommu.c index e44e6e0a125..ecd1f158548 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1871,10 +1871,6 @@ unsigned long arch_get_unmapped_area(struct file *file, unsigned long addr, return -ENOMEM; } -void arch_unmap_area(struct mm_struct *mm, unsigned long addr) -{ -} - void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows) diff --git a/mm/util.c b/mm/util.c index ab1424dbe2e..7441c41d00f 100644 --- a/mm/util.c +++ b/mm/util.c @@ -295,7 +295,6 @@ void arch_pick_mmap_layout(struct mm_struct *mm) { mm->mmap_base = TASK_UNMAPPED_BASE; mm->get_unmapped_area = arch_get_unmapped_area; - mm->unmap_area = arch_unmap_area; } #endif -- cgit v1.2.3-70-g09d2 From 85dfe87e24326c472454cc92313ba8c3b4efe53b Mon Sep 17 00:00:00 2001 From: Cornelia Huck Date: Wed, 3 Jul 2013 16:30:54 +0200 Subject: KVM: s390: use cookies for ioeventfd Make use of cookies for the virtio ccw notification hypercall to speed up lookup of devices on the io bus. Signed-off-by: Cornelia Huck [Small fix to a comment. - Paolo] Signed-off-by: Paolo Bonzini --- arch/s390/kvm/diag.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) (limited to 'arch/s390') diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c index 3074475c8ae..3a74d8af0d6 100644 --- a/arch/s390/kvm/diag.c +++ b/arch/s390/kvm/diag.c @@ -119,12 +119,21 @@ static int __diag_virtio_hypercall(struct kvm_vcpu *vcpu) * The layout is as follows: * - gpr 2 contains the subchannel id (passed as addr) * - gpr 3 contains the virtqueue index (passed as datamatch) + * - gpr 4 contains the index on the bus (optionally) */ - ret = kvm_io_bus_write(vcpu->kvm, KVM_VIRTIO_CCW_NOTIFY_BUS, - vcpu->run->s.regs.gprs[2], - 8, &vcpu->run->s.regs.gprs[3]); + ret = kvm_io_bus_write_cookie(vcpu->kvm, KVM_VIRTIO_CCW_NOTIFY_BUS, + vcpu->run->s.regs.gprs[2], + 8, &vcpu->run->s.regs.gprs[3], + vcpu->run->s.regs.gprs[4]); srcu_read_unlock(&vcpu->kvm->srcu, idx); - /* kvm_io_bus_write returns -EOPNOTSUPP if it found no match. */ + + /* + * Return cookie in gpr 2, but don't overwrite the register if the + * diagnose will be handled by userspace. + */ + if (ret != -EOPNOTSUPP) + vcpu->run->s.regs.gprs[2] = ret; + /* kvm_io_bus_write_cookie returns -EOPNOTSUPP if it found no match. */ return ret < 0 ? ret : 0; } -- cgit v1.2.3-70-g09d2 From e59dbe09f8e6fb8f6ee19dc79d1a2f14299e4cd2 Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Thu, 4 Jul 2013 13:40:29 +0900 Subject: KVM: Introduce kvm_arch_memslots_updated() This is called right after the memslots is updated, i.e. when the result of update_memslots() gets installed in install_new_memslots(). Since the memslots needs to be updated twice when we delete or move a memslot, kvm_arch_commit_memory_region() does not correspond to this exactly. In the following patch, x86 will use this new API to check if the mmio generation has reached its maximum value, in which case mmio sptes need to be flushed out. Signed-off-by: Takuya Yoshikawa Acked-by: Alexander Graf Reviewed-by: Xiao Guangrong Signed-off-by: Paolo Bonzini --- arch/arm/kvm/arm.c | 4 ++++ arch/ia64/kvm/kvm-ia64.c | 4 ++++ arch/mips/kvm/kvm_mips.c | 4 ++++ arch/powerpc/kvm/powerpc.c | 4 ++++ arch/s390/kvm/kvm-s390.c | 4 ++++ arch/x86/kvm/x86.c | 4 ++++ include/linux/kvm_host.h | 1 + virt/kvm/kvm_main.c | 5 ++++- 8 files changed, 29 insertions(+), 1 deletion(-) (limited to 'arch/s390') diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index 741f66a2edb..9c697db2787 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -219,6 +219,10 @@ long kvm_arch_dev_ioctl(struct file *filp, return -EINVAL; } +void kvm_arch_memslots_updated(struct kvm *kvm) +{ +} + int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, struct kvm_userspace_memory_region *mem, diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index 5b2dc0d10c8..bdfd8789b37 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -1560,6 +1560,10 @@ int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages) return 0; } +void kvm_arch_memslots_updated(struct kvm *kvm) +{ +} + int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, struct kvm_userspace_memory_region *mem, diff --git a/arch/mips/kvm/kvm_mips.c b/arch/mips/kvm/kvm_mips.c index dd203e59e6f..a7b044536de 100644 --- a/arch/mips/kvm/kvm_mips.c +++ b/arch/mips/kvm/kvm_mips.c @@ -208,6 +208,10 @@ int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages) return 0; } +void kvm_arch_memslots_updated(struct kvm *kvm) +{ +} + int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, struct kvm_userspace_memory_region *mem, diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 6316ee336e8..ae63ae4a1a5 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -420,6 +420,10 @@ int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages) return kvmppc_core_create_memslot(slot, npages); } +void kvm_arch_memslots_updated(struct kvm *kvm) +{ +} + int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, struct kvm_userspace_memory_region *mem, diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index ba694d2ba51..a3d797b689a 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -1056,6 +1056,10 @@ int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages) return 0; } +void kvm_arch_memslots_updated(struct kvm *kvm) +{ +} + /* Section: memory related */ int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index d21bce50531..9dd8799e87c 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7019,6 +7019,10 @@ out_free: return -ENOMEM; } +void kvm_arch_memslots_updated(struct kvm *kvm) +{ +} + int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, struct kvm_userspace_memory_region *mem, diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index ec590aece36..c11c7686ae5 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -503,6 +503,7 @@ int __kvm_set_memory_region(struct kvm *kvm, void kvm_arch_free_memslot(struct kvm_memory_slot *free, struct kvm_memory_slot *dont); int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages); +void kvm_arch_memslots_updated(struct kvm *kvm); int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, struct kvm_userspace_memory_region *mem, diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 71960fb03c2..a86735d80ee 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -731,7 +731,10 @@ static struct kvm_memslots *install_new_memslots(struct kvm *kvm, update_memslots(slots, new, kvm->memslots->generation); rcu_assign_pointer(kvm->memslots, slots); synchronize_srcu_expedited(&kvm->srcu); - return old_memslots; + + kvm_arch_memslots_updated(kvm); + + return old_memslots; } /* -- cgit v1.2.3-70-g09d2 From 3eabaee998c787e7e1565574821652548f7fc003 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Fri, 26 Jul 2013 15:04:02 +0200 Subject: KVM: s390: allow sie enablement for multi-threaded programs Improve the code to upgrade the standard 2K page tables to 4K page tables with PGSTEs to allow the operation to happen when the program is already multi-threaded. Signed-off-by: Martin Schwidefsky Signed-off-by: Christian Borntraeger Signed-off-by: Paolo Bonzini --- arch/s390/include/asm/mmu.h | 2 - arch/s390/include/asm/mmu_context.h | 19 +--- arch/s390/include/asm/pgtable.h | 11 +++ arch/s390/mm/pgtable.c | 181 +++++++++++++++++++++++------------- 4 files changed, 129 insertions(+), 84 deletions(-) (limited to 'arch/s390') diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h index 6340178748b..ff132ac64dd 100644 --- a/arch/s390/include/asm/mmu.h +++ b/arch/s390/include/asm/mmu.h @@ -12,8 +12,6 @@ typedef struct { unsigned long asce_bits; unsigned long asce_limit; unsigned long vdso_base; - /* Cloned contexts will be created with extended page tables. */ - unsigned int alloc_pgste:1; /* The mmu context has extended page tables. */ unsigned int has_pgste:1; } mm_context_t; diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index 084e7755ed9..4fb67a0e4dd 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -21,24 +21,7 @@ static inline int init_new_context(struct task_struct *tsk, #ifdef CONFIG_64BIT mm->context.asce_bits |= _ASCE_TYPE_REGION3; #endif - if (current->mm && current->mm->context.alloc_pgste) { - /* - * alloc_pgste indicates, that any NEW context will be created - * with extended page tables. The old context is unchanged. The - * page table allocation and the page table operations will - * look at has_pgste to distinguish normal and extended page - * tables. The only way to create extended page tables is to - * set alloc_pgste and then create a new context (e.g. dup_mm). - * The page table allocation is called after init_new_context - * and if has_pgste is set, it will create extended page - * tables. - */ - mm->context.has_pgste = 1; - mm->context.alloc_pgste = 1; - } else { - mm->context.has_pgste = 0; - mm->context.alloc_pgste = 0; - } + mm->context.has_pgste = 0; mm->context.asce_limit = STACK_TOP_MAX; crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm)); return 0; diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 75fb726de91..7a60bb93e83 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1361,6 +1361,17 @@ static inline pmd_t pmd_mkwrite(pmd_t pmd) } #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLB_PAGE */ +static inline void pmdp_flush_lazy(struct mm_struct *mm, + unsigned long address, pmd_t *pmdp) +{ + int active = (mm == current->active_mm) ? 1 : 0; + + if ((atomic_read(&mm->context.attach_count) & 0xffff) > active) + __pmd_idte(address, pmdp); + else + mm->context.flush_mm = 1; +} + #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_PGTABLE_DEPOSIT diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index a8154a1a2c9..6d332487f36 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -731,6 +731,11 @@ void gmap_do_ipte_notify(struct mm_struct *mm, unsigned long addr, pte_t *pte) spin_unlock(&gmap_notifier_lock); } +static inline int page_table_with_pgste(struct page *page) +{ + return atomic_read(&page->_mapcount) == 0; +} + static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm, unsigned long vmaddr) { @@ -750,7 +755,7 @@ static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm, mp->vmaddr = vmaddr & PMD_MASK; INIT_LIST_HEAD(&mp->mapper); page->index = (unsigned long) mp; - atomic_set(&page->_mapcount, 3); + atomic_set(&page->_mapcount, 0); table = (unsigned long *) page_to_phys(page); clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE/2); clear_table(table + PTRS_PER_PTE, 0, PAGE_SIZE/2); @@ -821,6 +826,11 @@ EXPORT_SYMBOL(set_guest_storage_key); #else /* CONFIG_PGSTE */ +static inline int page_table_with_pgste(struct page *page) +{ + return 0; +} + static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm, unsigned long vmaddr) { @@ -897,12 +907,12 @@ void page_table_free(struct mm_struct *mm, unsigned long *table) struct page *page; unsigned int bit, mask; - if (mm_has_pgste(mm)) { + page = pfn_to_page(__pa(table) >> PAGE_SHIFT); + if (page_table_with_pgste(page)) { gmap_disconnect_pgtable(mm, table); return page_table_free_pgste(table); } /* Free 1K/2K page table fragment of a 4K page */ - page = pfn_to_page(__pa(table) >> PAGE_SHIFT); bit = 1 << ((__pa(table) & ~PAGE_MASK)/(PTRS_PER_PTE*sizeof(pte_t))); spin_lock_bh(&mm->context.list_lock); if ((atomic_read(&page->_mapcount) & FRAG_MASK) != FRAG_MASK) @@ -940,14 +950,14 @@ void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table) unsigned int bit, mask; mm = tlb->mm; - if (mm_has_pgste(mm)) { + page = pfn_to_page(__pa(table) >> PAGE_SHIFT); + if (page_table_with_pgste(page)) { gmap_disconnect_pgtable(mm, table); table = (unsigned long *) (__pa(table) | FRAG_MASK); tlb_remove_table(tlb, table); return; } bit = 1 << ((__pa(table) & ~PAGE_MASK) / (PTRS_PER_PTE*sizeof(pte_t))); - page = pfn_to_page(__pa(table) >> PAGE_SHIFT); spin_lock_bh(&mm->context.list_lock); if ((atomic_read(&page->_mapcount) & FRAG_MASK) != FRAG_MASK) list_del(&page->lru); @@ -1033,36 +1043,120 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table) } #ifdef CONFIG_TRANSPARENT_HUGEPAGE -void thp_split_vma(struct vm_area_struct *vma) +static inline void thp_split_vma(struct vm_area_struct *vma) { unsigned long addr; - struct page *page; - for (addr = vma->vm_start; addr < vma->vm_end; addr += PAGE_SIZE) { - page = follow_page(vma, addr, FOLL_SPLIT); - } + for (addr = vma->vm_start; addr < vma->vm_end; addr += PAGE_SIZE) + follow_page(vma, addr, FOLL_SPLIT); } -void thp_split_mm(struct mm_struct *mm) +static inline void thp_split_mm(struct mm_struct *mm) { - struct vm_area_struct *vma = mm->mmap; + struct vm_area_struct *vma; - while (vma != NULL) { + for (vma = mm->mmap; vma != NULL; vma = vma->vm_next) { thp_split_vma(vma); vma->vm_flags &= ~VM_HUGEPAGE; vma->vm_flags |= VM_NOHUGEPAGE; - vma = vma->vm_next; } + mm->def_flags |= VM_NOHUGEPAGE; +} +#else +static inline void thp_split_mm(struct mm_struct *mm) +{ } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +static unsigned long page_table_realloc_pmd(struct mmu_gather *tlb, + struct mm_struct *mm, pud_t *pud, + unsigned long addr, unsigned long end) +{ + unsigned long next, *table, *new; + struct page *page; + pmd_t *pmd; + + pmd = pmd_offset(pud, addr); + do { + next = pmd_addr_end(addr, end); +again: + if (pmd_none_or_clear_bad(pmd)) + continue; + table = (unsigned long *) pmd_deref(*pmd); + page = pfn_to_page(__pa(table) >> PAGE_SHIFT); + if (page_table_with_pgste(page)) + continue; + /* Allocate new page table with pgstes */ + new = page_table_alloc_pgste(mm, addr); + if (!new) { + mm->context.has_pgste = 0; + continue; + } + spin_lock(&mm->page_table_lock); + if (likely((unsigned long *) pmd_deref(*pmd) == table)) { + /* Nuke pmd entry pointing to the "short" page table */ + pmdp_flush_lazy(mm, addr, pmd); + pmd_clear(pmd); + /* Copy ptes from old table to new table */ + memcpy(new, table, PAGE_SIZE/2); + clear_table(table, _PAGE_INVALID, PAGE_SIZE/2); + /* Establish new table */ + pmd_populate(mm, pmd, (pte_t *) new); + /* Free old table with rcu, there might be a walker! */ + page_table_free_rcu(tlb, table); + new = NULL; + } + spin_unlock(&mm->page_table_lock); + if (new) { + page_table_free_pgste(new); + goto again; + } + } while (pmd++, addr = next, addr != end); + + return addr; +} + +static unsigned long page_table_realloc_pud(struct mmu_gather *tlb, + struct mm_struct *mm, pgd_t *pgd, + unsigned long addr, unsigned long end) +{ + unsigned long next; + pud_t *pud; + + pud = pud_offset(pgd, addr); + do { + next = pud_addr_end(addr, end); + if (pud_none_or_clear_bad(pud)) + continue; + next = page_table_realloc_pmd(tlb, mm, pud, addr, next); + } while (pud++, addr = next, addr != end); + + return addr; +} + +static void page_table_realloc(struct mmu_gather *tlb, struct mm_struct *mm, + unsigned long addr, unsigned long end) +{ + unsigned long next; + pgd_t *pgd; + + pgd = pgd_offset(mm, addr); + do { + next = pgd_addr_end(addr, end); + if (pgd_none_or_clear_bad(pgd)) + continue; + next = page_table_realloc_pud(tlb, mm, pgd, addr, next); + } while (pgd++, addr = next, addr != end); +} + /* * switch on pgstes for its userspace process (for kvm) */ int s390_enable_sie(void) { struct task_struct *tsk = current; - struct mm_struct *mm, *old_mm; + struct mm_struct *mm = tsk->mm; + struct mmu_gather tlb; /* Do we have switched amode? If no, we cannot do sie */ if (s390_user_mode == HOME_SPACE_MODE) @@ -1072,57 +1166,16 @@ int s390_enable_sie(void) if (mm_has_pgste(tsk->mm)) return 0; - /* lets check if we are allowed to replace the mm */ - task_lock(tsk); - if (!tsk->mm || atomic_read(&tsk->mm->mm_users) > 1 || -#ifdef CONFIG_AIO - !hlist_empty(&tsk->mm->ioctx_list) || -#endif - tsk->mm != tsk->active_mm) { - task_unlock(tsk); - return -EINVAL; - } - task_unlock(tsk); - - /* we copy the mm and let dup_mm create the page tables with_pgstes */ - tsk->mm->context.alloc_pgste = 1; - /* make sure that both mms have a correct rss state */ - sync_mm_rss(tsk->mm); - mm = dup_mm(tsk); - tsk->mm->context.alloc_pgste = 0; - if (!mm) - return -ENOMEM; - -#ifdef CONFIG_TRANSPARENT_HUGEPAGE + down_write(&mm->mmap_sem); /* split thp mappings and disable thp for future mappings */ thp_split_mm(mm); - mm->def_flags |= VM_NOHUGEPAGE; -#endif - - /* Now lets check again if something happened */ - task_lock(tsk); - if (!tsk->mm || atomic_read(&tsk->mm->mm_users) > 1 || -#ifdef CONFIG_AIO - !hlist_empty(&tsk->mm->ioctx_list) || -#endif - tsk->mm != tsk->active_mm) { - mmput(mm); - task_unlock(tsk); - return -EINVAL; - } - - /* ok, we are alone. No ptrace, no threads, etc. */ - old_mm = tsk->mm; - tsk->mm = tsk->active_mm = mm; - preempt_disable(); - update_mm(mm, tsk); - atomic_inc(&mm->context.attach_count); - atomic_dec(&old_mm->context.attach_count); - cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm)); - preempt_enable(); - task_unlock(tsk); - mmput(old_mm); - return 0; + /* Reallocate the page tables with pgstes */ + mm->context.has_pgste = 1; + tlb_gather_mmu(&tlb, mm, 0); + page_table_realloc(&tlb, mm, 0, TASK_SIZE); + tlb_finish_mmu(&tlb, 0, -1); + up_write(&mm->mmap_sem); + return mm->context.has_pgste ? 0 : -ENOMEM; } EXPORT_SYMBOL_GPL(s390_enable_sie); -- cgit v1.2.3-70-g09d2 From ee6ee55bb505c5bd8e64bc652281a93fb99c07b3 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Fri, 26 Jul 2013 15:04:03 +0200 Subject: KVM: s390: fix task size check The gmap_map_segment function uses PGDIR_SIZE in the check for the maximum address in the tasks address space. This incorrectly limits the amount of memory usable for a kvm guest to 4TB. The correct limit is (1UL << 53). As the TASK_SIZE has different values (4TB vs 8PB) dependent on the existance of the fourth page table level, create a new define 'TASK_MAX_SIZE' for (1UL << 53). Signed-off-by: Martin Schwidefsky Signed-off-by: Christian Borntraeger Signed-off-by: Paolo Bonzini --- arch/s390/include/asm/processor.h | 2 ++ arch/s390/mm/pgtable.c | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'arch/s390') diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 6b499870662..83c85c217f5 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -43,6 +43,7 @@ extern void execve_tail(void); #ifndef CONFIG_64BIT #define TASK_SIZE (1UL << 31) +#define TASK_MAX_SIZE (1UL << 31) #define TASK_UNMAPPED_BASE (1UL << 30) #else /* CONFIG_64BIT */ @@ -51,6 +52,7 @@ extern void execve_tail(void); #define TASK_UNMAPPED_BASE (test_thread_flag(TIF_31BIT) ? \ (1UL << 30) : (1UL << 41)) #define TASK_SIZE TASK_SIZE_OF(current) +#define TASK_MAX_SIZE (1UL << 53) #endif /* CONFIG_64BIT */ diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 6d332487f36..967d0bf1c05 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -335,7 +335,7 @@ int gmap_map_segment(struct gmap *gmap, unsigned long from, if ((from | to | len) & (PMD_SIZE - 1)) return -EINVAL; - if (len == 0 || from + len > PGDIR_SIZE || + if (len == 0 || from + len > TASK_MAX_SIZE || from + len < from || to + len < to) return -EINVAL; -- cgit v1.2.3-70-g09d2 From 78c4b59f721fb0c30e8520f1c8e78fbf47bddfdf Mon Sep 17 00:00:00 2001 From: Michael Mueller Date: Fri, 26 Jul 2013 15:04:04 +0200 Subject: KVM: s390: declare virtual HW facilities The patch renames the array holding the HW facility bitmaps. This allows to interprete the variable as set of virtual machine specific "virtual" facilities. The basic idea is to make virtual facilities externally managable in future. An availability test for virtual facilites has been added as well. Signed-off-by: Michael Mueller Signed-off-by: Christian Borntraeger Signed-off-by: Paolo Bonzini --- arch/s390/kvm/kvm-s390.c | 23 +++++++++++++++-------- arch/s390/kvm/kvm-s390.h | 3 +++ arch/s390/kvm/priv.c | 11 ++++------- 3 files changed, 22 insertions(+), 15 deletions(-) (limited to 'arch/s390') diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index a3d797b689a..ac8e6670c55 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include "kvm-s390.h" #include "gaccess.h" @@ -84,9 +85,15 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { NULL } }; -static unsigned long long *facilities; +unsigned long *vfacilities; static struct gmap_notifier gmap_notifier; +/* test availability of vfacility */ +static inline int test_vfacility(unsigned long nr) +{ + return __test_facility(nr, (void *) vfacilities); +} + /* Section: not file related */ int kvm_arch_hardware_enable(void *garbage) { @@ -387,7 +394,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) vcpu->arch.sie_block->ecb = 6; vcpu->arch.sie_block->ecb2 = 8; vcpu->arch.sie_block->eca = 0xC1002001U; - vcpu->arch.sie_block->fac = (int) (long) facilities; + vcpu->arch.sie_block->fac = (int) (long) vfacilities; hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS); tasklet_init(&vcpu->arch.tasklet, kvm_s390_tasklet, (unsigned long) vcpu); @@ -1126,20 +1133,20 @@ static int __init kvm_s390_init(void) * to hold the maximum amount of facilities. On the other hand, we * only set facilities that are known to work in KVM. */ - facilities = (unsigned long long *) get_zeroed_page(GFP_KERNEL|GFP_DMA); - if (!facilities) { + vfacilities = (unsigned long *) get_zeroed_page(GFP_KERNEL|GFP_DMA); + if (!vfacilities) { kvm_exit(); return -ENOMEM; } - memcpy(facilities, S390_lowcore.stfle_fac_list, 16); - facilities[0] &= 0xff82fff3f47c0000ULL; - facilities[1] &= 0x001c000000000000ULL; + memcpy(vfacilities, S390_lowcore.stfle_fac_list, 16); + vfacilities[0] &= 0xff82fff3f47c0000UL; + vfacilities[1] &= 0x001c000000000000UL; return 0; } static void __exit kvm_s390_exit(void) { - free_page((unsigned long) facilities); + free_page((unsigned long) vfacilities); kvm_exit(); } diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index 028ca9fd215..faa4df63347 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -24,6 +24,9 @@ typedef int (*intercept_handler_t)(struct kvm_vcpu *vcpu); +/* declare vfacilities extern */ +extern unsigned long *vfacilities; + /* negativ values are error codes, positive values for internal conditions */ #define SIE_INTERCEPT_RERUNVCPU (1<<0) #define SIE_INTERCEPT_UCONTROL (1<<1) diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 0da3e6eb6be..a14c4b68aed 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -227,7 +227,6 @@ static int handle_io_inst(struct kvm_vcpu *vcpu) static int handle_stfl(struct kvm_vcpu *vcpu) { - unsigned int facility_list; int rc; vcpu->stat.instruction_stfl++; @@ -235,15 +234,13 @@ static int handle_stfl(struct kvm_vcpu *vcpu) if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - /* only pass the facility bits, which we can handle */ - facility_list = S390_lowcore.stfl_fac_list & 0xff82fff3; - rc = copy_to_guest(vcpu, offsetof(struct _lowcore, stfl_fac_list), - &facility_list, sizeof(facility_list)); + vfacilities, 4); if (rc) return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); - VCPU_EVENT(vcpu, 5, "store facility list value %x", facility_list); - trace_kvm_s390_handle_stfl(vcpu, facility_list); + VCPU_EVENT(vcpu, 5, "store facility list value %x", + *(unsigned int *) vfacilities); + trace_kvm_s390_handle_stfl(vcpu, *(unsigned int *) vfacilities); return 0; } -- cgit v1.2.3-70-g09d2 From 843200e7cc5de5f482ebe8acbf81e35a1c8e4a3d Mon Sep 17 00:00:00 2001 From: Thomas Huth Date: Fri, 26 Jul 2013 15:04:05 +0200 Subject: KVM: s390: Fix sparse warnings in priv.c sparse complained about the missing UL postfix for long constants. Signed-off-by: Thomas Huth Acked-by: Cornelia Huck Signed-off-by: Christian Borntraeger Signed-off-by: Paolo Bonzini --- arch/s390/kvm/priv.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'arch/s390') diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index a14c4b68aed..697e34b5903 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -490,12 +490,12 @@ static int handle_epsw(struct kvm_vcpu *vcpu) kvm_s390_get_regs_rre(vcpu, ®1, ®2); /* This basically extracts the mask half of the psw. */ - vcpu->run->s.regs.gprs[reg1] &= 0xffffffff00000000; + vcpu->run->s.regs.gprs[reg1] &= 0xffffffff00000000UL; vcpu->run->s.regs.gprs[reg1] |= vcpu->arch.sie_block->gpsw.mask >> 32; if (reg2) { - vcpu->run->s.regs.gprs[reg2] &= 0xffffffff00000000; + vcpu->run->s.regs.gprs[reg2] &= 0xffffffff00000000UL; vcpu->run->s.regs.gprs[reg2] |= - vcpu->arch.sie_block->gpsw.mask & 0x00000000ffffffff; + vcpu->arch.sie_block->gpsw.mask & 0x00000000ffffffffUL; } return 0; } -- cgit v1.2.3-70-g09d2 From ea828ebf59f5b56e7261bfaeb94393c9dcb86260 Mon Sep 17 00:00:00 2001 From: Thomas Huth Date: Fri, 26 Jul 2013 15:04:06 +0200 Subject: KVM: s390: Add helper function for setting condition code Introduced a helper function for setting the CC in the guest PSW to improve the readability of the code. Signed-off-by: Thomas Huth Signed-off-by: Christian Borntraeger Signed-off-by: Paolo Bonzini --- arch/s390/kvm/kvm-s390.h | 7 +++++++ arch/s390/kvm/priv.c | 15 ++++++--------- 2 files changed, 13 insertions(+), 9 deletions(-) (limited to 'arch/s390') diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index faa4df63347..dc99f1ca426 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -115,6 +115,13 @@ static inline u64 kvm_s390_get_base_disp_rs(struct kvm_vcpu *vcpu) return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2; } +/* Set the condition code in the guest program status word */ +static inline void kvm_s390_set_psw_cc(struct kvm_vcpu *vcpu, unsigned long cc) +{ + vcpu->arch.sie_block->gpsw.mask &= ~(3UL << 44); + vcpu->arch.sie_block->gpsw.mask |= cc << 44; +} + int kvm_s390_handle_wait(struct kvm_vcpu *vcpu); enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer); void kvm_s390_tasklet(unsigned long parm); diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 697e34b5903..8f8d8ee9b1f 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -163,8 +163,7 @@ static int handle_tpi(struct kvm_vcpu *vcpu) kfree(inti); no_interrupt: /* Set condition code and we're done. */ - vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44); - vcpu->arch.sie_block->gpsw.mask |= (cc & 3ul) << 44; + kvm_s390_set_psw_cc(vcpu, cc); return 0; } @@ -219,8 +218,7 @@ static int handle_io_inst(struct kvm_vcpu *vcpu) * Set condition code 3 to stop the guest from issueing channel * I/O instructions. */ - vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44); - vcpu->arch.sie_block->gpsw.mask |= (3 & 3ul) << 44; + kvm_s390_set_psw_cc(vcpu, 3); return 0; } } @@ -383,7 +381,7 @@ static int handle_stsi(struct kvm_vcpu *vcpu) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); if (fc > 3) { - vcpu->arch.sie_block->gpsw.mask |= 3ul << 44; /* cc 3 */ + kvm_s390_set_psw_cc(vcpu, 3); return 0; } @@ -393,7 +391,7 @@ static int handle_stsi(struct kvm_vcpu *vcpu) if (fc == 0) { vcpu->run->s.regs.gprs[0] = 3 << 28; - vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44); /* cc 0 */ + kvm_s390_set_psw_cc(vcpu, 0); return 0; } @@ -427,12 +425,11 @@ static int handle_stsi(struct kvm_vcpu *vcpu) } trace_kvm_s390_handle_stsi(vcpu, fc, sel1, sel2, operand2); free_page(mem); - vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44); + kvm_s390_set_psw_cc(vcpu, 0); vcpu->run->s.regs.gprs[0] = 0; return 0; out_no_data: - /* condition code 3 */ - vcpu->arch.sie_block->gpsw.mask |= 3ul << 44; + kvm_s390_set_psw_cc(vcpu, 3); out_exception: free_page(mem); return rc; -- cgit v1.2.3-70-g09d2 From bf640876e21fe603f7f52b0c27d66b7716da0384 Mon Sep 17 00:00:00 2001 From: Dominik Dingel Date: Fri, 26 Jul 2013 15:04:07 +0200 Subject: KVM: s390: Make KVM_HVA_ERR_BAD usable on s390 Current common code uses PAGE_OFFSET to indicate a bad host virtual address. As this check won't work on architectures that don't map kernel and user memory into the same address space (e.g. s390), such architectures can now provide their own KVM_HVA_ERR_BAD defines. Signed-off-by: Dominik Dingel Signed-off-by: Christian Borntraeger Signed-off-by: Paolo Bonzini --- arch/s390/include/asm/kvm_host.h | 8 ++++++++ include/linux/kvm_host.h | 8 ++++++++ 2 files changed, 16 insertions(+) (limited to 'arch/s390') diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 3238d4004e8..e87ecaa2c56 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -274,6 +274,14 @@ struct kvm_arch{ int css_support; }; +#define KVM_HVA_ERR_BAD (-1UL) +#define KVM_HVA_ERR_RO_BAD (-2UL) + +static inline bool kvm_is_error_hva(unsigned long addr) +{ + return IS_ERR_VALUE(addr); +} + extern int sie64a(struct kvm_s390_sie_block *, u64 *); extern char sie_exit; #endif diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index c11c7686ae5..ca645a01d37 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -85,6 +85,12 @@ static inline bool is_noslot_pfn(pfn_t pfn) return pfn == KVM_PFN_NOSLOT; } +/* + * architectures with KVM_HVA_ERR_BAD other than PAGE_OFFSET (e.g. s390) + * provide own defines and kvm_is_error_hva + */ +#ifndef KVM_HVA_ERR_BAD + #define KVM_HVA_ERR_BAD (PAGE_OFFSET) #define KVM_HVA_ERR_RO_BAD (PAGE_OFFSET + PAGE_SIZE) @@ -93,6 +99,8 @@ static inline bool kvm_is_error_hva(unsigned long addr) return addr >= PAGE_OFFSET; } +#endif + #define KVM_ERR_PTR_BAD_PAGE (ERR_PTR(-ENOENT)) static inline bool is_error_page(struct page *page) -- cgit v1.2.3-70-g09d2