[gentoo-commits] linux-patches r2772 - genpatches-2.6/trunk/3.15

[Mike Pagano (mpagano)]

Author: mpagano
Date: 2014-05-05 14:28:48 +0000 (Mon, 05 May 2014)
New Revision: 2772

Removed:
   genpatches-2.6/trunk/3.15/1000_linux-3.14.1.patch
   genpatches-2.6/trunk/3.15/1001_linux-3.14.2.patch
   genpatches-2.6/trunk/3.15/4200_fbcondecor-0.9.6.patch
   genpatches-2.6/trunk/3.15/5000_enable-additional-cpu-optimizations-for-gcc.patch
   genpatches-2.6/trunk/3.15/5001_BFQ-1-block-cgroups-kconfig-build-bits-for-BFQ-v7r2-3.14.patch
   genpatches-2.6/trunk/3.15/5002_BFQ-2-block-introduce-the-BFQ-v7r2-I-O-sched-for-3.14.patch1
   genpatches-2.6/trunk/3.15/5003_BFQ-3-block-bfq-add-Early-Queue-Merge-EQM-to-BFQ-v7r2-for-3.14.0.patch
Modified:
   genpatches-2.6/trunk/3.15/0000_README
Log:
Remove patches incompatible with 3.15 until they can be worked on.

Modified: genpatches-2.6/trunk/3.15/0000_README
===================================================================
--- genpatches-2.6/trunk/3.15/0000_README	2014-05-05 14:22:27 UTC (rev 2771)
+++ genpatches-2.6/trunk/3.15/0000_README	2014-05-05 14:28:48 UTC (rev 2772)
@@ -42,14 +42,6 @@
 
 Individual Patch Descriptions:
 --------------------------------------------------------------------------
-Patch:  1000_linux-3.14.1.patch
-From:   http://www.kernel.org
-Desc:   Linux 3.14.1
-
-Patch:  1001_linux-3.14.2.patch
-From:   http://www.kernel.org
-Desc:   Linux 3.14.2
-
 Patch:  1500_XATTR_USER_PREFIX.patch
 From:   https://bugs.gentoo.org/show_bug.cgi?id=470644
 Desc:   Support for namespace user.pax.* on tmpfs.
@@ -74,10 +66,6 @@
 From:   Al Viro <viro <at> ZenIV.linux.org.uk>
 Desc:   Do not lock when UMH is waiting on current thread spawned by linuxrc. (bug #481344)
 
-Patch:  4200_fbcondecor-0.9.6.patch
-From:   http://dev.gentoo.org/~spock
-Desc:   Bootsplash successor by Michal Januszewski ported by Jeremy (bug #452574)
-
 Patch:  4500_support-for-pogoplug-e02.patch
 From:   Cristoph Junghans <ottxor@g.o>
 Desc:   Support for Pogoplug e02 (bug #460350), adjusted to be opt-in by TomWij.
@@ -85,20 +73,3 @@
 Patch:  4567_distro-Gentoo-Kconfig.patch
 From:   Tom Wijsman <TomWij@g.o>
 Desc:   Add Gentoo Linux support config settings and defaults.
-
-Patch:  5000_enable-additional-cpu-optimizations-for-gcc.patch
-From:   https://github.com/graysky2/kernel_gcc_patch/
-Desc:   Kernel patch enables gcc optimizations for additional CPUs.
-
-Patch:  5001_BFQ-1-block-cgroups-kconfig-build-bits-for-v7r2-3.14.patch
-From:   http://algo.ing.unimo.it/people/paolo/disk_sched/
-Desc:   BFQ v7r2 patch 1 for 3.14: Build, cgroups and kconfig bits
-
-Patch:  5002_BFQ-2-block-introduce-the-v7r2-I-O-sched-for-3.14.patch1
-From:   http://algo.ing.unimo.it/people/paolo/disk_sched/
-Desc:   BFQ v7r2 patch 2 for 3.14: BFQ Scheduler
-
-Patch:  5003_BFQ-3-block-add-Early-Queue-Merge-EQM-v7r2-for-3.14.0.patch
-From:   http://algo.ing.unimo.it/people/paolo/disk_sched/
-Desc:   BFQ v7r2 patch 3 for 3.14: Early Queue Merge (EQM)
-

Deleted: genpatches-2.6/trunk/3.15/1000_linux-3.14.1.patch
===================================================================
--- genpatches-2.6/trunk/3.15/1000_linux-3.14.1.patch	2014-05-05 14:22:27 UTC (rev 2771)
+++ genpatches-2.6/trunk/3.15/1000_linux-3.14.1.patch	2014-05-05 14:28:48 UTC (rev 2772)
@@ -1,1221 +0,0 @@
-diff --git a/Makefile b/Makefile
-index e5ac8a62e6e5..7d0b6992d9ed 100644
---- a/Makefile
-+++ b/Makefile
-@@ -1,6 +1,6 @@
- VERSION = 3
- PATCHLEVEL = 14
--SUBLEVEL = 0
-+SUBLEVEL = 1
- EXTRAVERSION =
- NAME = Shuffling Zombie Juror
- 
-diff --git a/arch/arc/boot/dts/nsimosci.dts b/arch/arc/boot/dts/nsimosci.dts
-index ea16d782af58..4f31b2eb5cdf 100644
---- a/arch/arc/boot/dts/nsimosci.dts
-+++ b/arch/arc/boot/dts/nsimosci.dts
-@@ -11,13 +11,16 @@
- 
- / {
- 	compatible = "snps,nsimosci";
--	clock-frequency = <80000000>;	/* 80 MHZ */
-+	clock-frequency = <20000000>;	/* 20 MHZ */
- 	#address-cells = <1>;
- 	#size-cells = <1>;
- 	interrupt-parent = <&intc>;
- 
- 	chosen {
--		bootargs = "console=tty0 consoleblank=0";
-+		/* this is for console on PGU */
-+		/* bootargs = "console=tty0 consoleblank=0"; */
-+		/* this is for console on serial */
-+		bootargs = "earlycon=uart8250,mmio32,0xc0000000,115200n8 console=ttyS0,115200n8 consoleblank=0 debug";
- 	};
- 
- 	aliases {
-@@ -44,15 +47,14 @@
- 		};
- 
- 		uart0: serial@c0000000 {
--			compatible = "snps,dw-apb-uart";
-+			compatible = "ns8250";
- 			reg = <0xc0000000 0x2000>;
- 			interrupts = <11>;
--			#clock-frequency = <80000000>;
- 			clock-frequency = <3686400>;
- 			baud = <115200>;
- 			reg-shift = <2>;
- 			reg-io-width = <4>;
--			status = "okay";
-+			no-loopback-test = <1>;
- 		};
- 
- 		pgu0: pgu@c9000000 {
-diff --git a/arch/arc/configs/nsimosci_defconfig b/arch/arc/configs/nsimosci_defconfig
-index 451af30914f6..c01ba35a4eff 100644
---- a/arch/arc/configs/nsimosci_defconfig
-+++ b/arch/arc/configs/nsimosci_defconfig
-@@ -54,6 +54,7 @@ CONFIG_SERIO_ARC_PS2=y
- CONFIG_SERIAL_8250=y
- CONFIG_SERIAL_8250_CONSOLE=y
- CONFIG_SERIAL_8250_DW=y
-+CONFIG_SERIAL_OF_PLATFORM=y
- CONFIG_SERIAL_ARC=y
- CONFIG_SERIAL_ARC_CONSOLE=y
- # CONFIG_HW_RANDOM is not set
-diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
-index dbdd2231c75d..b2e322939256 100644
---- a/arch/m68k/Kconfig
-+++ b/arch/m68k/Kconfig
-@@ -17,6 +17,7 @@ config M68K
- 	select FPU if MMU
- 	select ARCH_WANT_IPC_PARSE_VERSION
- 	select ARCH_USES_GETTIMEOFFSET if MMU && !COLDFIRE
-+	select HAVE_FUTEX_CMPXCHG if MMU && FUTEX
- 	select HAVE_MOD_ARCH_SPECIFIC
- 	select MODULES_USE_ELF_REL
- 	select MODULES_USE_ELF_RELA
-diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
-index 65a07750f4f9..bb74b21f007a 100644
---- a/arch/s390/Kconfig
-+++ b/arch/s390/Kconfig
-@@ -117,6 +117,7 @@ config S390
- 	select HAVE_FUNCTION_GRAPH_TRACER
- 	select HAVE_FUNCTION_TRACER
- 	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
-+	select HAVE_FUTEX_CMPXCHG if FUTEX
- 	select HAVE_KERNEL_BZIP2
- 	select HAVE_KERNEL_GZIP
- 	select HAVE_KERNEL_LZ4
-diff --git a/arch/x86/crypto/ghash-clmulni-intel_asm.S b/arch/x86/crypto/ghash-clmulni-intel_asm.S
-index 586f41aac361..185fad49d86f 100644
---- a/arch/x86/crypto/ghash-clmulni-intel_asm.S
-+++ b/arch/x86/crypto/ghash-clmulni-intel_asm.S
-@@ -24,10 +24,6 @@
- .align 16
- .Lbswap_mask:
- 	.octa 0x000102030405060708090a0b0c0d0e0f
--.Lpoly:
--	.octa 0xc2000000000000000000000000000001
--.Ltwo_one:
--	.octa 0x00000001000000000000000000000001
- 
- #define DATA	%xmm0
- #define SHASH	%xmm1
-@@ -134,28 +130,3 @@ ENTRY(clmul_ghash_update)
- .Lupdate_just_ret:
- 	ret
- ENDPROC(clmul_ghash_update)
--
--/*
-- * void clmul_ghash_setkey(be128 *shash, const u8 *key);
-- *
-- * Calculate hash_key << 1 mod poly
-- */
--ENTRY(clmul_ghash_setkey)
--	movaps .Lbswap_mask, BSWAP
--	movups (%rsi), %xmm0
--	PSHUFB_XMM BSWAP %xmm0
--	movaps %xmm0, %xmm1
--	psllq $1, %xmm0
--	psrlq $63, %xmm1
--	movaps %xmm1, %xmm2
--	pslldq $8, %xmm1
--	psrldq $8, %xmm2
--	por %xmm1, %xmm0
--	# reduction
--	pshufd $0b00100100, %xmm2, %xmm1
--	pcmpeqd .Ltwo_one, %xmm1
--	pand .Lpoly, %xmm1
--	pxor %xmm1, %xmm0
--	movups %xmm0, (%rdi)
--	ret
--ENDPROC(clmul_ghash_setkey)
-diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c
-index 6759dd1135be..d785cf2c529c 100644
---- a/arch/x86/crypto/ghash-clmulni-intel_glue.c
-+++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c
-@@ -30,8 +30,6 @@ void clmul_ghash_mul(char *dst, const be128 *shash);
- void clmul_ghash_update(char *dst, const char *src, unsigned int srclen,
- 			const be128 *shash);
- 
--void clmul_ghash_setkey(be128 *shash, const u8 *key);
--
- struct ghash_async_ctx {
- 	struct cryptd_ahash *cryptd_tfm;
- };
-@@ -58,13 +56,23 @@ static int ghash_setkey(struct crypto_shash *tfm,
- 			const u8 *key, unsigned int keylen)
- {
- 	struct ghash_ctx *ctx = crypto_shash_ctx(tfm);
-+	be128 *x = (be128 *)key;
-+	u64 a, b;
- 
- 	if (keylen != GHASH_BLOCK_SIZE) {
- 		crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
- 		return -EINVAL;
- 	}
- 
--	clmul_ghash_setkey(&ctx->shash, key);
-+	/* perform multiplication by 'x' in GF(2^128) */
-+	a = be64_to_cpu(x->a);
-+	b = be64_to_cpu(x->b);
-+
-+	ctx->shash.a = (__be64)((b << 1) | (a >> 63));
-+	ctx->shash.b = (__be64)((a << 1) | (b >> 63));
-+
-+	if (a >> 63)
-+		ctx->shash.b ^= cpu_to_be64(0xc2);
- 
- 	return 0;
- }
-diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
-index acd86c850414..f949715e3957 100644
---- a/arch/x86/include/asm/efi.h
-+++ b/arch/x86/include/asm/efi.h
-@@ -130,7 +130,8 @@ extern void efi_memory_uc(u64 addr, unsigned long size);
- extern void __init efi_map_region(efi_memory_desc_t *md);
- extern void __init efi_map_region_fixed(efi_memory_desc_t *md);
- extern void efi_sync_low_kernel_mappings(void);
--extern void efi_setup_page_tables(void);
-+extern int efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages);
-+extern void efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages);
- extern void __init old_map_region(efi_memory_desc_t *md);
- extern void __init runtime_code_page_mkexec(void);
- extern void __init efi_runtime_mkexec(void);
-diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
-index 1aa9ccd43223..94e40f1efdfd 100644
---- a/arch/x86/include/asm/pgtable_types.h
-+++ b/arch/x86/include/asm/pgtable_types.h
-@@ -385,6 +385,8 @@ extern pte_t *lookup_address(unsigned long address, unsigned int *level);
- extern phys_addr_t slow_virt_to_phys(void *__address);
- extern int kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
- 				   unsigned numpages, unsigned long page_flags);
-+void kernel_unmap_pages_in_pgd(pgd_t *root, unsigned long address,
-+			       unsigned numpages);
- #endif	/* !__ASSEMBLY__ */
- 
- #endif /* _ASM_X86_PGTABLE_DEFS_H */
-diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
-index b3b19f46c016..a3488689e301 100644
---- a/arch/x86/mm/pageattr.c
-+++ b/arch/x86/mm/pageattr.c
-@@ -692,6 +692,18 @@ static bool try_to_free_pmd_page(pmd_t *pmd)
- 	return true;
- }
- 
-+static bool try_to_free_pud_page(pud_t *pud)
-+{
-+	int i;
-+
-+	for (i = 0; i < PTRS_PER_PUD; i++)
-+		if (!pud_none(pud[i]))
-+			return false;
-+
-+	free_page((unsigned long)pud);
-+	return true;
-+}
-+
- static bool unmap_pte_range(pmd_t *pmd, unsigned long start, unsigned long end)
- {
- 	pte_t *pte = pte_offset_kernel(pmd, start);
-@@ -805,6 +817,16 @@ static void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end)
- 	 */
- }
- 
-+static void unmap_pgd_range(pgd_t *root, unsigned long addr, unsigned long end)
-+{
-+	pgd_t *pgd_entry = root + pgd_index(addr);
-+
-+	unmap_pud_range(pgd_entry, addr, end);
-+
-+	if (try_to_free_pud_page((pud_t *)pgd_page_vaddr(*pgd_entry)))
-+		pgd_clear(pgd_entry);
-+}
-+
- static int alloc_pte_page(pmd_t *pmd)
- {
- 	pte_t *pte = (pte_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK);
-@@ -999,9 +1021,8 @@ static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd,
- static int populate_pgd(struct cpa_data *cpa, unsigned long addr)
- {
- 	pgprot_t pgprot = __pgprot(_KERNPG_TABLE);
--	bool allocd_pgd = false;
--	pgd_t *pgd_entry;
- 	pud_t *pud = NULL;	/* shut up gcc */
-+	pgd_t *pgd_entry;
- 	int ret;
- 
- 	pgd_entry = cpa->pgd + pgd_index(addr);
-@@ -1015,7 +1036,6 @@ static int populate_pgd(struct cpa_data *cpa, unsigned long addr)
- 			return -1;
- 
- 		set_pgd(pgd_entry, __pgd(__pa(pud) | _KERNPG_TABLE));
--		allocd_pgd = true;
- 	}
- 
- 	pgprot_val(pgprot) &= ~pgprot_val(cpa->mask_clr);
-@@ -1023,19 +1043,11 @@ static int populate_pgd(struct cpa_data *cpa, unsigned long addr)
- 
- 	ret = populate_pud(cpa, addr, pgd_entry, pgprot);
- 	if (ret < 0) {
--		unmap_pud_range(pgd_entry, addr,
-+		unmap_pgd_range(cpa->pgd, addr,
- 				addr + (cpa->numpages << PAGE_SHIFT));
--
--		if (allocd_pgd) {
--			/*
--			 * If I allocated this PUD page, I can just as well
--			 * free it in this error path.
--			 */
--			pgd_clear(pgd_entry);
--			free_page((unsigned long)pud);
--		}
- 		return ret;
- 	}
-+
- 	cpa->numpages = ret;
- 	return 0;
- }
-@@ -1861,6 +1873,12 @@ out:
- 	return retval;
- }
- 
-+void kernel_unmap_pages_in_pgd(pgd_t *root, unsigned long address,
-+			       unsigned numpages)
-+{
-+	unmap_pgd_range(root, address, address + (numpages << PAGE_SHIFT));
-+}
-+
- /*
-  * The testcases use internal knowledge of the implementation that shouldn't
-  * be exposed to the rest of the kernel. Include these directly here.
-diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
-index b97acecf3fd9..abb81b0ad83f 100644
---- a/arch/x86/platform/efi/efi.c
-+++ b/arch/x86/platform/efi/efi.c
-@@ -939,14 +939,36 @@ static void __init efi_map_regions_fixed(void)
- 
- }
- 
-+static void *realloc_pages(void *old_memmap, int old_shift)
-+{
-+	void *ret;
-+
-+	ret = (void *)__get_free_pages(GFP_KERNEL, old_shift + 1);
-+	if (!ret)
-+		goto out;
-+
-+	/*
-+	 * A first-time allocation doesn't have anything to copy.
-+	 */
-+	if (!old_memmap)
-+		return ret;
-+
-+	memcpy(ret, old_memmap, PAGE_SIZE << old_shift);
-+
-+out:
-+	free_pages((unsigned long)old_memmap, old_shift);
-+	return ret;
-+}
-+
- /*
-- * Map efi memory ranges for runtime serivce and update new_memmap with virtual
-- * addresses.
-+ * Map the efi memory ranges of the runtime services and update new_mmap with
-+ * virtual addresses.
-  */
--static void * __init efi_map_regions(int *count)
-+static void * __init efi_map_regions(int *count, int *pg_shift)
- {
-+	void *p, *new_memmap = NULL;
-+	unsigned long left = 0;
- 	efi_memory_desc_t *md;
--	void *p, *tmp, *new_memmap = NULL;
- 
- 	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
- 		md = p;
-@@ -961,20 +983,23 @@ static void * __init efi_map_regions(int *count)
- 		efi_map_region(md);
- 		get_systab_virt_addr(md);
- 
--		tmp = krealloc(new_memmap, (*count + 1) * memmap.desc_size,
--			       GFP_KERNEL);
--		if (!tmp)
--			goto out;
--		new_memmap = tmp;
-+		if (left < memmap.desc_size) {
-+			new_memmap = realloc_pages(new_memmap, *pg_shift);
-+			if (!new_memmap)
-+				return NULL;
-+
-+			left += PAGE_SIZE << *pg_shift;
-+			(*pg_shift)++;
-+		}
-+
- 		memcpy(new_memmap + (*count * memmap.desc_size), md,
- 		       memmap.desc_size);
-+
-+		left -= memmap.desc_size;
- 		(*count)++;
- 	}
- 
- 	return new_memmap;
--out:
--	kfree(new_memmap);
--	return NULL;
- }
- 
- /*
-@@ -1000,9 +1025,9 @@ out:
-  */
- void __init efi_enter_virtual_mode(void)
- {
--	efi_status_t status;
-+	int err, count = 0, pg_shift = 0;
- 	void *new_memmap = NULL;
--	int err, count = 0;
-+	efi_status_t status;
- 
- 	efi.systab = NULL;
- 
-@@ -1019,20 +1044,24 @@ void __init efi_enter_virtual_mode(void)
- 		efi_map_regions_fixed();
- 	} else {
- 		efi_merge_regions();
--		new_memmap = efi_map_regions(&count);
-+		new_memmap = efi_map_regions(&count, &pg_shift);
- 		if (!new_memmap) {
- 			pr_err("Error reallocating memory, EFI runtime non-functional!\n");
- 			return;
- 		}
--	}
- 
--	err = save_runtime_map();
--	if (err)
--		pr_err("Error saving runtime map, efi runtime on kexec non-functional!!\n");
-+		err = save_runtime_map();
-+		if (err)
-+			pr_err("Error saving runtime map, efi runtime on kexec non-functional!!\n");
-+	}
- 
- 	BUG_ON(!efi.systab);
- 
--	efi_setup_page_tables();
-+	if (!efi_setup) {
-+		if (efi_setup_page_tables(__pa(new_memmap), 1 << pg_shift))
-+			return;
-+	}
-+
- 	efi_sync_low_kernel_mappings();
- 
- 	if (!efi_setup) {
-@@ -1072,7 +1101,35 @@ void __init efi_enter_virtual_mode(void)
- 
- 	efi_runtime_mkexec();
- 
--	kfree(new_memmap);
-+
-+	/*
-+	 * We mapped the descriptor array into the EFI pagetable above but we're
-+	 * not unmapping it here. Here's why:
-+	 *
-+	 * We're copying select PGDs from the kernel page table to the EFI page
-+	 * table and when we do so and make changes to those PGDs like unmapping
-+	 * stuff from them, those changes appear in the kernel page table and we
-+	 * go boom.
-+	 *
-+	 * From setup_real_mode():
-+	 *
-+	 * ...
-+	 * trampoline_pgd[0] = init_level4_pgt[pgd_index(__PAGE_OFFSET)].pgd;
-+	 *
-+	 * In this particular case, our allocation is in PGD 0 of the EFI page
-+	 * table but we've copied that PGD from PGD[272] of the EFI page table:
-+	 *
-+	 *	pgd_index(__PAGE_OFFSET = 0xffff880000000000) = 272
-+	 *
-+	 * where the direct memory mapping in kernel space is.
-+	 *
-+	 * new_memmap's VA comes from that direct mapping and thus clearing it,
-+	 * it would get cleared in the kernel page table too.
-+	 *
-+	 * efi_cleanup_page_tables(__pa(new_memmap), 1 << pg_shift);
-+	 */
-+	if (!efi_setup)
-+		free_pages((unsigned long)new_memmap, pg_shift);
- 
- 	/* clean DUMMY object */
- 	efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,
-diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c
-index 0b74cdf7f816..9ee3491e31fb 100644
---- a/arch/x86/platform/efi/efi_32.c
-+++ b/arch/x86/platform/efi/efi_32.c
-@@ -40,7 +40,12 @@
- static unsigned long efi_rt_eflags;
- 
- void efi_sync_low_kernel_mappings(void) {}
--void efi_setup_page_tables(void) {}
-+void __init efi_dump_pagetable(void) {}
-+int efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
-+{
-+	return 0;
-+}
-+void efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages) {}
- 
- void __init efi_map_region(efi_memory_desc_t *md)
- {
-diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
-index 0c2a234fef1e..666b74a09092 100644
---- a/arch/x86/platform/efi/efi_64.c
-+++ b/arch/x86/platform/efi/efi_64.c
-@@ -137,12 +137,38 @@ void efi_sync_low_kernel_mappings(void)
- 		sizeof(pgd_t) * num_pgds);
- }
- 
--void efi_setup_page_tables(void)
-+int efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
- {
-+	pgd_t *pgd;
-+
-+	if (efi_enabled(EFI_OLD_MEMMAP))
-+		return 0;
-+
- 	efi_scratch.efi_pgt = (pgd_t *)(unsigned long)real_mode_header->trampoline_pgd;
-+	pgd = __va(efi_scratch.efi_pgt);
- 
--	if (!efi_enabled(EFI_OLD_MEMMAP))
--		efi_scratch.use_pgd = true;
-+	/*
-+	 * It can happen that the physical address of new_memmap lands in memory
-+	 * which is not mapped in the EFI page table. Therefore we need to go
-+	 * and ident-map those pages containing the map before calling
-+	 * phys_efi_set_virtual_address_map().
-+	 */
-+	if (kernel_map_pages_in_pgd(pgd, pa_memmap, pa_memmap, num_pages, _PAGE_NX)) {
-+		pr_err("Error ident-mapping new memmap (0x%lx)!\n", pa_memmap);
-+		return 1;
-+	}
-+
-+	efi_scratch.use_pgd = true;
-+
-+
-+	return 0;
-+}
-+
-+void efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages)
-+{
-+	pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd);
-+
-+	kernel_unmap_pages_in_pgd(pgd, pa_memmap, num_pages);
- }
- 
- static void __init __map_region(efi_memory_desc_t *md, u64 va)
-diff --git a/drivers/isdn/isdnloop/isdnloop.c b/drivers/isdn/isdnloop/isdnloop.c
-index 02125e6a9109..5a4da94aefb0 100644
---- a/drivers/isdn/isdnloop/isdnloop.c
-+++ b/drivers/isdn/isdnloop/isdnloop.c
-@@ -518,9 +518,9 @@ static isdnloop_stat isdnloop_cmd_table[] =
- static void
- isdnloop_fake_err(isdnloop_card *card)
- {
--	char buf[60];
-+	char buf[64];
- 
--	sprintf(buf, "E%s", card->omsg);
-+	snprintf(buf, sizeof(buf), "E%s", card->omsg);
- 	isdnloop_fake(card, buf, -1);
- 	isdnloop_fake(card, "NAK", -1);
- }
-@@ -903,6 +903,8 @@ isdnloop_parse_cmd(isdnloop_card *card)
- 	case 7:
- 		/* 0x;EAZ */
- 		p += 3;
-+		if (strlen(p) >= sizeof(card->eazlist[0]))
-+			break;
- 		strcpy(card->eazlist[ch - 1], p);
- 		break;
- 	case 8:
-@@ -1070,6 +1072,12 @@ isdnloop_start(isdnloop_card *card, isdnloop_sdef *sdefp)
- 		return -EBUSY;
- 	if (copy_from_user((char *) &sdef, (char *) sdefp, sizeof(sdef)))
- 		return -EFAULT;
-+
-+	for (i = 0; i < 3; i++) {
-+		if (!memchr(sdef.num[i], 0, sizeof(sdef.num[i])))
-+			return -EINVAL;
-+	}
-+
- 	spin_lock_irqsave(&card->isdnloop_lock, flags);
- 	switch (sdef.ptype) {
- 	case ISDN_PTYPE_EURO:
-@@ -1127,7 +1135,7 @@ isdnloop_command(isdn_ctrl *c, isdnloop_card *card)
- {
- 	ulong a;
- 	int i;
--	char cbuf[60];
-+	char cbuf[80];
- 	isdn_ctrl cmd;
- 	isdnloop_cdef cdef;
- 
-@@ -1192,7 +1200,6 @@ isdnloop_command(isdn_ctrl *c, isdnloop_card *card)
- 			break;
- 		if ((c->arg & 255) < ISDNLOOP_BCH) {
- 			char *p;
--			char dial[50];
- 			char dcode[4];
- 
- 			a = c->arg;
-@@ -1204,10 +1211,10 @@ isdnloop_command(isdn_ctrl *c, isdnloop_card *card)
- 			} else
- 				/* Normal Dial */
- 				strcpy(dcode, "CAL");
--			strcpy(dial, p);
--			sprintf(cbuf, "%02d;D%s_R%s,%02d,%02d,%s\n", (int) (a + 1),
--				dcode, dial, c->parm.setup.si1,
--				c->parm.setup.si2, c->parm.setup.eazmsn);
-+			snprintf(cbuf, sizeof(cbuf),
-+				 "%02d;D%s_R%s,%02d,%02d,%s\n", (int) (a + 1),
-+				 dcode, p, c->parm.setup.si1,
-+				 c->parm.setup.si2, c->parm.setup.eazmsn);
- 			i = isdnloop_writecmd(cbuf, strlen(cbuf), 0, card);
- 		}
- 		break;
-diff --git a/drivers/net/ethernet/cadence/at91_ether.c b/drivers/net/ethernet/cadence/at91_ether.c
-index ce75de9bae9e..4a79edaf3885 100644
---- a/drivers/net/ethernet/cadence/at91_ether.c
-+++ b/drivers/net/ethernet/cadence/at91_ether.c
-@@ -342,6 +342,9 @@ static int __init at91ether_probe(struct platform_device *pdev)
- 	}
- 	clk_enable(lp->pclk);
- 
-+	lp->hclk = ERR_PTR(-ENOENT);
-+	lp->tx_clk = ERR_PTR(-ENOENT);
-+
- 	/* Install the interrupt handler */
- 	dev->irq = platform_get_irq(pdev, 0);
- 	res = devm_request_irq(&pdev->dev, dev->irq, at91ether_interrupt, 0, dev->name, dev);
-diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
-index 174a92f5fe51..7645a3ce3854 100644
---- a/drivers/net/ethernet/sfc/ef10.c
-+++ b/drivers/net/ethernet/sfc/ef10.c
-@@ -565,10 +565,17 @@ static int efx_ef10_dimension_resources(struct efx_nic *efx)
- 	 * several of each (in fact that's the only option if host
- 	 * page size is >4K).  So we may allocate some extra VIs just
- 	 * for writing PIO buffers through.
-+	 *
-+	 * The UC mapping contains (min_vis - 1) complete VIs and the
-+	 * first half of the next VI.  Then the WC mapping begins with
-+	 * the second half of this last VI.
- 	 */
- 	uc_mem_map_size = PAGE_ALIGN((min_vis - 1) * EFX_VI_PAGE_SIZE +
- 				     ER_DZ_TX_PIOBUF);
- 	if (nic_data->n_piobufs) {
-+		/* pio_write_vi_base rounds down to give the number of complete
-+		 * VIs inside the UC mapping.
-+		 */
- 		pio_write_vi_base = uc_mem_map_size / EFX_VI_PAGE_SIZE;
- 		wc_mem_map_size = (PAGE_ALIGN((pio_write_vi_base +
- 					       nic_data->n_piobufs) *
-diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
-index 83d464347021..f06c790fba5a 100644
---- a/drivers/net/ethernet/sfc/efx.c
-+++ b/drivers/net/ethernet/sfc/efx.c
-@@ -1603,6 +1603,8 @@ static int efx_probe_nic(struct efx_nic *efx)
- 	if (rc)
- 		goto fail1;
- 
-+	efx_set_channels(efx);
-+
- 	rc = efx->type->dimension_resources(efx);
- 	if (rc)
- 		goto fail2;
-@@ -1613,7 +1615,6 @@ static int efx_probe_nic(struct efx_nic *efx)
- 		efx->rx_indir_table[i] =
- 			ethtool_rxfh_indir_default(i, efx->rss_spread);
- 
--	efx_set_channels(efx);
- 	netif_set_real_num_tx_queues(efx->net_dev, efx->n_tx_channels);
- 	netif_set_real_num_rx_queues(efx->net_dev, efx->n_rx_channels);
- 
-diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
-index 1236812c7be6..d091e52b00e1 100644
---- a/drivers/net/vxlan.c
-+++ b/drivers/net/vxlan.c
-@@ -871,6 +871,9 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
- 	if (err)
- 		return err;
- 
-+	if (vxlan->default_dst.remote_ip.sa.sa_family != ip.sa.sa_family)
-+		return -EAFNOSUPPORT;
-+
- 	spin_lock_bh(&vxlan->hash_lock);
- 	err = vxlan_fdb_create(vxlan, addr, &ip, ndm->ndm_state, flags,
- 			       port, vni, ifindex, ndm->ndm_flags);
-@@ -2612,9 +2615,10 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,
- 	vni = nla_get_u32(data[IFLA_VXLAN_ID]);
- 	dst->remote_vni = vni;
- 
-+	/* Unless IPv6 is explicitly requested, assume IPv4 */
-+	dst->remote_ip.sa.sa_family = AF_INET;
- 	if (data[IFLA_VXLAN_GROUP]) {
- 		dst->remote_ip.sin.sin_addr.s_addr = nla_get_be32(data[IFLA_VXLAN_GROUP]);
--		dst->remote_ip.sa.sa_family = AF_INET;
- 	} else if (data[IFLA_VXLAN_GROUP6]) {
- 		if (!IS_ENABLED(CONFIG_IPV6))
- 			return -EPFNOSUPPORT;
-diff --git a/drivers/net/wireless/iwlwifi/mvm/rs.c b/drivers/net/wireless/iwlwifi/mvm/rs.c
-index 6abf74e1351f..5bc871513505 100644
---- a/drivers/net/wireless/iwlwifi/mvm/rs.c
-+++ b/drivers/net/wireless/iwlwifi/mvm/rs.c
-@@ -211,9 +211,9 @@ static const struct rs_tx_column rs_tx_columns[] = {
- 		.next_columns = {
- 			RS_COLUMN_LEGACY_ANT_B,
- 			RS_COLUMN_SISO_ANT_A,
-+			RS_COLUMN_SISO_ANT_B,
- 			RS_COLUMN_MIMO2,
--			RS_COLUMN_INVALID,
--			RS_COLUMN_INVALID,
-+			RS_COLUMN_MIMO2_SGI,
- 		},
- 	},
- 	[RS_COLUMN_LEGACY_ANT_B] = {
-@@ -221,10 +221,10 @@ static const struct rs_tx_column rs_tx_columns[] = {
- 		.ant = ANT_B,
- 		.next_columns = {
- 			RS_COLUMN_LEGACY_ANT_A,
-+			RS_COLUMN_SISO_ANT_A,
- 			RS_COLUMN_SISO_ANT_B,
- 			RS_COLUMN_MIMO2,
--			RS_COLUMN_INVALID,
--			RS_COLUMN_INVALID,
-+			RS_COLUMN_MIMO2_SGI,
- 		},
- 	},
- 	[RS_COLUMN_SISO_ANT_A] = {
-@@ -234,8 +234,8 @@ static const struct rs_tx_column rs_tx_columns[] = {
- 			RS_COLUMN_SISO_ANT_B,
- 			RS_COLUMN_MIMO2,
- 			RS_COLUMN_SISO_ANT_A_SGI,
--			RS_COLUMN_INVALID,
--			RS_COLUMN_INVALID,
-+			RS_COLUMN_SISO_ANT_B_SGI,
-+			RS_COLUMN_MIMO2_SGI,
- 		},
- 		.checks = {
- 			rs_siso_allow,
-@@ -248,8 +248,8 @@ static const struct rs_tx_column rs_tx_columns[] = {
- 			RS_COLUMN_SISO_ANT_A,
- 			RS_COLUMN_MIMO2,
- 			RS_COLUMN_SISO_ANT_B_SGI,
--			RS_COLUMN_INVALID,
--			RS_COLUMN_INVALID,
-+			RS_COLUMN_SISO_ANT_A_SGI,
-+			RS_COLUMN_MIMO2_SGI,
- 		},
- 		.checks = {
- 			rs_siso_allow,
-@@ -263,8 +263,8 @@ static const struct rs_tx_column rs_tx_columns[] = {
- 			RS_COLUMN_SISO_ANT_B_SGI,
- 			RS_COLUMN_MIMO2_SGI,
- 			RS_COLUMN_SISO_ANT_A,
--			RS_COLUMN_INVALID,
--			RS_COLUMN_INVALID,
-+			RS_COLUMN_SISO_ANT_B,
-+			RS_COLUMN_MIMO2,
- 		},
- 		.checks = {
- 			rs_siso_allow,
-@@ -279,8 +279,8 @@ static const struct rs_tx_column rs_tx_columns[] = {
- 			RS_COLUMN_SISO_ANT_A_SGI,
- 			RS_COLUMN_MIMO2_SGI,
- 			RS_COLUMN_SISO_ANT_B,
--			RS_COLUMN_INVALID,
--			RS_COLUMN_INVALID,
-+			RS_COLUMN_SISO_ANT_A,
-+			RS_COLUMN_MIMO2,
- 		},
- 		.checks = {
- 			rs_siso_allow,
-@@ -292,10 +292,10 @@ static const struct rs_tx_column rs_tx_columns[] = {
- 		.ant = ANT_AB,
- 		.next_columns = {
- 			RS_COLUMN_SISO_ANT_A,
-+			RS_COLUMN_SISO_ANT_B,
-+			RS_COLUMN_SISO_ANT_A_SGI,
-+			RS_COLUMN_SISO_ANT_B_SGI,
- 			RS_COLUMN_MIMO2_SGI,
--			RS_COLUMN_INVALID,
--			RS_COLUMN_INVALID,
--			RS_COLUMN_INVALID,
- 		},
- 		.checks = {
- 			rs_mimo_allow,
-@@ -307,10 +307,10 @@ static const struct rs_tx_column rs_tx_columns[] = {
- 		.sgi = true,
- 		.next_columns = {
- 			RS_COLUMN_SISO_ANT_A_SGI,
-+			RS_COLUMN_SISO_ANT_B_SGI,
-+			RS_COLUMN_SISO_ANT_A,
-+			RS_COLUMN_SISO_ANT_B,
- 			RS_COLUMN_MIMO2,
--			RS_COLUMN_INVALID,
--			RS_COLUMN_INVALID,
--			RS_COLUMN_INVALID,
- 		},
- 		.checks = {
- 			rs_mimo_allow,
-diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
-index ae413a2cbee7..4bf5b334664e 100644
---- a/drivers/net/xen-netback/common.h
-+++ b/drivers/net/xen-netback/common.h
-@@ -113,6 +113,11 @@ struct xenvif {
- 	domid_t          domid;
- 	unsigned int     handle;
- 
-+	/* Is this interface disabled? True when backend discovers
-+	 * frontend is rogue.
-+	 */
-+	bool disabled;
-+
- 	/* Use NAPI for guest TX */
- 	struct napi_struct napi;
- 	/* When feature-split-event-channels = 0, tx_irq = rx_irq. */
-diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
-index 301cc037fda8..2e92d52c0a6d 100644
---- a/drivers/net/xen-netback/interface.c
-+++ b/drivers/net/xen-netback/interface.c
-@@ -62,6 +62,15 @@ static int xenvif_poll(struct napi_struct *napi, int budget)
- 	struct xenvif *vif = container_of(napi, struct xenvif, napi);
- 	int work_done;
- 
-+	/* This vif is rogue, we pretend we've there is nothing to do
-+	 * for this vif to deschedule it from NAPI. But this interface
-+	 * will be turned off in thread context later.
-+	 */
-+	if (unlikely(vif->disabled)) {
-+		napi_complete(napi);
-+		return 0;
-+	}
-+
- 	work_done = xenvif_tx_action(vif, budget);
- 
- 	if (work_done < budget) {
-@@ -321,6 +330,8 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid,
- 	vif->ip_csum = 1;
- 	vif->dev = dev;
- 
-+	vif->disabled = false;
-+
- 	vif->credit_bytes = vif->remaining_credit = ~0UL;
- 	vif->credit_usec  = 0UL;
- 	init_timer(&vif->credit_timeout);
-diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
-index 438d0c09b7e6..97030c193afd 100644
---- a/drivers/net/xen-netback/netback.c
-+++ b/drivers/net/xen-netback/netback.c
-@@ -192,8 +192,8 @@ static bool start_new_rx_buffer(int offset, unsigned long size, int head)
- 	 * into multiple copies tend to give large frags their
- 	 * own buffers as before.
- 	 */
--	if ((offset + size > MAX_BUFFER_OFFSET) &&
--	    (size <= MAX_BUFFER_OFFSET) && offset && !head)
-+	BUG_ON(size > MAX_BUFFER_OFFSET);
-+	if ((offset + size > MAX_BUFFER_OFFSET) && offset && !head)
- 		return true;
- 
- 	return false;
-@@ -482,6 +482,8 @@ static void xenvif_rx_action(struct xenvif *vif)
- 
- 	while ((skb = skb_dequeue(&vif->rx_queue)) != NULL) {
- 		RING_IDX max_slots_needed;
-+		RING_IDX old_req_cons;
-+		RING_IDX ring_slots_used;
- 		int i;
- 
- 		/* We need a cheap worse case estimate for the number of
-@@ -493,9 +495,28 @@ static void xenvif_rx_action(struct xenvif *vif)
- 						PAGE_SIZE);
- 		for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
- 			unsigned int size;
-+			unsigned int offset;
-+
- 			size = skb_frag_size(&skb_shinfo(skb)->frags[i]);
--			max_slots_needed += DIV_ROUND_UP(size, PAGE_SIZE);
-+			offset = skb_shinfo(skb)->frags[i].page_offset;
-+
-+			/* For a worse-case estimate we need to factor in
-+			 * the fragment page offset as this will affect the
-+			 * number of times xenvif_gop_frag_copy() will
-+			 * call start_new_rx_buffer().
-+			 */
-+			max_slots_needed += DIV_ROUND_UP(offset + size,
-+							 PAGE_SIZE);
- 		}
-+
-+		/* To avoid the estimate becoming too pessimal for some
-+		 * frontends that limit posted rx requests, cap the estimate
-+		 * at MAX_SKB_FRAGS.
-+		 */
-+		if (max_slots_needed > MAX_SKB_FRAGS)
-+			max_slots_needed = MAX_SKB_FRAGS;
-+
-+		/* We may need one more slot for GSO metadata */
- 		if (skb_is_gso(skb) &&
- 		   (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4 ||
- 		    skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6))
-@@ -511,8 +532,12 @@ static void xenvif_rx_action(struct xenvif *vif)
- 			vif->rx_last_skb_slots = 0;
- 
- 		sco = (struct skb_cb_overlay *)skb->cb;
-+
-+		old_req_cons = vif->rx.req_cons;
- 		sco->meta_slots_used = xenvif_gop_skb(skb, &npo);
--		BUG_ON(sco->meta_slots_used > max_slots_needed);
-+		ring_slots_used = vif->rx.req_cons - old_req_cons;
-+
-+		BUG_ON(ring_slots_used > max_slots_needed);
- 
- 		__skb_queue_tail(&rxq, skb);
- 	}
-@@ -655,7 +680,8 @@ static void xenvif_tx_err(struct xenvif *vif,
- static void xenvif_fatal_tx_err(struct xenvif *vif)
- {
- 	netdev_err(vif->dev, "fatal error; disabling device\n");
--	xenvif_carrier_off(vif);
-+	vif->disabled = true;
-+	xenvif_kick_thread(vif);
- }
- 
- static int xenvif_count_requests(struct xenvif *vif,
-@@ -1126,7 +1152,7 @@ static unsigned xenvif_tx_build_gops(struct xenvif *vif, int budget)
- 				   vif->tx.sring->req_prod, vif->tx.req_cons,
- 				   XEN_NETIF_TX_RING_SIZE);
- 			xenvif_fatal_tx_err(vif);
--			continue;
-+			break;
- 		}
- 
- 		work_to_do = RING_HAS_UNCONSUMED_REQUESTS(&vif->tx);
-@@ -1548,7 +1574,18 @@ int xenvif_kthread(void *data)
- 	while (!kthread_should_stop()) {
- 		wait_event_interruptible(vif->wq,
- 					 rx_work_todo(vif) ||
-+					 vif->disabled ||
- 					 kthread_should_stop());
-+
-+		/* This frontend is found to be rogue, disable it in
-+		 * kthread context. Currently this is only set when
-+		 * netback finds out frontend sends malformed packet,
-+		 * but we cannot disable the interface in softirq
-+		 * context so we defer it here.
-+		 */
-+		if (unlikely(vif->disabled && netif_carrier_ok(vif->dev)))
-+			xenvif_carrier_off(vif);
-+
- 		if (kthread_should_stop())
- 			break;
- 
-diff --git a/include/linux/futex.h b/include/linux/futex.h
-index b0d95cac826e..6435f46d6e13 100644
---- a/include/linux/futex.h
-+++ b/include/linux/futex.h
-@@ -55,7 +55,11 @@ union futex_key {
- #ifdef CONFIG_FUTEX
- extern void exit_robust_list(struct task_struct *curr);
- extern void exit_pi_state_list(struct task_struct *curr);
-+#ifdef CONFIG_HAVE_FUTEX_CMPXCHG
-+#define futex_cmpxchg_enabled 1
-+#else
- extern int futex_cmpxchg_enabled;
-+#endif
- #else
- static inline void exit_robust_list(struct task_struct *curr)
- {
-diff --git a/init/Kconfig b/init/Kconfig
-index 009a797dd242..d56cb03c1b49 100644
---- a/init/Kconfig
-+++ b/init/Kconfig
-@@ -1387,6 +1387,13 @@ config FUTEX
- 	  support for "fast userspace mutexes".  The resulting kernel may not
- 	  run glibc-based applications correctly.
- 
-+config HAVE_FUTEX_CMPXCHG
-+	bool
-+	help
-+	  Architectures should select this if futex_atomic_cmpxchg_inatomic()
-+	  is implemented and always working. This removes a couple of runtime
-+	  checks.
-+
- config EPOLL
- 	bool "Enable eventpoll support" if EXPERT
- 	default y
-diff --git a/kernel/futex.c b/kernel/futex.c
-index 08ec814ad9d2..6801b3751a95 100644
---- a/kernel/futex.c
-+++ b/kernel/futex.c
-@@ -157,7 +157,9 @@
-  * enqueue.
-  */
- 
-+#ifndef CONFIG_HAVE_FUTEX_CMPXCHG
- int __read_mostly futex_cmpxchg_enabled;
-+#endif
- 
- /*
-  * Futex flags used to encode options to functions and preserve them across
-@@ -1450,6 +1452,7 @@ retry:
- 	hb2 = hash_futex(&key2);
- 
- retry_private:
-+	hb_waiters_inc(hb2);
- 	double_lock_hb(hb1, hb2);
- 
- 	if (likely(cmpval != NULL)) {
-@@ -1459,6 +1462,7 @@ retry_private:
- 
- 		if (unlikely(ret)) {
- 			double_unlock_hb(hb1, hb2);
-+			hb_waiters_dec(hb2);
- 
- 			ret = get_user(curval, uaddr1);
- 			if (ret)
-@@ -1508,6 +1512,7 @@ retry_private:
- 			break;
- 		case -EFAULT:
- 			double_unlock_hb(hb1, hb2);
-+			hb_waiters_dec(hb2);
- 			put_futex_key(&key2);
- 			put_futex_key(&key1);
- 			ret = fault_in_user_writeable(uaddr2);
-@@ -1517,6 +1522,7 @@ retry_private:
- 		case -EAGAIN:
- 			/* The owner was exiting, try again. */
- 			double_unlock_hb(hb1, hb2);
-+			hb_waiters_dec(hb2);
- 			put_futex_key(&key2);
- 			put_futex_key(&key1);
- 			cond_resched();
-@@ -1592,6 +1598,7 @@ retry_private:
- 
- out_unlock:
- 	double_unlock_hb(hb1, hb2);
-+	hb_waiters_dec(hb2);
- 
- 	/*
- 	 * drop_futex_key_refs() must be called outside the spinlocks. During
-@@ -2875,9 +2882,28 @@ SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
- 	return do_futex(uaddr, op, val, tp, uaddr2, val2, val3);
- }
- 
--static int __init futex_init(void)
-+static void __init futex_detect_cmpxchg(void)
- {
-+#ifndef CONFIG_HAVE_FUTEX_CMPXCHG
- 	u32 curval;
-+
-+	/*
-+	 * This will fail and we want it. Some arch implementations do
-+	 * runtime detection of the futex_atomic_cmpxchg_inatomic()
-+	 * functionality. We want to know that before we call in any
-+	 * of the complex code paths. Also we want to prevent
-+	 * registration of robust lists in that case. NULL is
-+	 * guaranteed to fault and we get -EFAULT on functional
-+	 * implementation, the non-functional ones will return
-+	 * -ENOSYS.
-+	 */
-+	if (cmpxchg_futex_value_locked(&curval, NULL, 0, 0) == -EFAULT)
-+		futex_cmpxchg_enabled = 1;
-+#endif
-+}
-+
-+static int __init futex_init(void)
-+{
- 	unsigned int futex_shift;
- 	unsigned long i;
- 
-@@ -2893,18 +2919,8 @@ static int __init futex_init(void)
- 					       &futex_shift, NULL,
- 					       futex_hashsize, futex_hashsize);
- 	futex_hashsize = 1UL << futex_shift;
--	/*
--	 * This will fail and we want it. Some arch implementations do
--	 * runtime detection of the futex_atomic_cmpxchg_inatomic()
--	 * functionality. We want to know that before we call in any
--	 * of the complex code paths. Also we want to prevent
--	 * registration of robust lists in that case. NULL is
--	 * guaranteed to fault and we get -EFAULT on functional
--	 * implementation, the non-functional ones will return
--	 * -ENOSYS.
--	 */
--	if (cmpxchg_futex_value_locked(&curval, NULL, 0, 0) == -EFAULT)
--		futex_cmpxchg_enabled = 1;
-+
-+	futex_detect_cmpxchg();
- 
- 	for (i = 0; i < futex_hashsize; i++) {
- 		atomic_set(&futex_queues[i].waiters, 0);
-diff --git a/lib/nlattr.c b/lib/nlattr.c
-index 18eca7809b08..fc6754720ced 100644
---- a/lib/nlattr.c
-+++ b/lib/nlattr.c
-@@ -303,9 +303,15 @@ int nla_memcmp(const struct nlattr *nla, const void *data,
-  */
- int nla_strcmp(const struct nlattr *nla, const char *str)
- {
--	int len = strlen(str) + 1;
--	int d = nla_len(nla) - len;
-+	int len = strlen(str);
-+	char *buf = nla_data(nla);
-+	int attrlen = nla_len(nla);
-+	int d;
- 
-+	if (attrlen > 0 && buf[attrlen - 1] == '\0')
-+		attrlen--;
-+
-+	d = attrlen - len;
- 	if (d == 0)
- 		d = memcmp(nla_data(nla), str, len);
- 
-diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
-index f2610e157660..7b326529e6a2 100644
---- a/net/ipv6/icmp.c
-+++ b/net/ipv6/icmp.c
-@@ -520,7 +520,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
- 			      np->tclass, NULL, &fl6, (struct rt6_info *)dst,
- 			      MSG_DONTWAIT, np->dontfrag);
- 	if (err) {
--		ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTERRORS);
-+		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS);
- 		ip6_flush_pending_frames(sk);
- 	} else {
- 		err = icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr,
-diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
-index 64d6073731d3..3702d179506d 100644
---- a/net/ipv6/ip6_output.c
-+++ b/net/ipv6/ip6_output.c
-@@ -1566,8 +1566,8 @@ int ip6_push_pending_frames(struct sock *sk)
- 	if (proto == IPPROTO_ICMPV6) {
- 		struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
- 
--		ICMP6MSGOUT_INC_STATS_BH(net, idev, icmp6_hdr(skb)->icmp6_type);
--		ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS);
-+		ICMP6MSGOUT_INC_STATS(net, idev, icmp6_hdr(skb)->icmp6_type);
-+		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
- 	}
- 
- 	err = ip6_local_out(skb);
-diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
-index e1e47350784b..08b367c6b9cf 100644
---- a/net/ipv6/mcast.c
-+++ b/net/ipv6/mcast.c
-@@ -1620,11 +1620,12 @@ static void mld_sendpack(struct sk_buff *skb)
- 		      dst_output);
- out:
- 	if (!err) {
--		ICMP6MSGOUT_INC_STATS_BH(net, idev, ICMPV6_MLD2_REPORT);
--		ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS);
--		IP6_UPD_PO_STATS_BH(net, idev, IPSTATS_MIB_OUTMCAST, payload_len);
--	} else
--		IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_OUTDISCARDS);
-+		ICMP6MSGOUT_INC_STATS(net, idev, ICMPV6_MLD2_REPORT);
-+		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
-+		IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, payload_len);
-+	} else {
-+		IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
-+	}
- 
- 	rcu_read_unlock();
- 	return;
-diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
-index 587bbdcb22b4..bda74291c3e0 100644
---- a/net/ipv6/ping.c
-+++ b/net/ipv6/ping.c
-@@ -182,8 +182,8 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
- 			      MSG_DONTWAIT, np->dontfrag);
- 
- 	if (err) {
--		ICMP6_INC_STATS_BH(sock_net(sk), rt->rt6i_idev,
--				   ICMP6_MIB_OUTERRORS);
-+		ICMP6_INC_STATS(sock_net(sk), rt->rt6i_idev,
-+				ICMP6_MIB_OUTERRORS);
- 		ip6_flush_pending_frames(sk);
- 	} else {
- 		err = icmpv6_push_pending_frames(sk, &fl6,
-diff --git a/net/rds/iw.c b/net/rds/iw.c
-index 7826d46baa70..589935661d66 100644
---- a/net/rds/iw.c
-+++ b/net/rds/iw.c
-@@ -239,7 +239,8 @@ static int rds_iw_laddr_check(__be32 addr)
- 	ret = rdma_bind_addr(cm_id, (struct sockaddr *)&sin);
- 	/* due to this, we will claim to support IB devices unless we
- 	   check node_type. */
--	if (ret || cm_id->device->node_type != RDMA_NODE_RNIC)
-+	if (ret || !cm_id->device ||
-+	    cm_id->device->node_type != RDMA_NODE_RNIC)
- 		ret = -EADDRNOTAVAIL;
- 
- 	rdsdebug("addr %pI4 ret %d node type %d\n",
-diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
-index b332e2cc0954..e294b86c8d88 100644
---- a/security/selinux/hooks.c
-+++ b/security/selinux/hooks.c
-@@ -1418,15 +1418,33 @@ static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dent
- 		isec->sid = sbsec->sid;
- 
- 		if ((sbsec->flags & SE_SBPROC) && !S_ISLNK(inode->i_mode)) {
--			if (opt_dentry) {
--				isec->sclass = inode_mode_to_security_class(inode->i_mode);
--				rc = selinux_proc_get_sid(opt_dentry,
--							  isec->sclass,
--							  &sid);
--				if (rc)
--					goto out_unlock;
--				isec->sid = sid;
--			}
-+			/* We must have a dentry to determine the label on
-+			 * procfs inodes */
-+			if (opt_dentry)
-+				/* Called from d_instantiate or
-+				 * d_splice_alias. */
-+				dentry = dget(opt_dentry);
-+			else
-+				/* Called from selinux_complete_init, try to
-+				 * find a dentry. */
-+				dentry = d_find_alias(inode);
-+			/*
-+			 * This can be hit on boot when a file is accessed
-+			 * before the policy is loaded.  When we load policy we
-+			 * may find inodes that have no dentry on the
-+			 * sbsec->isec_head list.  No reason to complain as
-+			 * these will get fixed up the next time we go through
-+			 * inode_doinit() with a dentry, before these inodes
-+			 * could be used again by userspace.
-+			 */
-+			if (!dentry)
-+				goto out_unlock;
-+			isec->sclass = inode_mode_to_security_class(inode->i_mode);
-+			rc = selinux_proc_get_sid(dentry, isec->sclass, &sid);
-+			dput(dentry);
-+			if (rc)
-+				goto out_unlock;
-+			isec->sid = sid;
- 		}
- 		break;
- 	}
-diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
-index e354ab1ec20f..a8dec9e9e876 100644
---- a/sound/pci/hda/hda_intel.c
-+++ b/sound/pci/hda/hda_intel.c
-@@ -297,9 +297,9 @@ enum { SDI0, SDI1, SDI2, SDI3, SDO0, SDO1, SDO2, SDO3 };
- #define ULI_NUM_CAPTURE		5
- #define ULI_NUM_PLAYBACK	6
- 
--/* ATI HDMI may have up to 8 playbacks and 0 capture */
-+/* ATI HDMI has 1 playback and 0 capture */
- #define ATIHDMI_NUM_CAPTURE	0
--#define ATIHDMI_NUM_PLAYBACK	8
-+#define ATIHDMI_NUM_PLAYBACK	1
- 
- /* TERA has 4 playback and 3 capture */
- #define TERA_NUM_CAPTURE	3

Deleted: genpatches-2.6/trunk/3.15/1001_linux-3.14.2.patch
===================================================================
--- genpatches-2.6/trunk/3.15/1001_linux-3.14.2.patch	2014-05-05 14:22:27 UTC (rev 2771)
+++ genpatches-2.6/trunk/3.15/1001_linux-3.14.2.patch	2014-05-05 14:28:48 UTC (rev 2772)
@@ -1,1201 +0,0 @@
-diff --git a/Makefile b/Makefile
-index 7d0b6992d9ed..b2f7de81e9a2 100644
---- a/Makefile
-+++ b/Makefile
-@@ -1,6 +1,6 @@
- VERSION = 3
- PATCHLEVEL = 14
--SUBLEVEL = 1
-+SUBLEVEL = 2
- EXTRAVERSION =
- NAME = Shuffling Zombie Juror
- 
-diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
-index 9f7ca266864a..832d05a914ba 100644
---- a/arch/x86/kernel/cpu/mshyperv.c
-+++ b/arch/x86/kernel/cpu/mshyperv.c
-@@ -26,6 +26,7 @@
- #include <asm/irq_regs.h>
- #include <asm/i8259.h>
- #include <asm/apic.h>
-+#include <asm/timer.h>
- 
- struct ms_hyperv_info ms_hyperv;
- EXPORT_SYMBOL_GPL(ms_hyperv);
-@@ -105,6 +106,11 @@ static void __init ms_hyperv_init_platform(void)
- 
- 	if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE)
- 		clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100);
-+
-+#ifdef CONFIG_X86_IO_APIC
-+	no_timer_check = 1;
-+#endif
-+
- }
- 
- const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = {
-diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
-index bc4a088f9023..6d7d5a1260a6 100644
---- a/arch/x86/kernel/early-quirks.c
-+++ b/arch/x86/kernel/early-quirks.c
-@@ -203,18 +203,15 @@ static void __init intel_remapping_check(int num, int slot, int func)
- 	revision = read_pci_config_byte(num, slot, func, PCI_REVISION_ID);
- 
- 	/*
-- 	 * Revision 13 of all triggering devices id in this quirk have
--	 * a problem draining interrupts when irq remapping is enabled,
--	 * and should be flagged as broken.  Additionally revisions 0x12
--	 * and 0x22 of device id 0x3405 has this problem.
-+	 * Revision <= 13 of all triggering devices id in this quirk
-+	 * have a problem draining interrupts when irq remapping is
-+	 * enabled, and should be flagged as broken. Additionally
-+	 * revision 0x22 of device id 0x3405 has this problem.
- 	 */
--	if (revision == 0x13)
-+	if (revision <= 0x13)
- 		set_irq_remapping_broken();
--	else if ((device == 0x3405) &&
--	    ((revision == 0x12) ||
--	     (revision == 0x22)))
-+	else if (device == 0x3405 && revision == 0x22)
- 		set_irq_remapping_broken();
--
- }
- 
- /*
-diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c
-index 714e957a871a..db35594d4df7 100644
---- a/drivers/acpi/button.c
-+++ b/drivers/acpi/button.c
-@@ -302,6 +302,10 @@ static void acpi_button_notify(struct acpi_device *device, u32 event)
- 			input_sync(input);
- 
- 			pm_wakeup_event(&device->dev, 0);
-+			acpi_bus_generate_netlink_event(
-+					device->pnp.device_class,
-+					dev_name(&device->dev),
-+					event, ++button->pushed);
- 		}
- 		break;
- 	default:
-diff --git a/drivers/char/ipmi/ipmi_bt_sm.c b/drivers/char/ipmi/ipmi_bt_sm.c
-index f5e4cd7617f6..61e71616689b 100644
---- a/drivers/char/ipmi/ipmi_bt_sm.c
-+++ b/drivers/char/ipmi/ipmi_bt_sm.c
-@@ -352,7 +352,7 @@ static inline void write_all_bytes(struct si_sm_data *bt)
- 
- static inline int read_all_bytes(struct si_sm_data *bt)
- {
--	unsigned char i;
-+	unsigned int i;
- 
- 	/*
- 	 * length is "framing info", minimum = 4: NetFn, Seq, Cmd, cCode.
-diff --git a/drivers/pci/host/pcie-designware.c b/drivers/pci/host/pcie-designware.c
-index 17ce88f79d2b..f173dd09fce4 100644
---- a/drivers/pci/host/pcie-designware.c
-+++ b/drivers/pci/host/pcie-designware.c
-@@ -522,13 +522,13 @@ static void dw_pcie_prog_viewport_cfg1(struct pcie_port *pp, u32 busdev)
- 	dw_pcie_writel_rc(pp, PCIE_ATU_REGION_OUTBOUND | PCIE_ATU_REGION_INDEX1,
- 			  PCIE_ATU_VIEWPORT);
- 	dw_pcie_writel_rc(pp, PCIE_ATU_TYPE_CFG1, PCIE_ATU_CR1);
--	dw_pcie_writel_rc(pp, PCIE_ATU_ENABLE, PCIE_ATU_CR2);
- 	dw_pcie_writel_rc(pp, pp->cfg1_base, PCIE_ATU_LOWER_BASE);
- 	dw_pcie_writel_rc(pp, (pp->cfg1_base >> 32), PCIE_ATU_UPPER_BASE);
- 	dw_pcie_writel_rc(pp, pp->cfg1_base + pp->config.cfg1_size - 1,
- 			  PCIE_ATU_LIMIT);
- 	dw_pcie_writel_rc(pp, busdev, PCIE_ATU_LOWER_TARGET);
- 	dw_pcie_writel_rc(pp, 0, PCIE_ATU_UPPER_TARGET);
-+	dw_pcie_writel_rc(pp, PCIE_ATU_ENABLE, PCIE_ATU_CR2);
- }
- 
- static void dw_pcie_prog_viewport_mem_outbound(struct pcie_port *pp)
-@@ -537,7 +537,6 @@ static void dw_pcie_prog_viewport_mem_outbound(struct pcie_port *pp)
- 	dw_pcie_writel_rc(pp, PCIE_ATU_REGION_OUTBOUND | PCIE_ATU_REGION_INDEX0,
- 			  PCIE_ATU_VIEWPORT);
- 	dw_pcie_writel_rc(pp, PCIE_ATU_TYPE_MEM, PCIE_ATU_CR1);
--	dw_pcie_writel_rc(pp, PCIE_ATU_ENABLE, PCIE_ATU_CR2);
- 	dw_pcie_writel_rc(pp, pp->mem_base, PCIE_ATU_LOWER_BASE);
- 	dw_pcie_writel_rc(pp, (pp->mem_base >> 32), PCIE_ATU_UPPER_BASE);
- 	dw_pcie_writel_rc(pp, pp->mem_base + pp->config.mem_size - 1,
-@@ -545,6 +544,7 @@ static void dw_pcie_prog_viewport_mem_outbound(struct pcie_port *pp)
- 	dw_pcie_writel_rc(pp, pp->config.mem_bus_addr, PCIE_ATU_LOWER_TARGET);
- 	dw_pcie_writel_rc(pp, upper_32_bits(pp->config.mem_bus_addr),
- 			  PCIE_ATU_UPPER_TARGET);
-+	dw_pcie_writel_rc(pp, PCIE_ATU_ENABLE, PCIE_ATU_CR2);
- }
- 
- static void dw_pcie_prog_viewport_io_outbound(struct pcie_port *pp)
-@@ -553,7 +553,6 @@ static void dw_pcie_prog_viewport_io_outbound(struct pcie_port *pp)
- 	dw_pcie_writel_rc(pp, PCIE_ATU_REGION_OUTBOUND | PCIE_ATU_REGION_INDEX1,
- 			  PCIE_ATU_VIEWPORT);
- 	dw_pcie_writel_rc(pp, PCIE_ATU_TYPE_IO, PCIE_ATU_CR1);
--	dw_pcie_writel_rc(pp, PCIE_ATU_ENABLE, PCIE_ATU_CR2);
- 	dw_pcie_writel_rc(pp, pp->io_base, PCIE_ATU_LOWER_BASE);
- 	dw_pcie_writel_rc(pp, (pp->io_base >> 32), PCIE_ATU_UPPER_BASE);
- 	dw_pcie_writel_rc(pp, pp->io_base + pp->config.io_size - 1,
-@@ -561,6 +560,7 @@ static void dw_pcie_prog_viewport_io_outbound(struct pcie_port *pp)
- 	dw_pcie_writel_rc(pp, pp->config.io_bus_addr, PCIE_ATU_LOWER_TARGET);
- 	dw_pcie_writel_rc(pp, upper_32_bits(pp->config.io_bus_addr),
- 			  PCIE_ATU_UPPER_TARGET);
-+	dw_pcie_writel_rc(pp, PCIE_ATU_ENABLE, PCIE_ATU_CR2);
- }
- 
- static int dw_pcie_rd_other_conf(struct pcie_port *pp, struct pci_bus *bus,
-@@ -800,7 +800,7 @@ void dw_pcie_setup_rc(struct pcie_port *pp)
- 
- 	/* setup RC BARs */
- 	dw_pcie_writel_rc(pp, 0x00000004, PCI_BASE_ADDRESS_0);
--	dw_pcie_writel_rc(pp, 0x00000004, PCI_BASE_ADDRESS_1);
-+	dw_pcie_writel_rc(pp, 0x00000000, PCI_BASE_ADDRESS_1);
- 
- 	/* setup interrupt pins */
- 	dw_pcie_readl_rc(pp, PCI_INTERRUPT_LINE, &val);
-diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
-index 470954aba728..36d1a23f14be 100644
---- a/drivers/scsi/sd.c
-+++ b/drivers/scsi/sd.c
-@@ -1463,8 +1463,8 @@ static int sd_sync_cache(struct scsi_disk *sdkp)
- 			sd_print_sense_hdr(sdkp, &sshdr);
- 		/* we need to evaluate the error return  */
- 		if (scsi_sense_valid(&sshdr) &&
--			/* 0x3a is medium not present */
--			sshdr.asc == 0x3a)
-+			(sshdr.asc == 0x3a ||	/* medium not present */
-+			 sshdr.asc == 0x20))	/* invalid command */
- 				/* this is no error here */
- 				return 0;
- 
-diff --git a/drivers/staging/comedi/comedi_buf.c b/drivers/staging/comedi/comedi_buf.c
-index 924fce977985..257595016161 100644
---- a/drivers/staging/comedi/comedi_buf.c
-+++ b/drivers/staging/comedi/comedi_buf.c
-@@ -61,6 +61,8 @@ static void __comedi_buf_free(struct comedi_device *dev,
- 			      struct comedi_subdevice *s)
- {
- 	struct comedi_async *async = s->async;
-+	struct comedi_buf_map *bm;
-+	unsigned long flags;
- 
- 	if (async->prealloc_buf) {
- 		vunmap(async->prealloc_buf);
-@@ -68,8 +70,11 @@ static void __comedi_buf_free(struct comedi_device *dev,
- 		async->prealloc_bufsz = 0;
- 	}
- 
--	comedi_buf_map_put(async->buf_map);
-+	spin_lock_irqsave(&s->spin_lock, flags);
-+	bm = async->buf_map;
- 	async->buf_map = NULL;
-+	spin_unlock_irqrestore(&s->spin_lock, flags);
-+	comedi_buf_map_put(bm);
- }
- 
- static void __comedi_buf_alloc(struct comedi_device *dev,
-@@ -80,6 +85,7 @@ static void __comedi_buf_alloc(struct comedi_device *dev,
- 	struct page **pages = NULL;
- 	struct comedi_buf_map *bm;
- 	struct comedi_buf_page *buf;
-+	unsigned long flags;
- 	unsigned i;
- 
- 	if (!IS_ENABLED(CONFIG_HAS_DMA) && s->async_dma_dir != DMA_NONE) {
-@@ -92,8 +98,10 @@ static void __comedi_buf_alloc(struct comedi_device *dev,
- 	if (!bm)
- 		return;
- 
--	async->buf_map = bm;
- 	kref_init(&bm->refcount);
-+	spin_lock_irqsave(&s->spin_lock, flags);
-+	async->buf_map = bm;
-+	spin_unlock_irqrestore(&s->spin_lock, flags);
- 	bm->dma_dir = s->async_dma_dir;
- 	if (bm->dma_dir != DMA_NONE)
- 		/* Need ref to hardware device to free buffer later. */
-@@ -127,7 +135,9 @@ static void __comedi_buf_alloc(struct comedi_device *dev,
- 
- 		pages[i] = virt_to_page(buf->virt_addr);
- 	}
-+	spin_lock_irqsave(&s->spin_lock, flags);
- 	bm->n_pages = i;
-+	spin_unlock_irqrestore(&s->spin_lock, flags);
- 
- 	/* vmap the prealloc_buf if all the pages were allocated */
- 	if (i == n_pages)
-@@ -150,6 +160,29 @@ int comedi_buf_map_put(struct comedi_buf_map *bm)
- 	return 1;
- }
- 
-+/* returns s->async->buf_map and increments its kref refcount */
-+struct comedi_buf_map *
-+comedi_buf_map_from_subdev_get(struct comedi_subdevice *s)
-+{
-+	struct comedi_async *async = s->async;
-+	struct comedi_buf_map *bm = NULL;
-+	unsigned long flags;
-+
-+	if (!async)
-+		return NULL;
-+
-+	spin_lock_irqsave(&s->spin_lock, flags);
-+	bm = async->buf_map;
-+	/* only want it if buffer pages allocated */
-+	if (bm && bm->n_pages)
-+		comedi_buf_map_get(bm);
-+	else
-+		bm = NULL;
-+	spin_unlock_irqrestore(&s->spin_lock, flags);
-+
-+	return bm;
-+}
-+
- bool comedi_buf_is_mmapped(struct comedi_async *async)
- {
- 	struct comedi_buf_map *bm = async->buf_map;
-diff --git a/drivers/staging/comedi/comedi_fops.c b/drivers/staging/comedi/comedi_fops.c
-index c22c617b0da1..eae3ee139330 100644
---- a/drivers/staging/comedi/comedi_fops.c
-+++ b/drivers/staging/comedi/comedi_fops.c
-@@ -1923,14 +1923,21 @@ static int comedi_mmap(struct file *file, struct vm_area_struct *vma)
- 	struct comedi_device *dev = file->private_data;
- 	struct comedi_subdevice *s;
- 	struct comedi_async *async;
--	struct comedi_buf_map *bm;
-+	struct comedi_buf_map *bm = NULL;
- 	unsigned long start = vma->vm_start;
- 	unsigned long size;
- 	int n_pages;
- 	int i;
- 	int retval;
- 
--	mutex_lock(&dev->mutex);
-+	/*
-+	 * 'trylock' avoids circular dependency with current->mm->mmap_sem
-+	 * and down-reading &dev->attach_lock should normally succeed without
-+	 * contention unless the device is in the process of being attached
-+	 * or detached.
-+	 */
-+	if (!down_read_trylock(&dev->attach_lock))
-+		return -EAGAIN;
- 
- 	if (!dev->attached) {
- 		dev_dbg(dev->class_dev, "no driver attached\n");
-@@ -1970,7 +1977,9 @@ static int comedi_mmap(struct file *file, struct vm_area_struct *vma)
- 	}
- 
- 	n_pages = size >> PAGE_SHIFT;
--	bm = async->buf_map;
-+
-+	/* get reference to current buf map (if any) */
-+	bm = comedi_buf_map_from_subdev_get(s);
- 	if (!bm || n_pages > bm->n_pages) {
- 		retval = -EINVAL;
- 		goto done;
-@@ -1994,7 +2003,8 @@ static int comedi_mmap(struct file *file, struct vm_area_struct *vma)
- 
- 	retval = 0;
- done:
--	mutex_unlock(&dev->mutex);
-+	up_read(&dev->attach_lock);
-+	comedi_buf_map_put(bm);	/* put reference to buf map - okay if NULL */
- 	return retval;
- }
- 
-diff --git a/drivers/staging/comedi/comedi_internal.h b/drivers/staging/comedi/comedi_internal.h
-index 9a746570f161..a492f2d2436e 100644
---- a/drivers/staging/comedi/comedi_internal.h
-+++ b/drivers/staging/comedi/comedi_internal.h
-@@ -19,6 +19,8 @@ void comedi_buf_reset(struct comedi_async *async);
- bool comedi_buf_is_mmapped(struct comedi_async *async);
- void comedi_buf_map_get(struct comedi_buf_map *bm);
- int comedi_buf_map_put(struct comedi_buf_map *bm);
-+struct comedi_buf_map *comedi_buf_map_from_subdev_get(
-+		struct comedi_subdevice *s);
- unsigned int comedi_buf_write_n_allocated(struct comedi_async *async);
- void comedi_device_cancel_all(struct comedi_device *dev);
- 
-diff --git a/drivers/staging/comedi/drivers/8255_pci.c b/drivers/staging/comedi/drivers/8255_pci.c
-index 8a57c3c1ade0..1097dc6a3086 100644
---- a/drivers/staging/comedi/drivers/8255_pci.c
-+++ b/drivers/staging/comedi/drivers/8255_pci.c
-@@ -56,6 +56,7 @@ Configuration Options: not applicable, uses PCI auto config
- #include "../comedidev.h"
- 
- #include "8255.h"
-+#include "mite.h"
- 
- enum pci_8255_boardid {
- 	BOARD_ADLINK_PCI7224,
-@@ -79,6 +80,7 @@ struct pci_8255_boardinfo {
- 	const char *name;
- 	int dio_badr;
- 	int n_8255;
-+	unsigned int has_mite:1;
- };
- 
- static const struct pci_8255_boardinfo pci_8255_boards[] = {
-@@ -126,36 +128,43 @@ static const struct pci_8255_boardinfo pci_8255_boards[] = {
- 		.name		= "ni_pci-dio-96",
- 		.dio_badr	= 1,
- 		.n_8255		= 4,
-+		.has_mite	= 1,
- 	},
- 	[BOARD_NI_PCIDIO96B] = {
- 		.name		= "ni_pci-dio-96b",
- 		.dio_badr	= 1,
- 		.n_8255		= 4,
-+		.has_mite	= 1,
- 	},
- 	[BOARD_NI_PXI6508] = {
- 		.name		= "ni_pxi-6508",
- 		.dio_badr	= 1,
- 		.n_8255		= 4,
-+		.has_mite	= 1,
- 	},
- 	[BOARD_NI_PCI6503] = {
- 		.name		= "ni_pci-6503",
- 		.dio_badr	= 1,
- 		.n_8255		= 1,
-+		.has_mite	= 1,
- 	},
- 	[BOARD_NI_PCI6503B] = {
- 		.name		= "ni_pci-6503b",
- 		.dio_badr	= 1,
- 		.n_8255		= 1,
-+		.has_mite	= 1,
- 	},
- 	[BOARD_NI_PCI6503X] = {
- 		.name		= "ni_pci-6503x",
- 		.dio_badr	= 1,
- 		.n_8255		= 1,
-+		.has_mite	= 1,
- 	},
- 	[BOARD_NI_PXI_6503] = {
- 		.name		= "ni_pxi-6503",
- 		.dio_badr	= 1,
- 		.n_8255		= 1,
-+		.has_mite	= 1,
- 	},
- };
- 
-@@ -163,6 +172,25 @@ struct pci_8255_private {
- 	void __iomem *mmio_base;
- };
- 
-+static int pci_8255_mite_init(struct pci_dev *pcidev)
-+{
-+	void __iomem *mite_base;
-+	u32 main_phys_addr;
-+
-+	/* ioremap the MITE registers (BAR 0) temporarily */
-+	mite_base = pci_ioremap_bar(pcidev, 0);
-+	if (!mite_base)
-+		return -ENOMEM;
-+
-+	/* set data window to main registers (BAR 1) */
-+	main_phys_addr = pci_resource_start(pcidev, 1);
-+	writel(main_phys_addr | WENAB, mite_base + MITE_IODWBSR);
-+
-+	/* finished with MITE registers */
-+	iounmap(mite_base);
-+	return 0;
-+}
-+
- static int pci_8255_mmio(int dir, int port, int data, unsigned long iobase)
- {
- 	void __iomem *mmio_base = (void __iomem *)iobase;
-@@ -201,6 +229,12 @@ static int pci_8255_auto_attach(struct comedi_device *dev,
- 	if (ret)
- 		return ret;
- 
-+	if (board->has_mite) {
-+		ret = pci_8255_mite_init(pcidev);
-+		if (ret)
-+			return ret;
-+	}
-+
- 	is_mmio = (pci_resource_flags(pcidev, board->dio_badr) &
- 		   IORESOURCE_MEM) != 0;
- 	if (is_mmio) {
-diff --git a/drivers/tty/ipwireless/tty.c b/drivers/tty/ipwireless/tty.c
-index ebd5bff0f5c1..17ee3bf0926b 100644
---- a/drivers/tty/ipwireless/tty.c
-+++ b/drivers/tty/ipwireless/tty.c
-@@ -176,9 +176,6 @@ void ipwireless_tty_received(struct ipw_tty *tty, unsigned char *data,
- 				": %d chars not inserted to flip buffer!\n",
- 				length - work);
- 
--	/*
--	 * This may sleep if ->low_latency is set
--	 */
- 	if (work)
- 		tty_flip_buffer_push(&tty->port);
- }
-diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c
-index 765125dff20e..8ebd9f88a6f6 100644
---- a/drivers/tty/tty_buffer.c
-+++ b/drivers/tty/tty_buffer.c
-@@ -351,14 +351,11 @@ EXPORT_SYMBOL(tty_insert_flip_string_flags);
-  *	Takes any pending buffers and transfers their ownership to the
-  *	ldisc side of the queue. It then schedules those characters for
-  *	processing by the line discipline.
-- *	Note that this function can only be used when the low_latency flag
-- *	is unset. Otherwise the workqueue won't be flushed.
-  */
- 
- void tty_schedule_flip(struct tty_port *port)
- {
- 	struct tty_bufhead *buf = &port->buf;
--	WARN_ON(port->low_latency);
- 
- 	buf->tail->commit = buf->tail->used;
- 	schedule_work(&buf->work);
-@@ -482,17 +479,15 @@ static void flush_to_ldisc(struct work_struct *work)
-  */
- void tty_flush_to_ldisc(struct tty_struct *tty)
- {
--	if (!tty->port->low_latency)
--		flush_work(&tty->port->buf.work);
-+	flush_work(&tty->port->buf.work);
- }
- 
- /**
-  *	tty_flip_buffer_push	-	terminal
-  *	@port: tty port to push
-  *
-- *	Queue a push of the terminal flip buffers to the line discipline. This
-- *	function must not be called from IRQ context if port->low_latency is
-- *	set.
-+ *	Queue a push of the terminal flip buffers to the line discipline.
-+ *	Can be called from IRQ/atomic context.
-  *
-  *	In the event of the queue being busy for flipping the work will be
-  *	held off and retried later.
-@@ -500,14 +495,7 @@ void tty_flush_to_ldisc(struct tty_struct *tty)
- 
- void tty_flip_buffer_push(struct tty_port *port)
- {
--	struct tty_bufhead *buf = &port->buf;
--
--	buf->tail->commit = buf->tail->used;
--
--	if (port->low_latency)
--		flush_to_ldisc(&buf->work);
--	else
--		schedule_work(&buf->work);
-+	tty_schedule_flip(port);
- }
- EXPORT_SYMBOL(tty_flip_buffer_push);
- 
-diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
-index c74a00ad7add..d3448a90f0f9 100644
---- a/drivers/tty/tty_io.c
-+++ b/drivers/tty/tty_io.c
-@@ -1271,12 +1271,13 @@ static void pty_line_name(struct tty_driver *driver, int index, char *p)
-  *
-  *	Locking: None
-  */
--static void tty_line_name(struct tty_driver *driver, int index, char *p)
-+static ssize_t tty_line_name(struct tty_driver *driver, int index, char *p)
- {
- 	if (driver->flags & TTY_DRIVER_UNNUMBERED_NODE)
--		strcpy(p, driver->name);
-+		return sprintf(p, "%s", driver->name);
- 	else
--		sprintf(p, "%s%d", driver->name, index + driver->name_base);
-+		return sprintf(p, "%s%d", driver->name,
-+			       index + driver->name_base);
- }
- 
- /**
-@@ -3545,9 +3546,19 @@ static ssize_t show_cons_active(struct device *dev,
- 		if (i >= ARRAY_SIZE(cs))
- 			break;
- 	}
--	while (i--)
--		count += sprintf(buf + count, "%s%d%c",
--				 cs[i]->name, cs[i]->index, i ? ' ':'\n');
-+	while (i--) {
-+		int index = cs[i]->index;
-+		struct tty_driver *drv = cs[i]->device(cs[i], &index);
-+
-+		/* don't resolve tty0 as some programs depend on it */
-+		if (drv && (cs[i]->index > 0 || drv->major != TTY_MAJOR))
-+			count += tty_line_name(drv, index, buf + count);
-+		else
-+			count += sprintf(buf + count, "%s%d",
-+					 cs[i]->name, cs[i]->index);
-+
-+		count += sprintf(buf + count, "%c", i ? ' ':'\n');
-+	}
- 	console_unlock();
- 
- 	return count;
-diff --git a/drivers/usb/gadget/u_serial.c b/drivers/usb/gadget/u_serial.c
-index b369292d4b90..ad0aca812002 100644
---- a/drivers/usb/gadget/u_serial.c
-+++ b/drivers/usb/gadget/u_serial.c
-@@ -549,8 +549,8 @@ static void gs_rx_push(unsigned long _port)
- 		port->read_started--;
- 	}
- 
--	/* Push from tty to ldisc; without low_latency set this is handled by
--	 * a workqueue, so we won't get callbacks and can hold port_lock
-+	/* Push from tty to ldisc; this is handled by a workqueue,
-+	 * so we won't get callbacks and can hold port_lock
- 	 */
- 	if (do_push)
- 		tty_flip_buffer_push(&port->port);
-diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
-index 81ea55314b1f..9a527a1826df 100644
---- a/fs/btrfs/disk-io.c
-+++ b/fs/btrfs/disk-io.c
-@@ -3244,6 +3244,8 @@ static int barrier_all_devices(struct btrfs_fs_info *info)
- 	/* send down all the barriers */
- 	head = &info->fs_devices->devices;
- 	list_for_each_entry_rcu(dev, head, dev_list) {
-+		if (dev->missing)
-+			continue;
- 		if (!dev->bdev) {
- 			errors_send++;
- 			continue;
-@@ -3258,6 +3260,8 @@ static int barrier_all_devices(struct btrfs_fs_info *info)
- 
- 	/* wait for all the barriers */
- 	list_for_each_entry_rcu(dev, head, dev_list) {
-+		if (dev->missing)
-+			continue;
- 		if (!dev->bdev) {
- 			errors_wait++;
- 			continue;
-diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
-index 32312e09f0f5..3c8e68da9ef8 100644
---- a/fs/btrfs/extent-tree.c
-+++ b/fs/btrfs/extent-tree.c
-@@ -2444,7 +2444,8 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
- 			spin_unlock(&locked_ref->lock);
- 			spin_lock(&delayed_refs->lock);
- 			spin_lock(&locked_ref->lock);
--			if (rb_first(&locked_ref->ref_root)) {
-+			if (rb_first(&locked_ref->ref_root) ||
-+			    locked_ref->extent_op) {
- 				spin_unlock(&locked_ref->lock);
- 				spin_unlock(&delayed_refs->lock);
- 				continue;
-diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
-index 34cd83184c4a..b05bf58b9395 100644
---- a/fs/btrfs/transaction.c
-+++ b/fs/btrfs/transaction.c
-@@ -683,7 +683,8 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
- 	int lock = (trans->type != TRANS_JOIN_NOLOCK);
- 	int err = 0;
- 
--	if (--trans->use_count) {
-+	if (trans->use_count > 1) {
-+		trans->use_count--;
- 		trans->block_rsv = trans->orig_rsv;
- 		return 0;
- 	}
-@@ -731,17 +732,10 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
- 	}
- 
- 	if (lock && ACCESS_ONCE(cur_trans->state) == TRANS_STATE_BLOCKED) {
--		if (throttle) {
--			/*
--			 * We may race with somebody else here so end up having
--			 * to call end_transaction on ourselves again, so inc
--			 * our use_count.
--			 */
--			trans->use_count++;
-+		if (throttle)
- 			return btrfs_commit_transaction(trans, root);
--		} else {
-+		else
- 			wake_up_process(info->transaction_kthread);
--		}
- 	}
- 
- 	if (trans->type & __TRANS_FREEZABLE)
-diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
-index 74bc2d549c58..47188916dd8d 100644
---- a/fs/ext4/extents.c
-+++ b/fs/ext4/extents.c
-@@ -2585,6 +2585,27 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
- 	ex_ee_block = le32_to_cpu(ex->ee_block);
- 	ex_ee_len = ext4_ext_get_actual_len(ex);
- 
-+	/*
-+	 * If we're starting with an extent other than the last one in the
-+	 * node, we need to see if it shares a cluster with the extent to
-+	 * the right (towards the end of the file). If its leftmost cluster
-+	 * is this extent's rightmost cluster and it is not cluster aligned,
-+	 * we'll mark it as a partial that is not to be deallocated.
-+	 */
-+
-+	if (ex != EXT_LAST_EXTENT(eh)) {
-+		ext4_fsblk_t current_pblk, right_pblk;
-+		long long current_cluster, right_cluster;
-+
-+		current_pblk = ext4_ext_pblock(ex) + ex_ee_len - 1;
-+		current_cluster = (long long)EXT4_B2C(sbi, current_pblk);
-+		right_pblk = ext4_ext_pblock(ex + 1);
-+		right_cluster = (long long)EXT4_B2C(sbi, right_pblk);
-+		if (current_cluster == right_cluster &&
-+			EXT4_PBLK_COFF(sbi, right_pblk))
-+			*partial_cluster = -right_cluster;
-+	}
-+
- 	trace_ext4_ext_rm_leaf(inode, start, ex, *partial_cluster);
- 
- 	while (ex >= EXT_FIRST_EXTENT(eh) &&
-@@ -2710,10 +2731,15 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
- 		err = ext4_ext_correct_indexes(handle, inode, path);
- 
- 	/*
--	 * Free the partial cluster only if the current extent does not
--	 * reference it. Otherwise we might free used cluster.
-+	 * If there's a partial cluster and at least one extent remains in
-+	 * the leaf, free the partial cluster if it isn't shared with the
-+	 * current extent.  If there's a partial cluster and no extents
-+	 * remain in the leaf, it can't be freed here.  It can only be
-+	 * freed when it's possible to determine if it's not shared with
-+	 * any other extent - when the next leaf is processed or when space
-+	 * removal is complete.
- 	 */
--	if (*partial_cluster > 0 &&
-+	if (*partial_cluster > 0 && eh->eh_entries &&
- 	    (EXT4_B2C(sbi, ext4_ext_pblock(ex) + ex_ee_len - 1) !=
- 	     *partial_cluster)) {
- 		int flags = get_default_free_blocks_flags(inode);
-@@ -4128,7 +4154,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
- 	struct ext4_extent newex, *ex, *ex2;
- 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
- 	ext4_fsblk_t newblock = 0;
--	int free_on_err = 0, err = 0, depth;
-+	int free_on_err = 0, err = 0, depth, ret;
- 	unsigned int allocated = 0, offset = 0;
- 	unsigned int allocated_clusters = 0;
- 	struct ext4_allocation_request ar;
-@@ -4189,9 +4215,13 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
- 			if (!ext4_ext_is_uninitialized(ex))
- 				goto out;
- 
--			allocated = ext4_ext_handle_uninitialized_extents(
-+			ret = ext4_ext_handle_uninitialized_extents(
- 				handle, inode, map, path, flags,
- 				allocated, newblock);
-+			if (ret < 0)
-+				err = ret;
-+			else
-+				allocated = ret;
- 			goto out3;
- 		}
- 	}
-diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
-index d754e3cf99a8..a16315957ef3 100644
---- a/fs/fs-writeback.c
-+++ b/fs/fs-writeback.c
-@@ -89,16 +89,29 @@ static inline struct inode *wb_inode(struct list_head *head)
- #define CREATE_TRACE_POINTS
- #include <trace/events/writeback.h>
- 
-+static void bdi_wakeup_thread(struct backing_dev_info *bdi)
-+{
-+	spin_lock_bh(&bdi->wb_lock);
-+	if (test_bit(BDI_registered, &bdi->state))
-+		mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
-+	spin_unlock_bh(&bdi->wb_lock);
-+}
-+
- static void bdi_queue_work(struct backing_dev_info *bdi,
- 			   struct wb_writeback_work *work)
- {
- 	trace_writeback_queue(bdi, work);
- 
- 	spin_lock_bh(&bdi->wb_lock);
-+	if (!test_bit(BDI_registered, &bdi->state)) {
-+		if (work->done)
-+			complete(work->done);
-+		goto out_unlock;
-+	}
- 	list_add_tail(&work->list, &bdi->work_list);
--	spin_unlock_bh(&bdi->wb_lock);
--
- 	mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
-+out_unlock:
-+	spin_unlock_bh(&bdi->wb_lock);
- }
- 
- static void
-@@ -114,7 +127,7 @@ __bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
- 	work = kzalloc(sizeof(*work), GFP_ATOMIC);
- 	if (!work) {
- 		trace_writeback_nowork(bdi);
--		mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
-+		bdi_wakeup_thread(bdi);
- 		return;
- 	}
- 
-@@ -161,7 +174,7 @@ void bdi_start_background_writeback(struct backing_dev_info *bdi)
- 	 * writeback as soon as there is no other work to do.
- 	 */
- 	trace_writeback_wake_background(bdi);
--	mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
-+	bdi_wakeup_thread(bdi);
- }
- 
- /*
-@@ -1017,7 +1030,7 @@ void bdi_writeback_workfn(struct work_struct *work)
- 	current->flags |= PF_SWAPWRITE;
- 
- 	if (likely(!current_is_workqueue_rescuer() ||
--		   list_empty(&bdi->bdi_list))) {
-+		   !test_bit(BDI_registered, &bdi->state))) {
- 		/*
- 		 * The normal path.  Keep writing back @bdi until its
- 		 * work_list is empty.  Note that this path is also taken
-@@ -1039,10 +1052,10 @@ void bdi_writeback_workfn(struct work_struct *work)
- 		trace_writeback_pages_written(pages_written);
- 	}
- 
--	if (!list_empty(&bdi->work_list) ||
--	    (wb_has_dirty_io(wb) && dirty_writeback_interval))
--		queue_delayed_work(bdi_wq, &wb->dwork,
--			msecs_to_jiffies(dirty_writeback_interval * 10));
-+	if (!list_empty(&bdi->work_list))
-+		mod_delayed_work(bdi_wq, &wb->dwork, 0);
-+	else if (wb_has_dirty_io(wb) && dirty_writeback_interval)
-+		bdi_wakeup_thread_delayed(bdi);
- 
- 	current->flags &= ~PF_SWAPWRITE;
- }
-diff --git a/fs/jffs2/compr_rtime.c b/fs/jffs2/compr_rtime.c
-index 16a5047903a6..406d9cc84ba8 100644
---- a/fs/jffs2/compr_rtime.c
-+++ b/fs/jffs2/compr_rtime.c
-@@ -33,7 +33,7 @@ static int jffs2_rtime_compress(unsigned char *data_in,
- 				unsigned char *cpage_out,
- 				uint32_t *sourcelen, uint32_t *dstlen)
- {
--	short positions[256];
-+	unsigned short positions[256];
- 	int outpos = 0;
- 	int pos=0;
- 
-@@ -74,7 +74,7 @@ static int jffs2_rtime_decompress(unsigned char *data_in,
- 				  unsigned char *cpage_out,
- 				  uint32_t srclen, uint32_t destlen)
- {
--	short positions[256];
-+	unsigned short positions[256];
- 	int outpos = 0;
- 	int pos=0;
- 
-diff --git a/fs/jffs2/nodelist.h b/fs/jffs2/nodelist.h
-index e4619b00f7c5..fa35ff79ab35 100644
---- a/fs/jffs2/nodelist.h
-+++ b/fs/jffs2/nodelist.h
-@@ -231,7 +231,7 @@ struct jffs2_tmp_dnode_info
- 	uint32_t version;
- 	uint32_t data_crc;
- 	uint32_t partial_crc;
--	uint16_t csize;
-+	uint32_t csize;
- 	uint16_t overlapped;
- };
- 
-diff --git a/fs/jffs2/nodemgmt.c b/fs/jffs2/nodemgmt.c
-index 03310721712f..b6bd4affd9ad 100644
---- a/fs/jffs2/nodemgmt.c
-+++ b/fs/jffs2/nodemgmt.c
-@@ -179,6 +179,7 @@ int jffs2_reserve_space(struct jffs2_sb_info *c, uint32_t minsize,
- 					spin_unlock(&c->erase_completion_lock);
- 
- 					schedule();
-+					remove_wait_queue(&c->erase_wait, &wait);
- 				} else
- 					spin_unlock(&c->erase_completion_lock);
- 			} else if (ret)
-@@ -211,20 +212,25 @@ out:
- int jffs2_reserve_space_gc(struct jffs2_sb_info *c, uint32_t minsize,
- 			   uint32_t *len, uint32_t sumsize)
- {
--	int ret = -EAGAIN;
-+	int ret;
- 	minsize = PAD(minsize);
- 
- 	jffs2_dbg(1, "%s(): Requested 0x%x bytes\n", __func__, minsize);
- 
--	spin_lock(&c->erase_completion_lock);
--	while(ret == -EAGAIN) {
-+	while (true) {
-+		spin_lock(&c->erase_completion_lock);
- 		ret = jffs2_do_reserve_space(c, minsize, len, sumsize);
- 		if (ret) {
- 			jffs2_dbg(1, "%s(): looping, ret is %d\n",
- 				  __func__, ret);
- 		}
-+		spin_unlock(&c->erase_completion_lock);
-+
-+		if (ret == -EAGAIN)
-+			cond_resched();
-+		else
-+			break;
- 	}
--	spin_unlock(&c->erase_completion_lock);
- 	if (!ret)
- 		ret = jffs2_prealloc_raw_node_refs(c, c->nextblock, 1);
- 
-diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
-index bd6e18be6e1a..39c0143fb3af 100644
---- a/fs/kernfs/dir.c
-+++ b/fs/kernfs/dir.c
-@@ -37,7 +37,7 @@ static unsigned int kernfs_name_hash(const char *name, const void *ns)
- 	hash = (end_name_hash(hash) ^ hash_ptr((void *)ns, 31));
- 	hash &= 0x7fffffffU;
- 	/* Reserve hash numbers 0, 1 and INT_MAX for magic directory entries */
--	if (hash < 1)
-+	if (hash < 2)
- 		hash += 2;
- 	if (hash >= INT_MAX)
- 		hash = INT_MAX - 1;
-diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c
-index e55126f85bd2..553946c9d952 100644
---- a/fs/kernfs/inode.c
-+++ b/fs/kernfs/inode.c
-@@ -48,14 +48,18 @@ void __init kernfs_inode_init(void)
- 
- static struct kernfs_iattrs *kernfs_iattrs(struct kernfs_node *kn)
- {
-+	static DEFINE_MUTEX(iattr_mutex);
-+	struct kernfs_iattrs *ret;
- 	struct iattr *iattrs;
- 
-+	mutex_lock(&iattr_mutex);
-+
- 	if (kn->iattr)
--		return kn->iattr;
-+		goto out_unlock;
- 
- 	kn->iattr = kzalloc(sizeof(struct kernfs_iattrs), GFP_KERNEL);
- 	if (!kn->iattr)
--		return NULL;
-+		goto out_unlock;
- 	iattrs = &kn->iattr->ia_iattr;
- 
- 	/* assign default attributes */
-@@ -65,8 +69,10 @@ static struct kernfs_iattrs *kernfs_iattrs(struct kernfs_node *kn)
- 	iattrs->ia_atime = iattrs->ia_mtime = iattrs->ia_ctime = CURRENT_TIME;
- 
- 	simple_xattrs_init(&kn->iattr->xattrs);
--
--	return kn->iattr;
-+out_unlock:
-+	ret = kn->iattr;
-+	mutex_unlock(&iattr_mutex);
-+	return ret;
- }
- 
- static int __kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr)
-diff --git a/fs/posix_acl.c b/fs/posix_acl.c
-index 11c54fd51e16..9e363e41dacc 100644
---- a/fs/posix_acl.c
-+++ b/fs/posix_acl.c
-@@ -723,7 +723,7 @@ posix_acl_to_xattr(struct user_namespace *user_ns, const struct posix_acl *acl,
- 		   void *buffer, size_t size)
- {
- 	posix_acl_xattr_header *ext_acl = (posix_acl_xattr_header *)buffer;
--	posix_acl_xattr_entry *ext_entry = ext_acl->a_entries;
-+	posix_acl_xattr_entry *ext_entry;
- 	int real_size, n;
- 
- 	real_size = posix_acl_xattr_size(acl->a_count);
-@@ -731,7 +731,8 @@ posix_acl_to_xattr(struct user_namespace *user_ns, const struct posix_acl *acl,
- 		return real_size;
- 	if (real_size > size)
- 		return -ERANGE;
--	
-+
-+	ext_entry = ext_acl->a_entries;
- 	ext_acl->a_version = cpu_to_le32(POSIX_ACL_XATTR_VERSION);
- 
- 	for (n=0; n < acl->a_count; n++, ext_entry++) {
-diff --git a/fs/xfs/xfs_da_btree.c b/fs/xfs/xfs_da_btree.c
-index 796272a2e129..e69d57be866b 100644
---- a/fs/xfs/xfs_da_btree.c
-+++ b/fs/xfs/xfs_da_btree.c
-@@ -1295,7 +1295,7 @@ xfs_da3_fixhashpath(
- 		node = blk->bp->b_addr;
- 		dp->d_ops->node_hdr_from_disk(&nodehdr, node);
- 		btree = dp->d_ops->node_tree_p(node);
--		if (be32_to_cpu(btree->hashval) == lasthash)
-+		if (be32_to_cpu(btree[blk->index].hashval) == lasthash)
- 			break;
- 		blk->hashval = lasthash;
- 		btree[blk->index].hashval = cpu_to_be32(lasthash);
-diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
-index 24819001f5c8..e488e9459a93 100644
---- a/include/linux/backing-dev.h
-+++ b/include/linux/backing-dev.h
-@@ -95,7 +95,7 @@ struct backing_dev_info {
- 	unsigned int max_ratio, max_prop_frac;
- 
- 	struct bdi_writeback wb;  /* default writeback info for this bdi */
--	spinlock_t wb_lock;	  /* protects work_list */
-+	spinlock_t wb_lock;	  /* protects work_list & wb.dwork scheduling */
- 
- 	struct list_head work_list;
- 
-diff --git a/include/linux/tty.h b/include/linux/tty.h
-index 90b4fdc8a61f..b90b5c221ff0 100644
---- a/include/linux/tty.h
-+++ b/include/linux/tty.h
-@@ -208,7 +208,7 @@ struct tty_port {
- 	wait_queue_head_t	delta_msr_wait;	/* Modem status change */
- 	unsigned long		flags;		/* TTY flags ASY_*/
- 	unsigned char		console:1,	/* port is a console */
--				low_latency:1;	/* direct buffer flush */
-+				low_latency:1;	/* optional: tune for latency */
- 	struct mutex		mutex;		/* Locking */
- 	struct mutex		buf_mutex;	/* Buffer alloc lock */
- 	unsigned char		*xmit_buf;	/* Optional buffer */
-diff --git a/kernel/exit.c b/kernel/exit.c
-index 1e77fc645317..81b3d6789ee8 100644
---- a/kernel/exit.c
-+++ b/kernel/exit.c
-@@ -560,9 +560,6 @@ static void reparent_leader(struct task_struct *father, struct task_struct *p,
- 				struct list_head *dead)
- {
- 	list_move_tail(&p->sibling, &p->real_parent->children);
--
--	if (p->exit_state == EXIT_DEAD)
--		return;
- 	/*
- 	 * If this is a threaded reparent there is no need to
- 	 * notify anyone anything has happened.
-@@ -570,9 +567,19 @@ static void reparent_leader(struct task_struct *father, struct task_struct *p,
- 	if (same_thread_group(p->real_parent, father))
- 		return;
- 
--	/* We don't want people slaying init.  */
-+	/*
-+	 * We don't want people slaying init.
-+	 *
-+	 * Note: we do this even if it is EXIT_DEAD, wait_task_zombie()
-+	 * can change ->exit_state to EXIT_ZOMBIE. If this is the final
-+	 * state, do_notify_parent() was already called and ->exit_signal
-+	 * doesn't matter.
-+	 */
- 	p->exit_signal = SIGCHLD;
- 
-+	if (p->exit_state == EXIT_DEAD)
-+		return;
-+
- 	/* If it has exited notify the new parent about this child's death. */
- 	if (!p->ptrace &&
- 	    p->exit_state == EXIT_ZOMBIE && thread_group_empty(p)) {
-@@ -784,6 +791,8 @@ void do_exit(long code)
- 	exit_shm(tsk);
- 	exit_files(tsk);
- 	exit_fs(tsk);
-+	if (group_dead)
-+		disassociate_ctty(1);
- 	exit_task_namespaces(tsk);
- 	exit_task_work(tsk);
- 	check_stack_usage();
-@@ -799,13 +808,9 @@ void do_exit(long code)
- 
- 	cgroup_exit(tsk, 1);
- 
--	if (group_dead)
--		disassociate_ctty(1);
--
- 	module_put(task_thread_info(tsk)->exec_domain->module);
- 
- 	proc_exit_connector(tsk);
--
- 	/*
- 	 * FIXME: do that only when needed, using sched_exit tracepoint
- 	 */
-diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
-index 06c62de9c711..db95d8eb761b 100644
---- a/kernel/pid_namespace.c
-+++ b/kernel/pid_namespace.c
-@@ -318,7 +318,9 @@ static void *pidns_get(struct task_struct *task)
- 	struct pid_namespace *ns;
- 
- 	rcu_read_lock();
--	ns = get_pid_ns(task_active_pid_ns(task));
-+	ns = task_active_pid_ns(task);
-+	if (ns)
-+		get_pid_ns(ns);
- 	rcu_read_unlock();
- 
- 	return ns;
-diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
-index dd06439b9c84..80a57afd8647 100644
---- a/kernel/user_namespace.c
-+++ b/kernel/user_namespace.c
-@@ -152,7 +152,7 @@ static u32 map_id_range_down(struct uid_gid_map *map, u32 id, u32 count)
- 
- 	/* Find the matching extent */
- 	extents = map->nr_extents;
--	smp_read_barrier_depends();
-+	smp_rmb();
- 	for (idx = 0; idx < extents; idx++) {
- 		first = map->extent[idx].first;
- 		last = first + map->extent[idx].count - 1;
-@@ -176,7 +176,7 @@ static u32 map_id_down(struct uid_gid_map *map, u32 id)
- 
- 	/* Find the matching extent */
- 	extents = map->nr_extents;
--	smp_read_barrier_depends();
-+	smp_rmb();
- 	for (idx = 0; idx < extents; idx++) {
- 		first = map->extent[idx].first;
- 		last = first + map->extent[idx].count - 1;
-@@ -199,7 +199,7 @@ static u32 map_id_up(struct uid_gid_map *map, u32 id)
- 
- 	/* Find the matching extent */
- 	extents = map->nr_extents;
--	smp_read_barrier_depends();
-+	smp_rmb();
- 	for (idx = 0; idx < extents; idx++) {
- 		first = map->extent[idx].lower_first;
- 		last = first + map->extent[idx].count - 1;
-@@ -615,9 +615,8 @@ static ssize_t map_write(struct file *file, const char __user *buf,
- 	 * were written before the count of the extents.
- 	 *
- 	 * To achieve this smp_wmb() is used on guarantee the write
--	 * order and smp_read_barrier_depends() is guaranteed that we
--	 * don't have crazy architectures returning stale data.
--	 *
-+	 * order and smp_rmb() is guaranteed that we don't have crazy
-+	 * architectures returning stale data.
- 	 */
- 	mutex_lock(&id_map_mutex);
- 
-diff --git a/mm/backing-dev.c b/mm/backing-dev.c
-index ce682f7a4f29..09d9591b7708 100644
---- a/mm/backing-dev.c
-+++ b/mm/backing-dev.c
-@@ -288,13 +288,19 @@ int bdi_has_dirty_io(struct backing_dev_info *bdi)
-  * Note, we wouldn't bother setting up the timer, but this function is on the
-  * fast-path (used by '__mark_inode_dirty()'), so we save few context switches
-  * by delaying the wake-up.
-+ *
-+ * We have to be careful not to postpone flush work if it is scheduled for
-+ * earlier. Thus we use queue_delayed_work().
-  */
- void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi)
- {
- 	unsigned long timeout;
- 
- 	timeout = msecs_to_jiffies(dirty_writeback_interval * 10);
--	mod_delayed_work(bdi_wq, &bdi->wb.dwork, timeout);
-+	spin_lock_bh(&bdi->wb_lock);
-+	if (test_bit(BDI_registered, &bdi->state))
-+		queue_delayed_work(bdi_wq, &bdi->wb.dwork, timeout);
-+	spin_unlock_bh(&bdi->wb_lock);
- }
- 
- /*
-@@ -307,9 +313,6 @@ static void bdi_remove_from_list(struct backing_dev_info *bdi)
- 	spin_unlock_bh(&bdi_lock);
- 
- 	synchronize_rcu_expedited();
--
--	/* bdi_list is now unused, clear it to mark @bdi dying */
--	INIT_LIST_HEAD(&bdi->bdi_list);
- }
- 
- int bdi_register(struct backing_dev_info *bdi, struct device *parent,
-@@ -360,6 +363,11 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi)
- 	 */
- 	bdi_remove_from_list(bdi);
- 
-+	/* Make sure nobody queues further work */
-+	spin_lock_bh(&bdi->wb_lock);
-+	clear_bit(BDI_registered, &bdi->state);
-+	spin_unlock_bh(&bdi->wb_lock);
-+
- 	/*
- 	 * Drain work list and shutdown the delayed_work.  At this point,
- 	 * @bdi->bdi_list is empty telling bdi_Writeback_workfn() that @bdi
-diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
-index 5f812455a450..60828cf02eb8 100644
---- a/net/bluetooth/hci_event.c
-+++ b/net/bluetooth/hci_event.c
-@@ -3593,7 +3593,13 @@ static void hci_le_ltk_request_evt(struct hci_dev *hdev, struct sk_buff *skb)
- 
- 	hci_send_cmd(hdev, HCI_OP_LE_LTK_REPLY, sizeof(cp), &cp);
- 
--	if (ltk->type & HCI_SMP_STK) {
-+	/* Ref. Bluetooth Core SPEC pages 1975 and 2004. STK is a
-+	 * temporary key used to encrypt a connection following
-+	 * pairing. It is used during the Encrypted Session Setup to
-+	 * distribute the keys. Later, security can be re-established
-+	 * using a distributed LTK.
-+	 */
-+	if (ltk->type == HCI_SMP_STK_SLAVE) {
- 		list_del(&ltk->list);
- 		kfree(ltk);
- 	}
-diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h
-index 0356e1d437ca..f79fa8be203c 100644
---- a/security/integrity/ima/ima.h
-+++ b/security/integrity/ima/ima.h
-@@ -27,7 +27,7 @@
- #include "../integrity.h"
- 
- enum ima_show_type { IMA_SHOW_BINARY, IMA_SHOW_BINARY_NO_FIELD_LEN,
--		     IMA_SHOW_ASCII };
-+		     IMA_SHOW_BINARY_OLD_STRING_FMT, IMA_SHOW_ASCII };
- enum tpm_pcrs { TPM_PCR0 = 0, TPM_PCR8 = 8 };
- 
- /* digest size for IMA, fits SHA1 or MD5 */
-diff --git a/security/integrity/ima/ima_fs.c b/security/integrity/ima/ima_fs.c
-index db01125926bd..468a3ba3c539 100644
---- a/security/integrity/ima/ima_fs.c
-+++ b/security/integrity/ima/ima_fs.c
-@@ -160,6 +160,8 @@ static int ima_measurements_show(struct seq_file *m, void *v)
- 
- 		if (is_ima_template && strcmp(field->field_id, "d") == 0)
- 			show = IMA_SHOW_BINARY_NO_FIELD_LEN;
-+		if (is_ima_template && strcmp(field->field_id, "n") == 0)
-+			show = IMA_SHOW_BINARY_OLD_STRING_FMT;
- 		field->field_show(m, show, &e->template_data[i]);
- 	}
- 	return 0;
-diff --git a/security/integrity/ima/ima_template_lib.c b/security/integrity/ima/ima_template_lib.c
-index 1683bbf289a4..e8592e7bfc21 100644
---- a/security/integrity/ima/ima_template_lib.c
-+++ b/security/integrity/ima/ima_template_lib.c
-@@ -109,13 +109,16 @@ static void ima_show_template_data_binary(struct seq_file *m,
- 					  enum data_formats datafmt,
- 					  struct ima_field_data *field_data)
- {
-+	u32 len = (show == IMA_SHOW_BINARY_OLD_STRING_FMT) ?
-+	    strlen(field_data->data) : field_data->len;
-+
- 	if (show != IMA_SHOW_BINARY_NO_FIELD_LEN)
--		ima_putc(m, &field_data->len, sizeof(u32));
-+		ima_putc(m, &len, sizeof(len));
- 
--	if (!field_data->len)
-+	if (!len)
- 		return;
- 
--	ima_putc(m, field_data->data, field_data->len);
-+	ima_putc(m, field_data->data, len);
- }
- 
- static void ima_show_template_field_data(struct seq_file *m,
-@@ -129,6 +132,7 @@ static void ima_show_template_field_data(struct seq_file *m,
- 		break;
- 	case IMA_SHOW_BINARY:
- 	case IMA_SHOW_BINARY_NO_FIELD_LEN:
-+	case IMA_SHOW_BINARY_OLD_STRING_FMT:
- 		ima_show_template_data_binary(m, show, datafmt, field_data);
- 		break;
- 	default:

Deleted: genpatches-2.6/trunk/3.15/4200_fbcondecor-0.9.6.patch
===================================================================
--- genpatches-2.6/trunk/3.15/4200_fbcondecor-0.9.6.patch	2014-05-05 14:22:27 UTC (rev 2771)
+++ genpatches-2.6/trunk/3.15/4200_fbcondecor-0.9.6.patch	2014-05-05 14:28:48 UTC (rev 2772)
@@ -1,2177 +0,0 @@
-diff --git a/Documentation/fb/00-INDEX b/Documentation/fb/00-INDEX
-index 30a7054..9b6a733 100644
---- a/Documentation/fb/00-INDEX
-+++ b/Documentation/fb/00-INDEX
-@@ -21,6 +21,8 @@ ep93xx-fb.txt
- 	- info on the driver for EP93xx LCD controller.
- fbcon.txt
- 	- intro to and usage guide for the framebuffer console (fbcon).
-+fbcondecor.txt
-+	- info on the Framebuffer Console Decoration
- framebuffer.txt
- 	- introduction to frame buffer devices.
- gxfb.txt
-diff --git a/Documentation/fb/fbcondecor.txt b/Documentation/fb/fbcondecor.txt
-new file mode 100644
-index 0000000..15889f3
---- /dev/null
-+++ b/Documentation/fb/fbcondecor.txt
-@@ -0,0 +1,207 @@
-+What is it?
-+-----------
-+
-+The framebuffer decorations are a kernel feature which allows displaying a 
-+background picture on selected consoles.
-+
-+What do I need to get it to work?
-+---------------------------------
-+
-+To get fbcondecor up-and-running you will have to:
-+ 1) get a copy of splashutils [1] or a similar program
-+ 2) get some fbcondecor themes
-+ 3) build the kernel helper program
-+ 4) build your kernel with the FB_CON_DECOR option enabled.
-+
-+To get fbcondecor operational right after fbcon initialization is finished, you
-+will have to include a theme and the kernel helper into your initramfs image.
-+Please refer to splashutils documentation for instructions on how to do that.
-+
-+[1] The splashutils package can be downloaded from:
-+    http://dev.gentoo.org/~spock/projects/splashutils/
-+
-+The userspace helper
-+--------------------
-+
-+The userspace fbcondecor helper (by default: /sbin/fbcondecor_helper) is called by the
-+kernel whenever an important event occurs and the kernel needs some kind of
-+job to be carried out. Important events include console switches and video
-+mode switches (the kernel requests background images and configuration
-+parameters for the current console). The fbcondecor helper must be accessible at
-+all times. If it's not, fbcondecor will be switched off automatically.
-+
-+It's possible to set path to the fbcondecor helper by writing it to
-+/proc/sys/kernel/fbcondecor.
-+
-+*****************************************************************************
-+
-+The information below is mostly technical stuff. There's probably no need to
-+read it unless you plan to develop a userspace helper.
-+
-+The fbcondecor protocol
-+-----------------------
-+
-+The fbcondecor protocol defines a communication interface between the kernel and
-+the userspace fbcondecor helper.
-+
-+The kernel side is responsible for:
-+
-+ * rendering console text, using an image as a background (instead of a
-+   standard solid color fbcon uses),
-+ * accepting commands from the user via ioctls on the fbcondecor device,
-+ * calling the userspace helper to set things up as soon as the fb subsystem 
-+   is initialized.
-+
-+The userspace helper is responsible for everything else, including parsing
-+configuration files, decompressing the image files whenever the kernel needs
-+it, and communicating with the kernel if necessary.
-+
-+The fbcondecor protocol specifies how communication is done in both ways:
-+kernel->userspace and userspace->helper.
-+  
-+Kernel -> Userspace
-+-------------------
-+
-+The kernel communicates with the userspace helper by calling it and specifying
-+the task to be done in a series of arguments.
-+
-+The arguments follow the pattern:
-+<fbcondecor protocol version> <command> <parameters>
-+
-+All commands defined in fbcondecor protocol v2 have the following parameters:
-+ virtual console
-+ framebuffer number
-+ theme
-+
-+Fbcondecor protocol v1 specified an additional 'fbcondecor mode' after the
-+framebuffer number. Fbcondecor protocol v1 is deprecated and should not be used.
-+
-+Fbcondecor protocol v2 specifies the following commands:
-+
-+getpic
-+------
-+ The kernel issues this command to request image data. It's up to the 
-+ userspace  helper to find a background image appropriate for the specified 
-+ theme and the current resolution. The userspace helper should respond by 
-+ issuing the FBIOCONDECOR_SETPIC ioctl.
-+
-+init
-+----
-+ The kernel issues this command after the fbcondecor device is created and
-+ the fbcondecor interface is initialized. Upon receiving 'init', the userspace
-+ helper should parse the kernel command line (/proc/cmdline) or otherwise
-+ decide whether fbcondecor is to be activated.
-+
-+ To activate fbcondecor on the first console the helper should issue the
-+ FBIOCONDECOR_SETCFG, FBIOCONDECOR_SETPIC and FBIOCONDECOR_SETSTATE commands,
-+ in the above-mentioned order.
-+
-+ When the userspace helper is called in an early phase of the boot process
-+ (right after the initialization of fbcon), no filesystems will be mounted.
-+ The helper program should mount sysfs and then create the appropriate
-+ framebuffer, fbcondecor and tty0 devices (if they don't already exist) to get
-+ current display settings and to be able to communicate with the kernel side.
-+ It should probably also mount the procfs to be able to parse the kernel
-+ command line parameters.
-+
-+ Note that the console sem is not held when the kernel calls fbcondecor_helper
-+ with the 'init' command. The fbcondecor helper should perform all ioctls with
-+ origin set to FBCON_DECOR_IO_ORIG_USER.
-+
-+modechange
-+----------
-+ The kernel issues this command on a mode change. The helper's response should
-+ be similar to the response to the 'init' command. Note that this time the
-+ console sem is held and all ioctls must be performed with origin set to
-+ FBCON_DECOR_IO_ORIG_KERNEL.
-+
-+
-+Userspace -> Kernel
-+-------------------
-+
-+Userspace programs can communicate with fbcondecor via ioctls on the
-+fbcondecor device. These ioctls are to be used by both the userspace helper
-+(called only by the kernel) and userspace configuration tools (run by the users).
-+
-+The fbcondecor helper should set the origin field to FBCON_DECOR_IO_ORIG_KERNEL
-+when doing the appropriate ioctls. All userspace configuration tools should
-+use FBCON_DECOR_IO_ORIG_USER. Failure to set the appropriate value in the origin
-+field when performing ioctls from the kernel helper will most likely result
-+in a console deadlock.
-+
-+FBCON_DECOR_IO_ORIG_KERNEL instructs fbcondecor not to try to acquire the console
-+semaphore. Not surprisingly, FBCON_DECOR_IO_ORIG_USER instructs it to acquire
-+the console sem.
-+
-+The framebuffer console decoration provides the following ioctls (all defined in 
-+linux/fb.h):
-+
-+FBIOCONDECOR_SETPIC
-+description: loads a background picture for a virtual console
-+argument: struct fbcon_decor_iowrapper*; data: struct fb_image*
-+notes: 
-+If called for consoles other than the current foreground one, the picture data
-+will be ignored.
-+
-+If the current virtual console is running in a 8-bpp mode, the cmap substruct
-+of fb_image has to be filled appropriately: start should be set to 16 (first
-+16 colors are reserved for fbcon), len to a value <= 240 and red, green and
-+blue should point to valid cmap data. The transp field is ingored. The fields
-+dx, dy, bg_color, fg_color in fb_image are ignored as well.
-+
-+FBIOCONDECOR_SETCFG
-+description: sets the fbcondecor config for a virtual console
-+argument: struct fbcon_decor_iowrapper*; data: struct vc_decor*
-+notes: The structure has to be filled with valid data.
-+
-+FBIOCONDECOR_GETCFG
-+description: gets the fbcondecor config for a virtual console
-+argument: struct fbcon_decor_iowrapper*; data: struct vc_decor*
-+
-+FBIOCONDECOR_SETSTATE
-+description: sets the fbcondecor state for a virtual console
-+argument: struct fbcon_decor_iowrapper*; data: unsigned int*
-+          values: 0 = disabled, 1 = enabled.
-+
-+FBIOCONDECOR_GETSTATE
-+description: gets the fbcondecor state for a virtual console
-+argument: struct fbcon_decor_iowrapper*; data: unsigned int*
-+          values: as in FBIOCONDECOR_SETSTATE
-+
-+Info on used structures:
-+
-+Definition of struct vc_decor can be found in linux/console_decor.h. It's
-+heavily commented. Note that the 'theme' field should point to a string
-+no longer than FBCON_DECOR_THEME_LEN. When FBIOCONDECOR_GETCFG call is
-+performed, the theme field should point to a char buffer of length
-+FBCON_DECOR_THEME_LEN.
-+
-+Definition of struct fbcon_decor_iowrapper can be found in linux/fb.h.
-+The fields in this struct have the following meaning:
-+
-+vc: 
-+Virtual console number.
-+
-+origin: 
-+Specifies if the ioctl is performed as a response to a kernel request. The
-+fbcondecor helper should set this field to FBCON_DECOR_IO_ORIG_KERNEL, userspace
-+programs should set it to FBCON_DECOR_IO_ORIG_USER. This field is necessary to
-+avoid console semaphore deadlocks.
-+
-+data: 
-+Pointer to a data structure appropriate for the performed ioctl. Type of
-+the data struct is specified in the ioctls description.
-+
-+*****************************************************************************
-+
-+Credit
-+------
-+
-+Original 'bootsplash' project & implementation by:
-+  Volker Poplawski <volker@×××××××××.de>, Stefan Reinauer <stepan@××××.de>,
-+  Steffen Winterfeldt <snwint@××××.de>, Michael Schroeder <mls@××××.de>,
-+  Ken Wimer <wimer@××××.de>.
-+
-+Fbcondecor, fbcondecor protocol design, current implementation & docs by:
-+  Michal Januszewski <spock@g.o>
-+
-diff --git a/drivers/Makefile b/drivers/Makefile
-index 95952c8..b55db6d 100644
---- a/drivers/Makefile
-+++ b/drivers/Makefile
-@@ -16,4 +16,8 @@ obj-$(CONFIG_PCI)		+= pci/
- obj-$(CONFIG_PARISC)		+= parisc/
- obj-$(CONFIG_RAPIDIO)		+= rapidio/
-+# tty/ comes before char/ so that the VT console is the boot-time
-+# default.
-+obj-y				+= tty/
-+obj-y				+= char/
- obj-y				+= video/
- obj-y				+= idle/
-@@ -37,11 +41,6 @@ obj-$(CONFIG_XEN)		+= xen/
- # regulators early, since some subsystems rely on them to initialize
- obj-$(CONFIG_REGULATOR)		+= regulator/
- 
--# tty/ comes before char/ so that the VT console is the boot-time
--# default.
--obj-y				+= tty/
--obj-y				+= char/
--
- # gpu/ comes after char for AGP vs DRM startup
- obj-y				+= gpu/
- 
-diff --git a/drivers/video/Kconfig b/drivers/video/Kconfig
-index a290be5..3a4ca32 100644
---- a/drivers/video/Kconfig
-+++ b/drivers/video/Kconfig
-@@ -1229,7 +1229,6 @@ config FB_MATROX
- 	select FB_CFB_FILLRECT
- 	select FB_CFB_COPYAREA
- 	select FB_CFB_IMAGEBLIT
--	select FB_TILEBLITTING
- 	select FB_MACMODES if PPC_PMAC
- 	---help---
- 	  Say Y here if you have a Matrox Millennium, Matrox Millennium II,
-diff --git a/drivers/video/console/Kconfig b/drivers/video/console/Kconfig
-index c2d11fe..1be9de4 100644
---- a/drivers/video/console/Kconfig
-+++ b/drivers/video/console/Kconfig
-@@ -120,6 +120,19 @@ config FRAMEBUFFER_CONSOLE_ROTATION
-          such that other users of the framebuffer will remain normally
-          oriented.
- 
-+config FB_CON_DECOR
-+	bool "Support for the Framebuffer Console Decorations"
-+	depends on FRAMEBUFFER_CONSOLE=y && !FB_TILEBLITTING
-+	default n
-+	---help---
-+	  This option enables support for framebuffer console decorations which
-+	  makes it possible to display images in the background of the system
-+	  consoles.  Note that userspace utilities are necessary in order to take 
-+	  advantage of these features. Refer to Documentation/fb/fbcondecor.txt 
-+	  for more information.
-+
-+	  If unsure, say N.
-+
- config STI_CONSOLE
-         bool "STI text console"
-         depends on PARISC
---- a/drivers/video/console/Makefile    2013-08-26 14:02:39.905817618 -0400
-+++ b/drivers/video/console/Makefile    2013-08-26 14:05:06.258848595 -0400
-@@ -16,4 +16,5 @@ obj-$(CONFIG_FRAMEBUFFER_CONSOLE)     +=
-                                          fbcon_ccw.o
- endif
-
-+obj-$(CONFIG_FB_CON_DECOR)           += fbcondecor.o cfbcondecor.o
- obj-$(CONFIG_FB_STI)              += sticore.o
-diff --git a/drivers/video/console/bitblit.c b/drivers/video/console/bitblit.c
-index 28b1a83..33712c0 100644
---- a/drivers/video/console/bitblit.c
-+++ b/drivers/video/console/bitblit.c
-@@ -18,6 +18,7 @@
- #include <linux/console.h>
- #include <asm/types.h>
- #include "fbcon.h"
-+#include "fbcondecor.h"
- 
- /*
-  * Accelerated handlers.
-@@ -55,6 +56,13 @@ static void bit_bmove(struct vc_data *vc, struct fb_info *info, int sy,
- 	area.height = height * vc->vc_font.height;
- 	area.width = width * vc->vc_font.width;
- 
-+	if (fbcon_decor_active(info, vc)) {
-+ 		area.sx += vc->vc_decor.tx;
-+ 		area.sy += vc->vc_decor.ty;
-+ 		area.dx += vc->vc_decor.tx;
-+ 		area.dy += vc->vc_decor.ty;
-+ 	}
-+
- 	info->fbops->fb_copyarea(info, &area);
- }
- 
-@@ -380,11 +388,15 @@ static void bit_cursor(struct vc_data *vc, struct fb_info *info, int mode,
- 	cursor.image.depth = 1;
- 	cursor.rop = ROP_XOR;
- 
--	if (info->fbops->fb_cursor)
--		err = info->fbops->fb_cursor(info, &cursor);
-+	if (fbcon_decor_active(info, vc)) {
-+		fbcon_decor_cursor(info, &cursor);
-+	} else {
-+		if (info->fbops->fb_cursor)
-+			err = info->fbops->fb_cursor(info, &cursor);
- 
--	if (err)
--		soft_cursor(info, &cursor);
-+		if (err)
-+			soft_cursor(info, &cursor);
-+	}
- 
- 	ops->cursor_reset = 0;
- }
-diff --git a/drivers/video/console/cfbcondecor.c b/drivers/video/console/cfbcondecor.c
-new file mode 100644
-index 0000000..09381d3
---- /dev/null
-+++ b/drivers/video/console/cfbcondecor.c
-@@ -0,0 +1,471 @@
-+/*
-+ *  linux/drivers/video/cfbcon_decor.c -- Framebuffer decor render functions
-+ *
-+ *  Copyright (C) 2004 Michal Januszewski <spock@g.o>
-+ *
-+ *  Code based upon "Bootdecor" (C) 2001-2003
-+ *       Volker Poplawski <volker@×××××××××.de>,
-+ *       Stefan Reinauer <stepan@××××.de>,
-+ *       Steffen Winterfeldt <snwint@××××.de>,
-+ *       Michael Schroeder <mls@××××.de>,
-+ *       Ken Wimer <wimer@××××.de>.
-+ *
-+ *  This file is subject to the terms and conditions of the GNU General Public
-+ *  License.  See the file COPYING in the main directory of this archive for
-+ *  more details.
-+ */
-+#include <linux/module.h>
-+#include <linux/types.h>
-+#include <linux/fb.h>
-+#include <linux/selection.h>
-+#include <linux/slab.h>
-+#include <linux/vt_kern.h>
-+#include <asm/irq.h>
-+
-+#include "fbcon.h"
-+#include "fbcondecor.h"
-+
-+#define parse_pixel(shift,bpp,type)						\
-+	do {									\
-+		if (d & (0x80 >> (shift)))					\
-+			dd2[(shift)] = fgx;					\
-+		else								\
-+			dd2[(shift)] = transparent ? *(type *)decor_src : bgx;	\
-+		decor_src += (bpp);						\
-+	} while (0)								\
-+
-+extern int get_color(struct vc_data *vc, struct fb_info *info,
-+		     u16 c, int is_fg);
-+
-+void fbcon_decor_fix_pseudo_pal(struct fb_info *info, struct vc_data *vc)
-+{
-+	int i, j, k;
-+	int minlen = min(min(info->var.red.length, info->var.green.length),
-+			     info->var.blue.length);
-+	u32 col;
-+
-+	for (j = i = 0; i < 16; i++) {
-+		k = color_table[i];
-+
-+		col = ((vc->vc_palette[j++]  >> (8-minlen))
-+			<< info->var.red.offset);
-+		col |= ((vc->vc_palette[j++] >> (8-minlen))
-+			<< info->var.green.offset);
-+		col |= ((vc->vc_palette[j++] >> (8-minlen))
-+			<< info->var.blue.offset);
-+			((u32 *)info->pseudo_palette)[k] = col;
-+	}
-+}
-+
-+void fbcon_decor_renderc(struct fb_info *info, int ypos, int xpos, int height,
-+		      int width, u8* src, u32 fgx, u32 bgx, u8 transparent)
-+{
-+	unsigned int x, y;
-+	u32 dd;
-+	int bytespp = ((info->var.bits_per_pixel + 7) >> 3);
-+	unsigned int d = ypos * info->fix.line_length + xpos * bytespp;
-+	unsigned int ds = (ypos * info->var.xres + xpos) * bytespp;
-+	u16 dd2[4];
-+
-+	u8* decor_src = (u8 *)(info->bgdecor.data + ds);
-+	u8* dst = (u8 *)(info->screen_base + d);
-+
-+	if ((ypos + height) > info->var.yres || (xpos + width) > info->var.xres)
-+		return;
-+
-+	for (y = 0; y < height; y++) {
-+		switch (info->var.bits_per_pixel) {
-+
-+		case 32:
-+			for (x = 0; x < width; x++) {
-+
-+				if ((x & 7) == 0)
-+					d = *src++;
-+				if (d & 0x80)
-+					dd = fgx;
-+				else
-+					dd = transparent ?
-+					     *(u32 *)decor_src : bgx;
-+
-+				d <<= 1;
-+				decor_src += 4;
-+				fb_writel(dd, dst);
-+				dst += 4;
-+			}
-+			break;
-+		case 24:
-+			for (x = 0; x < width; x++) {
-+
-+				if ((x & 7) == 0)
-+					d = *src++;
-+				if (d & 0x80)
-+					dd = fgx;
-+				else
-+					dd = transparent ?
-+					     (*(u32 *)decor_src & 0xffffff) : bgx;
-+
-+				d <<= 1;
-+				decor_src += 3;
-+#ifdef __LITTLE_ENDIAN
-+				fb_writew(dd & 0xffff, dst);
-+				dst += 2;
-+				fb_writeb((dd >> 16), dst);
-+#else
-+				fb_writew(dd >> 8, dst);
-+				dst += 2;
-+				fb_writeb(dd & 0xff, dst);
-+#endif
-+				dst++;
-+			}
-+			break;
-+		case 16:
-+			for (x = 0; x < width; x += 2) {
-+				if ((x & 7) == 0)
-+					d = *src++;
-+
-+				parse_pixel(0, 2, u16);
-+				parse_pixel(1, 2, u16);
-+#ifdef __LITTLE_ENDIAN
-+				dd = dd2[0] | (dd2[1] << 16);
-+#else
-+				dd = dd2[1] | (dd2[0] << 16);
-+#endif
-+				d <<= 2;
-+				fb_writel(dd, dst);
-+				dst += 4;
-+			}
-+			break;
-+
-+		case 8:
-+			for (x = 0; x < width; x += 4) {
-+				if ((x & 7) == 0)
-+					d = *src++;
-+
-+				parse_pixel(0, 1, u8);
-+				parse_pixel(1, 1, u8);
-+				parse_pixel(2, 1, u8);
-+				parse_pixel(3, 1, u8);
-+
-+#ifdef __LITTLE_ENDIAN
-+				dd = dd2[0] | (dd2[1] << 8) | (dd2[2] << 16) | (dd2[3] << 24);
-+#else
-+				dd = dd2[3] | (dd2[2] << 8) | (dd2[1] << 16) | (dd2[0] << 24);
-+#endif
-+				d <<= 4;
-+				fb_writel(dd, dst);
-+				dst += 4;
-+			}
-+		}
-+
-+		dst += info->fix.line_length - width * bytespp;
-+		decor_src += (info->var.xres - width) * bytespp;
-+	}
-+}
-+
-+#define cc2cx(a) 						\
-+	((info->fix.visual == FB_VISUAL_TRUECOLOR || 		\
-+	  info->fix.visual == FB_VISUAL_DIRECTCOLOR) ? 		\
-+	 ((u32*)info->pseudo_palette)[a] : a)
-+
-+void fbcon_decor_putcs(struct vc_data *vc, struct fb_info *info,
-+		   const unsigned short *s, int count, int yy, int xx)
-+{
-+	unsigned short charmask = vc->vc_hi_font_mask ? 0x1ff : 0xff;
-+	struct fbcon_ops *ops = info->fbcon_par;
-+	int fg_color, bg_color, transparent;
-+	u8 *src;
-+	u32 bgx, fgx;
-+	u16 c = scr_readw(s);
-+
-+	fg_color = get_color(vc, info, c, 1);
-+        bg_color = get_color(vc, info, c, 0);
-+
-+	/* Don't paint the background image if console is blanked */
-+	transparent = ops->blank_state ? 0 :
-+		(vc->vc_decor.bg_color == bg_color);
-+
-+	xx = xx * vc->vc_font.width + vc->vc_decor.tx;
-+	yy = yy * vc->vc_font.height + vc->vc_decor.ty;
-+
-+	fgx = cc2cx(fg_color);
-+	bgx = cc2cx(bg_color);
-+
-+	while (count--) {
-+		c = scr_readw(s++);
-+		src = vc->vc_font.data + (c & charmask) * vc->vc_font.height *
-+		      ((vc->vc_font.width + 7) >> 3);
-+
-+		fbcon_decor_renderc(info, yy, xx, vc->vc_font.height,
-+			       vc->vc_font.width, src, fgx, bgx, transparent);
-+		xx += vc->vc_font.width;
-+	}
-+}
-+
-+void fbcon_decor_cursor(struct fb_info *info, struct fb_cursor *cursor)
-+{
-+	int i;
-+	unsigned int dsize, s_pitch;
-+	struct fbcon_ops *ops = info->fbcon_par;
-+	struct vc_data* vc;
-+	u8 *src;
-+
-+	/* we really don't need any cursors while the console is blanked */
-+	if (info->state != FBINFO_STATE_RUNNING || ops->blank_state)
-+		return;
-+
-+	vc = vc_cons[ops->currcon].d;
-+
-+	src = kmalloc(64 + sizeof(struct fb_image), GFP_ATOMIC);
-+	if (!src)
-+		return;
-+
-+	s_pitch = (cursor->image.width + 7) >> 3;
-+	dsize = s_pitch * cursor->image.height;
-+	if (cursor->enable) {
-+		switch (cursor->rop) {
-+		case ROP_XOR:
-+			for (i = 0; i < dsize; i++)
-+				src[i] = cursor->image.data[i] ^ cursor->mask[i];
-+                        break;
-+		case ROP_COPY:
-+		default:
-+			for (i = 0; i < dsize; i++)
-+				src[i] = cursor->image.data[i] & cursor->mask[i];
-+			break;
-+		}
-+	} else
-+		memcpy(src, cursor->image.data, dsize);
-+
-+	fbcon_decor_renderc(info,
-+			cursor->image.dy + vc->vc_decor.ty,
-+			cursor->image.dx + vc->vc_decor.tx,
-+			cursor->image.height,
-+			cursor->image.width,
-+			(u8*)src,
-+			cc2cx(cursor->image.fg_color),
-+			cc2cx(cursor->image.bg_color),
-+			cursor->image.bg_color == vc->vc_decor.bg_color);
-+
-+	kfree(src);
-+}
-+
-+static void decorset(u8 *dst, int height, int width, int dstbytes,
-+		        u32 bgx, int bpp)
-+{
-+	int i;
-+
-+	if (bpp == 8)
-+		bgx |= bgx << 8;
-+	if (bpp == 16 || bpp == 8)
-+		bgx |= bgx << 16;
-+
-+	while (height-- > 0) {
-+		u8 *p = dst;
-+
-+		switch (bpp) {
-+
-+		case 32:
-+			for (i=0; i < width; i++) {
-+				fb_writel(bgx, p); p += 4;
-+			}
-+			break;
-+		case 24:
-+			for (i=0; i < width; i++) {
-+#ifdef __LITTLE_ENDIAN
-+				fb_writew((bgx & 0xffff),(u16*)p); p += 2;
-+				fb_writeb((bgx >> 16),p++);
-+#else
-+				fb_writew((bgx >> 8),(u16*)p); p += 2;
-+				fb_writeb((bgx & 0xff),p++);
-+#endif
-+			}
-+		case 16:
-+			for (i=0; i < width/4; i++) {
-+				fb_writel(bgx,p); p += 4;
-+				fb_writel(bgx,p); p += 4;
-+			}
-+			if (width & 2) {
-+				fb_writel(bgx,p); p += 4;
-+			}
-+			if (width & 1)
-+				fb_writew(bgx,(u16*)p);
-+			break;
-+		case 8:
-+			for (i=0; i < width/4; i++) {
-+				fb_writel(bgx,p); p += 4;
-+			}
-+
-+			if (width & 2) {
-+				fb_writew(bgx,p); p += 2;
-+			}
-+			if (width & 1)
-+				fb_writeb(bgx,(u8*)p);
-+			break;
-+
-+		}
-+		dst += dstbytes;
-+	}
-+}
-+
-+void fbcon_decor_copy(u8 *dst, u8 *src, int height, int width, int linebytes,
-+		   int srclinebytes, int bpp)
-+{
-+	int i;
-+
-+	while (height-- > 0) {
-+		u32 *p = (u32 *)dst;
-+		u32 *q = (u32 *)src;
-+
-+		switch (bpp) {
-+
-+		case 32:
-+			for (i=0; i < width; i++)
-+				fb_writel(*q++, p++);
-+			break;
-+		case 24:
-+			for (i=0; i < (width*3/4); i++)
-+				fb_writel(*q++, p++);
-+			if ((width*3) % 4) {
-+				if (width & 2) {
-+					fb_writeb(*(u8*)q, (u8*)p);
-+				} else if (width & 1) {
-+					fb_writew(*(u16*)q, (u16*)p);
-+					fb_writeb(*(u8*)((u16*)q+1),(u8*)((u16*)p+2));
-+				}
-+			}
-+			break;
-+		case 16:
-+			for (i=0; i < width/4; i++) {
-+				fb_writel(*q++, p++);
-+				fb_writel(*q++, p++);
-+			}
-+			if (width & 2)
-+				fb_writel(*q++, p++);
-+			if (width & 1)
-+				fb_writew(*(u16*)q, (u16*)p);
-+			break;
-+		case 8:
-+			for (i=0; i < width/4; i++)
-+				fb_writel(*q++, p++);
-+
-+			if (width & 2) {
-+				fb_writew(*(u16*)q, (u16*)p);
-+				q = (u32*) ((u16*)q + 1);
-+				p = (u32*) ((u16*)p + 1);
-+			}
-+			if (width & 1)
-+				fb_writeb(*(u8*)q, (u8*)p);
-+			break;
-+		}
-+
-+		dst += linebytes;
-+		src += srclinebytes;
-+	}
-+}
-+
-+static void decorfill(struct fb_info *info, int sy, int sx, int height,
-+		       int width)
-+{
-+	int bytespp = ((info->var.bits_per_pixel + 7) >> 3);
-+	int d  = sy * info->fix.line_length + sx * bytespp;
-+	int ds = (sy * info->var.xres + sx) * bytespp;
-+
-+	fbcon_decor_copy((u8 *)(info->screen_base + d), (u8 *)(info->bgdecor.data + ds),
-+		    height, width, info->fix.line_length, info->var.xres * bytespp,
-+		    info->var.bits_per_pixel);
-+}
-+
-+void fbcon_decor_clear(struct vc_data *vc, struct fb_info *info, int sy, int sx,
-+		    int height, int width)
-+{
-+	int bgshift = (vc->vc_hi_font_mask) ? 13 : 12;
-+	struct fbcon_ops *ops = info->fbcon_par;
-+	u8 *dst;
-+	int transparent, bg_color = attr_bgcol_ec(bgshift, vc, info);
-+
-+	transparent = (vc->vc_decor.bg_color == bg_color);
-+	sy = sy * vc->vc_font.height + vc->vc_decor.ty;
-+	sx = sx * vc->vc_font.width + vc->vc_decor.tx;
-+	height *= vc->vc_font.height;
-+	width *= vc->vc_font.width;
-+
-+	/* Don't paint the background image if console is blanked */
-+	if (transparent && !ops->blank_state) {
-+		decorfill(info, sy, sx, height, width);
-+	} else {
-+		dst = (u8 *)(info->screen_base + sy * info->fix.line_length +
-+			     sx * ((info->var.bits_per_pixel + 7) >> 3));
-+		decorset(dst, height, width, info->fix.line_length, cc2cx(bg_color),
-+			  info->var.bits_per_pixel);
-+	}
-+}
-+
-+void fbcon_decor_clear_margins(struct vc_data *vc, struct fb_info *info,
-+			    int bottom_only)
-+{
-+	unsigned int tw = vc->vc_cols*vc->vc_font.width;
-+	unsigned int th = vc->vc_rows*vc->vc_font.height;
-+
-+	if (!bottom_only) {
-+		/* top margin */
-+		decorfill(info, 0, 0, vc->vc_decor.ty, info->var.xres);
-+		/* left margin */
-+		decorfill(info, vc->vc_decor.ty, 0, th, vc->vc_decor.tx);
-+		/* right margin */
-+		decorfill(info, vc->vc_decor.ty, vc->vc_decor.tx + tw, th, 
-+			   info->var.xres - vc->vc_decor.tx - tw);
-+	}
-+	decorfill(info, vc->vc_decor.ty + th, 0, 
-+		   info->var.yres - vc->vc_decor.ty - th, info->var.xres);
-+}
-+
-+void fbcon_decor_bmove_redraw(struct vc_data *vc, struct fb_info *info, int y, 
-+			   int sx, int dx, int width)
-+{
-+	u16 *d = (u16 *) (vc->vc_origin + vc->vc_size_row * y + dx * 2);
-+	u16 *s = d + (dx - sx);
-+	u16 *start = d;
-+	u16 *ls = d;
-+	u16 *le = d + width;
-+	u16 c;
-+	int x = dx;
-+	u16 attr = 1;
-+
-+	do {
-+		c = scr_readw(d);
-+		if (attr != (c & 0xff00)) {
-+			attr = c & 0xff00;
-+			if (d > start) {
-+				fbcon_decor_putcs(vc, info, start, d - start, y, x);
-+				x += d - start;
-+				start = d;
-+			}
-+		}
-+		if (s >= ls && s < le && c == scr_readw(s)) {
-+			if (d > start) {
-+				fbcon_decor_putcs(vc, info, start, d - start, y, x);
-+				x += d - start + 1;
-+				start = d + 1;
-+			} else {
-+				x++;
-+				start++;
-+			}
-+		}
-+		s++;
-+		d++;
-+	} while (d < le);
-+	if (d > start)
-+		fbcon_decor_putcs(vc, info, start, d - start, y, x);
-+}
-+
-+void fbcon_decor_blank(struct vc_data *vc, struct fb_info *info, int blank)
-+{
-+	if (blank) {
-+		decorset((u8 *)info->screen_base, info->var.yres, info->var.xres,
-+			  info->fix.line_length, 0, info->var.bits_per_pixel);
-+	} else {
-+		update_screen(vc);
-+		fbcon_decor_clear_margins(vc, info, 0);
-+	}
-+}
-+
-From ea6ca92753106f1e0773acd1f18c71ae79a6f9b0 Mon Sep 17 00:00:00 2001
-From: Mike Pagano <mpagano@g.o>
-Date: Tue, 27 Aug 2013 07:58:05 -0400
-Subject: [PATCH] gbcondecor port
-
----
- drivers/video/console/fbcon.c | 167 ++++++++++++++++++++++++++++++++++++------
- 1 file changed, 143 insertions(+), 24 deletions(-)
-
-diff --git a/drivers/video/console/fbcon.c b/drivers/video/console/fbcon.c
-index cd8a802..666556c 100644
---- a/drivers/video/console/fbcon.c
-+++ b/drivers/video/console/fbcon.c
-@@ -79,6 +79,7 @@
- #include <asm/irq.h>
- 
- #include "fbcon.h"
-+#include "fbcondecor.h"
- 
- #ifdef FBCONDEBUG
- #  define DPRINTK(fmt, args...) printk(KERN_DEBUG "%s: " fmt, __func__ , ## args)
-@@ -94,7 +95,7 @@ enum {
- 
- static struct display fb_display[MAX_NR_CONSOLES];
- 
--static signed char con2fb_map[MAX_NR_CONSOLES];
-+signed char con2fb_map[MAX_NR_CONSOLES];
- static signed char con2fb_map_boot[MAX_NR_CONSOLES];
- 
- static int logo_lines;
-@@ -286,7 +287,7 @@ static inline int fbcon_is_inactive(struct vc_data *vc, struct fb_info *info)
- 		!vt_force_oops_output(vc);
- }
- 
--static int get_color(struct vc_data *vc, struct fb_info *info,
-+int get_color(struct vc_data *vc, struct fb_info *info,
- 	      u16 c, int is_fg)
- {
- 	int depth = fb_get_color_depth(&info->var, &info->fix);
-@@ -551,6 +552,9 @@ static int do_fbcon_takeover(int show_logo)
- 		info_idx = -1;
- 	} else {
- 		fbcon_has_console_bind = 1;
-+#ifdef CONFIG_FB_CON_DECOR
-+		fbcon_decor_init();
-+#endif
- 	}
- 
- 	return err;
-@@ -1007,6 +1011,12 @@ static const char *fbcon_startup(void)
- 	rows = FBCON_SWAP(ops->rotate, info->var.yres, info->var.xres);
- 	cols /= vc->vc_font.width;
- 	rows /= vc->vc_font.height;
-+
-+	if (fbcon_decor_active(info, vc)) {
-+		cols = vc->vc_decor.twidth / vc->vc_font.width;
-+		rows = vc->vc_decor.theight / vc->vc_font.height;
-+	}
-+
- 	vc_resize(vc, cols, rows);
- 
- 	DPRINTK("mode:   %s\n", info->fix.id);
-@@ -1036,7 +1046,7 @@ static void fbcon_init(struct vc_data *vc, int init)
- 	cap = info->flags;
- 
- 	if (vc != svc || logo_shown == FBCON_LOGO_DONTSHOW ||
--	    (info->fix.type == FB_TYPE_TEXT))
-+	    (info->fix.type == FB_TYPE_TEXT) || fbcon_decor_active(info, vc))
- 		logo = 0;
- 
- 	if (var_to_display(p, &info->var, info))
-@@ -1260,6 +1270,11 @@ static void fbcon_clear(struct vc_data *vc, int sy, int sx, int height,
- 		fbcon_clear_margins(vc, 0);
- 	}
- 
-+	if (fbcon_decor_active(info, vc)) {
-+		fbcon_decor_clear(vc, info, sy, sx, height, width);
-+		return;
-+	}
-+
- 	/* Split blits that cross physical y_wrap boundary */
- 
- 	y_break = p->vrows - p->yscroll;
-@@ -1279,10 +1294,15 @@ static void fbcon_putcs(struct vc_data *vc, const unsigned short *s,
- 	struct display *p = &fb_display[vc->vc_num];
- 	struct fbcon_ops *ops = info->fbcon_par;
- 
--	if (!fbcon_is_inactive(vc, info))
--		ops->putcs(vc, info, s, count, real_y(p, ypos), xpos,
--			   get_color(vc, info, scr_readw(s), 1),
--			   get_color(vc, info, scr_readw(s), 0));
-+	if (!fbcon_is_inactive(vc, info)) {
-+
-+		if (fbcon_decor_active(info, vc))
-+			fbcon_decor_putcs(vc, info, s, count, ypos, xpos);
-+		else
-+			ops->putcs(vc, info, s, count, real_y(p, ypos), xpos,
-+			get_color(vc, info, scr_readw(s), 1),
-+			get_color(vc, info, scr_readw(s), 0));
-+	}
- }
- 
- static void fbcon_putc(struct vc_data *vc, int c, int ypos, int xpos)
-@@ -1297,9 +1317,6 @@ static void fbcon_clear_margins(struct vc_data *vc, int bottom_only)
- {
- 	struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]];
- 	struct fbcon_ops *ops = info->fbcon_par;
--
--	if (!fbcon_is_inactive(vc, info))
--		ops->clear_margins(vc, info, bottom_only);
- }
- 
- static void fbcon_cursor(struct vc_data *vc, int mode)
-@@ -1819,7 +1836,7 @@ static int fbcon_scroll(struct vc_data *vc, int t, int b, int dir,
- 			count = vc->vc_rows;
- 		if (softback_top)
- 			fbcon_softback_note(vc, t, count);
--		if (logo_shown >= 0)
-+		if (logo_shown >= 0 || fbcon_decor_active(info, vc))
- 			goto redraw_up;
- 		switch (p->scrollmode) {
- 		case SCROLL_MOVE:
-@@ -1912,6 +1929,8 @@ static int fbcon_scroll(struct vc_data *vc, int t, int b, int dir,
- 			count = vc->vc_rows;
- 		if (logo_shown >= 0)
- 			goto redraw_down;
-+		if (fbcon_decor_active(info, vc))
-+			goto redraw_down;
- 		switch (p->scrollmode) {
- 		case SCROLL_MOVE:
- 			fbcon_redraw_blit(vc, info, p, b - 1, b - t - count,
-@@ -2060,6 +2079,13 @@ static void fbcon_bmove_rec(struct vc_data *vc, struct display *p, int sy, int s
- 		}
- 		return;
- 	}
-+
-+	if (fbcon_decor_active(info, vc) && sy == dy && height == 1) {
-+		/* must use slower redraw bmove to keep background pic intact */
-+		fbcon_decor_bmove_redraw(vc, info, sy, sx, dx, width);
-+		return;
-+	}
-+
- 	ops->bmove(vc, info, real_y(p, sy), sx, real_y(p, dy), dx,
- 		   height, width);
- }
-@@ -2130,8 +2156,8 @@ static int fbcon_resize(struct vc_data *vc, unsigned int width,
- 	var.yres = virt_h * virt_fh;
- 	x_diff = info->var.xres - var.xres;
- 	y_diff = info->var.yres - var.yres;
--	if (x_diff < 0 || x_diff > virt_fw ||
--	    y_diff < 0 || y_diff > virt_fh) {
-+	if ((x_diff < 0 || x_diff > virt_fw ||
-+		y_diff < 0 || y_diff > virt_fh) && !vc->vc_decor.state) {
- 		const struct fb_videomode *mode;
- 
- 		DPRINTK("attempting resize %ix%i\n", var.xres, var.yres);
-@@ -2168,6 +2194,22 @@ static int fbcon_switch(struct vc_data *vc)
- 	info = registered_fb[con2fb_map[vc->vc_num]];
- 	ops = info->fbcon_par;
- 
-+	prev_console = ops->currcon;
-+	if (prev_console != -1)
-+		old_info = registered_fb[con2fb_map[prev_console]];
-+
-+#ifdef CONFIG_FB_CON_DECOR
-+		if (!fbcon_decor_active_vc(vc) && info->fix.visual == FB_VISUAL_DIRECTCOLOR) {
-+			struct vc_data *vc_curr = vc_cons[prev_console].d;
-+			if (vc_curr && fbcon_decor_active_vc(vc_curr)) {
-+				/* Clear the screen to avoid displaying funky colors during
-+				 * * palette updates. */
-+				memset((u8*)info->screen_base + info->fix.line_length * info->var.yoffset,
-+					0, info->var.yres * info->fix.line_length);
-+			}
-+		}
-+#endif
-+
- 	if (softback_top) {
- 		if (softback_lines)
- 			fbcon_set_origin(vc);
-@@ -2185,9 +2227,6 @@ static int fbcon_switch(struct vc_data *vc)
- 		logo_shown = FBCON_LOGO_CANSHOW;
- 	}
- 
--	prev_console = ops->currcon;
--	if (prev_console != -1)
--		old_info = registered_fb[con2fb_map[prev_console]];
- 	/*
- 	 * FIXME: If we have multiple fbdev's loaded, we need to
- 	 * update all info->currcon.  Perhaps, we can place this
-@@ -2231,6 +2270,18 @@ static int fbcon_switch(struct vc_data *vc)
- 			fbcon_del_cursor_timer(old_info);
- 	}
- 
-+ 	if (fbcon_decor_active_vc(vc)) {
-+		struct vc_data *vc_curr = vc_cons[prev_console].d;
-+
-+		if (!vc_curr->vc_decor.theme ||
-+			strcmp(vc->vc_decor.theme, vc_curr->vc_decor.theme) ||
-+			(fbcon_decor_active_nores(info, vc_curr) &&
-+			!fbcon_decor_active(info, vc_curr))) {
-+				fbcon_decor_disable(vc, 0);
-+				fbcon_decor_call_helper("modechange", vc->vc_num);
-+		}
-+	}
-+
- 	if (fbcon_is_inactive(vc, info) ||
- 	    ops->blank_state != FB_BLANK_UNBLANK)
- 		fbcon_del_cursor_timer(info);
-@@ -2344,10 +2395,14 @@ static int fbcon_blank(struct vc_data *vc, int blank, int mode_switch)
- 			ops->blank_state = blank;
- 			fbcon_cursor(vc, blank ? CM_ERASE : CM_DRAW);
- 			ops->cursor_flash = (!blank);
--
--			if (!(info->flags & FBINFO_MISC_USEREVENT))
--				if (fb_blank(info, blank))
--					fbcon_generic_blank(vc, info, blank);
-+            if (!(info->flags & FBINFO_MISC_USEREVENT)) {
-+				if (fb_blank(info, blank)) {
-+					if (fbcon_decor_active(info, vc))
-+						fbcon_decor_blank(vc, info, blank);
-+					else
-+						fbcon_generic_blank(vc, info, blank);
-+				}
-+			}
- 		}
- 
- 		if (!blank)
-@@ -2522,10 +2577,18 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h,
- 	}
- 
- 	if (resize) {
-+		/* reset wrap/pan */
- 		int cols, rows;
- 
- 		cols = FBCON_SWAP(ops->rotate, info->var.xres, info->var.yres);
- 		rows = FBCON_SWAP(ops->rotate, info->var.yres, info->var.xres);
-+
-+		if (fbcon_decor_active(info, vc)) {
-+			info->var.xoffset = info->var.yoffset = p->yscroll = 0;
-+			cols = vc->vc_decor.twidth;
-+			rows = vc->vc_decor.theight;
-+		}
-+
- 		cols /= w;
- 		rows /= h;
- 		vc_resize(vc, cols, rows);
-@@ -2657,7 +2720,11 @@ static int fbcon_set_palette(struct vc_data *vc, unsigned char *table)
- 	int i, j, k, depth;
- 	u8 val;
- 
--	if (fbcon_is_inactive(vc, info))
-+	if (fbcon_is_inactive(vc, info)
-+#ifdef CONFIG_FB_CON_DECOR
-+		|| vc->vc_num != fg_console
-+#endif
-+	)
- 		return -EINVAL;
- 
- 	if (!CON_IS_VISIBLE(vc))
-@@ -2683,7 +2750,49 @@ static int fbcon_set_palette(struct vc_data *vc, unsigned char *table)
- 	} else
- 		fb_copy_cmap(fb_default_cmap(1 << depth), &palette_cmap);
- 
--	return fb_set_cmap(&palette_cmap, info);
-+	if (fbcon_decor_active(info, vc_cons[fg_console].d) &&
-+       info->fix.visual == FB_VISUAL_DIRECTCOLOR) {
-+
-+       u16 *red, *green, *blue;
-+       int minlen = min(min(info->var.red.length, info->var.green.length),
-+                    info->var.blue.length);
-+       int h;
-+
-+       struct fb_cmap cmap = {
-+           .start = 0,
-+           .len = (1 << minlen),
-+           .red = NULL,
-+           .green = NULL,
-+           .blue = NULL,
-+           .transp = NULL
-+       };
-+
-+       red = kmalloc(256 * sizeof(u16) * 3, GFP_KERNEL);
-+
-+       if (!red)
-+           goto out;
-+
-+       green = red + 256;
-+       blue = green + 256;
-+       cmap.red = red;
-+       cmap.green = green;
-+       cmap.blue = blue;
-+
-+       for (i = 0; i < cmap.len; i++) {
-+           red[i] = green[i] = blue[i] = (0xffff * i)/(cmap.len-1);
-+       }
-+
-+       h = fb_set_cmap(&cmap, info);
-+       fbcon_decor_fix_pseudo_pal(info, vc_cons[fg_console].d);
-+       kfree(red);
-+
-+       return h;
-+
-+   } else if (fbcon_decor_active(info, vc_cons[fg_console].d) &&
-+          info->var.bits_per_pixel == 8 && info->bgdecor.cmap.red != NULL)
-+       fb_set_cmap(&info->bgdecor.cmap, info);
-+
-+out:   return fb_set_cmap(&palette_cmap, info);
- }
- 
- static u16 *fbcon_screen_pos(struct vc_data *vc, int offset)
-@@ -2909,7 +3018,13 @@ static void fbcon_modechanged(struct fb_info *info)
- 		rows = FBCON_SWAP(ops->rotate, info->var.yres, info->var.xres);
- 		cols /= vc->vc_font.width;
- 		rows /= vc->vc_font.height;
--		vc_resize(vc, cols, rows);
-+ 		if (!fbcon_decor_active_nores(info, vc)) {
-+           vc_resize(vc, cols, rows);
-+		} else {
-+        	fbcon_decor_disable(vc, 0);
-+           	fbcon_decor_call_helper("modechange", vc->vc_num);
-+       	}
-+
- 		updatescrollmode(p, info, vc);
- 		scrollback_max = 0;
- 		scrollback_current = 0;
-@@ -2954,7 +3069,10 @@ static void fbcon_set_all_vcs(struct fb_info *info)
- 		rows = FBCON_SWAP(ops->rotate, info->var.yres, info->var.xres);
- 		cols /= vc->vc_font.width;
- 		rows /= vc->vc_font.height;
--		vc_resize(vc, cols, rows);
-+		if (!fbcon_decor_active_nores(info, vc)) {
-+        	vc_resize(vc, cols, rows);
-+		}
-+
- 	}
- 
- 	if (fg != -1)
-@@ -3570,6 +3688,7 @@ static void fbcon_exit(void)
- 		}
- 	}
- 
-+	fbcon_decor_exit();
- 	fbcon_has_exited = 1;
- }
- 
--- 
-1.8.1.5
-
-diff --git a/drivers/video/console/fbcondecor.c b/drivers/video/console/fbcondecor.c
-new file mode 100644
-index 0000000..7189ce6
---- /dev/null
-+++ b/drivers/video/console/fbcondecor.c
-@@ -0,0 +1,555 @@
-+/*
-+ *  linux/drivers/video/console/fbcondecor.c -- Framebuffer console decorations
-+ *
-+ *  Copyright (C) 2004-2009 Michal Januszewski <spock@g.o>
-+ *
-+ *  Code based upon "Bootsplash" (C) 2001-2003
-+ *       Volker Poplawski <volker@×××××××××.de>,
-+ *       Stefan Reinauer <stepan@××××.de>,
-+ *       Steffen Winterfeldt <snwint@××××.de>,
-+ *       Michael Schroeder <mls@××××.de>,
-+ *       Ken Wimer <wimer@××××.de>.
-+ *
-+ *  Compat ioctl support by Thorsten Klein <TK@××××××××××××××.de>.
-+ *
-+ *  This file is subject to the terms and conditions of the GNU General Public
-+ *  License.  See the file COPYING in the main directory of this archive for
-+ *  more details.
-+ *
-+ */
-+#include <linux/module.h>
-+#include <linux/kernel.h>
-+#include <linux/string.h>
-+#include <linux/types.h>
-+#include <linux/fb.h>
-+#include <linux/vt_kern.h>
-+#include <linux/vmalloc.h>
-+#include <linux/unistd.h>
-+#include <linux/syscalls.h>
-+#include <linux/init.h>
-+#include <linux/proc_fs.h>
-+#include <linux/workqueue.h>
-+#include <linux/kmod.h>
-+#include <linux/miscdevice.h>
-+#include <linux/device.h>
-+#include <linux/fs.h>
-+#include <linux/compat.h>
-+#include <linux/console.h>
-+
-+#include <asm/uaccess.h>
-+#include <asm/irq.h>
-+
-+#include "fbcon.h"
-+#include "fbcondecor.h"
-+
-+extern signed char con2fb_map[];
-+static int fbcon_decor_enable(struct vc_data *vc);
-+char fbcon_decor_path[KMOD_PATH_LEN] = "/sbin/fbcondecor_helper";
-+static int initialized = 0;
-+
-+int fbcon_decor_call_helper(char* cmd, unsigned short vc)
-+{
-+	char *envp[] = {
-+		"HOME=/",
-+		"PATH=/sbin:/bin",
-+		NULL
-+	};
-+
-+	char tfb[5];
-+	char tcons[5];
-+	unsigned char fb = (int) con2fb_map[vc];
-+
-+	char *argv[] = {
-+		fbcon_decor_path,
-+		"2",
-+		cmd,
-+		tcons,
-+		tfb,
-+		vc_cons[vc].d->vc_decor.theme,
-+		NULL
-+	};
-+
-+	snprintf(tfb,5,"%d",fb);
-+	snprintf(tcons,5,"%d",vc);
-+
-+	return call_usermodehelper(fbcon_decor_path, argv, envp, UMH_WAIT_EXEC);
-+}
-+
-+/* Disables fbcondecor on a virtual console; called with console sem held. */
-+int fbcon_decor_disable(struct vc_data *vc, unsigned char redraw)
-+{
-+	struct fb_info* info;
-+
-+	if (!vc->vc_decor.state)
-+		return -EINVAL;
-+
-+	info = registered_fb[(int) con2fb_map[vc->vc_num]];
-+
-+	if (info == NULL)
-+		return -EINVAL;
-+
-+	vc->vc_decor.state = 0;
-+	vc_resize(vc, info->var.xres / vc->vc_font.width,
-+		  info->var.yres / vc->vc_font.height);
-+
-+	if (fg_console == vc->vc_num && redraw) {
-+		redraw_screen(vc, 0);
-+		update_region(vc, vc->vc_origin +
-+			      vc->vc_size_row * vc->vc_top,
-+			      vc->vc_size_row * (vc->vc_bottom - vc->vc_top) / 2);
-+	}
-+
-+	printk(KERN_INFO "fbcondecor: switched decor state to 'off' on console %d\n",
-+			 vc->vc_num);
-+
-+	return 0;
-+}
-+
-+/* Enables fbcondecor on a virtual console; called with console sem held. */
-+static int fbcon_decor_enable(struct vc_data *vc)
-+{
-+	struct fb_info* info;
-+
-+	info = registered_fb[(int) con2fb_map[vc->vc_num]];
-+
-+	if (vc->vc_decor.twidth == 0 || vc->vc_decor.theight == 0 ||
-+	    info == NULL || vc->vc_decor.state || (!info->bgdecor.data &&
-+	    vc->vc_num == fg_console))
-+		return -EINVAL;
-+
-+	vc->vc_decor.state = 1;
-+	vc_resize(vc, vc->vc_decor.twidth / vc->vc_font.width,
-+		  vc->vc_decor.theight / vc->vc_font.height);
-+
-+	if (fg_console == vc->vc_num) {
-+		redraw_screen(vc, 0);
-+		update_region(vc, vc->vc_origin +
-+			      vc->vc_size_row * vc->vc_top,
-+			      vc->vc_size_row * (vc->vc_bottom - vc->vc_top) / 2);
-+		fbcon_decor_clear_margins(vc, info, 0);
-+	}
-+
-+	printk(KERN_INFO "fbcondecor: switched decor state to 'on' on console %d\n",
-+			 vc->vc_num);
-+
-+	return 0;
-+}
-+
-+static inline int fbcon_decor_ioctl_dosetstate(struct vc_data *vc, unsigned int state, unsigned char origin)
-+{
-+	int ret;
-+
-+//	if (origin == FBCON_DECOR_IO_ORIG_USER)
-+		console_lock();
-+	if (!state)
-+		ret = fbcon_decor_disable(vc, 1);
-+	else
-+		ret = fbcon_decor_enable(vc);
-+//	if (origin == FBCON_DECOR_IO_ORIG_USER)
-+		console_unlock();
-+
-+	return ret;
-+}
-+
-+static inline void fbcon_decor_ioctl_dogetstate(struct vc_data *vc, unsigned int *state)
-+{
-+	*state = vc->vc_decor.state;
-+}
-+
-+static int fbcon_decor_ioctl_dosetcfg(struct vc_data *vc, struct vc_decor *cfg, unsigned char origin)
-+{
-+	struct fb_info *info;
-+	int len;
-+	char *tmp;
-+
-+	info = registered_fb[(int) con2fb_map[vc->vc_num]];
-+
-+	if (info == NULL || !cfg->twidth || !cfg->theight ||
-+	    cfg->tx + cfg->twidth  > info->var.xres ||
-+	    cfg->ty + cfg->theight > info->var.yres)
-+		return -EINVAL;
-+
-+	len = strlen_user(cfg->theme);
-+	if (!len || len > FBCON_DECOR_THEME_LEN)
-+		return -EINVAL;
-+	tmp = kmalloc(len, GFP_KERNEL);
-+	if (!tmp)
-+		return -ENOMEM;
-+	if (copy_from_user(tmp, (void __user *)cfg->theme, len))
-+		return -EFAULT;
-+	cfg->theme = tmp;
-+	cfg->state = 0;
-+
-+	/* If this ioctl is a response to a request from kernel, the console sem
-+	 * is already held; we also don't need to disable decor because either the
-+	 * new config and background picture will be successfully loaded, and the
-+	 * decor will stay on, or in case of a failure it'll be turned off in fbcon. */
-+//	if (origin == FBCON_DECOR_IO_ORIG_USER) {
-+		console_lock();
-+		if (vc->vc_decor.state)
-+			fbcon_decor_disable(vc, 1);
-+//	}
-+
-+	if (vc->vc_decor.theme)
-+		kfree(vc->vc_decor.theme);
-+
-+	vc->vc_decor = *cfg;
-+
-+//	if (origin == FBCON_DECOR_IO_ORIG_USER)
-+		console_unlock();
-+
-+	printk(KERN_INFO "fbcondecor: console %d using theme '%s'\n",
-+			 vc->vc_num, vc->vc_decor.theme);
-+	return 0;
-+}
-+
-+static int fbcon_decor_ioctl_dogetcfg(struct vc_data *vc, struct vc_decor *decor)
-+{
-+	char __user *tmp;
-+
-+	tmp = decor->theme;
-+	*decor = vc->vc_decor;
-+	decor->theme = tmp;
-+
-+	if (vc->vc_decor.theme) {
-+		if (copy_to_user(tmp, vc->vc_decor.theme, strlen(vc->vc_decor.theme) + 1))
-+			return -EFAULT;
-+	} else
-+		if (put_user(0, tmp))
-+			return -EFAULT;
-+
-+	return 0;
-+}
-+
-+static int fbcon_decor_ioctl_dosetpic(struct vc_data *vc, struct fb_image *img, unsigned char origin)
-+{
-+	struct fb_info *info;
-+	int len;
-+	u8 *tmp;
-+
-+	if (vc->vc_num != fg_console)
-+		return -EINVAL;
-+
-+	info = registered_fb[(int) con2fb_map[vc->vc_num]];
-+
-+	if (info == NULL)
-+		return -EINVAL;
-+
-+	if (img->width != info->var.xres || img->height != info->var.yres) {
-+		printk(KERN_ERR "fbcondecor: picture dimensions mismatch\n");
-+		printk(KERN_ERR "%dx%d vs %dx%d\n", img->width, img->height, info->var.xres, info->var.yres);
-+		return -EINVAL;
-+	}
-+
-+	if (img->depth != info->var.bits_per_pixel) {
-+		printk(KERN_ERR "fbcondecor: picture depth mismatch\n");
-+		return -EINVAL;
-+	}
-+
-+	if (img->depth == 8) {
-+		if (!img->cmap.len || !img->cmap.red || !img->cmap.green ||
-+		    !img->cmap.blue)
-+			return -EINVAL;
-+
-+		tmp = vmalloc(img->cmap.len * 3 * 2);
-+		if (!tmp)
-+			return -ENOMEM;
-+
-+		if (copy_from_user(tmp,
-+			    	   (void __user*)img->cmap.red, (img->cmap.len << 1)) ||
-+		    copy_from_user(tmp + (img->cmap.len << 1),
-+			    	   (void __user*)img->cmap.green, (img->cmap.len << 1)) ||
-+		    copy_from_user(tmp + (img->cmap.len << 2),
-+			    	   (void __user*)img->cmap.blue, (img->cmap.len << 1))) {
-+			vfree(tmp);
-+			return -EFAULT;
-+		}
-+
-+		img->cmap.transp = NULL;
-+		img->cmap.red = (u16*)tmp;
-+		img->cmap.green = img->cmap.red + img->cmap.len;
-+		img->cmap.blue = img->cmap.green + img->cmap.len;
-+	} else {
-+		img->cmap.red = NULL;
-+	}
-+
-+	len = ((img->depth + 7) >> 3) * img->width * img->height;
-+
-+	/*
-+	 * Allocate an additional byte so that we never go outside of the
-+	 * buffer boundaries in the rendering functions in a 24 bpp mode.
-+	 */
-+	tmp = vmalloc(len + 1);
-+
-+	if (!tmp)
-+		goto out;
-+
-+	if (copy_from_user(tmp, (void __user*)img->data, len))
-+		goto out;
-+
-+	img->data = tmp;
-+
-+	/* If this ioctl is a response to a request from kernel, the console sem
-+	 * is already held. */
-+//	if (origin == FBCON_DECOR_IO_ORIG_USER)
-+		console_lock();
-+
-+	if (info->bgdecor.data)
-+		vfree((u8*)info->bgdecor.data);
-+	if (info->bgdecor.cmap.red)
-+		vfree(info->bgdecor.cmap.red);
-+
-+	info->bgdecor = *img;
-+
-+	if (fbcon_decor_active_vc(vc) && fg_console == vc->vc_num) {
-+		redraw_screen(vc, 0);
-+		update_region(vc, vc->vc_origin +
-+			      vc->vc_size_row * vc->vc_top,
-+			      vc->vc_size_row * (vc->vc_bottom - vc->vc_top) / 2);
-+		fbcon_decor_clear_margins(vc, info, 0);
-+	}
-+
-+//	if (origin == FBCON_DECOR_IO_ORIG_USER)
-+		console_unlock();
-+
-+	return 0;
-+
-+out:	if (img->cmap.red)
-+		vfree(img->cmap.red);
-+
-+	if (tmp)
-+		vfree(tmp);
-+	return -ENOMEM;
-+}
-+
-+static long fbcon_decor_ioctl(struct file *filp, u_int cmd, u_long arg)
-+{
-+	struct fbcon_decor_iowrapper __user *wrapper = (void __user*) arg;
-+	struct vc_data *vc = NULL;
-+	unsigned short vc_num = 0;
-+	unsigned char origin = 0;
-+	void __user *data = NULL;
-+
-+	if (!access_ok(VERIFY_READ, wrapper,
-+			sizeof(struct fbcon_decor_iowrapper)))
-+		return -EFAULT;
-+
-+	__get_user(vc_num, &wrapper->vc);
-+	__get_user(origin, &wrapper->origin);
-+	__get_user(data, &wrapper->data);
-+
-+	if (!vc_cons_allocated(vc_num))
-+		return -EINVAL;
-+
-+	vc = vc_cons[vc_num].d;
-+
-+	switch (cmd) {
-+	case FBIOCONDECOR_SETPIC:
-+	{
-+		struct fb_image img;
-+		if (copy_from_user(&img, (struct fb_image __user *)data, sizeof(struct fb_image)))
-+			return -EFAULT;
-+
-+		return fbcon_decor_ioctl_dosetpic(vc, &img, origin);
-+	}
-+	case FBIOCONDECOR_SETCFG:
-+	{
-+		struct vc_decor cfg;
-+		if (copy_from_user(&cfg, (struct vc_decor __user *)data, sizeof(struct vc_decor)))
-+			return -EFAULT;
-+
-+		return fbcon_decor_ioctl_dosetcfg(vc, &cfg, origin);
-+	}
-+	case FBIOCONDECOR_GETCFG:
-+	{
-+		int rval;
-+		struct vc_decor cfg;
-+
-+		if (copy_from_user(&cfg, (struct vc_decor __user *)data, sizeof(struct vc_decor)))
-+			return -EFAULT;
-+
-+		rval = fbcon_decor_ioctl_dogetcfg(vc, &cfg);
-+
-+		if (copy_to_user(data, &cfg, sizeof(struct vc_decor)))
-+			return -EFAULT;
-+		return rval;
-+	}
-+	case FBIOCONDECOR_SETSTATE:
-+	{
-+		unsigned int state = 0;
-+		if (get_user(state, (unsigned int __user *)data))
-+			return -EFAULT;
-+		return fbcon_decor_ioctl_dosetstate(vc, state, origin);
-+	}
-+	case FBIOCONDECOR_GETSTATE:
-+	{
-+		unsigned int state = 0;
-+		fbcon_decor_ioctl_dogetstate(vc, &state);
-+		return put_user(state, (unsigned int __user *)data);
-+	}
-+
-+	default:
-+		return -ENOIOCTLCMD;
-+	}
-+}
-+
-+#ifdef CONFIG_COMPAT
-+
-+static long fbcon_decor_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) {
-+
-+	struct fbcon_decor_iowrapper32 __user *wrapper = (void __user *)arg;
-+	struct vc_data *vc = NULL;
-+	unsigned short vc_num = 0;
-+	unsigned char origin = 0;
-+	compat_uptr_t data_compat = 0;
-+	void __user *data = NULL;
-+
-+	if (!access_ok(VERIFY_READ, wrapper,
-+                       sizeof(struct fbcon_decor_iowrapper32)))
-+		return -EFAULT;
-+
-+	__get_user(vc_num, &wrapper->vc);
-+	__get_user(origin, &wrapper->origin);
-+	__get_user(data_compat, &wrapper->data);
-+	data = compat_ptr(data_compat);
-+
-+	if (!vc_cons_allocated(vc_num))
-+		return -EINVAL;
-+
-+	vc = vc_cons[vc_num].d;
-+
-+	switch (cmd) {
-+	case FBIOCONDECOR_SETPIC32:
-+	{
-+		struct fb_image32 img_compat;
-+		struct fb_image img;
-+
-+		if (copy_from_user(&img_compat, (struct fb_image32 __user *)data, sizeof(struct fb_image32)))
-+			return -EFAULT;
-+
-+		fb_image_from_compat(img, img_compat);
-+
-+		return fbcon_decor_ioctl_dosetpic(vc, &img, origin);
-+	}
-+
-+	case FBIOCONDECOR_SETCFG32:
-+	{
-+		struct vc_decor32 cfg_compat;
-+		struct vc_decor cfg;
-+
-+		if (copy_from_user(&cfg_compat, (struct vc_decor32 __user *)data, sizeof(struct vc_decor32)))
-+			return -EFAULT;
-+
-+		vc_decor_from_compat(cfg, cfg_compat);
-+
-+		return fbcon_decor_ioctl_dosetcfg(vc, &cfg, origin);
-+	}
-+
-+	case FBIOCONDECOR_GETCFG32:
-+	{
-+		int rval;
-+		struct vc_decor32 cfg_compat;
-+		struct vc_decor cfg;
-+
-+		if (copy_from_user(&cfg_compat, (struct vc_decor32 __user *)data, sizeof(struct vc_decor32)))
-+			return -EFAULT;
-+		cfg.theme = compat_ptr(cfg_compat.theme);
-+
-+		rval = fbcon_decor_ioctl_dogetcfg(vc, &cfg);
-+
-+		vc_decor_to_compat(cfg_compat, cfg);
-+
-+		if (copy_to_user((struct vc_decor32 __user *)data, &cfg_compat, sizeof(struct vc_decor32)))
-+			return -EFAULT;
-+		return rval;
-+	}
-+
-+	case FBIOCONDECOR_SETSTATE32:
-+	{
-+		compat_uint_t state_compat = 0;
-+		unsigned int state = 0;
-+
-+		if (get_user(state_compat, (compat_uint_t __user *)data))
-+			return -EFAULT;
-+
-+		state = (unsigned int)state_compat;
-+
-+		return fbcon_decor_ioctl_dosetstate(vc, state, origin);
-+	}
-+
-+	case FBIOCONDECOR_GETSTATE32:
-+	{
-+		compat_uint_t state_compat = 0;
-+		unsigned int state = 0;
-+
-+		fbcon_decor_ioctl_dogetstate(vc, &state);
-+		state_compat = (compat_uint_t)state;
-+
-+		return put_user(state_compat, (compat_uint_t __user *)data);
-+	}
-+
-+	default:
-+		return -ENOIOCTLCMD;
-+	}
-+}
-+#else
-+  #define fbcon_decor_compat_ioctl NULL
-+#endif
-+
-+static struct file_operations fbcon_decor_ops = {
-+	.owner = THIS_MODULE,
-+	.unlocked_ioctl = fbcon_decor_ioctl,
-+	.compat_ioctl = fbcon_decor_compat_ioctl
-+};
-+
-+static struct miscdevice fbcon_decor_dev = {
-+	.minor = MISC_DYNAMIC_MINOR,
-+	.name = "fbcondecor",
-+	.fops = &fbcon_decor_ops
-+};
-+
-+void fbcon_decor_reset()
-+{
-+	int i;
-+
-+	for (i = 0; i < num_registered_fb; i++) {
-+		registered_fb[i]->bgdecor.data = NULL;
-+		registered_fb[i]->bgdecor.cmap.red = NULL;
-+	}
-+
-+	for (i = 0; i < MAX_NR_CONSOLES && vc_cons[i].d; i++) {
-+		vc_cons[i].d->vc_decor.state = vc_cons[i].d->vc_decor.twidth =
-+						vc_cons[i].d->vc_decor.theight = 0;
-+		vc_cons[i].d->vc_decor.theme = NULL;
-+	}
-+
-+	return;
-+}
-+
-+int fbcon_decor_init()
-+{
-+	int i;
-+
-+	fbcon_decor_reset();
-+
-+	if (initialized)
-+		return 0;
-+
-+	i = misc_register(&fbcon_decor_dev);
-+	if (i) {
-+		printk(KERN_ERR "fbcondecor: failed to register device\n");
-+		return i;
-+	}
-+
-+	fbcon_decor_call_helper("init", 0);
-+	initialized = 1;
-+	return 0;
-+}
-+
-+int fbcon_decor_exit(void)
-+{
-+	fbcon_decor_reset();
-+	return 0;
-+}
-+
-+EXPORT_SYMBOL(fbcon_decor_path);
---- a/drivers/video/console/fbcondecor.h	2014-01-21 09:50:42.229900176 -0500
-+++ b/drivers/video/console/fbcondecor.h	2014-01-21 09:50:21.489900340 -0500
-@@ -0,0 +1,79 @@
-+/* 
-+ *  linux/drivers/video/console/fbcondecor.h -- Framebuffer Console Decoration headers
-+ *
-+ *  Copyright (C) 2004 Michal Januszewski <spock@g.o>
-+ *
-+ */
-+
-+#ifndef __FBCON_DECOR_H
-+#define __FBCON_DECOR_H
-+
-+#ifndef _LINUX_FB_H
-+#include <linux/fb.h>
-+#endif
-+
-+/* This is needed for vc_cons in fbcmap.c */
-+#include <linux/vt_kern.h>
-+
-+struct fb_cursor;
-+struct fb_info;
-+struct vc_data;
-+
-+#ifdef CONFIG_FB_CON_DECOR
-+/* fbcondecor.c */
-+int fbcon_decor_init(void);
-+int fbcon_decor_exit(void);
-+int fbcon_decor_call_helper(char* cmd, unsigned short cons);
-+int fbcon_decor_disable(struct vc_data *vc, unsigned char redraw);
-+void fbcon_decor_reset(void);
-+
-+/* cfbcondecor.c */
-+void fbcon_decor_putcs(struct vc_data *vc, struct fb_info *info, const unsigned short *s, int count, int yy, int xx);
-+void fbcon_decor_cursor(struct fb_info *info, struct fb_cursor *cursor);
-+void fbcon_decor_clear(struct vc_data *vc, struct fb_info *info, int sy, int sx, int height, int width);
-+void fbcon_decor_clear_margins(struct vc_data *vc, struct fb_info *info, int bottom_only);
-+void fbcon_decor_blank(struct vc_data *vc, struct fb_info *info, int blank);
-+void fbcon_decor_bmove_redraw(struct vc_data *vc, struct fb_info *info, int y, int sx, int dx, int width);
-+void fbcon_decor_copy(u8 *dst, u8 *src, int height, int width, int linebytes, int srclinesbytes, int bpp);
-+void fbcon_decor_fix_pseudo_pal(struct fb_info *info, struct vc_data *vc);
-+
-+/* vt.c */
-+void acquire_console_sem(void);
-+void release_console_sem(void);
-+void do_unblank_screen(int entering_gfx);
-+
-+/* struct vc_data *y */
-+#define fbcon_decor_active_vc(y) (y->vc_decor.state && y->vc_decor.theme) 
-+
-+/* struct fb_info *x, struct vc_data *y */
-+#define fbcon_decor_active_nores(x,y) (x->bgdecor.data && fbcon_decor_active_vc(y))
-+
-+/* struct fb_info *x, struct vc_data *y */
-+#define fbcon_decor_active(x,y) (fbcon_decor_active_nores(x,y) &&		\
-+			      x->bgdecor.width == x->var.xres && 	\
-+			      x->bgdecor.height == x->var.yres &&	\
-+			      x->bgdecor.depth == x->var.bits_per_pixel)
-+
-+
-+#else /* CONFIG_FB_CON_DECOR */
-+
-+static inline void fbcon_decor_putcs(struct vc_data *vc, struct fb_info *info, const unsigned short *s, int count, int yy, int xx) {}
-+static inline void fbcon_decor_putc(struct vc_data *vc, struct fb_info *info, int c, int ypos, int xpos) {}
-+static inline void fbcon_decor_cursor(struct fb_info *info, struct fb_cursor *cursor) {}
-+static inline void fbcon_decor_clear(struct vc_data *vc, struct fb_info *info, int sy, int sx, int height, int width) {}
-+static inline void fbcon_decor_clear_margins(struct vc_data *vc, struct fb_info *info, int bottom_only) {}
-+static inline void fbcon_decor_blank(struct vc_data *vc, struct fb_info *info, int blank) {}
-+static inline void fbcon_decor_bmove_redraw(struct vc_data *vc, struct fb_info *info, int y, int sx, int dx, int width) {}
-+static inline void fbcon_decor_fix_pseudo_pal(struct fb_info *info, struct vc_data *vc) {}
-+static inline int fbcon_decor_call_helper(char* cmd, unsigned short cons) { return 0; }
-+static inline int fbcon_decor_init(void) { return 0; }
-+static inline int fbcon_decor_exit(void) { return 0; }
-+static inline int fbcon_decor_disable(struct vc_data *vc, unsigned char redraw) { return 0; }
-+
-+#define fbcon_decor_active_vc(y) (0)
-+#define fbcon_decor_active_nores(x,y) (0)
-+#define fbcon_decor_active(x,y) (0)
-+
-+#endif /* CONFIG_FB_CON_DECOR */
-+
-+#endif /* __FBCON_DECOR_H */
-diff --git a/drivers/video/fbcmap.c b/drivers/video/fbcmap.c
-index 5c3960d..162b5f4 100644
---- a/drivers/video/fbcmap.c
-+++ b/drivers/video/fbcmap.c
-@@ -17,6 +17,8 @@
- #include <linux/slab.h>
- #include <linux/uaccess.h>
- 
-+#include "console/fbcondecor.h"
-+
- static u16 red2[] __read_mostly = {
-     0x0000, 0xaaaa
- };
-@@ -249,14 +251,17 @@ int fb_set_cmap(struct fb_cmap *cmap, struct fb_info *info)
- 			if (transp)
- 				htransp = *transp++;
- 			if (info->fbops->fb_setcolreg(start++,
--						      hred, hgreen, hblue,
-+						      hred, hgreen, hblue, 
- 						      htransp, info))
- 				break;
- 		}
- 	}
--	if (rc == 0)
-+	if (rc == 0) {
- 		fb_copy_cmap(cmap, &info->cmap);
--
-+		if (fbcon_decor_active(info, vc_cons[fg_console].d) &&
-+		    info->fix.visual == FB_VISUAL_DIRECTCOLOR)
-+			fbcon_decor_fix_pseudo_pal(info, vc_cons[fg_console].d);
-+	}
- 	return rc;
- }
- 
-diff --git a/drivers/video/fbmem.c b/drivers/video/fbmem.c
-index c6ce416..7ce6640 100644
---- a/drivers/video/fbmem.c
-+++ b/drivers/video/fbmem.c
-@@ -1231,15 +1231,6 @@ struct fb_fix_screeninfo32 {
- 	u16			reserved[3];
- };
- 
--struct fb_cmap32 {
--	u32			start;
--	u32			len;
--	compat_caddr_t	red;
--	compat_caddr_t	green;
--	compat_caddr_t	blue;
--	compat_caddr_t	transp;
--};
--
- static int fb_getput_cmap(struct fb_info *info, unsigned int cmd,
- 			  unsigned long arg)
- {
-diff --git a/include/linux/console_decor.h b/include/linux/console_decor.h
-new file mode 100644
-index 0000000..04b8d80
---- /dev/null
-+++ b/include/linux/console_decor.h
-@@ -0,0 +1,46 @@
-+#ifndef _LINUX_CONSOLE_DECOR_H_
-+#define _LINUX_CONSOLE_DECOR_H_ 1
-+
-+/* A structure used by the framebuffer console decorations (drivers/video/console/fbcondecor.c) */
-+struct vc_decor {
-+	__u8 bg_color;				/* The color that is to be treated as transparent */
-+	__u8 state;				/* Current decor state: 0 = off, 1 = on */
-+	__u16 tx, ty;				/* Top left corner coordinates of the text field */
-+	__u16 twidth, theight;			/* Width and height of the text field */
-+	char* theme;
-+};
-+
-+#ifdef __KERNEL__
-+#ifdef CONFIG_COMPAT
-+#include <linux/compat.h>
-+
-+struct vc_decor32 {
-+	__u8 bg_color;				/* The color that is to be treated as transparent */
-+	__u8 state;				/* Current decor state: 0 = off, 1 = on */
-+	__u16 tx, ty;				/* Top left corner coordinates of the text field */
-+	__u16 twidth, theight;			/* Width and height of the text field */
-+	compat_uptr_t theme;
-+};
-+
-+#define vc_decor_from_compat(to, from) \
-+	(to).bg_color = (from).bg_color; \
-+	(to).state    = (from).state; \
-+	(to).tx       = (from).tx; \
-+	(to).ty       = (from).ty; \
-+	(to).twidth   = (from).twidth; \
-+	(to).theight  = (from).theight; \
-+	(to).theme    = compat_ptr((from).theme)
-+
-+#define vc_decor_to_compat(to, from) \
-+	(to).bg_color = (from).bg_color; \
-+	(to).state    = (from).state; \
-+	(to).tx       = (from).tx; \
-+	(to).ty       = (from).ty; \
-+	(to).twidth   = (from).twidth; \
-+	(to).theight  = (from).theight; \
-+	(to).theme    = ptr_to_compat((from).theme)
-+
-+#endif /* CONFIG_COMPAT */
-+#endif /* __KERNEL__ */
-+
-+#endif
-diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h
-index 7f0c329..98f5d60 100644
---- a/include/linux/console_struct.h
-+++ b/include/linux/console_struct.h
-@@ -19,6 +19,7 @@
- struct vt_struct;
- 
- #define NPAR 16
-+#include <linux/console_decor.h>
- 
- struct vc_data {
- 	struct tty_port port;			/* Upper level data */
-@@ -107,6 +108,8 @@ struct vc_data {
- 	unsigned long	vc_uni_pagedir;
- 	unsigned long	*vc_uni_pagedir_loc;  /* [!] Location of uni_pagedir variable for this console */
- 	bool vc_panic_force_write; /* when oops/panic this VC can accept forced output/blanking */
-+
-+	struct vc_decor vc_decor;
- 	/* additional information is in vt_kern.h */
- };
- 
-diff --git a/include/uapi/linux/fb.h b/include/uapi/linux/fb.h
-index d31cb68..ad161bb 100644
---- a/include/uapi/linux/fb.h
-+++ b/include/uapi/linux/fb.h
-@@ -8,6 +8,25 @@
- 
- #define FB_MAX			32	/* sufficient for now */
- 
-+struct fbcon_decor_iowrapper
-+{
-+	unsigned short vc;		/* Virtual console */
-+	unsigned char origin;		/* Point of origin of the request */
-+	void *data;
-+};
-+
-+#ifdef __KERNEL__
-+#ifdef CONFIG_COMPAT
-+#include <linux/compat.h>
-+struct fbcon_decor_iowrapper32
-+{
-+	unsigned short vc;		/* Virtual console */
-+	unsigned char origin;		/* Point of origin of the request */
-+	compat_uptr_t data;
-+};
-+#endif /* CONFIG_COMPAT */
-+#endif /* __KERNEL__ */
-+
- /* ioctls
-    0x46 is 'F'								*/
- #define FBIOGET_VSCREENINFO	0x4600
-@@ -34,6 +53,24 @@
- #define FBIOPUT_MODEINFO        0x4617
- #define FBIOGET_DISPINFO        0x4618
- #define FBIO_WAITFORVSYNC	_IOW('F', 0x20, __u32)
-+#define FBIOCONDECOR_SETCFG	_IOWR('F', 0x19, struct fbcon_decor_iowrapper)
-+#define FBIOCONDECOR_GETCFG	_IOR('F', 0x1A, struct fbcon_decor_iowrapper)
-+#define FBIOCONDECOR_SETSTATE	_IOWR('F', 0x1B, struct fbcon_decor_iowrapper)
-+#define FBIOCONDECOR_GETSTATE	_IOR('F', 0x1C, struct fbcon_decor_iowrapper)
-+#define FBIOCONDECOR_SETPIC 	_IOWR('F', 0x1D, struct fbcon_decor_iowrapper)
-+#ifdef __KERNEL__
-+#ifdef CONFIG_COMPAT
-+#define FBIOCONDECOR_SETCFG32	_IOWR('F', 0x19, struct fbcon_decor_iowrapper32)
-+#define FBIOCONDECOR_GETCFG32	_IOR('F', 0x1A, struct fbcon_decor_iowrapper32)
-+#define FBIOCONDECOR_SETSTATE32	_IOWR('F', 0x1B, struct fbcon_decor_iowrapper32)
-+#define FBIOCONDECOR_GETSTATE32	_IOR('F', 0x1C, struct fbcon_decor_iowrapper32)
-+#define FBIOCONDECOR_SETPIC32	_IOWR('F', 0x1D, struct fbcon_decor_iowrapper32)
-+#endif /* CONFIG_COMPAT */
-+#endif /* __KERNEL__ */
-+
-+#define FBCON_DECOR_THEME_LEN		128	/* Maximum lenght of a theme name */
-+#define FBCON_DECOR_IO_ORIG_KERNEL	0	/* Kernel ioctl origin */
-+#define FBCON_DECOR_IO_ORIG_USER	1	/* User ioctl origin */
- 
- #define FB_TYPE_PACKED_PIXELS		0	/* Packed Pixels	*/
- #define FB_TYPE_PLANES			1	/* Non interleaved planes */
-@@ -286,6 +323,28 @@ struct fb_cmap {
- 	__u16 *transp;			/* transparency, can be NULL */
- };
- 
-+#ifdef __KERNEL__
-+#ifdef CONFIG_COMPAT
-+struct fb_cmap32 {
-+	__u32 start;
-+	__u32 len;			/* Number of entries */
-+	compat_uptr_t red;		/* Red values	*/
-+	compat_uptr_t green;
-+	compat_uptr_t blue;
-+	compat_uptr_t transp;		/* transparency, can be NULL */
-+};
-+
-+#define fb_cmap_from_compat(to, from) \
-+	(to).start  = (from).start; \
-+	(to).len    = (from).len; \
-+	(to).red    = compat_ptr((from).red); \
-+	(to).green  = compat_ptr((from).green); \
-+	(to).blue   = compat_ptr((from).blue); \
-+	(to).transp = compat_ptr((from).transp)
-+
-+#endif /* CONFIG_COMPAT */
-+#endif /* __KERNEL__ */
-+
- struct fb_con2fbmap {
- 	__u32 console;
- 	__u32 framebuffer;
-@@ -367,6 +426,34 @@ struct fb_image {
- 	struct fb_cmap cmap;	/* color map info */
- };
- 
-+#ifdef __KERNEL__
-+#ifdef CONFIG_COMPAT
-+struct fb_image32 {
-+	__u32 dx;			/* Where to place image */
-+	__u32 dy;
-+	__u32 width;			/* Size of image */
-+	__u32 height;
-+	__u32 fg_color;			/* Only used when a mono bitmap */
-+	__u32 bg_color;
-+	__u8  depth;			/* Depth of the image */
-+	const compat_uptr_t data;	/* Pointer to image data */
-+	struct fb_cmap32 cmap;		/* color map info */
-+};
-+
-+#define fb_image_from_compat(to, from) \
-+	(to).dx       = (from).dx; \
-+	(to).dy       = (from).dy; \
-+	(to).width    = (from).width; \
-+	(to).height   = (from).height; \
-+	(to).fg_color = (from).fg_color; \
-+	(to).bg_color = (from).bg_color; \
-+	(to).depth    = (from).depth; \
-+	(to).data     = compat_ptr((from).data); \
-+	fb_cmap_from_compat((to).cmap, (from).cmap)
-+
-+#endif /* CONFIG_COMPAT */
-+#endif /* __KERNEL__ */
-+
- /*
-  * hardware cursor control
-  */
-
-diff --git a/include/linux/fb.h b/include/linux/fb.h
-index d31cb68..ad161bb 100644
---- a/include/linux/fb.h
-+++ b/include/linux/fb.h
-@@ -488,5 +488,8 @@ #define FBINFO_STATE_SUSPENDED		1
- 	u32 state;			/* Hardware state i.e suspend */
- 	void *fbcon_par;                /* fbcon use-only private area */
-+
-+	struct fb_image bgdecor;
-+
- 	/* From here on everything is device dependent */
- 	void *par;
- 	/* we need the PCI or similar aperture base/size not
-
-diff --git a/kernel/sysctl.c b/kernel/sysctl.c
-index 4ab1187..6561627 100644
---- a/kernel/sysctl.c
-+++ b/kernel/sysctl.c
-@@ -145,6 +145,10 @@ static int min_percpu_pagelist_fract = 8;
- static int ngroups_max = NGROUPS_MAX;
- static const int cap_last_cap = CAP_LAST_CAP;
- 
-+#ifdef CONFIG_FB_CON_DECOR
-+extern char fbcon_decor_path[];
-+#endif
-+
- #ifdef CONFIG_INOTIFY_USER
- #include <linux/inotify.h>
- #endif
-@@ -248,6 +252,15 @@ static struct ctl_table sysctl_base_table[] = {
- 		.mode		= 0555,
- 		.child		= dev_table,
- 	},
-+#ifdef CONFIG_FB_CON_DECOR
-+	{
-+		.procname	= "fbcondecor",
-+		.data		= &fbcon_decor_path,
-+		.maxlen		= KMOD_PATH_LEN,
-+		.mode		= 0644,
-+		.proc_handler	= &proc_dostring,
-+	},
-+#endif
- 	{ }
- };
- 
-@@ -1091,7 +1104,7 @@ static struct ctl_table vm_table[] = {
- 		.proc_handler	= proc_dointvec,
- 	},
- 	{
--		.procname	= "page-cluster", 
-+		.procname	= "page-cluster",
- 		.data		= &page_cluster,
- 		.maxlen		= sizeof(int),
- 		.mode		= 0644,
-@@ -1535,7 +1548,7 @@ static struct ctl_table fs_table[] = {
- 		.mode		= 0555,
- 		.child		= inotify_table,
- 	},
--#endif	
-+#endif
- #ifdef CONFIG_EPOLL
- 	{
- 		.procname	= "epoll",
-@@ -1873,12 +1886,12 @@ static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table,
- 	unsigned long page = 0;
- 	size_t left;
- 	char *kbuf;
--	
-+
- 	if (!tbl_data || !table->maxlen || !*lenp || (*ppos && !write)) {
- 		*lenp = 0;
- 		return 0;
- 	}
--	
-+
- 	i = (int *) tbl_data;
- 	vleft = table->maxlen / sizeof(*i);
- 	left = *lenp;
-@@ -1967,7 +1980,7 @@ static int do_proc_dointvec(struct ctl_table *table, int write,
-  * @ppos: file position
-  *
-  * Reads/writes up to table->maxlen/sizeof(unsigned int) integer
-- * values from/to the user buffer, treated as an ASCII string. 
-+ * values from/to the user buffer, treated as an ASCII string.
-  *
-  * Returns 0 on success.
-  */
-@@ -2326,7 +2339,7 @@ static int do_proc_dointvec_ms_jiffies_conv(bool *negp, unsigned long *lvalp,
-  * @ppos: file position
-  *
-  * Reads/writes up to table->maxlen/sizeof(unsigned int) integer
-- * values from/to the user buffer, treated as an ASCII string. 
-+ * values from/to the user buffer, treated as an ASCII string.
-  * The values read are assumed to be in seconds, and are converted into
-  * jiffies.
-  *
-@@ -2348,8 +2361,8 @@ int proc_dointvec_jiffies(struct ctl_table *table, int write,
-  * @ppos: pointer to the file position
-  *
-  * Reads/writes up to table->maxlen/sizeof(unsigned int) integer
-- * values from/to the user buffer, treated as an ASCII string. 
-- * The values read are assumed to be in 1/USER_HZ seconds, and 
-+ * values from/to the user buffer, treated as an ASCII string.
-+ * The values read are assumed to be in 1/USER_HZ seconds, and
-  * are converted into jiffies.
-  *
-  * Returns 0 on success.
-@@ -2371,8 +2384,8 @@ int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write,
-  * @ppos: the current position in the file
-  *
-  * Reads/writes up to table->maxlen/sizeof(unsigned int) integer
-- * values from/to the user buffer, treated as an ASCII string. 
-- * The values read are assumed to be in 1/1000 seconds, and 
-+ * values from/to the user buffer, treated as an ASCII string.
-+ * The values read are assumed to be in 1/1000 seconds, and
-  * are converted into jiffies.
-  *
-  * Returns 0 on success.
--- 
-1.7.10
-

Deleted: genpatches-2.6/trunk/3.15/5000_enable-additional-cpu-optimizations-for-gcc.patch
===================================================================
--- genpatches-2.6/trunk/3.15/5000_enable-additional-cpu-optimizations-for-gcc.patch	2014-05-05 14:22:27 UTC (rev 2771)
+++ genpatches-2.6/trunk/3.15/5000_enable-additional-cpu-optimizations-for-gcc.patch	2014-05-05 14:28:48 UTC (rev 2772)
@@ -1,325 +0,0 @@
-This patch has been tested on and known to work with kernel versions from 3.2
-up to the latest git version (pulled on 12/14/2013).
-
-This patch will expand the number of microarchitectures to include new
-processors including: AMD K10-family, AMD Family 10h (Barcelona), AMD Family
-14h (Bobcat), AMD Family 15h (Bulldozer), AMD Family 15h (Piledriver), AMD
-Family 16h (Jaguar), Intel 1st Gen Core i3/i5/i7 (Nehalem), Intel 2nd Gen Core
-i3/i5/i7 (Sandybridge), Intel 3rd Gen Core i3/i5/i7 (Ivybridge), and Intel 4th
-Gen Core i3/i5/i7 (Haswell). It also offers the compiler the 'native' flag.
-
-Small but real speed increases are measurable using a make endpoint comparing
-a generic kernel to one built with one of the respective microarchs.
-
-See the following experimental evidence supporting this statement:
-https://github.com/graysky2/kernel_gcc_patch
-
----
-diff -uprN a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h
---- a/arch/x86/include/asm/module.h	2013-11-03 18:41:51.000000000 -0500
-+++ b/arch/x86/include/asm/module.h	2013-12-15 06:21:24.351122516 -0500
-@@ -15,6 +15,16 @@
- #define MODULE_PROC_FAMILY "586MMX "
- #elif defined CONFIG_MCORE2
- #define MODULE_PROC_FAMILY "CORE2 "
-+#elif defined CONFIG_MNATIVE
-+#define MODULE_PROC_FAMILY "NATIVE "
-+#elif defined CONFIG_MCOREI7
-+#define MODULE_PROC_FAMILY "COREI7 "
-+#elif defined CONFIG_MCOREI7AVX
-+#define MODULE_PROC_FAMILY "COREI7AVX "
-+#elif defined CONFIG_MCOREAVXI
-+#define MODULE_PROC_FAMILY "COREAVXI "
-+#elif defined CONFIG_MCOREAVX2
-+#define MODULE_PROC_FAMILY "COREAVX2 "
- #elif defined CONFIG_MATOM
- #define MODULE_PROC_FAMILY "ATOM "
- #elif defined CONFIG_M686
-@@ -33,6 +43,18 @@
- #define MODULE_PROC_FAMILY "K7 "
- #elif defined CONFIG_MK8
- #define MODULE_PROC_FAMILY "K8 "
-+#elif defined CONFIG_MK10
-+#define MODULE_PROC_FAMILY "K10 "
-+#elif defined CONFIG_MBARCELONA
-+#define MODULE_PROC_FAMILY "BARCELONA "
-+#elif defined CONFIG_MBOBCAT
-+#define MODULE_PROC_FAMILY "BOBCAT "
-+#elif defined CONFIG_MBULLDOZER
-+#define MODULE_PROC_FAMILY "BULLDOZER "
-+#elif defined CONFIG_MPILEDRIVER
-+#define MODULE_PROC_FAMILY "PILEDRIVER "
-+#elif defined CONFIG_MJAGUAR
-+#define MODULE_PROC_FAMILY "JAGUAR "
- #elif defined CONFIG_MELAN
- #define MODULE_PROC_FAMILY "ELAN "
- #elif defined CONFIG_MCRUSOE
-diff -uprN a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
---- a/arch/x86/Kconfig.cpu	2013-11-03 18:41:51.000000000 -0500
-+++ b/arch/x86/Kconfig.cpu	2013-12-15 06:21:24.351122516 -0500
-@@ -139,7 +139,7 @@ config MPENTIUM4
- 
- 
- config MK6
--	bool "K6/K6-II/K6-III"
-+	bool "AMD K6/K6-II/K6-III"
- 	depends on X86_32
- 	---help---
- 	  Select this for an AMD K6-family processor.  Enables use of
-@@ -147,7 +147,7 @@ config MK6
- 	  flags to GCC.
- 
- config MK7
--	bool "Athlon/Duron/K7"
-+	bool "AMD Athlon/Duron/K7"
- 	depends on X86_32
- 	---help---
- 	  Select this for an AMD Athlon K7-family processor.  Enables use of
-@@ -155,12 +155,55 @@ config MK7
- 	  flags to GCC.
- 
- config MK8
--	bool "Opteron/Athlon64/Hammer/K8"
-+	bool "AMD Opteron/Athlon64/Hammer/K8"
- 	---help---
- 	  Select this for an AMD Opteron or Athlon64 Hammer-family processor.
- 	  Enables use of some extended instructions, and passes appropriate
- 	  optimization flags to GCC.
- 
-+config MK10
-+	bool "AMD 61xx/7x50/PhenomX3/X4/II/K10"
-+	---help---
-+	  Select this for an AMD 61xx Eight-Core Magny-Cours, Athlon X2 7x50,
-+		Phenom X3/X4/II, Athlon II X2/X3/X4, or Turion II-family processor.
-+	  Enables use of some extended instructions, and passes appropriate
-+	  optimization flags to GCC.
-+
-+config MBARCELONA
-+	bool "AMD Barcelona"
-+	---help---
-+	  Select this for AMD Barcelona and newer processors.
-+
-+	  Enables -march=barcelona
-+
-+config MBOBCAT
-+	bool "AMD Bobcat"
-+	---help---
-+	  Select this for AMD Bobcat processors.
-+
-+	  Enables -march=btver1
-+
-+config MBULLDOZER
-+	bool "AMD Bulldozer"
-+	---help---
-+	  Select this for AMD Bulldozer processors.
-+
-+	  Enables -march=bdver1
-+
-+config MPILEDRIVER
-+	bool "AMD Piledriver"
-+	---help---
-+	  Select this for AMD Piledriver processors.
-+
-+	  Enables -march=bdver2
-+
-+config MJAGUAR
-+	bool "AMD Jaguar"
-+	---help---
-+	  Select this for AMD Jaguar processors.
-+
-+	  Enables -march=btver2
-+
- config MCRUSOE
- 	bool "Crusoe"
- 	depends on X86_32
-@@ -251,8 +294,17 @@ config MPSC
- 	  using the cpu family field
- 	  in /proc/cpuinfo. Family 15 is an older Xeon, Family 6 a newer one.
- 
-+config MATOM
-+	bool "Intel Atom"
-+	---help---
-+
-+	  Select this for the Intel Atom platform. Intel Atom CPUs have an
-+	  in-order pipelining architecture and thus can benefit from
-+	  accordingly optimized code. Use a recent GCC with specific Atom
-+	  support in order to fully benefit from selecting this option.
-+
- config MCORE2
--	bool "Core 2/newer Xeon"
-+	bool "Intel Core 2"
- 	---help---
- 
- 	  Select this for Intel Core 2 and newer Core 2 Xeons (Xeon 51xx and
-@@ -260,14 +312,40 @@ config MCORE2
- 	  family in /proc/cpuinfo. Newer ones have 6 and older ones 15
- 	  (not a typo)
- 
--config MATOM
--	bool "Intel Atom"
-+	  Enables -march=core2
-+
-+config MCOREI7
-+	bool "Intel Core i7"
- 	---help---
- 
--	  Select this for the Intel Atom platform. Intel Atom CPUs have an
--	  in-order pipelining architecture and thus can benefit from
--	  accordingly optimized code. Use a recent GCC with specific Atom
--	  support in order to fully benefit from selecting this option.
-+	  Select this for the Intel Nehalem platform. Intel Nehalem proecessors
-+	  include Core i3, i5, i7, Xeon: 34xx, 35xx, 55xx, 56xx, 75xx processors.
-+
-+	  Enables -march=corei7
-+
-+config MCOREI7AVX
-+	bool "Intel Core 2nd Gen AVX"
-+	---help---
-+
-+	  Select this for 2nd Gen Core processors including Sandy Bridge.
-+
-+	  Enables -march=corei7-avx
-+
-+config MCOREAVXI
-+	bool "Intel Core 3rd Gen AVX"
-+	---help---
-+
-+	  Select this for 3rd Gen Core processors including Ivy Bridge.
-+
-+	  Enables -march=core-avx-i
-+
-+config MCOREAVX2
-+	bool "Intel Core AVX2"
-+	---help---
-+
-+	  Select this for AVX2 enabled processors including Haswell.
-+
-+	  Enables -march=core-avx2
- 
- config GENERIC_CPU
- 	bool "Generic-x86-64"
-@@ -276,6 +354,19 @@ config GENERIC_CPU
- 	  Generic x86-64 CPU.
- 	  Run equally well on all x86-64 CPUs.
- 
-+config MNATIVE
-+ bool "Native optimizations autodetected by GCC"
-+ ---help---
-+
-+   GCC 4.2 and above support -march=native, which automatically detects
-+   the optimum settings to use based on your processor. -march=native 
-+   also detects and applies additional settings beyond -march specific
-+   to your CPU, (eg. -msse4). Unless you have a specific reason not to
-+   (e.g. distcc cross-compiling), you should probably be using
-+   -march=native rather than anything listed below.
-+
-+   Enables -march=native
-+
- endchoice
- 
- config X86_GENERIC
-@@ -300,7 +391,7 @@ config X86_INTERNODE_CACHE_SHIFT
- config X86_L1_CACHE_SHIFT
- 	int
- 	default "7" if MPENTIUM4 || MPSC
--	default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MATOM || MVIAC7 || X86_GENERIC || GENERIC_CPU
-+	default "6" if MK7 || MK8 || MK10 || MBARCELONA || MBOBCAT || MBULLDOZER || MPILEDRIVER || MJAGUAR || MPENTIUMM || MCORE2 || MCOREI7 || MCOREI7AVX || MCOREAVXI || MCOREAVX2 || MATOM || MVIAC7 || X86_GENERIC || MNATIVE || GENERIC_CPU
- 	default "4" if MELAN || M486 || MGEODEGX1
- 	default "5" if MWINCHIP3D || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX
- 
-@@ -331,11 +422,11 @@ config X86_ALIGNMENT_16
- 
- config X86_INTEL_USERCOPY
- 	def_bool y
--	depends on MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M586MMX || X86_GENERIC || MK8 || MK7 || MEFFICEON || MCORE2
-+	depends on MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M586MMX || MNATIVE || X86_GENERIC || MK8 || MK7 || MK10 || MBARCELONA || MEFFICEON || MCORE2 || MCOREI7 || MCOREI7AVX || MCOREAVXI || MCOREAVX2
- 
- config X86_USE_PPRO_CHECKSUM
- 	def_bool y
--	depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC3_2 || MVIAC7 || MEFFICEON || MGEODE_LX || MCORE2 || MATOM
-+	depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MK10 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC3_2 || MVIAC7 || MEFFICEON || MGEODE_LX || MCORE2 || MCOREI7 || MCOREI7AVX || MCOREAVXI || MCOREAVX2 || MATOM || MNATIVE
- 
- config X86_USE_3DNOW
- 	def_bool y
-@@ -363,17 +454,17 @@ config X86_P6_NOP
- 
- config X86_TSC
- 	def_bool y
--	depends on ((MWINCHIP3D || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2 || MATOM) && !X86_NUMAQ) || X86_64
-+	depends on ((MWINCHIP3D || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MK10 || MBARCELONA || MBOBCAT || MBULLDOZER || MPILEDRIVER || MJAGUAR || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2 || MCOREI7 || MCOREI7-AVX || MATOM) && !X86_NUMAQ) || X86_64 || MNATIVE
- 
- config X86_CMPXCHG64
- 	def_bool y
--	depends on X86_PAE || X86_64 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MATOM
-+	depends on X86_PAE || X86_64 || MCORE2 || MCOREI7 || MCOREI7AVX || MCOREAVXI || MCOREAVX2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MATOM || MNATIVE
- 
- # this should be set for all -march=.. options where the compiler
- # generates cmov.
- config X86_CMOV
- 	def_bool y
--	depends on (MK8 || MK7 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MCRUSOE || MEFFICEON || X86_64 || MATOM || MGEODE_LX)
-+	depends on (MK8 || MK10 || MBARCELONA || MBOBCAT || MBULLDOZER || MPILEDRIVER || MJAGUAR || MK7 || MCORE2 || MCOREI7 || MCOREI7AVX || MCOREAVXI || MCOREAVX2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MCRUSOE || MEFFICEON || X86_64 || MNATIVE || MATOM || MGEODE_LX)
- 
- config X86_MINIMUM_CPU_FAMILY
- 	int
-diff -uprN a/arch/x86/Makefile b/arch/x86/Makefile
---- a/arch/x86/Makefile	2013-11-03 18:41:51.000000000 -0500
-+++ b/arch/x86/Makefile	2013-12-15 06:21:24.354455723 -0500
-@@ -61,11 +61,26 @@ else
- 	KBUILD_CFLAGS += $(call cc-option,-mno-sse -mpreferred-stack-boundary=3)
- 
-         # FIXME - should be integrated in Makefile.cpu (Makefile_32.cpu)
-+        cflags-$(CONFIG_MNATIVE) += $(call cc-option,-march=native)
-         cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8)
-+        cflags-$(CONFIG_MK10) += $(call cc-option,-march=amdfam10)
-+        cflags-$(CONFIG_MBARCELONA) += $(call cc-option,-march=barcelona)
-+        cflags-$(CONFIG_MBOBCAT) += $(call cc-option,-march=btver1)
-+        cflags-$(CONFIG_MBULLDOZER) += $(call cc-option,-march=bdver1)
-+        cflags-$(CONFIG_MPILEDRIVER) += $(call cc-option,-march=bdver2)
-+        cflags-$(CONFIG_MJAGUAR) += $(call cc-option,-march=btver2)
-         cflags-$(CONFIG_MPSC) += $(call cc-option,-march=nocona)
- 
-         cflags-$(CONFIG_MCORE2) += \
--                $(call cc-option,-march=core2,$(call cc-option,-mtune=generic))
-+                $(call cc-option,-march=core2,$(call cc-option,-mtune=core2))
-+        cflags-$(CONFIG_MCOREI7) += \
-+                $(call cc-option,-march=corei7,$(call cc-option,-mtune=corei7))
-+        cflags-$(CONFIG_MCOREI7AVX) += \
-+                $(call cc-option,-march=corei7-avx,$(call cc-option,-mtune=corei7-avx))
-+        cflags-$(CONFIG_MCOREAVXI) += \
-+                $(call cc-option,-march=core-avx-i,$(call cc-option,-mtune=core-avx-i))
-+        cflags-$(CONFIG_MCOREAVX2) += \
-+                $(call cc-option,-march=core-avx2,$(call cc-option,-mtune=core-avx2))
- 	cflags-$(CONFIG_MATOM) += $(call cc-option,-march=atom) \
- 		$(call cc-option,-mtune=atom,$(call cc-option,-mtune=generic))
-         cflags-$(CONFIG_GENERIC_CPU) += $(call cc-option,-mtune=generic)
-diff -uprN a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu
---- a/arch/x86/Makefile_32.cpu	2013-11-03 18:41:51.000000000 -0500
-+++ b/arch/x86/Makefile_32.cpu	2013-12-15 06:21:24.354455723 -0500
-@@ -23,7 +23,14 @@ cflags-$(CONFIG_MK6)		+= -march=k6
- # Please note, that patches that add -march=athlon-xp and friends are pointless.
- # They make zero difference whatsosever to performance at this time.
- cflags-$(CONFIG_MK7)		+= -march=athlon
-+cflags-$(CONFIG_MNATIVE) += $(call cc-option,-march=native)
- cflags-$(CONFIG_MK8)		+= $(call cc-option,-march=k8,-march=athlon)
-+cflags-$(CONFIG_MK10)	+= $(call cc-option,-march=amdfam10,-march=athlon)
-+cflags-$(CONFIG_MBARCELONA)	+= $(call cc-option,-march=barcelona,-march=athlon)
-+cflags-$(CONFIG_MBOBCAT)	+= $(call cc-option,-march=btver1,-march=athlon)
-+cflags-$(CONFIG_MBULLDOZER)	+= $(call cc-option,-march=bdver1,-march=athlon)
-+cflags-$(CONFIG_MPILEDRIVER)	+= $(call cc-option,-march=bdver2,-march=athlon)
-+cflags-$(CONFIG_MJAGUAR)	+= $(call cc-option,-march=btver2,-march=athlon)
- cflags-$(CONFIG_MCRUSOE)	+= -march=i686 $(align)-functions=0 $(align)-jumps=0 $(align)-loops=0
- cflags-$(CONFIG_MEFFICEON)	+= -march=i686 $(call tune,pentium3) $(align)-functions=0 $(align)-jumps=0 $(align)-loops=0
- cflags-$(CONFIG_MWINCHIPC6)	+= $(call cc-option,-march=winchip-c6,-march=i586)
-@@ -32,6 +39,10 @@ cflags-$(CONFIG_MCYRIXIII)	+= $(call cc-
- cflags-$(CONFIG_MVIAC3_2)	+= $(call cc-option,-march=c3-2,-march=i686)
- cflags-$(CONFIG_MVIAC7)		+= -march=i686
- cflags-$(CONFIG_MCORE2)		+= -march=i686 $(call tune,core2)
-+cflags-$(CONFIG_MCOREI7)	+= -march=i686 $(call tune,corei7)
-+cflags-$(CONFIG_MCOREI7AVX)	+= -march=i686 $(call tune,corei7-avx)
-+cflags-$(CONFIG_MCOREAVXI)	+= -march=i686 $(call tune,core-avx-i)
-+cflags-$(CONFIG_MCOREAVX2)	+= -march=i686 $(call tune,core-avx2)
- cflags-$(CONFIG_MATOM)		+= $(call cc-option,-march=atom,$(call cc-option,-march=core2,-march=i686)) \
- 	$(call cc-option,-mtune=atom,$(call cc-option,-mtune=generic))
- 
-

Deleted: genpatches-2.6/trunk/3.15/5001_BFQ-1-block-cgroups-kconfig-build-bits-for-BFQ-v7r2-3.14.patch
===================================================================
--- genpatches-2.6/trunk/3.15/5001_BFQ-1-block-cgroups-kconfig-build-bits-for-BFQ-v7r2-3.14.patch	2014-05-05 14:22:27 UTC (rev 2771)
+++ genpatches-2.6/trunk/3.15/5001_BFQ-1-block-cgroups-kconfig-build-bits-for-BFQ-v7r2-3.14.patch	2014-05-05 14:28:48 UTC (rev 2772)
@@ -1,104 +0,0 @@
-From c3280db98437c9520f04ecacfdf1a868d7a4b7b3 Mon Sep 17 00:00:00 2001
-From: Paolo Valente <paolo.valente@×××××××.it>
-Date: Tue, 3 Sep 2013 16:50:42 +0200
-Subject: [PATCH 1/3] block: cgroups, kconfig, build bits for BFQ-v7r2-3.14
-
-Update Kconfig.iosched and do the related Makefile changes to include
-kernel configuration options for BFQ. Also add the bfqio controller
-to the cgroups subsystem.
-
-Signed-off-by: Paolo Valente <paolo.valente@×××××××.it>
-Signed-off-by: Arianna Avanzini <avanzini.arianna@×××××.com>
----
- block/Kconfig.iosched         | 32 ++++++++++++++++++++++++++++++++
- block/Makefile                |  1 +
- include/linux/cgroup_subsys.h |  4 ++++
- 3 files changed, 37 insertions(+)
-
-diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched
-index 421bef9..0ee5f0f 100644
---- a/block/Kconfig.iosched
-+++ b/block/Kconfig.iosched
-@@ -39,6 +39,27 @@ config CFQ_GROUP_IOSCHED
- 	---help---
- 	  Enable group IO scheduling in CFQ.
- 
-+config IOSCHED_BFQ
-+	tristate "BFQ I/O scheduler"
-+	default n
-+	---help---
-+	  The BFQ I/O scheduler tries to distribute bandwidth among
-+	  all processes according to their weights.
-+	  It aims at distributing the bandwidth as desired, independently of
-+	  the disk parameters and with any workload. It also tries to
-+	  guarantee low latency to interactive and soft real-time
-+	  applications. If compiled built-in (saying Y here), BFQ can
-+	  be configured to support hierarchical scheduling.
-+
-+config CGROUP_BFQIO
-+	bool "BFQ hierarchical scheduling support"
-+	depends on CGROUPS && IOSCHED_BFQ=y
-+	default n
-+	---help---
-+	  Enable hierarchical scheduling in BFQ, using the cgroups
-+	  filesystem interface.  The name of the subsystem will be
-+	  bfqio.
-+
- choice
- 	prompt "Default I/O scheduler"
- 	default DEFAULT_CFQ
-@@ -52,6 +73,16 @@ choice
- 	config DEFAULT_CFQ
- 		bool "CFQ" if IOSCHED_CFQ=y
- 
-+	config DEFAULT_BFQ
-+		bool "BFQ" if IOSCHED_BFQ=y
-+		help
-+		  Selects BFQ as the default I/O scheduler which will be
-+		  used by default for all block devices.
-+		  The BFQ I/O scheduler aims at distributing the bandwidth
-+		  as desired, independently of the disk parameters and with
-+		  any workload. It also tries to guarantee low latency to
-+		  interactive and soft real-time applications.
-+
- 	config DEFAULT_NOOP
- 		bool "No-op"
- 
-@@ -61,6 +92,7 @@ config DEFAULT_IOSCHED
- 	string
- 	default "deadline" if DEFAULT_DEADLINE
- 	default "cfq" if DEFAULT_CFQ
-+	default "bfq" if DEFAULT_BFQ
- 	default "noop" if DEFAULT_NOOP
- 
- endmenu
-diff --git a/block/Makefile b/block/Makefile
-index 20645e8..cbd83fb 100644
---- a/block/Makefile
-+++ b/block/Makefile
-@@ -16,6 +16,7 @@ obj-$(CONFIG_BLK_DEV_THROTTLING)	+= blk-throttle.o
- obj-$(CONFIG_IOSCHED_NOOP)	+= noop-iosched.o
- obj-$(CONFIG_IOSCHED_DEADLINE)	+= deadline-iosched.o
- obj-$(CONFIG_IOSCHED_CFQ)	+= cfq-iosched.o
-+obj-$(CONFIG_IOSCHED_BFQ)	+= bfq-iosched.o
- 
- obj-$(CONFIG_BLOCK_COMPAT)	+= compat_ioctl.o
- obj-$(CONFIG_BLK_DEV_INTEGRITY)	+= blk-integrity.o
-diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h
-index 7b99d71..4e8c0ff 100644
---- a/include/linux/cgroup_subsys.h
-+++ b/include/linux/cgroup_subsys.h
-@@ -39,6 +39,10 @@ SUBSYS(net_cls)
- SUBSYS(blkio)
- #endif
- 
-+#if IS_SUBSYS_ENABLED(CONFIG_CGROUP_BFQIO)
-+SUBSYS(bfqio)
-+#endif
-+
- #if IS_SUBSYS_ENABLED(CONFIG_CGROUP_PERF)
- SUBSYS(perf)
- #endif
--- 
-1.9.0
-

Deleted: genpatches-2.6/trunk/3.15/5002_BFQ-2-block-introduce-the-BFQ-v7r2-I-O-sched-for-3.14.patch1
===================================================================
--- genpatches-2.6/trunk/3.15/5002_BFQ-2-block-introduce-the-BFQ-v7r2-I-O-sched-for-3.14.patch1	2014-05-05 14:22:27 UTC (rev 2771)
+++ genpatches-2.6/trunk/3.15/5002_BFQ-2-block-introduce-the-BFQ-v7r2-I-O-sched-for-3.14.patch1	2014-05-05 14:28:48 UTC (rev 2772)
@@ -1,6065 +0,0 @@
-From 5055277df59d9280da6b60cf90bed8e5e57dc44d Mon Sep 17 00:00:00 2001
-From: Paolo Valente <paolo.valente@×××××××.it>
-Date: Thu, 9 May 2013 19:10:02 +0200
-Subject: [PATCH 2/3] block: introduce the BFQ-v7r2 I/O sched for 3.14
-
-Add the BFQ-v7r2 I/O scheduler to 3.14.
-The general structure is borrowed from CFQ, as much of the code for
-handling I/O contexts. Over time, several useful features have been
-ported from CFQ as well (details in the changelog in README.BFQ). A
-(bfq_)queue is associated to each task doing I/O on a device, and each
-time a scheduling decision has to be made a queue is selected and served
-until it expires.
-
-    - Slices are given in the service domain: tasks are assigned
-      budgets, measured in number of sectors. Once got the disk, a task
-      must however consume its assigned budget within a configurable
-      maximum time (by default, the maximum possible value of the
-      budgets is automatically computed to comply with this timeout).
-      This allows the desired latency vs "throughput boosting" tradeoff
-      to be set.
-
-    - Budgets are scheduled according to a variant of WF2Q+, implemented
-      using an augmented rb-tree to take eligibility into account while
-      preserving an O(log N) overall complexity.
-
-    - A low-latency tunable is provided; if enabled, both interactive
-      and soft real-time applications are guaranteed a very low latency.
-
-    - Latency guarantees are preserved also in the presence of NCQ.
-
-    - Also with flash-based devices, a high throughput is achieved
-      while still preserving latency guarantees.
-
-    - BFQ features Early Queue Merge (EQM), a sort of fusion of the
-      cooperating-queue-merging and the preemption mechanisms present
-      in CFQ. EQM is in fact a unified mechanism that tries to get a
-      sequential read pattern, and hence a high throughput, with any
-      set of processes performing interleaved I/O over a contiguous
-      sequence of sectors.
-
-    - BFQ supports full hierarchical scheduling, exporting a cgroups
-      interface.  Since each node has a full scheduler, each group can
-      be assigned its own weight.
-
-    - If the cgroups interface is not used, only I/O priorities can be
-      assigned to processes, with ioprio values mapped to weights
-      with the relation weight = IOPRIO_BE_NR - ioprio.
-
-    - ioprio classes are served in strict priority order, i.e., lower
-      priority queues are not served as long as there are higher
-      priority queues.  Among queues in the same class the bandwidth is
-      distributed in proportion to the weight of each queue. A very
-      thin extra bandwidth is however guaranteed to the Idle class, to
-      prevent it from starving.
-
-Signed-off-by: Paolo Valente <paolo.valente@×××××××.it>
-Signed-off-by: Arianna Avanzini <avanzini.arianna@×××××.com>
----
- block/bfq-cgroup.c  |  926 +++++++++++++++
- block/bfq-ioc.c     |   36 +
- block/bfq-iosched.c | 3300 +++++++++++++++++++++++++++++++++++++++++++++++++++
- block/bfq-sched.c   | 1078 +++++++++++++++++
- block/bfq.h         |  622 ++++++++++
- 5 files changed, 5962 insertions(+)
- create mode 100644 block/bfq-cgroup.c
- create mode 100644 block/bfq-ioc.c
- create mode 100644 block/bfq-iosched.c
- create mode 100644 block/bfq-sched.c
- create mode 100644 block/bfq.h
-
-diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
-new file mode 100644
-index 0000000..bcecdb4
---- /dev/null
-+++ b/block/bfq-cgroup.c
-@@ -0,0 +1,926 @@
-+/*
-+ * BFQ: CGROUPS support.
-+ *
-+ * Based on ideas and code from CFQ:
-+ * Copyright (C) 2003 Jens Axboe <axboe@××××××.dk>
-+ *
-+ * Copyright (C) 2008 Fabio Checconi <fabio@×××××××××××××.it>
-+ *		      Paolo Valente <paolo.valente@×××××××.it>
-+ *
-+ * Copyright (C) 2010 Paolo Valente <paolo.valente@×××××××.it>
-+ *
-+ * Licensed under the GPL-2 as detailed in the accompanying COPYING.BFQ file.
-+ */
-+
-+#ifdef CONFIG_CGROUP_BFQIO
-+
-+static DEFINE_MUTEX(bfqio_mutex);
-+
-+static bool bfqio_is_removed(struct bfqio_cgroup *bgrp)
-+{
-+	return bgrp ? !bgrp->online : false;
-+}
-+
-+static struct bfqio_cgroup bfqio_root_cgroup = {
-+	.weight = BFQ_DEFAULT_GRP_WEIGHT,
-+	.ioprio = BFQ_DEFAULT_GRP_IOPRIO,
-+	.ioprio_class = BFQ_DEFAULT_GRP_CLASS,
-+};
-+
-+static inline void bfq_init_entity(struct bfq_entity *entity,
-+				   struct bfq_group *bfqg)
-+{
-+	entity->weight = entity->new_weight;
-+	entity->orig_weight = entity->new_weight;
-+	entity->ioprio = entity->new_ioprio;
-+	entity->ioprio_class = entity->new_ioprio_class;
-+	entity->parent = bfqg->my_entity;
-+	entity->sched_data = &bfqg->sched_data;
-+}
-+
-+static struct bfqio_cgroup *css_to_bfqio(struct cgroup_subsys_state *css)
-+{
-+	return css ? container_of(css, struct bfqio_cgroup, css) : NULL;
-+}
-+
-+/*
-+ * Search the bfq_group for bfqd into the hash table (by now only a list)
-+ * of bgrp.  Must be called under rcu_read_lock().
-+ */
-+static struct bfq_group *bfqio_lookup_group(struct bfqio_cgroup *bgrp,
-+					    struct bfq_data *bfqd)
-+{
-+	struct bfq_group *bfqg;
-+	void *key;
-+
-+	hlist_for_each_entry_rcu(bfqg, &bgrp->group_data, group_node) {
-+		key = rcu_dereference(bfqg->bfqd);
-+		if (key == bfqd)
-+			return bfqg;
-+	}
-+
-+	return NULL;
-+}
-+
-+static inline void bfq_group_init_entity(struct bfqio_cgroup *bgrp,
-+					 struct bfq_group *bfqg)
-+{
-+	struct bfq_entity *entity = &bfqg->entity;
-+
-+	/*
-+	 * If the weight of the entity has never been set via the sysfs
-+	 * interface, then bgrp->weight == 0. In this case we initialize
-+	 * the weight from the current ioprio value. Otherwise, the group
-+	 * weight, if set, has priority over the ioprio value.
-+	 */
-+	if (bgrp->weight == 0) {
-+		entity->new_weight = bfq_ioprio_to_weight(bgrp->ioprio);
-+		entity->new_ioprio = bgrp->ioprio;
-+	} else {
-+		entity->new_weight = bgrp->weight;
-+		entity->new_ioprio = bfq_weight_to_ioprio(bgrp->weight);
-+	}
-+	entity->orig_weight = entity->weight = entity->new_weight;
-+	entity->ioprio = entity->new_ioprio;
-+	entity->ioprio_class = entity->new_ioprio_class = bgrp->ioprio_class;
-+	entity->my_sched_data = &bfqg->sched_data;
-+}
-+
-+static inline void bfq_group_set_parent(struct bfq_group *bfqg,
-+					struct bfq_group *parent)
-+{
-+	struct bfq_entity *entity;
-+
-+	BUG_ON(parent == NULL);
-+	BUG_ON(bfqg == NULL);
-+
-+	entity = &bfqg->entity;
-+	entity->parent = parent->my_entity;
-+	entity->sched_data = &parent->sched_data;
-+}
-+
-+/**
-+ * bfq_group_chain_alloc - allocate a chain of groups.
-+ * @bfqd: queue descriptor.
-+ * @css: the leaf cgroup_subsys_state this chain starts from.
-+ *
-+ * Allocate a chain of groups starting from the one belonging to
-+ * @cgroup up to the root cgroup.  Stop if a cgroup on the chain
-+ * to the root has already an allocated group on @bfqd.
-+ */
-+static struct bfq_group *bfq_group_chain_alloc(struct bfq_data *bfqd,
-+					       struct cgroup_subsys_state *css)
-+{
-+	struct bfqio_cgroup *bgrp;
-+	struct bfq_group *bfqg, *prev = NULL, *leaf = NULL;
-+
-+	for (; css != NULL; css = css->parent) {
-+		bgrp = css_to_bfqio(css);
-+
-+		bfqg = bfqio_lookup_group(bgrp, bfqd);
-+		if (bfqg != NULL) {
-+			/*
-+			 * All the cgroups in the path from there to the
-+			 * root must have a bfq_group for bfqd, so we don't
-+			 * need any more allocations.
-+			 */
-+			break;
-+		}
-+
-+		bfqg = kzalloc(sizeof(*bfqg), GFP_ATOMIC);
-+		if (bfqg == NULL)
-+			goto cleanup;
-+
-+		bfq_group_init_entity(bgrp, bfqg);
-+		bfqg->my_entity = &bfqg->entity;
-+
-+		if (leaf == NULL) {
-+			leaf = bfqg;
-+			prev = leaf;
-+		} else {
-+			bfq_group_set_parent(prev, bfqg);
-+			/*
-+			 * Build a list of allocated nodes using the bfqd
-+			 * filed, that is still unused and will be initialized
-+			 * only after the node will be connected.
-+			 */
-+			prev->bfqd = bfqg;
-+			prev = bfqg;
-+		}
-+	}
-+
-+	return leaf;
-+
-+cleanup:
-+	while (leaf != NULL) {
-+		prev = leaf;
-+		leaf = leaf->bfqd;
-+		kfree(prev);
-+	}
-+
-+	return NULL;
-+}
-+
-+/**
-+ * bfq_group_chain_link - link an allocated group chain to a cgroup hierarchy.
-+ * @bfqd: the queue descriptor.
-+ * @css: the leaf cgroup_subsys_state to start from.
-+ * @leaf: the leaf group (to be associated to @cgroup).
-+ *
-+ * Try to link a chain of groups to a cgroup hierarchy, connecting the
-+ * nodes bottom-up, so we can be sure that when we find a cgroup in the
-+ * hierarchy that already as a group associated to @bfqd all the nodes
-+ * in the path to the root cgroup have one too.
-+ *
-+ * On locking: the queue lock protects the hierarchy (there is a hierarchy
-+ * per device) while the bfqio_cgroup lock protects the list of groups
-+ * belonging to the same cgroup.
-+ */
-+static void bfq_group_chain_link(struct bfq_data *bfqd,
-+				 struct cgroup_subsys_state *css,
-+				 struct bfq_group *leaf)
-+{
-+	struct bfqio_cgroup *bgrp;
-+	struct bfq_group *bfqg, *next, *prev = NULL;
-+	unsigned long flags;
-+
-+	assert_spin_locked(bfqd->queue->queue_lock);
-+
-+	for (; css != NULL && leaf != NULL; css = css->parent) {
-+		bgrp = css_to_bfqio(css);
-+		next = leaf->bfqd;
-+
-+		bfqg = bfqio_lookup_group(bgrp, bfqd);
-+		BUG_ON(bfqg != NULL);
-+
-+		spin_lock_irqsave(&bgrp->lock, flags);
-+
-+		rcu_assign_pointer(leaf->bfqd, bfqd);
-+		hlist_add_head_rcu(&leaf->group_node, &bgrp->group_data);
-+		hlist_add_head(&leaf->bfqd_node, &bfqd->group_list);
-+
-+		spin_unlock_irqrestore(&bgrp->lock, flags);
-+
-+		prev = leaf;
-+		leaf = next;
-+	}
-+
-+	BUG_ON(css == NULL && leaf != NULL);
-+	if (css != NULL && prev != NULL) {
-+		bgrp = css_to_bfqio(css);
-+		bfqg = bfqio_lookup_group(bgrp, bfqd);
-+		bfq_group_set_parent(prev, bfqg);
-+	}
-+}
-+
-+/**
-+ * bfq_find_alloc_group - return the group associated to @bfqd in @cgroup.
-+ * @bfqd: queue descriptor.
-+ * @cgroup: cgroup being searched for.
-+ *
-+ * Return a group associated to @bfqd in @cgroup, allocating one if
-+ * necessary.  When a group is returned all the cgroups in the path
-+ * to the root have a group associated to @bfqd.
-+ *
-+ * If the allocation fails, return the root group: this breaks guarantees
-+ * but is a safe fallback.  If this loss becomes a problem it can be
-+ * mitigated using the equivalent weight (given by the product of the
-+ * weights of the groups in the path from @group to the root) in the
-+ * root scheduler.
-+ *
-+ * We allocate all the missing nodes in the path from the leaf cgroup
-+ * to the root and we connect the nodes only after all the allocations
-+ * have been successful.
-+ */
-+static struct bfq_group *bfq_find_alloc_group(struct bfq_data *bfqd,
-+					      struct cgroup_subsys_state *css)
-+{
-+	struct bfqio_cgroup *bgrp = css_to_bfqio(css);
-+	struct bfq_group *bfqg;
-+
-+	bfqg = bfqio_lookup_group(bgrp, bfqd);
-+	if (bfqg != NULL)
-+		return bfqg;
-+
-+	bfqg = bfq_group_chain_alloc(bfqd, css);
-+	if (bfqg != NULL)
-+		bfq_group_chain_link(bfqd, css, bfqg);
-+	else
-+		bfqg = bfqd->root_group;
-+
-+	return bfqg;
-+}
-+
-+/**
-+ * bfq_bfqq_move - migrate @bfqq to @bfqg.
-+ * @bfqd: queue descriptor.
-+ * @bfqq: the queue to move.
-+ * @entity: @bfqq's entity.
-+ * @bfqg: the group to move to.
-+ *
-+ * Move @bfqq to @bfqg, deactivating it from its old group and reactivating
-+ * it on the new one.  Avoid putting the entity on the old group idle tree.
-+ *
-+ * Must be called under the queue lock; the cgroup owning @bfqg must
-+ * not disappear (by now this just means that we are called under
-+ * rcu_read_lock()).
-+ */
-+static void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
-+			  struct bfq_entity *entity, struct bfq_group *bfqg)
-+{
-+	int busy, resume;
-+
-+	busy = bfq_bfqq_busy(bfqq);
-+	resume = !RB_EMPTY_ROOT(&bfqq->sort_list);
-+
-+	BUG_ON(resume && !entity->on_st);
-+	BUG_ON(busy && !resume && entity->on_st &&
-+	       bfqq != bfqd->in_service_queue);
-+
-+	if (busy) {
-+		BUG_ON(atomic_read(&bfqq->ref) < 2);
-+
-+		if (!resume)
-+			bfq_del_bfqq_busy(bfqd, bfqq, 0);
-+		else
-+			bfq_deactivate_bfqq(bfqd, bfqq, 0);
-+	} else if (entity->on_st)
-+		bfq_put_idle_entity(bfq_entity_service_tree(entity), entity);
-+
-+	/*
-+	 * Here we use a reference to bfqg.  We don't need a refcounter
-+	 * as the cgroup reference will not be dropped, so that its
-+	 * destroy() callback will not be invoked.
-+	 */
-+	entity->parent = bfqg->my_entity;
-+	entity->sched_data = &bfqg->sched_data;
-+
-+	if (busy && resume)
-+		bfq_activate_bfqq(bfqd, bfqq);
-+
-+	if (bfqd->in_service_queue == NULL && !bfqd->rq_in_driver)
-+		bfq_schedule_dispatch(bfqd);
-+}
-+
-+/**
-+ * __bfq_bic_change_cgroup - move @bic to @cgroup.
-+ * @bfqd: the queue descriptor.
-+ * @bic: the bic to move.
-+ * @cgroup: the cgroup to move to.
-+ *
-+ * Move bic to cgroup, assuming that bfqd->queue is locked; the caller
-+ * has to make sure that the reference to cgroup is valid across the call.
-+ *
-+ * NOTE: an alternative approach might have been to store the current
-+ * cgroup in bfqq and getting a reference to it, reducing the lookup
-+ * time here, at the price of slightly more complex code.
-+ */
-+static struct bfq_group *__bfq_bic_change_cgroup(struct bfq_data *bfqd,
-+						struct bfq_io_cq *bic,
-+						struct cgroup_subsys_state *css)
-+{
-+	struct bfq_queue *async_bfqq = bic_to_bfqq(bic, 0);
-+	struct bfq_queue *sync_bfqq = bic_to_bfqq(bic, 1);
-+	struct bfq_entity *entity;
-+	struct bfq_group *bfqg;
-+	struct bfqio_cgroup *bgrp;
-+
-+	bgrp = css_to_bfqio(css);
-+
-+	bfqg = bfq_find_alloc_group(bfqd, css);
-+	if (async_bfqq != NULL) {
-+		entity = &async_bfqq->entity;
-+
-+		if (entity->sched_data != &bfqg->sched_data) {
-+			bic_set_bfqq(bic, NULL, 0);
-+			bfq_log_bfqq(bfqd, async_bfqq,
-+				     "bic_change_group: %p %d",
-+				     async_bfqq, atomic_read(&async_bfqq->ref));
-+			bfq_put_queue(async_bfqq);
-+		}
-+	}
-+
-+	if (sync_bfqq != NULL) {
-+		entity = &sync_bfqq->entity;
-+		if (entity->sched_data != &bfqg->sched_data)
-+			bfq_bfqq_move(bfqd, sync_bfqq, entity, bfqg);
-+	}
-+
-+	return bfqg;
-+}
-+
-+/**
-+ * bfq_bic_change_cgroup - move @bic to @cgroup.
-+ * @bic: the bic being migrated.
-+ * @cgroup: the destination cgroup.
-+ *
-+ * When the task owning @bic is moved to @cgroup, @bic is immediately
-+ * moved into its new parent group.
-+ */
-+static void bfq_bic_change_cgroup(struct bfq_io_cq *bic,
-+				  struct cgroup_subsys_state *css)
-+{
-+	struct bfq_data *bfqd;
-+	unsigned long uninitialized_var(flags);
-+
-+	bfqd = bfq_get_bfqd_locked(&(bic->icq.q->elevator->elevator_data),
-+				   &flags);
-+	if (bfqd != NULL) {
-+		__bfq_bic_change_cgroup(bfqd, bic, css);
-+		bfq_put_bfqd_unlock(bfqd, &flags);
-+	}
-+}
-+
-+/**
-+ * bfq_bic_update_cgroup - update the cgroup of @bic.
-+ * @bic: the @bic to update.
-+ *
-+ * Make sure that @bic is enqueued in the cgroup of the current task.
-+ * We need this in addition to moving bics during the cgroup attach
-+ * phase because the task owning @bic could be at its first disk
-+ * access or we may end up in the root cgroup as the result of a
-+ * memory allocation failure and here we try to move to the right
-+ * group.
-+ *
-+ * Must be called under the queue lock.  It is safe to use the returned
-+ * value even after the rcu_read_unlock() as the migration/destruction
-+ * paths act under the queue lock too.  IOW it is impossible to race with
-+ * group migration/destruction and end up with an invalid group as:
-+ *   a) here cgroup has not yet been destroyed, nor its destroy callback
-+ *      has started execution, as current holds a reference to it,
-+ *   b) if it is destroyed after rcu_read_unlock() [after current is
-+ *      migrated to a different cgroup] its attach() callback will have
-+ *      taken care of remove all the references to the old cgroup data.
-+ */
-+static struct bfq_group *bfq_bic_update_cgroup(struct bfq_io_cq *bic)
-+{
-+	struct bfq_data *bfqd = bic_to_bfqd(bic);
-+	struct bfq_group *bfqg;
-+	struct cgroup_subsys_state *css;
-+
-+	BUG_ON(bfqd == NULL);
-+
-+	rcu_read_lock();
-+	css = task_css(current, bfqio_subsys_id);
-+	bfqg = __bfq_bic_change_cgroup(bfqd, bic, css);
-+	rcu_read_unlock();
-+
-+	return bfqg;
-+}
-+
-+/**
-+ * bfq_flush_idle_tree - deactivate any entity on the idle tree of @st.
-+ * @st: the service tree being flushed.
-+ */
-+static inline void bfq_flush_idle_tree(struct bfq_service_tree *st)
-+{
-+	struct bfq_entity *entity = st->first_idle;
-+
-+	for (; entity != NULL; entity = st->first_idle)
-+		__bfq_deactivate_entity(entity, 0);
-+}
-+
-+/**
-+ * bfq_reparent_leaf_entity - move leaf entity to the root_group.
-+ * @bfqd: the device data structure with the root group.
-+ * @entity: the entity to move.
-+ */
-+static inline void bfq_reparent_leaf_entity(struct bfq_data *bfqd,
-+					    struct bfq_entity *entity)
-+{
-+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
-+
-+	BUG_ON(bfqq == NULL);
-+	bfq_bfqq_move(bfqd, bfqq, entity, bfqd->root_group);
-+	return;
-+}
-+
-+/**
-+ * bfq_reparent_active_entities - move to the root group all active entities.
-+ * @bfqd: the device data structure with the root group.
-+ * @bfqg: the group to move from.
-+ * @st: the service tree with the entities.
-+ *
-+ * Needs queue_lock to be taken and reference to be valid over the call.
-+ */
-+static inline void bfq_reparent_active_entities(struct bfq_data *bfqd,
-+						struct bfq_group *bfqg,
-+						struct bfq_service_tree *st)
-+{
-+	struct rb_root *active = &st->active;
-+	struct bfq_entity *entity = NULL;
-+
-+	if (!RB_EMPTY_ROOT(&st->active))
-+		entity = bfq_entity_of(rb_first(active));
-+
-+	for (; entity != NULL; entity = bfq_entity_of(rb_first(active)))
-+		bfq_reparent_leaf_entity(bfqd, entity);
-+
-+	if (bfqg->sched_data.in_service_entity != NULL)
-+		bfq_reparent_leaf_entity(bfqd,
-+			bfqg->sched_data.in_service_entity);
-+
-+	return;
-+}
-+
-+/**
-+ * bfq_destroy_group - destroy @bfqg.
-+ * @bgrp: the bfqio_cgroup containing @bfqg.
-+ * @bfqg: the group being destroyed.
-+ *
-+ * Destroy @bfqg, making sure that it is not referenced from its parent.
-+ */
-+static void bfq_destroy_group(struct bfqio_cgroup *bgrp, struct bfq_group *bfqg)
-+{
-+	struct bfq_data *bfqd;
-+	struct bfq_service_tree *st;
-+	struct bfq_entity *entity = bfqg->my_entity;
-+	unsigned long uninitialized_var(flags);
-+	int i;
-+
-+	hlist_del(&bfqg->group_node);
-+
-+	/*
-+	 * Empty all service_trees belonging to this group before deactivating
-+	 * the group itself.
-+	 */
-+	for (i = 0; i < BFQ_IOPRIO_CLASSES; i++) {
-+		st = bfqg->sched_data.service_tree + i;
-+
-+		/*
-+		 * The idle tree may still contain bfq_queues belonging
-+		 * to exited task because they never migrated to a different
-+		 * cgroup from the one being destroyed now.  No one else
-+		 * can access them so it's safe to act without any lock.
-+		 */
-+		bfq_flush_idle_tree(st);
-+
-+		/*
-+		 * It may happen that some queues are still active
-+		 * (busy) upon group destruction (if the corresponding
-+		 * processes have been forced to terminate). We move
-+		 * all the leaf entities corresponding to these queues
-+		 * to the root_group.
-+		 * Also, it may happen that the group has an entity
-+		 * under service, which is disconnected from the active
-+		 * tree: it must be moved, too.
-+		 * There is no need to put the sync queues, as the
-+		 * scheduler has taken no reference.
-+		 */
-+		bfqd = bfq_get_bfqd_locked(&bfqg->bfqd, &flags);
-+		if (bfqd != NULL) {
-+			bfq_reparent_active_entities(bfqd, bfqg, st);
-+			bfq_put_bfqd_unlock(bfqd, &flags);
-+		}
-+		BUG_ON(!RB_EMPTY_ROOT(&st->active));
-+		BUG_ON(!RB_EMPTY_ROOT(&st->idle));
-+	}
-+	BUG_ON(bfqg->sched_data.next_in_service != NULL);
-+	BUG_ON(bfqg->sched_data.in_service_entity != NULL);
-+
-+	/*
-+	 * We may race with device destruction, take extra care when
-+	 * dereferencing bfqg->bfqd.
-+	 */
-+	bfqd = bfq_get_bfqd_locked(&bfqg->bfqd, &flags);
-+	if (bfqd != NULL) {
-+		hlist_del(&bfqg->bfqd_node);
-+		__bfq_deactivate_entity(entity, 0);
-+		bfq_put_async_queues(bfqd, bfqg);
-+		bfq_put_bfqd_unlock(bfqd, &flags);
-+	}
-+	BUG_ON(entity->tree != NULL);
-+
-+	/*
-+	 * No need to defer the kfree() to the end of the RCU grace
-+	 * period: we are called from the destroy() callback of our
-+	 * cgroup, so we can be sure that no one is a) still using
-+	 * this cgroup or b) doing lookups in it.
-+	 */
-+	kfree(bfqg);
-+}
-+
-+static void bfq_end_raising_async(struct bfq_data *bfqd)
-+{
-+	struct hlist_node *tmp;
-+	struct bfq_group *bfqg;
-+
-+	hlist_for_each_entry_safe(bfqg, tmp, &bfqd->group_list, bfqd_node)
-+		bfq_end_raising_async_queues(bfqd, bfqg);
-+	bfq_end_raising_async_queues(bfqd, bfqd->root_group);
-+}
-+
-+/**
-+ * bfq_disconnect_groups - disconnect @bfqd from all its groups.
-+ * @bfqd: the device descriptor being exited.
-+ *
-+ * When the device exits we just make sure that no lookup can return
-+ * the now unused group structures.  They will be deallocated on cgroup
-+ * destruction.
-+ */
-+static void bfq_disconnect_groups(struct bfq_data *bfqd)
-+{
-+	struct hlist_node *tmp;
-+	struct bfq_group *bfqg;
-+
-+	bfq_log(bfqd, "disconnect_groups beginning");
-+	hlist_for_each_entry_safe(bfqg, tmp, &bfqd->group_list, bfqd_node) {
-+		hlist_del(&bfqg->bfqd_node);
-+
-+		__bfq_deactivate_entity(bfqg->my_entity, 0);
-+
-+		/*
-+		 * Don't remove from the group hash, just set an
-+		 * invalid key.  No lookups can race with the
-+		 * assignment as bfqd is being destroyed; this
-+		 * implies also that new elements cannot be added
-+		 * to the list.
-+		 */
-+		rcu_assign_pointer(bfqg->bfqd, NULL);
-+
-+		bfq_log(bfqd, "disconnect_groups: put async for group %p",
-+			bfqg);
-+		bfq_put_async_queues(bfqd, bfqg);
-+	}
-+}
-+
-+static inline void bfq_free_root_group(struct bfq_data *bfqd)
-+{
-+	struct bfqio_cgroup *bgrp = &bfqio_root_cgroup;
-+	struct bfq_group *bfqg = bfqd->root_group;
-+
-+	bfq_put_async_queues(bfqd, bfqg);
-+
-+	spin_lock_irq(&bgrp->lock);
-+	hlist_del_rcu(&bfqg->group_node);
-+	spin_unlock_irq(&bgrp->lock);
-+
-+	/*
-+	 * No need to synchronize_rcu() here: since the device is gone
-+	 * there cannot be any read-side access to its root_group.
-+	 */
-+	kfree(bfqg);
-+}
-+
-+static struct bfq_group *bfq_alloc_root_group(struct bfq_data *bfqd, int node)
-+{
-+	struct bfq_group *bfqg;
-+	struct bfqio_cgroup *bgrp;
-+	int i;
-+
-+	bfqg = kzalloc_node(sizeof(*bfqg), GFP_KERNEL, node);
-+	if (bfqg == NULL)
-+		return NULL;
-+
-+	bfqg->entity.parent = NULL;
-+	for (i = 0; i < BFQ_IOPRIO_CLASSES; i++)
-+		bfqg->sched_data.service_tree[i] = BFQ_SERVICE_TREE_INIT;
-+
-+	bgrp = &bfqio_root_cgroup;
-+	spin_lock_irq(&bgrp->lock);
-+	rcu_assign_pointer(bfqg->bfqd, bfqd);
-+	hlist_add_head_rcu(&bfqg->group_node, &bgrp->group_data);
-+	spin_unlock_irq(&bgrp->lock);
-+
-+	return bfqg;
-+}
-+
-+#define SHOW_FUNCTION(__VAR)						\
-+static u64 bfqio_cgroup_##__VAR##_read(struct cgroup_subsys_state *css, \
-+				       struct cftype *cftype)		\
-+{									\
-+	struct bfqio_cgroup *bgrp = css_to_bfqio(css);			\
-+	u64 ret = -ENODEV;						\
-+									\
-+	mutex_lock(&bfqio_mutex);					\
-+	if (bfqio_is_removed(bgrp))					\
-+		goto out_unlock;					\
-+									\
-+	spin_lock_irq(&bgrp->lock);					\
-+	ret = bgrp->__VAR;						\
-+	spin_unlock_irq(&bgrp->lock);					\
-+									\
-+out_unlock:								\
-+	mutex_unlock(&bfqio_mutex);					\
-+	return ret;							\
-+}
-+
-+SHOW_FUNCTION(weight);
-+SHOW_FUNCTION(ioprio);
-+SHOW_FUNCTION(ioprio_class);
-+#undef SHOW_FUNCTION
-+
-+#define STORE_FUNCTION(__VAR, __MIN, __MAX)				\
-+static int bfqio_cgroup_##__VAR##_write(struct cgroup_subsys_state *css,\
-+					struct cftype *cftype,		\
-+					u64 val)			\
-+{									\
-+	struct bfqio_cgroup *bgrp = css_to_bfqio(css);			\
-+	struct bfq_group *bfqg;						\
-+	int ret = -EINVAL;						\
-+									\
-+	if (val < (__MIN) || val > (__MAX))				\
-+		return ret;						\
-+									\
-+	ret = -ENODEV;							\
-+	mutex_lock(&bfqio_mutex);					\
-+	if (bfqio_is_removed(bgrp))					\
-+		goto out_unlock;					\
-+	ret = 0;							\
-+									\
-+	spin_lock_irq(&bgrp->lock);					\
-+	bgrp->__VAR = (unsigned short)val;				\
-+	hlist_for_each_entry(bfqg, &bgrp->group_data, group_node) {	\
-+		/*							\
-+		 * Setting the ioprio_changed flag of the entity        \
-+		 * to 1 with new_##__VAR == ##__VAR would re-set        \
-+		 * the value of the weight to its ioprio mapping.       \
-+		 * Set the flag only if necessary.			\
-+		 */							\
-+		if ((unsigned short)val != bfqg->entity.new_##__VAR) {  \
-+			bfqg->entity.new_##__VAR = (unsigned short)val; \
-+			/*						\
-+			 * Make sure that the above new value has been	\
-+			 * stored in bfqg->entity.new_##__VAR before	\
-+			 * setting the ioprio_changed flag. In fact,	\
-+			 * this flag may be read asynchronously (in	\
-+			 * critical sections protected by a different	\
-+			 * lock than that held here), and finding this	\
-+			 * flag set may cause the execution of the code	\
-+			 * for updating parameters whose value may	\
-+			 * depend also on bfqg->entity.new_##__VAR (in	\
-+			 * __bfq_entity_update_weight_prio).		\
-+			 * This barrier makes sure that the new value	\
-+			 * of bfqg->entity.new_##__VAR is correctly	\
-+			 * seen in that code.				\
-+			 */						\
-+			smp_wmb();                                      \
-+			bfqg->entity.ioprio_changed = 1;                \
-+		}							\
-+	}								\
-+	spin_unlock_irq(&bgrp->lock);					\
-+									\
-+out_unlock:								\
-+	mutex_unlock(&bfqio_mutex);					\
-+	return ret;							\
-+}
-+
-+STORE_FUNCTION(weight, BFQ_MIN_WEIGHT, BFQ_MAX_WEIGHT);
-+STORE_FUNCTION(ioprio, 0, IOPRIO_BE_NR - 1);
-+STORE_FUNCTION(ioprio_class, IOPRIO_CLASS_RT, IOPRIO_CLASS_IDLE);
-+#undef STORE_FUNCTION
-+
-+static struct cftype bfqio_files[] = {
-+	{
-+		.name = "weight",
-+		.read_u64 = bfqio_cgroup_weight_read,
-+		.write_u64 = bfqio_cgroup_weight_write,
-+	},
-+	{
-+		.name = "ioprio",
-+		.read_u64 = bfqio_cgroup_ioprio_read,
-+		.write_u64 = bfqio_cgroup_ioprio_write,
-+	},
-+	{
-+		.name = "ioprio_class",
-+		.read_u64 = bfqio_cgroup_ioprio_class_read,
-+		.write_u64 = bfqio_cgroup_ioprio_class_write,
-+	},
-+	{ },	/* terminate */
-+};
-+
-+static struct cgroup_subsys_state *bfqio_create(struct cgroup_subsys_state
-+						*parent_css)
-+{
-+	struct bfqio_cgroup *bgrp;
-+
-+	if (parent_css != NULL) {
-+		bgrp = kzalloc(sizeof(*bgrp), GFP_KERNEL);
-+		if (bgrp == NULL)
-+			return ERR_PTR(-ENOMEM);
-+	} else
-+		bgrp = &bfqio_root_cgroup;
-+
-+	spin_lock_init(&bgrp->lock);
-+	INIT_HLIST_HEAD(&bgrp->group_data);
-+	bgrp->ioprio = BFQ_DEFAULT_GRP_IOPRIO;
-+	bgrp->ioprio_class = BFQ_DEFAULT_GRP_CLASS;
-+
-+	return &bgrp->css;
-+}
-+
-+/*
-+ * We cannot support shared io contexts, as we have no means to support
-+ * two tasks with the same ioc in two different groups without major rework
-+ * of the main bic/bfqq data structures.  By now we allow a task to change
-+ * its cgroup only if it's the only owner of its ioc; the drawback of this
-+ * behavior is that a group containing a task that forked using CLONE_IO
-+ * will not be destroyed until the tasks sharing the ioc die.
-+ */
-+static int bfqio_can_attach(struct cgroup_subsys_state *css,
-+			    struct cgroup_taskset *tset)
-+{
-+	struct task_struct *task;
-+	struct io_context *ioc;
-+	int ret = 0;
-+
-+	cgroup_taskset_for_each(task, css, tset) {
-+		/*
-+		 * task_lock() is needed to avoid races with
-+		 * exit_io_context()
-+		 */
-+		task_lock(task);
-+		ioc = task->io_context;
-+		if (ioc != NULL && atomic_read(&ioc->nr_tasks) > 1)
-+			/*
-+			 * ioc == NULL means that the task is either too young
-+			 * or exiting: if it has still no ioc the ioc can't be
-+			 * shared, if the task is exiting the attach will fail
-+			 * anyway, no matter what we return here.
-+			 */
-+			ret = -EINVAL;
-+		task_unlock(task);
-+		if (ret)
-+			break;
-+	}
-+
-+	return ret;
-+}
-+
-+static void bfqio_attach(struct cgroup_subsys_state *css,
-+			 struct cgroup_taskset *tset)
-+{
-+	struct task_struct *task;
-+	struct io_context *ioc;
-+	struct io_cq *icq;
-+
-+	/*
-+	 * IMPORTANT NOTE: The move of more than one process at a time to a
-+	 * new group has not yet been tested.
-+	 */
-+	cgroup_taskset_for_each(task, css, tset) {
-+		ioc = get_task_io_context(task, GFP_ATOMIC, NUMA_NO_NODE);
-+		if (ioc) {
-+			/*
-+			 * Handle cgroup change here.
-+			 */
-+			rcu_read_lock();
-+			hlist_for_each_entry_rcu(icq, &ioc->icq_list, ioc_node)
-+				if (!strncmp(
-+					icq->q->elevator->type->elevator_name,
-+					"bfq", ELV_NAME_MAX))
-+					bfq_bic_change_cgroup(icq_to_bic(icq),
-+							      css);
-+			rcu_read_unlock();
-+			put_io_context(ioc);
-+		}
-+	}
-+}
-+
-+static void bfqio_destroy(struct cgroup_subsys_state *css)
-+{
-+	struct bfqio_cgroup *bgrp = css_to_bfqio(css);
-+	struct hlist_node *tmp;
-+	struct bfq_group *bfqg;
-+
-+	/*
-+	 * Since we are destroying the cgroup, there are no more tasks
-+	 * referencing it, and all the RCU grace periods that may have
-+	 * referenced it are ended (as the destruction of the parent
-+	 * cgroup is RCU-safe); bgrp->group_data will not be accessed by
-+	 * anything else and we don't need any synchronization.
-+	 */
-+	hlist_for_each_entry_safe(bfqg, tmp, &bgrp->group_data, group_node)
-+		bfq_destroy_group(bgrp, bfqg);
-+
-+	BUG_ON(!hlist_empty(&bgrp->group_data));
-+
-+	kfree(bgrp);
-+}
-+
-+static int bfqio_css_online(struct cgroup_subsys_state *css)
-+{
-+	struct bfqio_cgroup *bgrp = css_to_bfqio(css);
-+
-+	mutex_lock(&bfqio_mutex);
-+	bgrp->online = true;
-+	mutex_unlock(&bfqio_mutex);
-+
-+	return 0;
-+}
-+
-+static void bfqio_css_offline(struct cgroup_subsys_state *css)
-+{
-+	struct bfqio_cgroup *bgrp = css_to_bfqio(css);
-+
-+	mutex_lock(&bfqio_mutex);
-+	bgrp->online = false;
-+	mutex_unlock(&bfqio_mutex);
-+}
-+
-+struct cgroup_subsys bfqio_subsys = {
-+	.name = "bfqio",
-+	.css_alloc = bfqio_create,
-+	.css_online = bfqio_css_online,
-+	.css_offline = bfqio_css_offline,
-+	.can_attach = bfqio_can_attach,
-+	.attach = bfqio_attach,
-+	.css_free = bfqio_destroy,
-+	.subsys_id = bfqio_subsys_id,
-+	.base_cftypes = bfqio_files,
-+};
-+#else
-+static inline void bfq_init_entity(struct bfq_entity *entity,
-+				   struct bfq_group *bfqg)
-+{
-+	entity->weight = entity->new_weight;
-+	entity->orig_weight = entity->new_weight;
-+	entity->ioprio = entity->new_ioprio;
-+	entity->ioprio_class = entity->new_ioprio_class;
-+	entity->sched_data = &bfqg->sched_data;
-+}
-+
-+static inline struct bfq_group *
-+bfq_bic_update_cgroup(struct bfq_io_cq *bic)
-+{
-+	struct bfq_data *bfqd = bic_to_bfqd(bic);
-+	return bfqd->root_group;
-+}
-+
-+static inline void bfq_bfqq_move(struct bfq_data *bfqd,
-+				 struct bfq_queue *bfqq,
-+				 struct bfq_entity *entity,
-+				 struct bfq_group *bfqg)
-+{
-+}
-+
-+static void bfq_end_raising_async(struct bfq_data *bfqd)
-+{
-+	bfq_end_raising_async_queues(bfqd, bfqd->root_group);
-+}
-+
-+static inline void bfq_disconnect_groups(struct bfq_data *bfqd)
-+{
-+	bfq_put_async_queues(bfqd, bfqd->root_group);
-+}
-+
-+static inline void bfq_free_root_group(struct bfq_data *bfqd)
-+{
-+	kfree(bfqd->root_group);
-+}
-+
-+static struct bfq_group *bfq_alloc_root_group(struct bfq_data *bfqd, int node)
-+{
-+	struct bfq_group *bfqg;
-+	int i;
-+
-+	bfqg = kmalloc_node(sizeof(*bfqg), GFP_KERNEL | __GFP_ZERO, node);
-+	if (bfqg == NULL)
-+		return NULL;
-+
-+	for (i = 0; i < BFQ_IOPRIO_CLASSES; i++)
-+		bfqg->sched_data.service_tree[i] = BFQ_SERVICE_TREE_INIT;
-+
-+	return bfqg;
-+}
-+#endif
-diff --git a/block/bfq-ioc.c b/block/bfq-ioc.c
-new file mode 100644
-index 0000000..7f6b000
---- /dev/null
-+++ b/block/bfq-ioc.c
-@@ -0,0 +1,36 @@
-+/*
-+ * BFQ: I/O context handling.
-+ *
-+ * Based on ideas and code from CFQ:
-+ * Copyright (C) 2003 Jens Axboe <axboe@××××××.dk>
-+ *
-+ * Copyright (C) 2008 Fabio Checconi <fabio@×××××××××××××.it>
-+ *		      Paolo Valente <paolo.valente@×××××××.it>
-+ *
-+ * Copyright (C) 2010 Paolo Valente <paolo.valente@×××××××.it>
-+ */
-+
-+/**
-+ * icq_to_bic - convert iocontext queue structure to bfq_io_cq.
-+ * @icq: the iocontext queue.
-+ */
-+static inline struct bfq_io_cq *icq_to_bic(struct io_cq *icq)
-+{
-+	/* bic->icq is the first member, %NULL will convert to %NULL */
-+	return container_of(icq, struct bfq_io_cq, icq);
-+}
-+
-+/**
-+ * bfq_bic_lookup - search into @ioc a bic associated to @bfqd.
-+ * @bfqd: the lookup key.
-+ * @ioc: the io_context of the process doing I/O.
-+ *
-+ * Queue lock must be held.
-+ */
-+static inline struct bfq_io_cq *bfq_bic_lookup(struct bfq_data *bfqd,
-+					       struct io_context *ioc)
-+{
-+	if (ioc)
-+		return icq_to_bic(ioc_lookup_icq(ioc, bfqd->queue));
-+	return NULL;
-+}
-diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
-new file mode 100644
-index 0000000..f5f71e4
---- /dev/null
-+++ b/block/bfq-iosched.c
-@@ -0,0 +1,3300 @@
-+/*
-+ * Budget Fair Queueing (BFQ) disk scheduler.
-+ *
-+ * Based on ideas and code from CFQ:
-+ * Copyright (C) 2003 Jens Axboe <axboe@××××××.dk>
-+ *
-+ * Copyright (C) 2008 Fabio Checconi <fabio@×××××××××××××.it>
-+ *		      Paolo Valente <paolo.valente@×××××××.it>
-+ *
-+ * Copyright (C) 2010 Paolo Valente <paolo.valente@×××××××.it>
-+ *
-+ * Licensed under the GPL-2 as detailed in the accompanying COPYING.BFQ file.
-+ *
-+ * BFQ is a proportional share disk scheduling algorithm based on the
-+ * slice-by-slice service scheme of CFQ. But BFQ assigns budgets, measured in
-+ * number of sectors, to tasks instead of time slices. The disk is not granted
-+ * to the in-service task for a given time slice, but until it has exhausted
-+ * its assigned budget. This change from the time to the service domain allows
-+ * BFQ to distribute the disk bandwidth among tasks as desired, without any
-+ * distortion due to ZBR, workload fluctuations or other factors. BFQ uses an
-+ * ad hoc internal scheduler, called B-WF2Q+, to schedule tasks according to
-+ * their budgets (more precisely BFQ schedules queues associated to tasks).
-+ * Thanks to this accurate scheduler, BFQ can afford to assign high budgets to
-+ * disk-bound non-seeky tasks (to boost the throughput), and yet guarantee low
-+ * latencies to interactive and soft real-time applications.
-+ *
-+ * BFQ is described in [1], where also a reference to the initial, more
-+ * theoretical paper on BFQ can be found. The interested reader can find in
-+ * the latter paper full details on the main algorithm as well as formulas of
-+ * the guarantees, plus formal proofs of all the properties. With respect to
-+ * the version of BFQ presented in these papers, this implementation adds a
-+ * few more heuristics, such as the one that guarantees a low latency to soft
-+ * real-time applications, and a hierarchical extension based on H-WF2Q+.
-+ *
-+ * B-WF2Q+ is based on WF2Q+, that is described in [2], together with
-+ * H-WF2Q+, while the augmented tree used to implement B-WF2Q+ with O(log N)
-+ * complexity derives from the one introduced with EEVDF in [3].
-+ *
-+ * [1] P. Valente and M. Andreolini, ``Improving Application Responsiveness
-+ *     with the BFQ Disk I/O Scheduler'',
-+ *     Proceedings of the 5th Annual International Systems and Storage
-+ *     Conference (SYSTOR '12), June 2012.
-+ *
-+ * http://algogroup.unimo.it/people/paolo/disk_sched/bf1-v1-suite-results.pdf
-+ *
-+ * [2] Jon C.R. Bennett and H. Zhang, ``Hierarchical Packet Fair Queueing
-+ *     Algorithms,'' IEEE/ACM Transactions on Networking, 5(5):675-689,
-+ *     Oct 1997.
-+ *
-+ * http://www.cs.cmu.edu/~hzhang/papers/TON-97-Oct.ps.gz
-+ *
-+ * [3] I. Stoica and H. Abdel-Wahab, ``Earliest Eligible Virtual Deadline
-+ *     First: A Flexible and Accurate Mechanism for Proportional Share
-+ *     Resource Allocation,'' technical report.
-+ *
-+ * http://www.cs.berkeley.edu/~istoica/papers/eevdf-tr-95.pdf
-+ */
-+#include <linux/module.h>
-+#include <linux/slab.h>
-+#include <linux/blkdev.h>
-+#include <linux/cgroup.h>
-+#include <linux/elevator.h>
-+#include <linux/jiffies.h>
-+#include <linux/rbtree.h>
-+#include <linux/ioprio.h>
-+#include "bfq.h"
-+#include "blk.h"
-+
-+/* Max number of dispatches in one round of service. */
-+static const int bfq_quantum = 4;
-+
-+/* Expiration time of sync (0) and async (1) requests, in jiffies. */
-+static const int bfq_fifo_expire[2] = { HZ / 4, HZ / 8 };
-+
-+/* Maximum backwards seek, in KiB. */
-+static const int bfq_back_max = 16 * 1024;
-+
-+/* Penalty of a backwards seek, in number of sectors. */
-+static const int bfq_back_penalty = 2;
-+
-+/* Idling period duration, in jiffies. */
-+static int bfq_slice_idle = HZ / 125;
-+
-+/* Default maximum budget values, in sectors and number of requests. */
-+static const int bfq_default_max_budget = 16 * 1024;
-+static const int bfq_max_budget_async_rq = 4;
-+
-+/*
-+ * Async to sync throughput distribution is controlled as follows:
-+ * when an async request is served, the entity is charged the number
-+ * of sectors of the request, multiplied by the factor below
-+ */
-+static const int bfq_async_charge_factor = 10;
-+
-+/* Default timeout values, in jiffies, approximating CFQ defaults. */
-+static const int bfq_timeout_sync = HZ / 8;
-+static int bfq_timeout_async = HZ / 25;
-+
-+struct kmem_cache *bfq_pool;
-+
-+/* Below this threshold (in ms), we consider thinktime immediate. */
-+#define BFQ_MIN_TT		2
-+
-+/* hw_tag detection: parallel requests threshold and min samples needed. */
-+#define BFQ_HW_QUEUE_THRESHOLD	4
-+#define BFQ_HW_QUEUE_SAMPLES	32
-+
-+#define BFQQ_SEEK_THR	 (sector_t)(8 * 1024)
-+#define BFQQ_SEEKY(bfqq) ((bfqq)->seek_mean > BFQQ_SEEK_THR)
-+
-+/* Min samples used for peak rate estimation (for autotuning). */
-+#define BFQ_PEAK_RATE_SAMPLES	32
-+
-+/* Shift used for peak rate fixed precision calculations. */
-+#define BFQ_RATE_SHIFT		16
-+
-+/*
-+ * The duration of the weight raising for interactive applications is
-+ * computed automatically (as default behaviour), using the following
-+ * formula: duration = (R / r) * T, where r is the peak rate of the
-+ * disk, and R and T are two reference parameters. In particular, R is
-+ * the peak rate of a reference disk, and T is about the maximum time
-+ * for starting popular large applications on that disk, under BFQ and
-+ * while reading two files in parallel. Finally, BFQ uses two
-+ * different pairs (R, T) depending on whether the disk is rotational
-+ * or non-rotational.
-+ */
-+#define T_rot			(msecs_to_jiffies(5500))
-+#define T_nonrot		(msecs_to_jiffies(2000))
-+/* Next two quantities are in sectors/usec, left-shifted by BFQ_RATE_SHIFT */
-+#define R_rot			17415
-+#define R_nonrot		34791
-+
-+#define BFQ_SERVICE_TREE_INIT	((struct bfq_service_tree)		\
-+				{ RB_ROOT, RB_ROOT, NULL, NULL, 0, 0 })
-+
-+#define RQ_BIC(rq)		((struct bfq_io_cq *) (rq)->elv.priv[0])
-+#define RQ_BFQQ(rq)		((rq)->elv.priv[1])
-+
-+static inline void bfq_schedule_dispatch(struct bfq_data *bfqd);
-+
-+#include "bfq-ioc.c"
-+#include "bfq-sched.c"
-+#include "bfq-cgroup.c"
-+
-+#define bfq_class_idle(bfqq)	((bfqq)->entity.ioprio_class ==\
-+				 IOPRIO_CLASS_IDLE)
-+#define bfq_class_rt(bfqq)	((bfqq)->entity.ioprio_class ==\
-+				 IOPRIO_CLASS_RT)
-+
-+#define bfq_sample_valid(samples)	((samples) > 80)
-+
-+/*
-+ * We regard a request as SYNC, if either it's a read or has the SYNC bit
-+ * set (in which case it could also be a direct WRITE).
-+ */
-+static inline int bfq_bio_sync(struct bio *bio)
-+{
-+	if (bio_data_dir(bio) == READ || (bio->bi_rw & REQ_SYNC))
-+		return 1;
-+
-+	return 0;
-+}
-+
-+/*
-+ * Scheduler run of queue, if there are requests pending and no one in the
-+ * driver that will restart queueing.
-+ */
-+static inline void bfq_schedule_dispatch(struct bfq_data *bfqd)
-+{
-+	if (bfqd->queued != 0) {
-+		bfq_log(bfqd, "schedule dispatch");
-+		kblockd_schedule_work(bfqd->queue, &bfqd->unplug_work);
-+	}
-+}
-+
-+/*
-+ * Lifted from AS - choose which of rq1 and rq2 that is best served now.
-+ * We choose the request that is closesr to the head right now.  Distance
-+ * behind the head is penalized and only allowed to a certain extent.
-+ */
-+static struct request *bfq_choose_req(struct bfq_data *bfqd,
-+				      struct request *rq1,
-+				      struct request *rq2,
-+				      sector_t last)
-+{
-+	sector_t s1, s2, d1 = 0, d2 = 0;
-+	unsigned long back_max;
-+#define BFQ_RQ1_WRAP	0x01 /* request 1 wraps */
-+#define BFQ_RQ2_WRAP	0x02 /* request 2 wraps */
-+	unsigned wrap = 0; /* bit mask: requests behind the disk head? */
-+
-+	if (rq1 == NULL || rq1 == rq2)
-+		return rq2;
-+	if (rq2 == NULL)
-+		return rq1;
-+
-+	if (rq_is_sync(rq1) && !rq_is_sync(rq2))
-+		return rq1;
-+	else if (rq_is_sync(rq2) && !rq_is_sync(rq1))
-+		return rq2;
-+	if ((rq1->cmd_flags & REQ_META) && !(rq2->cmd_flags & REQ_META))
-+		return rq1;
-+	else if ((rq2->cmd_flags & REQ_META) && !(rq1->cmd_flags & REQ_META))
-+		return rq2;
-+
-+	s1 = blk_rq_pos(rq1);
-+	s2 = blk_rq_pos(rq2);
-+
-+	/*
-+	 * By definition, 1KiB is 2 sectors.
-+	 */
-+	back_max = bfqd->bfq_back_max * 2;
-+
-+	/*
-+	 * Strict one way elevator _except_ in the case where we allow
-+	 * short backward seeks which are biased as twice the cost of a
-+	 * similar forward seek.
-+	 */
-+	if (s1 >= last)
-+		d1 = s1 - last;
-+	else if (s1 + back_max >= last)
-+		d1 = (last - s1) * bfqd->bfq_back_penalty;
-+	else
-+		wrap |= BFQ_RQ1_WRAP;
-+
-+	if (s2 >= last)
-+		d2 = s2 - last;
-+	else if (s2 + back_max >= last)
-+		d2 = (last - s2) * bfqd->bfq_back_penalty;
-+	else
-+		wrap |= BFQ_RQ2_WRAP;
-+
-+	/* Found required data */
-+
-+	/*
-+	 * By doing switch() on the bit mask "wrap" we avoid having to
-+	 * check two variables for all permutations: --> faster!
-+	 */
-+	switch (wrap) {
-+	case 0: /* common case for CFQ: rq1 and rq2 not wrapped */
-+		if (d1 < d2)
-+			return rq1;
-+		else if (d2 < d1)
-+			return rq2;
-+		else {
-+			if (s1 >= s2)
-+				return rq1;
-+			else
-+				return rq2;
-+		}
-+
-+	case BFQ_RQ2_WRAP:
-+		return rq1;
-+	case BFQ_RQ1_WRAP:
-+		return rq2;
-+	case (BFQ_RQ1_WRAP|BFQ_RQ2_WRAP): /* both rqs wrapped */
-+	default:
-+		/*
-+		 * Since both rqs are wrapped,
-+		 * start with the one that's further behind head
-+		 * (--> only *one* back seek required),
-+		 * since back seek takes more time than forward.
-+		 */
-+		if (s1 <= s2)
-+			return rq1;
-+		else
-+			return rq2;
-+	}
-+}
-+
-+static struct bfq_queue *
-+bfq_rq_pos_tree_lookup(struct bfq_data *bfqd, struct rb_root *root,
-+		     sector_t sector, struct rb_node **ret_parent,
-+		     struct rb_node ***rb_link)
-+{
-+	struct rb_node **p, *parent;
-+	struct bfq_queue *bfqq = NULL;
-+
-+	parent = NULL;
-+	p = &root->rb_node;
-+	while (*p) {
-+		struct rb_node **n;
-+
-+		parent = *p;
-+		bfqq = rb_entry(parent, struct bfq_queue, pos_node);
-+
-+		/*
-+		 * Sort strictly based on sector. Smallest to the left,
-+		 * largest to the right.
-+		 */
-+		if (sector > blk_rq_pos(bfqq->next_rq))
-+			n = &(*p)->rb_right;
-+		else if (sector < blk_rq_pos(bfqq->next_rq))
-+			n = &(*p)->rb_left;
-+		else
-+			break;
-+		p = n;
-+		bfqq = NULL;
-+	}
-+
-+	*ret_parent = parent;
-+	if (rb_link)
-+		*rb_link = p;
-+
-+	bfq_log(bfqd, "rq_pos_tree_lookup %llu: returning %d",
-+		(long long unsigned)sector,
-+		bfqq != NULL ? bfqq->pid : 0);
-+
-+	return bfqq;
-+}
-+
-+static void bfq_rq_pos_tree_add(struct bfq_data *bfqd, struct bfq_queue *bfqq)
-+{
-+	struct rb_node **p, *parent;
-+	struct bfq_queue *__bfqq;
-+
-+	if (bfqq->pos_root != NULL) {
-+		rb_erase(&bfqq->pos_node, bfqq->pos_root);
-+		bfqq->pos_root = NULL;
-+	}
-+
-+	if (bfq_class_idle(bfqq))
-+		return;
-+	if (!bfqq->next_rq)
-+		return;
-+
-+	bfqq->pos_root = &bfqd->rq_pos_tree;
-+	__bfqq = bfq_rq_pos_tree_lookup(bfqd, bfqq->pos_root,
-+			blk_rq_pos(bfqq->next_rq), &parent, &p);
-+	if (__bfqq == NULL) {
-+		rb_link_node(&bfqq->pos_node, parent, p);
-+		rb_insert_color(&bfqq->pos_node, bfqq->pos_root);
-+	} else
-+		bfqq->pos_root = NULL;
-+}
-+
-+static struct request *bfq_find_next_rq(struct bfq_data *bfqd,
-+					struct bfq_queue *bfqq,
-+					struct request *last)
-+{
-+	struct rb_node *rbnext = rb_next(&last->rb_node);
-+	struct rb_node *rbprev = rb_prev(&last->rb_node);
-+	struct request *next = NULL, *prev = NULL;
-+
-+	BUG_ON(RB_EMPTY_NODE(&last->rb_node));
-+
-+	if (rbprev != NULL)
-+		prev = rb_entry_rq(rbprev);
-+
-+	if (rbnext != NULL)
-+		next = rb_entry_rq(rbnext);
-+	else {
-+		rbnext = rb_first(&bfqq->sort_list);
-+		if (rbnext && rbnext != &last->rb_node)
-+			next = rb_entry_rq(rbnext);
-+	}
-+
-+	return bfq_choose_req(bfqd, next, prev, blk_rq_pos(last));
-+}
-+
-+static void bfq_del_rq_rb(struct request *rq)
-+{
-+	struct bfq_queue *bfqq = RQ_BFQQ(rq);
-+	struct bfq_data *bfqd = bfqq->bfqd;
-+	const int sync = rq_is_sync(rq);
-+
-+	BUG_ON(bfqq->queued[sync] == 0);
-+	bfqq->queued[sync]--;
-+	bfqd->queued--;
-+
-+	elv_rb_del(&bfqq->sort_list, rq);
-+
-+	if (RB_EMPTY_ROOT(&bfqq->sort_list)) {
-+		if (bfq_bfqq_busy(bfqq) && bfqq != bfqd->in_service_queue)
-+			bfq_del_bfqq_busy(bfqd, bfqq, 1);
-+		/*
-+		 * Remove queue from request-position tree as it is empty.
-+		 */
-+		if (bfqq->pos_root != NULL) {
-+			rb_erase(&bfqq->pos_node, bfqq->pos_root);
-+			bfqq->pos_root = NULL;
-+		}
-+	}
-+}
-+
-+/* see the definition of bfq_async_charge_factor for details */
-+static inline unsigned long bfq_serv_to_charge(struct request *rq,
-+					       struct bfq_queue *bfqq)
-+{
-+	return blk_rq_sectors(rq) *
-+		(1 + ((!bfq_bfqq_sync(bfqq)) * (bfqq->raising_coeff == 1) *
-+		bfq_async_charge_factor));
-+}
-+
-+/**
-+ * bfq_updated_next_req - update the queue after a new next_rq selection.
-+ * @bfqd: the device data the queue belongs to.
-+ * @bfqq: the queue to update.
-+ *
-+ * If the first request of a queue changes we make sure that the queue
-+ * has enough budget to serve at least its first request (if the
-+ * request has grown).  We do this because if the queue has not enough
-+ * budget for its first request, it has to go through two dispatch
-+ * rounds to actually get it dispatched.
-+ */
-+static void bfq_updated_next_req(struct bfq_data *bfqd,
-+				 struct bfq_queue *bfqq)
-+{
-+	struct bfq_entity *entity = &bfqq->entity;
-+	struct bfq_service_tree *st = bfq_entity_service_tree(entity);
-+	struct request *next_rq = bfqq->next_rq;
-+	unsigned long new_budget;
-+
-+	if (next_rq == NULL)
-+		return;
-+
-+	if (bfqq == bfqd->in_service_queue)
-+		/*
-+		 * In order not to break guarantees, budgets cannot be
-+		 * changed after an entity has been selected.
-+		 */
-+		return;
-+
-+	BUG_ON(entity->tree != &st->active);
-+	BUG_ON(entity == entity->sched_data->in_service_entity);
-+
-+	new_budget = max_t(unsigned long, bfqq->max_budget,
-+			   bfq_serv_to_charge(next_rq, bfqq));
-+	entity->budget = new_budget;
-+	bfq_log_bfqq(bfqd, bfqq, "updated next rq: new budget %lu", new_budget);
-+	bfq_activate_bfqq(bfqd, bfqq);
-+}
-+
-+static inline unsigned int bfq_wrais_duration(struct bfq_data *bfqd)
-+{
-+	u64 dur;
-+
-+	if (bfqd->bfq_raising_max_time > 0)
-+		return bfqd->bfq_raising_max_time;
-+
-+	dur = bfqd->RT_prod;
-+	do_div(dur, bfqd->peak_rate);
-+
-+	return dur;
-+}
-+
-+static void bfq_add_rq_rb(struct request *rq)
-+{
-+	struct bfq_queue *bfqq = RQ_BFQQ(rq);
-+	struct bfq_entity *entity = &bfqq->entity;
-+	struct bfq_data *bfqd = bfqq->bfqd;
-+	struct request *next_rq, *prev;
-+	unsigned long old_raising_coeff = bfqq->raising_coeff;
-+	int idle_for_long_time = 0;
-+
-+	bfq_log_bfqq(bfqd, bfqq, "add_rq_rb %d", rq_is_sync(rq));
-+	bfqq->queued[rq_is_sync(rq)]++;
-+	bfqd->queued++;
-+
-+	elv_rb_add(&bfqq->sort_list, rq);
-+
-+	/*
-+	 * Check if this request is a better next-serve candidate.
-+	 */
-+	prev = bfqq->next_rq;
-+	next_rq = bfq_choose_req(bfqd, bfqq->next_rq, rq, bfqd->last_position);
-+	BUG_ON(next_rq == NULL);
-+	bfqq->next_rq = next_rq;
-+
-+	/*
-+	 * Adjust priority tree position, if next_rq changes.
-+	 */
-+	if (prev != bfqq->next_rq)
-+		bfq_rq_pos_tree_add(bfqd, bfqq);
-+
-+	if (!bfq_bfqq_busy(bfqq)) {
-+		int soft_rt = bfqd->bfq_raising_max_softrt_rate > 0 &&
-+			time_is_before_jiffies(bfqq->soft_rt_next_start);
-+		idle_for_long_time = time_is_before_jiffies(
-+			bfqq->budget_timeout +
-+			bfqd->bfq_raising_min_idle_time);
-+		entity->budget = max_t(unsigned long, bfqq->max_budget,
-+				       bfq_serv_to_charge(next_rq, bfqq));
-+
-+		if (!bfqd->low_latency)
-+			goto add_bfqq_busy;
-+
-+		/*
-+		 * If the queue is not being boosted and has been idle
-+		 * for enough time, start a weight-raising period
-+		 */
-+		if (old_raising_coeff == 1 &&
-+		    (idle_for_long_time || soft_rt)) {
-+			bfqq->raising_coeff = bfqd->bfq_raising_coeff;
-+			if (idle_for_long_time)
-+				bfqq->raising_cur_max_time =
-+					bfq_wrais_duration(bfqd);
-+			else
-+				bfqq->raising_cur_max_time =
-+					bfqd->bfq_raising_rt_max_time;
-+			bfq_log_bfqq(bfqd, bfqq,
-+				     "wrais starting at %lu, "
-+				     "rais_max_time %u",
-+				     jiffies,
-+				     jiffies_to_msecs(bfqq->
-+					raising_cur_max_time));
-+		} else if (old_raising_coeff > 1) {
-+			if (idle_for_long_time)
-+				bfqq->raising_cur_max_time =
-+					bfq_wrais_duration(bfqd);
-+			else if (bfqq->raising_cur_max_time ==
-+				 bfqd->bfq_raising_rt_max_time &&
-+				 !soft_rt) {
-+				bfqq->raising_coeff = 1;
-+				bfq_log_bfqq(bfqd, bfqq,
-+					     "wrais ending at %lu, "
-+					     "rais_max_time %u",
-+					     jiffies,
-+					     jiffies_to_msecs(bfqq->
-+						raising_cur_max_time));
-+			} else if (time_before(
-+					bfqq->last_rais_start_finish +
-+					bfqq->raising_cur_max_time,
-+					jiffies +
-+					bfqd->bfq_raising_rt_max_time) &&
-+				   soft_rt) {
-+				/*
-+				 *
-+				 * The remaining weight-raising time is lower
-+				 * than bfqd->bfq_raising_rt_max_time, which
-+				 * means that the application is enjoying
-+				 * weight raising either because deemed soft-
-+				 * rt in the near past, or because deemed
-+				 * interactive a long ago. In both cases,
-+				 * resetting now the current remaining weight-
-+				 * raising time for the application to the
-+				 * weight-raising duration for soft rt
-+				 * applications would not cause any latency
-+				 * increase for the application (as the new
-+				 * duration would be higher than the remaining
-+				 * time).
-+				 *
-+				 * In addition, the application is now meeting
-+				 * the requirements for being deemed soft rt.
-+				 * In the end we can correctly and safely
-+				 * (re)charge the weight-raising duration for
-+				 * the application with the weight-raising
-+				 * duration for soft rt applications.
-+				 *
-+				 * In particular, doing this recharge now, i.e.,
-+				 * before the weight-raising period for the
-+				 * application finishes, reduces the probability
-+				 * of the following negative scenario:
-+				 * 1) the weight of a soft rt application is
-+				 *    raised at startup (as for any newly
-+				 *    created application),
-+				 * 2) since the application is not interactive,
-+				 *    at a certain time weight-raising is
-+				 *    stopped for the application,
-+				 * 3) at that time the application happens to
-+				 *    still have pending requests, and hence
-+				 *    is destined to not have a chance to be
-+				 *    deemed soft rt before these requests are
-+				 *    completed (see the comments to the
-+				 *    function bfq_bfqq_softrt_next_start()
-+				 *    for details on soft rt detection),
-+				 * 4) these pending requests experience a high
-+				 *    latency because the application is not
-+				 *    weight-raised while they are pending.
-+				 */
-+				bfqq->last_rais_start_finish = jiffies;
-+				bfqq->raising_cur_max_time =
-+					bfqd->bfq_raising_rt_max_time;
-+			}
-+		}
-+		if (old_raising_coeff != bfqq->raising_coeff)
-+			entity->ioprio_changed = 1;
-+add_bfqq_busy:
-+		bfqq->last_idle_bklogged = jiffies;
-+		bfqq->service_from_backlogged = 0;
-+		bfq_clear_bfqq_softrt_update(bfqq);
-+		bfq_add_bfqq_busy(bfqd, bfqq);
-+	} else {
-+		if (bfqd->low_latency && old_raising_coeff == 1 &&
-+			!rq_is_sync(rq) &&
-+			time_is_before_jiffies(
-+				bfqq->last_rais_start_finish +
-+				bfqd->bfq_raising_min_inter_arr_async)) {
-+			bfqq->raising_coeff = bfqd->bfq_raising_coeff;
-+			bfqq->raising_cur_max_time = bfq_wrais_duration(bfqd);
-+
-+			bfqd->raised_busy_queues++;
-+			entity->ioprio_changed = 1;
-+			bfq_log_bfqq(bfqd, bfqq,
-+				     "non-idle wrais starting at %lu, "
-+				     "rais_max_time %u",
-+				     jiffies,
-+				     jiffies_to_msecs(bfqq->
-+					raising_cur_max_time));
-+		}
-+		bfq_updated_next_req(bfqd, bfqq);
-+	}
-+
-+	if (bfqd->low_latency &&
-+		(old_raising_coeff == 1 || bfqq->raising_coeff == 1 ||
-+		 idle_for_long_time))
-+		bfqq->last_rais_start_finish = jiffies;
-+}
-+
-+static void bfq_reposition_rq_rb(struct bfq_queue *bfqq, struct request *rq)
-+{
-+	elv_rb_del(&bfqq->sort_list, rq);
-+	bfqq->queued[rq_is_sync(rq)]--;
-+	bfqq->bfqd->queued--;
-+	bfq_add_rq_rb(rq);
-+}
-+
-+static struct request *bfq_find_rq_fmerge(struct bfq_data *bfqd,
-+					  struct bio *bio)
-+{
-+	struct task_struct *tsk = current;
-+	struct bfq_io_cq *bic;
-+	struct bfq_queue *bfqq;
-+
-+	bic = bfq_bic_lookup(bfqd, tsk->io_context);
-+	if (bic == NULL)
-+		return NULL;
-+
-+	bfqq = bic_to_bfqq(bic, bfq_bio_sync(bio));
-+	if (bfqq != NULL)
-+		return elv_rb_find(&bfqq->sort_list, bio_end_sector(bio));
-+
-+	return NULL;
-+}
-+
-+static void bfq_activate_request(struct request_queue *q, struct request *rq)
-+{
-+	struct bfq_data *bfqd = q->elevator->elevator_data;
-+
-+	bfqd->rq_in_driver++;
-+	bfqd->last_position = blk_rq_pos(rq) + blk_rq_sectors(rq);
-+	bfq_log(bfqd, "activate_request: new bfqd->last_position %llu",
-+		(long long unsigned)bfqd->last_position);
-+}
-+
-+static void bfq_deactivate_request(struct request_queue *q, struct request *rq)
-+{
-+	struct bfq_data *bfqd = q->elevator->elevator_data;
-+
-+	WARN_ON(bfqd->rq_in_driver == 0);
-+	bfqd->rq_in_driver--;
-+}
-+
-+static void bfq_remove_request(struct request *rq)
-+{
-+	struct bfq_queue *bfqq = RQ_BFQQ(rq);
-+	struct bfq_data *bfqd = bfqq->bfqd;
-+
-+	if (bfqq->next_rq == rq) {
-+		bfqq->next_rq = bfq_find_next_rq(bfqd, bfqq, rq);
-+		bfq_updated_next_req(bfqd, bfqq);
-+	}
-+
-+	list_del_init(&rq->queuelist);
-+	bfq_del_rq_rb(rq);
-+
-+	if (rq->cmd_flags & REQ_META) {
-+		WARN_ON(bfqq->meta_pending == 0);
-+		bfqq->meta_pending--;
-+	}
-+}
-+
-+static int bfq_merge(struct request_queue *q, struct request **req,
-+		     struct bio *bio)
-+{
-+	struct bfq_data *bfqd = q->elevator->elevator_data;
-+	struct request *__rq;
-+
-+	__rq = bfq_find_rq_fmerge(bfqd, bio);
-+	if (__rq != NULL && elv_rq_merge_ok(__rq, bio)) {
-+		*req = __rq;
-+		return ELEVATOR_FRONT_MERGE;
-+	}
-+
-+	return ELEVATOR_NO_MERGE;
-+}
-+
-+static void bfq_merged_request(struct request_queue *q, struct request *req,
-+			       int type)
-+{
-+	if (type == ELEVATOR_FRONT_MERGE) {
-+		struct bfq_queue *bfqq = RQ_BFQQ(req);
-+
-+		bfq_reposition_rq_rb(bfqq, req);
-+	}
-+}
-+
-+static void bfq_merged_requests(struct request_queue *q, struct request *rq,
-+				struct request *next)
-+{
-+	struct bfq_queue *bfqq = RQ_BFQQ(rq);
-+
-+	/*
-+	 * Reposition in fifo if next is older than rq.
-+	 */
-+	if (!list_empty(&rq->queuelist) && !list_empty(&next->queuelist) &&
-+	    time_before(rq_fifo_time(next), rq_fifo_time(rq))) {
-+		list_move(&rq->queuelist, &next->queuelist);
-+		rq_set_fifo_time(rq, rq_fifo_time(next));
-+	}
-+
-+	if (bfqq->next_rq == next)
-+		bfqq->next_rq = rq;
-+
-+	bfq_remove_request(next);
-+}
-+
-+/* Must be called with bfqq != NULL */
-+static inline void bfq_bfqq_end_raising(struct bfq_queue *bfqq)
-+{
-+	BUG_ON(bfqq == NULL);
-+	if (bfq_bfqq_busy(bfqq))
-+		bfqq->bfqd->raised_busy_queues--;
-+	bfqq->raising_coeff = 1;
-+	bfqq->raising_cur_max_time = 0;
-+	/* Trigger a weight change on the next activation of the queue */
-+	bfqq->entity.ioprio_changed = 1;
-+}
-+
-+static void bfq_end_raising_async_queues(struct bfq_data *bfqd,
-+					struct bfq_group *bfqg)
-+{
-+	int i, j;
-+
-+	for (i = 0; i < 2; i++)
-+		for (j = 0; j < IOPRIO_BE_NR; j++)
-+			if (bfqg->async_bfqq[i][j] != NULL)
-+				bfq_bfqq_end_raising(bfqg->async_bfqq[i][j]);
-+	if (bfqg->async_idle_bfqq != NULL)
-+		bfq_bfqq_end_raising(bfqg->async_idle_bfqq);
-+}
-+
-+static void bfq_end_raising(struct bfq_data *bfqd)
-+{
-+	struct bfq_queue *bfqq;
-+
-+	spin_lock_irq(bfqd->queue->queue_lock);
-+
-+	list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list)
-+		bfq_bfqq_end_raising(bfqq);
-+	list_for_each_entry(bfqq, &bfqd->idle_list, bfqq_list)
-+		bfq_bfqq_end_raising(bfqq);
-+	bfq_end_raising_async(bfqd);
-+
-+	spin_unlock_irq(bfqd->queue->queue_lock);
-+}
-+
-+static int bfq_allow_merge(struct request_queue *q, struct request *rq,
-+			   struct bio *bio)
-+{
-+	struct bfq_data *bfqd = q->elevator->elevator_data;
-+	struct bfq_io_cq *bic;
-+	struct bfq_queue *bfqq;
-+
-+	/*
-+	 * Disallow merge of a sync bio into an async request.
-+	 */
-+	if (bfq_bio_sync(bio) && !rq_is_sync(rq))
-+		return 0;
-+
-+	/*
-+	 * Lookup the bfqq that this bio will be queued with. Allow
-+	 * merge only if rq is queued there.
-+	 * Queue lock is held here.
-+	 */
-+	bic = bfq_bic_lookup(bfqd, current->io_context);
-+	if (bic == NULL)
-+		return 0;
-+
-+	bfqq = bic_to_bfqq(bic, bfq_bio_sync(bio));
-+	return bfqq == RQ_BFQQ(rq);
-+}
-+
-+static void __bfq_set_in_service_queue(struct bfq_data *bfqd,
-+				       struct bfq_queue *bfqq)
-+{
-+	if (bfqq != NULL) {
-+		bfq_mark_bfqq_must_alloc(bfqq);
-+		bfq_mark_bfqq_budget_new(bfqq);
-+		bfq_clear_bfqq_fifo_expire(bfqq);
-+
-+		bfqd->budgets_assigned = (bfqd->budgets_assigned*7 + 256) / 8;
-+
-+		bfq_log_bfqq(bfqd, bfqq,
-+			     "set_in_service_queue, cur-budget = %lu",
-+			     bfqq->entity.budget);
-+	}
-+
-+	bfqd->in_service_queue = bfqq;
-+}
-+
-+/*
-+ * Get and set a new queue for service.
-+ */
-+static struct bfq_queue *bfq_set_in_service_queue(struct bfq_data *bfqd,
-+						  struct bfq_queue *bfqq)
-+{
-+	if (!bfqq)
-+		bfqq = bfq_get_next_queue(bfqd);
-+	else
-+		bfq_get_next_queue_forced(bfqd, bfqq);
-+
-+	__bfq_set_in_service_queue(bfqd, bfqq);
-+	return bfqq;
-+}
-+
-+static inline sector_t bfq_dist_from_last(struct bfq_data *bfqd,
-+					  struct request *rq)
-+{
-+	if (blk_rq_pos(rq) >= bfqd->last_position)
-+		return blk_rq_pos(rq) - bfqd->last_position;
-+	else
-+		return bfqd->last_position - blk_rq_pos(rq);
-+}
-+
-+/*
-+ * Return true if bfqq has no request pending and rq is close enough to
-+ * bfqd->last_position, or if rq is closer to bfqd->last_position than
-+ * bfqq->next_rq
-+ */
-+static inline int bfq_rq_close(struct bfq_data *bfqd, struct request *rq)
-+{
-+	return bfq_dist_from_last(bfqd, rq) <= BFQQ_SEEK_THR;
-+}
-+
-+static struct bfq_queue *bfqq_close(struct bfq_data *bfqd)
-+{
-+	struct rb_root *root = &bfqd->rq_pos_tree;
-+	struct rb_node *parent, *node;
-+	struct bfq_queue *__bfqq;
-+	sector_t sector = bfqd->last_position;
-+
-+	if (RB_EMPTY_ROOT(root))
-+		return NULL;
-+
-+	/*
-+	 * First, if we find a request starting at the end of the last
-+	 * request, choose it.
-+	 */
-+	__bfqq = bfq_rq_pos_tree_lookup(bfqd, root, sector, &parent, NULL);
-+	if (__bfqq != NULL)
-+		return __bfqq;
-+
-+	/*
-+	 * If the exact sector wasn't found, the parent of the NULL leaf
-+	 * will contain the closest sector (rq_pos_tree sorted by next_request
-+	 * position).
-+	 */
-+	__bfqq = rb_entry(parent, struct bfq_queue, pos_node);
-+	if (bfq_rq_close(bfqd, __bfqq->next_rq))
-+		return __bfqq;
-+
-+	if (blk_rq_pos(__bfqq->next_rq) < sector)
-+		node = rb_next(&__bfqq->pos_node);
-+	else
-+		node = rb_prev(&__bfqq->pos_node);
-+	if (node == NULL)
-+		return NULL;
-+
-+	__bfqq = rb_entry(node, struct bfq_queue, pos_node);
-+	if (bfq_rq_close(bfqd, __bfqq->next_rq))
-+		return __bfqq;
-+
-+	return NULL;
-+}
-+
-+/*
-+ * bfqd - obvious
-+ * cur_bfqq - passed in so that we don't decide that the current queue
-+ *            is closely cooperating with itself.
-+ *
-+ * We are assuming that cur_bfqq has dispatched at least one request,
-+ * and that bfqd->last_position reflects a position on the disk associated
-+ * with the I/O issued by cur_bfqq.
-+ */
-+static struct bfq_queue *bfq_close_cooperator(struct bfq_data *bfqd,
-+					      struct bfq_queue *cur_bfqq)
-+{
-+	struct bfq_queue *bfqq;
-+
-+	if (bfq_class_idle(cur_bfqq))
-+		return NULL;
-+	if (!bfq_bfqq_sync(cur_bfqq))
-+		return NULL;
-+	if (BFQQ_SEEKY(cur_bfqq))
-+		return NULL;
-+
-+	/* If device has only one backlogged bfq_queue, don't search. */
-+	if (bfqd->busy_queues == 1)
-+		return NULL;
-+
-+	/*
-+	 * We should notice if some of the queues are cooperating, e.g.
-+	 * working closely on the same area of the disk. In that case,
-+	 * we can group them together and don't waste time idling.
-+	 */
-+	bfqq = bfqq_close(bfqd);
-+	if (bfqq == NULL || bfqq == cur_bfqq)
-+		return NULL;
-+
-+	/*
-+	 * Do not merge queues from different bfq_groups.
-+	*/
-+	if (bfqq->entity.parent != cur_bfqq->entity.parent)
-+		return NULL;
-+
-+	/*
-+	 * It only makes sense to merge sync queues.
-+	 */
-+	if (!bfq_bfqq_sync(bfqq))
-+		return NULL;
-+	if (BFQQ_SEEKY(bfqq))
-+		return NULL;
-+
-+	/*
-+	 * Do not merge queues of different priority classes.
-+	 */
-+	if (bfq_class_rt(bfqq) != bfq_class_rt(cur_bfqq))
-+		return NULL;
-+
-+	return bfqq;
-+}
-+
-+/*
-+ * If enough samples have been computed, return the current max budget
-+ * stored in bfqd, which is dynamically updated according to the
-+ * estimated disk peak rate; otherwise return the default max budget
-+ */
-+static inline unsigned long bfq_max_budget(struct bfq_data *bfqd)
-+{
-+	if (bfqd->budgets_assigned < 194)
-+		return bfq_default_max_budget;
-+	else
-+		return bfqd->bfq_max_budget;
-+}
-+
-+/*
-+ * Return min budget, which is a fraction of the current or default
-+ * max budget (trying with 1/32)
-+ */
-+static inline unsigned long bfq_min_budget(struct bfq_data *bfqd)
-+{
-+	if (bfqd->budgets_assigned < 194)
-+		return bfq_default_max_budget / 32;
-+	else
-+		return bfqd->bfq_max_budget / 32;
-+}
-+
-+/*
-+ * Decides whether idling should be done for given device and
-+ * given in-service queue.
-+ */
-+static inline bool bfq_queue_nonrot_noidle(struct bfq_data *bfqd,
-+					   struct bfq_queue *in_service_bfqq)
-+{
-+	if (in_service_bfqq == NULL)
-+		return false;
-+	/*
-+	 * If the device is non-rotational, and hence has no seek penalty,
-+	 * disable idling; but do so only if:
-+	 * - device does not support queuing, otherwise we still have
-+	 *   a problem with sync vs async workloads;
-+	 * - the queue is not weight-raised, to preserve guarantees.
-+	 */
-+	return blk_queue_nonrot(bfqd->queue) && bfqd->hw_tag &&
-+	       (in_service_bfqq->raising_coeff == 1);
-+}
-+
-+static void bfq_arm_slice_timer(struct bfq_data *bfqd)
-+{
-+	struct bfq_queue *bfqq = bfqd->in_service_queue;
-+	struct bfq_io_cq *bic;
-+	unsigned long sl;
-+
-+	WARN_ON(!RB_EMPTY_ROOT(&bfqq->sort_list));
-+
-+	/* Tasks have exited, don't wait. */
-+	bic = bfqd->in_service_bic;
-+	if (bic == NULL || atomic_read(&bic->icq.ioc->active_ref) == 0)
-+		return;
-+
-+	bfq_mark_bfqq_wait_request(bfqq);
-+
-+	/*
-+	 * We don't want to idle for seeks, but we do want to allow
-+	 * fair distribution of slice time for a process doing back-to-back
-+	 * seeks. So allow a little bit of time for him to submit a new rq.
-+	 *
-+	 * To prevent processes with (partly) seeky workloads from
-+	 * being too ill-treated, grant them a small fraction of the
-+	 * assigned budget before reducing the waiting time to
-+	 * BFQ_MIN_TT. This happened to help reduce latency.
-+	 */
-+	sl = bfqd->bfq_slice_idle;
-+	if (bfq_sample_valid(bfqq->seek_samples) && BFQQ_SEEKY(bfqq) &&
-+	    bfqq->entity.service > bfq_max_budget(bfqd) / 8 &&
-+	    bfqq->raising_coeff == 1)
-+		sl = min(sl, msecs_to_jiffies(BFQ_MIN_TT));
-+	else if (bfqq->raising_coeff > 1)
-+		sl = sl * 3;
-+	bfqd->last_idling_start = ktime_get();
-+	mod_timer(&bfqd->idle_slice_timer, jiffies + sl);
-+	bfq_log(bfqd, "arm idle: %u/%u ms",
-+		jiffies_to_msecs(sl), jiffies_to_msecs(bfqd->bfq_slice_idle));
-+}
-+
-+/*
-+ * Set the maximum time for the in-service queue to consume its
-+ * budget. This prevents seeky processes from lowering the disk
-+ * throughput (always guaranteed with a time slice scheme as in CFQ).
-+ */
-+static void bfq_set_budget_timeout(struct bfq_data *bfqd)
-+{
-+	struct bfq_queue *bfqq = bfqd->in_service_queue;
-+	unsigned int timeout_coeff;
-+	if (bfqq->raising_cur_max_time == bfqd->bfq_raising_rt_max_time)
-+		timeout_coeff = 1;
-+	else
-+		timeout_coeff = bfqq->entity.weight / bfqq->entity.orig_weight;
-+
-+	bfqd->last_budget_start = ktime_get();
-+
-+	bfq_clear_bfqq_budget_new(bfqq);
-+	bfqq->budget_timeout = jiffies +
-+		bfqd->bfq_timeout[bfq_bfqq_sync(bfqq)] * timeout_coeff;
-+
-+	bfq_log_bfqq(bfqd, bfqq, "set budget_timeout %u",
-+		jiffies_to_msecs(bfqd->bfq_timeout[bfq_bfqq_sync(bfqq)] *
-+		timeout_coeff));
-+}
-+
-+/*
-+ * Move request from internal lists to the request queue dispatch list.
-+ */
-+static void bfq_dispatch_insert(struct request_queue *q, struct request *rq)
-+{
-+	struct bfq_data *bfqd = q->elevator->elevator_data;
-+	struct bfq_queue *bfqq = RQ_BFQQ(rq);
-+
-+	bfq_remove_request(rq);
-+	bfqq->dispatched++;
-+	elv_dispatch_sort(q, rq);
-+
-+	if (bfq_bfqq_sync(bfqq))
-+		bfqd->sync_flight++;
-+}
-+
-+/*
-+ * Return expired entry, or NULL to just start from scratch in rbtree.
-+ */
-+static struct request *bfq_check_fifo(struct bfq_queue *bfqq)
-+{
-+	struct request *rq = NULL;
-+
-+	if (bfq_bfqq_fifo_expire(bfqq))
-+		return NULL;
-+
-+	bfq_mark_bfqq_fifo_expire(bfqq);
-+
-+	if (list_empty(&bfqq->fifo))
-+		return NULL;
-+
-+	rq = rq_entry_fifo(bfqq->fifo.next);
-+
-+	if (time_before(jiffies, rq_fifo_time(rq)))
-+		return NULL;
-+
-+	return rq;
-+}
-+
-+/*
-+ * Must be called with the queue_lock held.
-+ */
-+static int bfqq_process_refs(struct bfq_queue *bfqq)
-+{
-+	int process_refs, io_refs;
-+
-+	io_refs = bfqq->allocated[READ] + bfqq->allocated[WRITE];
-+	process_refs = atomic_read(&bfqq->ref) - io_refs - bfqq->entity.on_st;
-+	BUG_ON(process_refs < 0);
-+	return process_refs;
-+}
-+
-+static void bfq_setup_merge(struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
-+{
-+	int process_refs, new_process_refs;
-+	struct bfq_queue *__bfqq;
-+
-+	/*
-+	 * If there are no process references on the new_bfqq, then it is
-+	 * unsafe to follow the ->new_bfqq chain as other bfqq's in the chain
-+	 * may have dropped their last reference (not just their last process
-+	 * reference).
-+	 */
-+	if (!bfqq_process_refs(new_bfqq))
-+		return;
-+
-+	/* Avoid a circular list and skip interim queue merges. */
-+	while ((__bfqq = new_bfqq->new_bfqq)) {
-+		if (__bfqq == bfqq)
-+			return;
-+		new_bfqq = __bfqq;
-+	}
-+
-+	process_refs = bfqq_process_refs(bfqq);
-+	new_process_refs = bfqq_process_refs(new_bfqq);
-+	/*
-+	 * If the process for the bfqq has gone away, there is no
-+	 * sense in merging the queues.
-+	 */
-+	if (process_refs == 0 || new_process_refs == 0)
-+		return;
-+
-+	/*
-+	 * Merge in the direction of the lesser amount of work.
-+	 */
-+	if (new_process_refs >= process_refs) {
-+		bfqq->new_bfqq = new_bfqq;
-+		atomic_add(process_refs, &new_bfqq->ref);
-+	} else {
-+		new_bfqq->new_bfqq = bfqq;
-+		atomic_add(new_process_refs, &bfqq->ref);
-+	}
-+	bfq_log_bfqq(bfqq->bfqd, bfqq, "scheduling merge with queue %d",
-+		new_bfqq->pid);
-+}
-+
-+static inline unsigned long bfq_bfqq_budget_left(struct bfq_queue *bfqq)
-+{
-+	struct bfq_entity *entity = &bfqq->entity;
-+	return entity->budget - entity->service;
-+}
-+
-+static void __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq)
-+{
-+	BUG_ON(bfqq != bfqd->in_service_queue);
-+
-+	__bfq_bfqd_reset_in_service(bfqd);
-+
-+	/*
-+	 * If this bfqq is shared between multiple processes, check
-+	 * to make sure that those processes are still issuing I/Os
-+	 * within the mean seek distance. If not, it may be time to
-+	 * break the queues apart again.
-+	 */
-+	if (bfq_bfqq_coop(bfqq) && BFQQ_SEEKY(bfqq))
-+		bfq_mark_bfqq_split_coop(bfqq);
-+
-+	if (RB_EMPTY_ROOT(&bfqq->sort_list)) {
-+		/*
-+		 * overloading budget_timeout field to store when
-+		 * the queue remains with no backlog, used by
-+		 * the weight-raising mechanism
-+		 */
-+		bfqq->budget_timeout = jiffies;
-+		bfq_del_bfqq_busy(bfqd, bfqq, 1);
-+	} else {
-+		bfq_activate_bfqq(bfqd, bfqq);
-+		/*
-+		 * Resort priority tree of potential close cooperators.
-+		 */
-+		bfq_rq_pos_tree_add(bfqd, bfqq);
-+	}
-+}
-+
-+/**
-+ * __bfq_bfqq_recalc_budget - try to adapt the budget to the @bfqq behavior.
-+ * @bfqd: device data.
-+ * @bfqq: queue to update.
-+ * @reason: reason for expiration.
-+ *
-+ * Handle the feedback on @bfqq budget.  See the body for detailed
-+ * comments.
-+ */
-+static void __bfq_bfqq_recalc_budget(struct bfq_data *bfqd,
-+				     struct bfq_queue *bfqq,
-+				     enum bfqq_expiration reason)
-+{
-+	struct request *next_rq;
-+	unsigned long budget, min_budget;
-+
-+	budget = bfqq->max_budget;
-+	min_budget = bfq_min_budget(bfqd);
-+
-+	BUG_ON(bfqq != bfqd->in_service_queue);
-+
-+	bfq_log_bfqq(bfqd, bfqq, "recalc_budg: last budg %lu, budg left %lu",
-+		bfqq->entity.budget, bfq_bfqq_budget_left(bfqq));
-+	bfq_log_bfqq(bfqd, bfqq, "recalc_budg: last max_budg %lu, min budg %lu",
-+		budget, bfq_min_budget(bfqd));
-+	bfq_log_bfqq(bfqd, bfqq, "recalc_budg: sync %d, seeky %d",
-+		bfq_bfqq_sync(bfqq), BFQQ_SEEKY(bfqd->in_service_queue));
-+
-+	if (bfq_bfqq_sync(bfqq)) {
-+		switch (reason) {
-+		/*
-+		 * Caveat: in all the following cases we trade latency
-+		 * for throughput.
-+		 */
-+		case BFQ_BFQQ_TOO_IDLE:
-+			/*
-+			 * This is the only case where we may reduce
-+			 * the budget: if there is no request of the
-+			 * process still waiting for completion, then
-+			 * we assume (tentatively) that the timer has
-+			 * expired because the batch of requests of
-+			 * the process could have been served with a
-+			 * smaller budget.  Hence, betting that
-+			 * process will behave in the same way when it
-+			 * becomes backlogged again, we reduce its
-+			 * next budget.  As long as we guess right,
-+			 * this budget cut reduces the latency
-+			 * experienced by the process.
-+			 *
-+			 * However, if there are still outstanding
-+			 * requests, then the process may have not yet
-+			 * issued its next request just because it is
-+			 * still waiting for the completion of some of
-+			 * the still outstanding ones.  So in this
-+			 * subcase we do not reduce its budget, on the
-+			 * contrary we increase it to possibly boost
-+			 * the throughput, as discussed in the
-+			 * comments to the BUDGET_TIMEOUT case.
-+			 */
-+			if (bfqq->dispatched > 0) /* still outstanding reqs */
-+				budget = min(budget * 2, bfqd->bfq_max_budget);
-+			else {
-+				if (budget > 5 * min_budget)
-+					budget -= 4 * min_budget;
-+				else
-+					budget = min_budget;
-+			}
-+			break;
-+		case BFQ_BFQQ_BUDGET_TIMEOUT:
-+			/*
-+			 * We double the budget here because: 1) it
-+			 * gives the chance to boost the throughput if
-+			 * this is not a seeky process (which may have
-+			 * bumped into this timeout because of, e.g.,
-+			 * ZBR), 2) together with charge_full_budget
-+			 * it helps give seeky processes higher
-+			 * timestamps, and hence be served less
-+			 * frequently.
-+			 */
-+			budget = min(budget * 2, bfqd->bfq_max_budget);
-+			break;
-+		case BFQ_BFQQ_BUDGET_EXHAUSTED:
-+			/*
-+			 * The process still has backlog, and did not
-+			 * let either the budget timeout or the disk
-+			 * idling timeout expire. Hence it is not
-+			 * seeky, has a short thinktime and may be
-+			 * happy with a higher budget too. So
-+			 * definitely increase the budget of this good
-+			 * candidate to boost the disk throughput.
-+			 */
-+			budget = min(budget * 4, bfqd->bfq_max_budget);
-+			break;
-+		case BFQ_BFQQ_NO_MORE_REQUESTS:
-+		       /*
-+			* Leave the budget unchanged.
-+			*/
-+		default:
-+			return;
-+		}
-+	} else /* async queue */
-+	    /* async queues get always the maximum possible budget
-+	     * (their ability to dispatch is limited by
-+	     * @bfqd->bfq_max_budget_async_rq).
-+	     */
-+		budget = bfqd->bfq_max_budget;
-+
-+	bfqq->max_budget = budget;
-+
-+	if (bfqd->budgets_assigned >= 194 && bfqd->bfq_user_max_budget == 0 &&
-+	    bfqq->max_budget > bfqd->bfq_max_budget)
-+		bfqq->max_budget = bfqd->bfq_max_budget;
-+
-+	/*
-+	 * Make sure that we have enough budget for the next request.
-+	 * Since the finish time of the bfqq must be kept in sync with
-+	 * the budget, be sure to call __bfq_bfqq_expire() after the
-+	 * update.
-+	 */
-+	next_rq = bfqq->next_rq;
-+	if (next_rq != NULL)
-+		bfqq->entity.budget = max_t(unsigned long, bfqq->max_budget,
-+					    bfq_serv_to_charge(next_rq, bfqq));
-+	else
-+		bfqq->entity.budget = bfqq->max_budget;
-+
-+	bfq_log_bfqq(bfqd, bfqq, "head sect: %u, new budget %lu",
-+			next_rq != NULL ? blk_rq_sectors(next_rq) : 0,
-+			bfqq->entity.budget);
-+}
-+
-+static unsigned long bfq_calc_max_budget(u64 peak_rate, u64 timeout)
-+{
-+	unsigned long max_budget;
-+
-+	/*
-+	 * The max_budget calculated when autotuning is equal to the
-+	 * amount of sectors transfered in timeout_sync at the
-+	 * estimated peak rate.
-+	 */
-+	max_budget = (unsigned long)(peak_rate * 1000 *
-+				     timeout >> BFQ_RATE_SHIFT);
-+
-+	return max_budget;
-+}
-+
-+/*
-+ * In addition to updating the peak rate, checks whether the process
-+ * is "slow", and returns 1 if so. This slow flag is used, in addition
-+ * to the budget timeout, to reduce the amount of service provided to
-+ * seeky processes, and hence reduce their chances to lower the
-+ * throughput. See the code for more details.
-+ */
-+static int bfq_update_peak_rate(struct bfq_data *bfqd, struct bfq_queue *bfqq,
-+				int compensate, enum bfqq_expiration reason)
-+{
-+	u64 bw, usecs, expected, timeout;
-+	ktime_t delta;
-+	int update = 0;
-+
-+	if (!bfq_bfqq_sync(bfqq) || bfq_bfqq_budget_new(bfqq))
-+		return 0;
-+
-+	if (compensate)
-+		delta = bfqd->last_idling_start;
-+	else
-+		delta = ktime_get();
-+	delta = ktime_sub(delta, bfqd->last_budget_start);
-+	usecs = ktime_to_us(delta);
-+
-+	/* Don't trust short/unrealistic values. */
-+	if (usecs < 100 || usecs >= LONG_MAX)
-+		return 0;
-+
-+	/*
-+	 * Calculate the bandwidth for the last slice.  We use a 64 bit
-+	 * value to store the peak rate, in sectors per usec in fixed
-+	 * point math.  We do so to have enough precision in the estimate
-+	 * and to avoid overflows.
-+	 */
-+	bw = (u64)bfqq->entity.service << BFQ_RATE_SHIFT;
-+	do_div(bw, (unsigned long)usecs);
-+
-+	timeout = jiffies_to_msecs(bfqd->bfq_timeout[BLK_RW_SYNC]);
-+
-+	/*
-+	 * Use only long (> 20ms) intervals to filter out spikes for
-+	 * the peak rate estimation.
-+	 */
-+	if (usecs > 20000) {
-+		if (bw > bfqd->peak_rate ||
-+		   (!BFQQ_SEEKY(bfqq) &&
-+		    reason == BFQ_BFQQ_BUDGET_TIMEOUT)) {
-+			bfq_log(bfqd, "measured bw =%llu", bw);
-+			/*
-+			 * To smooth oscillations use a low-pass filter with
-+			 * alpha=7/8, i.e.,
-+			 * new_rate = (7/8) * old_rate + (1/8) * bw
-+			 */
-+			do_div(bw, 8);
-+			if (bw == 0)
-+				return 0;
-+			bfqd->peak_rate *= 7;
-+			do_div(bfqd->peak_rate, 8);
-+			bfqd->peak_rate += bw;
-+			update = 1;
-+			bfq_log(bfqd, "new peak_rate=%llu", bfqd->peak_rate);
-+		}
-+
-+		update |= bfqd->peak_rate_samples == BFQ_PEAK_RATE_SAMPLES - 1;
-+
-+		if (bfqd->peak_rate_samples < BFQ_PEAK_RATE_SAMPLES)
-+			bfqd->peak_rate_samples++;
-+
-+		if (bfqd->peak_rate_samples == BFQ_PEAK_RATE_SAMPLES &&
-+		    update && bfqd->bfq_user_max_budget == 0) {
-+			bfqd->bfq_max_budget =
-+				bfq_calc_max_budget(bfqd->peak_rate, timeout);
-+			bfq_log(bfqd, "new max_budget=%lu",
-+				bfqd->bfq_max_budget);
-+		}
-+	}
-+
-+	/*
-+	 * If the process has been served for a too short time
-+	 * interval to let its possible sequential accesses prevail on
-+	 * the initial seek time needed to move the disk head on the
-+	 * first sector it requested, then give the process a chance
-+	 * and for the moment return false.
-+	 */
-+	if (bfqq->entity.budget <= bfq_max_budget(bfqd) / 8)
-+		return 0;
-+
-+	/*
-+	 * A process is considered ``slow'' (i.e., seeky, so that we
-+	 * cannot treat it fairly in the service domain, as it would
-+	 * slow down too much the other processes) if, when a slice
-+	 * ends for whatever reason, it has received service at a
-+	 * rate that would not be high enough to complete the budget
-+	 * before the budget timeout expiration.
-+	 */
-+	expected = bw * 1000 * timeout >> BFQ_RATE_SHIFT;
-+
-+	/*
-+	 * Caveat: processes doing IO in the slower disk zones will
-+	 * tend to be slow(er) even if not seeky. And the estimated
-+	 * peak rate will actually be an average over the disk
-+	 * surface. Hence, to not be too harsh with unlucky processes,
-+	 * we keep a budget/3 margin of safety before declaring a
-+	 * process slow.
-+	 */
-+	return expected > (4 * bfqq->entity.budget) / 3;
-+}
-+
-+/*
-+ * To be deemed as soft real-time, an application must meet two requirements.
-+ * First, the application must not require an average bandwidth higher than
-+ * the approximate bandwidth required to playback or record a compressed high-
-+ * definition video.
-+ * The next function is invoked on the completion of the last request of a
-+ * batch, to compute the next-start time instant, soft_rt_next_start, such
-+ * that, if the next request of the application does not arrive before
-+ * soft_rt_next_start, then the above requirement on the bandwidth is met.
-+ *
-+ * The second requirement is that the request pattern of the application is
-+ * isochronous, i.e., that, after issuing a request or a batch of requests,
-+ * the application stops issuing new requests until all its pending requests
-+ * have been completed. After that, the application may issue a new batch,
-+ * and so on.
-+ * For this reason the next function is invoked to compute soft_rt_next_start
-+ * only for applications that meet this requirement, whereas soft_rt_next_start
-+ * is set to infinity for applications that do not.
-+ *
-+ * Unfortunately, even a greedy application may happen to behave in an
-+ * isochronous way if the CPU load is high. In fact, the application may stop
-+ * issuing requests while the CPUs are busy serving other processes, then
-+ * restart, then stop again for a while, and so on. In addition, if the disk
-+ * achieves a low enough throughput with the request pattern issued by the
-+ * application (e.g., because the request pattern is random and/or the device
-+ * is slow), then the application may meet the above bandwidth requirement too.
-+ * To prevent such a greedy application to be deemed as soft real-time, a
-+ * further rule is used in the computation of soft_rt_next_start:
-+ * soft_rt_next_start must be higher than the current time plus the maximum
-+ * time for which the arrival of a request is waited for when a sync queue
-+ * becomes idle, namely bfqd->bfq_slice_idle.
-+ * This filters out greedy applications, as the latter issue instead their next
-+ * request as soon as possible after the last one has been completed (in
-+ * contrast, when a batch of requests is completed, a soft real-time application
-+ * spends some time processing data).
-+ *
-+ * Unfortunately, the last filter may easily generate false positives if only
-+ * bfqd->bfq_slice_idle is used as a reference time interval and one or both
-+ * the following cases occur:
-+ * 1) HZ is so low that the duration of a jiffy is comparable to or higher
-+ *    than bfqd->bfq_slice_idle. This happens, e.g., on slow devices with
-+ *    HZ=100.
-+ * 2) jiffies, instead of increasing at a constant rate, may stop increasing
-+ *    for a while, then suddenly 'jump' by several units to recover the lost
-+ *    increments. This seems to happen, e.g., inside virtual machines.
-+ * To address this issue, we do not use as a reference time interval just
-+ * bfqd->bfq_slice_idle, but bfqd->bfq_slice_idle plus a few jiffies. In
-+ * particular we add the minimum number of jiffies for which the filter seems
-+ * to be quite precise also in embedded systems and KVM/QEMU virtual machines.
-+ */
-+static inline unsigned long bfq_bfqq_softrt_next_start(struct bfq_data *bfqd,
-+						       struct bfq_queue *bfqq)
-+{
-+	return max(bfqq->last_idle_bklogged +
-+		   HZ * bfqq->service_from_backlogged /
-+		   bfqd->bfq_raising_max_softrt_rate,
-+		   jiffies + bfqq->bfqd->bfq_slice_idle + 4);
-+}
-+
-+/*
-+ * Return the largest-possible time instant such that, for as long as possible,
-+ * the current time will be lower than this time instant according to the macro
-+ * time_is_before_jiffies().
-+ */
-+static inline unsigned long bfq_infinity_from_now(unsigned long now)
-+{
-+	return now + ULONG_MAX / 2;
-+}
-+
-+/**
-+ * bfq_bfqq_expire - expire a queue.
-+ * @bfqd: device owning the queue.
-+ * @bfqq: the queue to expire.
-+ * @compensate: if true, compensate for the time spent idling.
-+ * @reason: the reason causing the expiration.
-+ *
-+ *
-+ * If the process associated to the queue is slow (i.e., seeky), or in
-+ * case of budget timeout, or, finally, if it is async, we
-+ * artificially charge it an entire budget (independently of the
-+ * actual service it received). As a consequence, the queue will get
-+ * higher timestamps than the correct ones upon reactivation, and
-+ * hence it will be rescheduled as if it had received more service
-+ * than what it actually received. In the end, this class of processes
-+ * will receive less service in proportion to how slowly they consume
-+ * their budgets (and hence how seriously they tend to lower the
-+ * throughput).
-+ *
-+ * In contrast, when a queue expires because it has been idling for
-+ * too much or because it exhausted its budget, we do not touch the
-+ * amount of service it has received. Hence when the queue will be
-+ * reactivated and its timestamps updated, the latter will be in sync
-+ * with the actual service received by the queue until expiration.
-+ *
-+ * Charging a full budget to the first type of queues and the exact
-+ * service to the others has the effect of using the WF2Q+ policy to
-+ * schedule the former on a timeslice basis, without violating the
-+ * service domain guarantees of the latter.
-+ */
-+static void bfq_bfqq_expire(struct bfq_data *bfqd,
-+			    struct bfq_queue *bfqq,
-+			    int compensate,
-+			    enum bfqq_expiration reason)
-+{
-+	int slow;
-+	BUG_ON(bfqq != bfqd->in_service_queue);
-+
-+	/* Update disk peak rate for autotuning and check whether the
-+	 * process is slow (see bfq_update_peak_rate).
-+	 */
-+	slow = bfq_update_peak_rate(bfqd, bfqq, compensate, reason);
-+
-+	/*
-+	 * As above explained, 'punish' slow (i.e., seeky), timed-out
-+	 * and async queues, to favor sequential sync workloads.
-+	 *
-+	 * Processes doing IO in the slower disk zones will tend to be
-+	 * slow(er) even if not seeky. Hence, since the estimated peak
-+	 * rate is actually an average over the disk surface, these
-+	 * processes may timeout just for bad luck. To avoid punishing
-+	 * them we do not charge a full budget to a process that
-+	 * succeeded in consuming at least 2/3 of its budget.
-+	 */
-+	if (slow || (reason == BFQ_BFQQ_BUDGET_TIMEOUT &&
-+		     bfq_bfqq_budget_left(bfqq) >=  bfqq->entity.budget / 3))
-+		bfq_bfqq_charge_full_budget(bfqq);
-+
-+	bfqq->service_from_backlogged += bfqq->entity.service;
-+
-+	if (bfqd->low_latency && bfqq->raising_coeff == 1)
-+		bfqq->last_rais_start_finish = jiffies;
-+
-+	if (bfqd->low_latency && bfqd->bfq_raising_max_softrt_rate > 0 &&
-+	    RB_EMPTY_ROOT(&bfqq->sort_list)) {
-+		/*
-+		 * If we get here, and there are no outstanding requests,
-+		 * then the request pattern is isochronous (see the comments
-+		 * to the function bfq_bfqq_softrt_next_start()). Hence we can
-+		 * compute soft_rt_next_start. If, instead, the queue still
-+		 * has outstanding requests, then we have to wait for the
-+		 * completion of all the outstanding requests to discover
-+		 * whether the request pattern is actually isochronous.
-+		 */
-+		if (bfqq->dispatched == 0)
-+			bfqq->soft_rt_next_start =
-+				bfq_bfqq_softrt_next_start(bfqd, bfqq);
-+		else {
-+			/*
-+			 * The application is still waiting for the
-+			 * completion of one or more requests:
-+			 * prevent it from possibly being incorrectly
-+			 * deemed as soft real-time by setting its
-+			 * soft_rt_next_start to infinity. In fact,
-+			 * without this assignment, the application
-+			 * would be incorrectly deemed as soft
-+			 * real-time if:
-+			 * 1) it issued a new request before the
-+			 *    completion of all its in-flight
-+			 *    requests, and
-+			 * 2) at that time, its soft_rt_next_start
-+			 *    happened to be in the past.
-+			 */
-+			bfqq->soft_rt_next_start =
-+				bfq_infinity_from_now(jiffies);
-+			/*
-+			 * Schedule an update of soft_rt_next_start to when
-+			 * the task may be discovered to be isochronous.
-+			 */
-+			bfq_mark_bfqq_softrt_update(bfqq);
-+		}
-+	}
-+
-+	bfq_log_bfqq(bfqd, bfqq,
-+		"expire (%d, slow %d, num_disp %d, idle_win %d)", reason, slow,
-+		bfqq->dispatched, bfq_bfqq_idle_window(bfqq));
-+
-+	/* Increase, decrease or leave budget unchanged according to reason */
-+	__bfq_bfqq_recalc_budget(bfqd, bfqq, reason);
-+	__bfq_bfqq_expire(bfqd, bfqq);
-+}
-+
-+/*
-+ * Budget timeout is not implemented through a dedicated timer, but
-+ * just checked on request arrivals and completions, as well as on
-+ * idle timer expirations.
-+ */
-+static int bfq_bfqq_budget_timeout(struct bfq_queue *bfqq)
-+{
-+	if (bfq_bfqq_budget_new(bfqq))
-+		return 0;
-+
-+	if (time_before(jiffies, bfqq->budget_timeout))
-+		return 0;
-+
-+	return 1;
-+}
-+
-+/*
-+ * If we expire a queue that is waiting for the arrival of a new
-+ * request, we may prevent the fictitious timestamp back-shifting that
-+ * allows the guarantees of the queue to be preserved (see [1] for
-+ * this tricky aspect). Hence we return true only if this condition
-+ * does not hold, or if the queue is slow enough to deserve only to be
-+ * kicked off for preserving a high throughput.
-+*/
-+static inline int bfq_may_expire_for_budg_timeout(struct bfq_queue *bfqq)
-+{
-+	bfq_log_bfqq(bfqq->bfqd, bfqq,
-+		"may_budget_timeout: wr %d left %d timeout %d",
-+		bfq_bfqq_wait_request(bfqq),
-+			bfq_bfqq_budget_left(bfqq) >=  bfqq->entity.budget / 3,
-+		bfq_bfqq_budget_timeout(bfqq));
-+
-+	return (!bfq_bfqq_wait_request(bfqq) ||
-+		bfq_bfqq_budget_left(bfqq) >=  bfqq->entity.budget / 3)
-+		&&
-+		bfq_bfqq_budget_timeout(bfqq);
-+}
-+
-+/*
-+ * For weight-raised queues issuing sync requests, idling is always performed,
-+ * as this is instrumental in guaranteeing a high fraction of the throughput
-+ * to these queues, and hence in guaranteeing a lower latency for their
-+ * requests. See [1] for details.
-+ *
-+ * For non-weight-raised queues, idling is instead disabled if the device is
-+ * NCQ-enabled and non-rotational, as this boosts the throughput on such
-+ * devices.
-+ */
-+static inline bool bfq_bfqq_must_not_expire(struct bfq_queue *bfqq)
-+{
-+	struct bfq_data *bfqd = bfqq->bfqd;
-+
-+	return bfq_bfqq_sync(bfqq) && (
-+		bfqq->raising_coeff > 1 ||
-+		(bfq_bfqq_idle_window(bfqq) &&
-+		 !(bfqd->hw_tag &&
-+		   (blk_queue_nonrot(bfqd->queue) ||
-+		 /*
-+		  * If there are weight-raised busy queues, then do not idle
-+		  * the disk for a sync non-weight-raised queue, and hence
-+		  * expire the queue immediately if empty. Combined with the
-+		  * timestamping rules of BFQ (see [1] for details), this
-+		  * causes sync non-weight-raised queues to get a lower
-+		  * fraction of the disk throughput, and hence reduces the rate
-+		  * at which the processes associated to these queues ask for
-+		  * requests from the request pool.
-+		  *
-+		  * This is beneficial for weight-raised processes, when the
-+		  * system operates in request-pool saturation conditions
-+		  * (e.g., in the presence of write hogs). In fact, if
-+		  * non-weight-raised processes ask for requests at a lower
-+		  * rate, then weight-raised processes have a higher
-+		  * probability to get a request from the pool immediately
-+		  * (or at least soon) when they need one. Hence they have a
-+		  * higher probability to actually get a fraction of the disk
-+		  * throughput proportional to their high weight. This is
-+		  * especially true with NCQ-enabled drives, which enqueue
-+		  * several requests in advance and further reorder
-+		  * internally-queued requests.
-+		  *
-+		  * Mistreating non-weight-raised queues in the above-described
-+		  * way, when there are busy weight-raised queues, seems to
-+		  * mitigate starvation problems in the presence of heavy write
-+		  * workloads and NCQ, and hence to guarantee a higher
-+		  * application and system responsiveness in these hostile
-+		  * scenarios.
-+		  */
-+		    bfqd->raised_busy_queues > 0)
-+		  )
-+		)
-+	);
-+}
-+
-+/*
-+ * If the in-service queue is empty, but it is sync and either of the following
-+ * conditions holds, then: 1) the queue must remain in service and cannot be
-+ * expired, and 2) the disk must be idled to wait for the possible arrival
-+ * of a new request for the queue. The conditions are:
-+ * - the device is rotational and not performing NCQ, and the queue has its
-+ *   idle window set (in this case, waiting for a new request for the queue
-+ *   is likely to boost the disk throughput);
-+ * - the queue is weight-raised (waiting for the request is necessary to
-+ *   provide the queue with fairness and latency guarantees, see [1] for
-+ *   details).
-+ */
-+static inline bool bfq_bfqq_must_idle(struct bfq_queue *bfqq)
-+{
-+	struct bfq_data *bfqd = bfqq->bfqd;
-+
-+	return RB_EMPTY_ROOT(&bfqq->sort_list) && bfqd->bfq_slice_idle != 0 &&
-+	       bfq_bfqq_must_not_expire(bfqq) &&
-+	       !bfq_queue_nonrot_noidle(bfqd, bfqq);
-+}
-+
-+/*
-+ * Select a queue for service.  If we have a current queue in service,
-+ * check whether to continue servicing it, or retrieve and set a new one.
-+ */
-+static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd)
-+{
-+	struct bfq_queue *bfqq, *new_bfqq = NULL;
-+	struct request *next_rq;
-+	enum bfqq_expiration reason = BFQ_BFQQ_BUDGET_TIMEOUT;
-+
-+	bfqq = bfqd->in_service_queue;
-+	if (bfqq == NULL)
-+		goto new_queue;
-+
-+	bfq_log_bfqq(bfqd, bfqq, "select_queue: already in-service queue");
-+
-+	/*
-+         * If another queue has a request waiting within our mean seek
-+         * distance, let it run. The expire code will check for close
-+         * cooperators and put the close queue at the front of the
-+         * service tree. If possible, merge the expiring queue with the
-+         * new bfqq.
-+         */
-+        new_bfqq = bfq_close_cooperator(bfqd, bfqq);
-+        if (new_bfqq != NULL && bfqq->new_bfqq == NULL)
-+                bfq_setup_merge(bfqq, new_bfqq);
-+
-+	if (bfq_may_expire_for_budg_timeout(bfqq) &&
-+	    !timer_pending(&bfqd->idle_slice_timer) &&
-+	    !bfq_bfqq_must_idle(bfqq))
-+		goto expire;
-+
-+	next_rq = bfqq->next_rq;
-+	/*
-+	 * If bfqq has requests queued and it has enough budget left to
-+	 * serve them, keep the queue, otherwise expire it.
-+	 */
-+	if (next_rq != NULL) {
-+		if (bfq_serv_to_charge(next_rq, bfqq) >
-+			bfq_bfqq_budget_left(bfqq)) {
-+			reason = BFQ_BFQQ_BUDGET_EXHAUSTED;
-+			goto expire;
-+		} else {
-+			/*
-+			 * The idle timer may be pending because we may not
-+			 * disable disk idling even when a new request arrives
-+			 */
-+			if (timer_pending(&bfqd->idle_slice_timer)) {
-+				/*
-+				 * If we get here: 1) at least a new request
-+				 * has arrived but we have not disabled the
-+				 * timer because the request was too small,
-+				 * 2) then the block layer has unplugged the
-+				 * device, causing the dispatch to be invoked.
-+				 *
-+				 * Since the device is unplugged, now the
-+				 * requests are probably large enough to
-+				 * provide a reasonable throughput.
-+				 * So we disable idling.
-+				 */
-+				bfq_clear_bfqq_wait_request(bfqq);
-+				del_timer(&bfqd->idle_slice_timer);
-+			}
-+			if (new_bfqq == NULL)
-+				goto keep_queue;
-+			else
-+				goto expire;
-+		}
-+	}
-+
-+	/*
-+	 * No requests pending.  If the in-service queue has no cooperator and
-+	 * still has requests in flight (possibly waiting for a completion)
-+	 * or is idling for a new request, then keep it.
-+	 */
-+	if (new_bfqq == NULL && (timer_pending(&bfqd->idle_slice_timer) ||
-+	    (bfqq->dispatched != 0 && bfq_bfqq_must_not_expire(bfqq)))) {
-+		bfqq = NULL;
-+		goto keep_queue;
-+	} else if (new_bfqq != NULL && timer_pending(&bfqd->idle_slice_timer)) {
-+		/*
-+		 * Expiring the queue because there is a close cooperator,
-+		 * cancel timer.
-+		 */
-+		bfq_clear_bfqq_wait_request(bfqq);
-+		del_timer(&bfqd->idle_slice_timer);
-+	}
-+
-+	reason = BFQ_BFQQ_NO_MORE_REQUESTS;
-+expire:
-+	bfq_bfqq_expire(bfqd, bfqq, 0, reason);
-+new_queue:
-+	bfqq = bfq_set_in_service_queue(bfqd, new_bfqq);
-+	bfq_log(bfqd, "select_queue: new queue %d returned",
-+		bfqq != NULL ? bfqq->pid : 0);
-+keep_queue:
-+	return bfqq;
-+}
-+
-+static void bfq_update_raising_data(struct bfq_data *bfqd,
-+				    struct bfq_queue *bfqq)
-+{
-+	if (bfqq->raising_coeff > 1) { /* queue is being boosted */
-+		struct bfq_entity *entity = &bfqq->entity;
-+
-+		bfq_log_bfqq(bfqd, bfqq,
-+			"raising period dur %u/%u msec, "
-+			"old raising coeff %u, w %d(%d)",
-+			jiffies_to_msecs(jiffies -
-+				bfqq->last_rais_start_finish),
-+			jiffies_to_msecs(bfqq->raising_cur_max_time),
-+			bfqq->raising_coeff,
-+			bfqq->entity.weight, bfqq->entity.orig_weight);
-+
-+		BUG_ON(bfqq != bfqd->in_service_queue && entity->weight !=
-+			entity->orig_weight * bfqq->raising_coeff);
-+		if (entity->ioprio_changed)
-+			bfq_log_bfqq(bfqd, bfqq,
-+			"WARN: pending prio change");
-+		/*
-+		 * If too much time has elapsed from the beginning
-+		 * of this weight-raising, stop it.
-+		 */
-+		if (time_is_before_jiffies(bfqq->last_rais_start_finish +
-+					   bfqq->raising_cur_max_time)) {
-+			bfqq->last_rais_start_finish = jiffies;
-+			bfq_log_bfqq(bfqd, bfqq,
-+				     "wrais ending at %lu, "
-+				     "rais_max_time %u",
-+				     bfqq->last_rais_start_finish,
-+				     jiffies_to_msecs(bfqq->
-+					raising_cur_max_time));
-+			bfq_bfqq_end_raising(bfqq);
-+			__bfq_entity_update_weight_prio(
-+				bfq_entity_service_tree(entity),
-+				entity);
-+		}
-+	}
-+}
-+
-+/*
-+ * Dispatch one request from bfqq, moving it to the request queue
-+ * dispatch list.
-+ */
-+static int bfq_dispatch_request(struct bfq_data *bfqd,
-+				struct bfq_queue *bfqq)
-+{
-+	int dispatched = 0;
-+	struct request *rq;
-+	unsigned long service_to_charge;
-+
-+	BUG_ON(RB_EMPTY_ROOT(&bfqq->sort_list));
-+
-+	/* Follow expired path, else get first next available. */
-+	rq = bfq_check_fifo(bfqq);
-+	if (rq == NULL)
-+		rq = bfqq->next_rq;
-+	service_to_charge = bfq_serv_to_charge(rq, bfqq);
-+
-+	if (service_to_charge > bfq_bfqq_budget_left(bfqq)) {
-+		/*
-+		 * This may happen if the next rq is chosen
-+		 * in fifo order instead of sector order.
-+		 * The budget is properly dimensioned
-+		 * to be always sufficient to serve the next request
-+		 * only if it is chosen in sector order. The reason is
-+		 * that it would be quite inefficient and little useful
-+		 * to always make sure that the budget is large enough
-+		 * to serve even the possible next rq in fifo order.
-+		 * In fact, requests are seldom served in fifo order.
-+		 *
-+		 * Expire the queue for budget exhaustion, and
-+		 * make sure that the next act_budget is enough
-+		 * to serve the next request, even if it comes
-+		 * from the fifo expired path.
-+		 */
-+		bfqq->next_rq = rq;
-+		/*
-+		 * Since this dispatch is failed, make sure that
-+		 * a new one will be performed
-+		 */
-+		if (!bfqd->rq_in_driver)
-+			bfq_schedule_dispatch(bfqd);
-+		goto expire;
-+	}
-+
-+	/* Finally, insert request into driver dispatch list. */
-+	bfq_bfqq_served(bfqq, service_to_charge);
-+	bfq_dispatch_insert(bfqd->queue, rq);
-+
-+	bfq_update_raising_data(bfqd, bfqq);
-+
-+	bfq_log_bfqq(bfqd, bfqq,
-+			"dispatched %u sec req (%llu), budg left %lu",
-+			blk_rq_sectors(rq),
-+			(long long unsigned)blk_rq_pos(rq),
-+			bfq_bfqq_budget_left(bfqq));
-+
-+	dispatched++;
-+
-+	if (bfqd->in_service_bic == NULL) {
-+		atomic_long_inc(&RQ_BIC(rq)->icq.ioc->refcount);
-+		bfqd->in_service_bic = RQ_BIC(rq);
-+	}
-+
-+	if (bfqd->busy_queues > 1 && ((!bfq_bfqq_sync(bfqq) &&
-+	    dispatched >= bfqd->bfq_max_budget_async_rq) ||
-+	    bfq_class_idle(bfqq)))
-+		goto expire;
-+
-+	return dispatched;
-+
-+expire:
-+	bfq_bfqq_expire(bfqd, bfqq, 0, BFQ_BFQQ_BUDGET_EXHAUSTED);
-+	return dispatched;
-+}
-+
-+static int __bfq_forced_dispatch_bfqq(struct bfq_queue *bfqq)
-+{
-+	int dispatched = 0;
-+
-+	while (bfqq->next_rq != NULL) {
-+		bfq_dispatch_insert(bfqq->bfqd->queue, bfqq->next_rq);
-+		dispatched++;
-+	}
-+
-+	BUG_ON(!list_empty(&bfqq->fifo));
-+	return dispatched;
-+}
-+
-+/*
-+ * Drain our current requests.  Used for barriers and when switching
-+ * io schedulers on-the-fly.
-+ */
-+static int bfq_forced_dispatch(struct bfq_data *bfqd)
-+{
-+	struct bfq_queue *bfqq, *n;
-+	struct bfq_service_tree *st;
-+	int dispatched = 0;
-+
-+	bfqq = bfqd->in_service_queue;
-+	if (bfqq != NULL)
-+		__bfq_bfqq_expire(bfqd, bfqq);
-+
-+	/*
-+	 * Loop through classes, and be careful to leave the scheduler
-+	 * in a consistent state, as feedback mechanisms and vtime
-+	 * updates cannot be disabled during the process.
-+	 */
-+	list_for_each_entry_safe(bfqq, n, &bfqd->active_list, bfqq_list) {
-+		st = bfq_entity_service_tree(&bfqq->entity);
-+
-+		dispatched += __bfq_forced_dispatch_bfqq(bfqq);
-+		bfqq->max_budget = bfq_max_budget(bfqd);
-+
-+		bfq_forget_idle(st);
-+	}
-+
-+	BUG_ON(bfqd->busy_queues != 0);
-+
-+	return dispatched;
-+}
-+
-+static int bfq_dispatch_requests(struct request_queue *q, int force)
-+{
-+	struct bfq_data *bfqd = q->elevator->elevator_data;
-+	struct bfq_queue *bfqq;
-+	int max_dispatch;
-+
-+	bfq_log(bfqd, "dispatch requests: %d busy queues", bfqd->busy_queues);
-+	if (bfqd->busy_queues == 0)
-+		return 0;
-+
-+	if (unlikely(force))
-+		return bfq_forced_dispatch(bfqd);
-+
-+	bfqq = bfq_select_queue(bfqd);
-+	if (bfqq == NULL)
-+		return 0;
-+
-+	max_dispatch = bfqd->bfq_quantum;
-+	if (bfq_class_idle(bfqq))
-+		max_dispatch = 1;
-+
-+	if (!bfq_bfqq_sync(bfqq))
-+		max_dispatch = bfqd->bfq_max_budget_async_rq;
-+
-+	if (bfqq->dispatched >= max_dispatch) {
-+		if (bfqd->busy_queues > 1)
-+			return 0;
-+		if (bfqq->dispatched >= 4 * max_dispatch)
-+			return 0;
-+	}
-+
-+	if (bfqd->sync_flight != 0 && !bfq_bfqq_sync(bfqq))
-+		return 0;
-+
-+	bfq_clear_bfqq_wait_request(bfqq);
-+	BUG_ON(timer_pending(&bfqd->idle_slice_timer));
-+
-+	if (!bfq_dispatch_request(bfqd, bfqq))
-+		return 0;
-+
-+	bfq_log_bfqq(bfqd, bfqq, "dispatched one request of %d (max_disp %d)",
-+			bfqq->pid, max_dispatch);
-+
-+	return 1;
-+}
-+
-+/*
-+ * Task holds one reference to the queue, dropped when task exits.  Each rq
-+ * in-flight on this queue also holds a reference, dropped when rq is freed.
-+ *
-+ * Queue lock must be held here.
-+ */
-+static void bfq_put_queue(struct bfq_queue *bfqq)
-+{
-+	struct bfq_data *bfqd = bfqq->bfqd;
-+
-+	BUG_ON(atomic_read(&bfqq->ref) <= 0);
-+
-+	bfq_log_bfqq(bfqd, bfqq, "put_queue: %p %d", bfqq,
-+		     atomic_read(&bfqq->ref));
-+	if (!atomic_dec_and_test(&bfqq->ref))
-+		return;
-+
-+	BUG_ON(rb_first(&bfqq->sort_list) != NULL);
-+	BUG_ON(bfqq->allocated[READ] + bfqq->allocated[WRITE] != 0);
-+	BUG_ON(bfqq->entity.tree != NULL);
-+	BUG_ON(bfq_bfqq_busy(bfqq));
-+	BUG_ON(bfqd->in_service_queue == bfqq);
-+
-+	bfq_log_bfqq(bfqd, bfqq, "put_queue: %p freed", bfqq);
-+
-+	kmem_cache_free(bfq_pool, bfqq);
-+}
-+
-+static void bfq_put_cooperator(struct bfq_queue *bfqq)
-+{
-+	struct bfq_queue *__bfqq, *next;
-+
-+	/*
-+	 * If this queue was scheduled to merge with another queue, be
-+	 * sure to drop the reference taken on that queue (and others in
-+	 * the merge chain). See bfq_setup_merge and bfq_merge_bfqqs.
-+	 */
-+	__bfqq = bfqq->new_bfqq;
-+	while (__bfqq) {
-+		if (__bfqq == bfqq) {
-+			WARN(1, "bfqq->new_bfqq loop detected.\n");
-+			break;
-+		}
-+		next = __bfqq->new_bfqq;
-+		bfq_put_queue(__bfqq);
-+		__bfqq = next;
-+	}
-+}
-+
-+static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
-+{
-+	if (bfqq == bfqd->in_service_queue) {
-+		__bfq_bfqq_expire(bfqd, bfqq);
-+		bfq_schedule_dispatch(bfqd);
-+	}
-+
-+	bfq_log_bfqq(bfqd, bfqq, "exit_bfqq: %p, %d", bfqq,
-+		     atomic_read(&bfqq->ref));
-+
-+	bfq_put_cooperator(bfqq);
-+
-+	bfq_put_queue(bfqq);
-+}
-+
-+static void bfq_init_icq(struct io_cq *icq)
-+{
-+	struct bfq_io_cq *bic = icq_to_bic(icq);
-+
-+	bic->ttime.last_end_request = jiffies;
-+}
-+
-+static void bfq_exit_icq(struct io_cq *icq)
-+{
-+	struct bfq_io_cq *bic = icq_to_bic(icq);
-+	struct bfq_data *bfqd = bic_to_bfqd(bic);
-+
-+	if (bic->bfqq[BLK_RW_ASYNC]) {
-+		bfq_exit_bfqq(bfqd, bic->bfqq[BLK_RW_ASYNC]);
-+		bic->bfqq[BLK_RW_ASYNC] = NULL;
-+	}
-+
-+	if (bic->bfqq[BLK_RW_SYNC]) {
-+		bfq_exit_bfqq(bfqd, bic->bfqq[BLK_RW_SYNC]);
-+		bic->bfqq[BLK_RW_SYNC] = NULL;
-+	}
-+}
-+
-+/*
-+ * Update the entity prio values; note that the new values will not
-+ * be used until the next (re)activation.
-+ */
-+static void bfq_init_prio_data(struct bfq_queue *bfqq, struct bfq_io_cq *bic)
-+{
-+	struct task_struct *tsk = current;
-+	int ioprio_class;
-+
-+	if (!bfq_bfqq_prio_changed(bfqq))
-+		return;
-+
-+	ioprio_class = IOPRIO_PRIO_CLASS(bic->ioprio);
-+	switch (ioprio_class) {
-+	default:
-+		dev_err(bfqq->bfqd->queue->backing_dev_info.dev,
-+			"bfq: bad prio %x\n", ioprio_class);
-+	case IOPRIO_CLASS_NONE:
-+		/*
-+		 * No prio set, inherit CPU scheduling settings.
-+		 */
-+		bfqq->entity.new_ioprio = task_nice_ioprio(tsk);
-+		bfqq->entity.new_ioprio_class = task_nice_ioclass(tsk);
-+		break;
-+	case IOPRIO_CLASS_RT:
-+		bfqq->entity.new_ioprio = IOPRIO_PRIO_DATA(bic->ioprio);
-+		bfqq->entity.new_ioprio_class = IOPRIO_CLASS_RT;
-+		break;
-+	case IOPRIO_CLASS_BE:
-+		bfqq->entity.new_ioprio = IOPRIO_PRIO_DATA(bic->ioprio);
-+		bfqq->entity.new_ioprio_class = IOPRIO_CLASS_BE;
-+		break;
-+	case IOPRIO_CLASS_IDLE:
-+		bfqq->entity.new_ioprio_class = IOPRIO_CLASS_IDLE;
-+		bfqq->entity.new_ioprio = 7;
-+		bfq_clear_bfqq_idle_window(bfqq);
-+		break;
-+	}
-+
-+	bfqq->entity.ioprio_changed = 1;
-+
-+	/*
-+	 * Keep track of original prio settings in case we have to temporarily
-+	 * elevate the priority of this queue.
-+	 */
-+	bfqq->org_ioprio = bfqq->entity.new_ioprio;
-+	bfq_clear_bfqq_prio_changed(bfqq);
-+}
-+
-+static void bfq_changed_ioprio(struct bfq_io_cq *bic)
-+{
-+	struct bfq_data *bfqd;
-+	struct bfq_queue *bfqq, *new_bfqq;
-+	struct bfq_group *bfqg;
-+	unsigned long uninitialized_var(flags);
-+	int ioprio = bic->icq.ioc->ioprio;
-+
-+	bfqd = bfq_get_bfqd_locked(&(bic->icq.q->elevator->elevator_data),
-+				   &flags);
-+	/*
-+	 * This condition may trigger on a newly created bic, be sure to drop
-+	 * the lock before returning.
-+	 */
-+	if (unlikely(bfqd == NULL) || likely(bic->ioprio == ioprio))
-+		goto out;
-+
-+	bfqq = bic->bfqq[BLK_RW_ASYNC];
-+	if (bfqq != NULL) {
-+		bfqg = container_of(bfqq->entity.sched_data, struct bfq_group,
-+				    sched_data);
-+		new_bfqq = bfq_get_queue(bfqd, bfqg, BLK_RW_ASYNC, bic,
-+					 GFP_ATOMIC);
-+		if (new_bfqq != NULL) {
-+			bic->bfqq[BLK_RW_ASYNC] = new_bfqq;
-+			bfq_log_bfqq(bfqd, bfqq,
-+				     "changed_ioprio: bfqq %p %d",
-+				     bfqq, atomic_read(&bfqq->ref));
-+			bfq_put_queue(bfqq);
-+		}
-+	}
-+
-+	bfqq = bic->bfqq[BLK_RW_SYNC];
-+	if (bfqq != NULL)
-+		bfq_mark_bfqq_prio_changed(bfqq);
-+
-+	bic->ioprio = ioprio;
-+
-+out:
-+	bfq_put_bfqd_unlock(bfqd, &flags);
-+}
-+
-+static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
-+			  pid_t pid, int is_sync)
-+{
-+	RB_CLEAR_NODE(&bfqq->entity.rb_node);
-+	INIT_LIST_HEAD(&bfqq->fifo);
-+
-+	atomic_set(&bfqq->ref, 0);
-+	bfqq->bfqd = bfqd;
-+
-+	bfq_mark_bfqq_prio_changed(bfqq);
-+
-+	if (is_sync) {
-+		if (!bfq_class_idle(bfqq))
-+			bfq_mark_bfqq_idle_window(bfqq);
-+		bfq_mark_bfqq_sync(bfqq);
-+	}
-+
-+	/* Tentative initial value to trade off between thr and lat */
-+	bfqq->max_budget = (2 * bfq_max_budget(bfqd)) / 3;
-+	bfqq->pid = pid;
-+
-+	bfqq->raising_coeff = 1;
-+	bfqq->last_rais_start_finish = 0;
-+	/*
-+	 * Set to the value for which bfqq will not be deemed as
-+	 * soft rt when it becomes backlogged.
-+	 */
-+	bfqq->soft_rt_next_start = bfq_infinity_from_now(jiffies);
-+}
-+
-+static struct bfq_queue *bfq_find_alloc_queue(struct bfq_data *bfqd,
-+					      struct bfq_group *bfqg,
-+					      int is_sync,
-+					      struct bfq_io_cq *bic,
-+					      gfp_t gfp_mask)
-+{
-+	struct bfq_queue *bfqq, *new_bfqq = NULL;
-+
-+retry:
-+	/* bic always exists here */
-+	bfqq = bic_to_bfqq(bic, is_sync);
-+
-+	/*
-+	 * Always try a new alloc if we fall back to the OOM bfqq
-+	 * originally, since it should just be a temporary situation.
-+	 */
-+	if (bfqq == NULL || bfqq == &bfqd->oom_bfqq) {
-+		bfqq = NULL;
-+		if (new_bfqq != NULL) {
-+			bfqq = new_bfqq;
-+			new_bfqq = NULL;
-+		} else if (gfp_mask & __GFP_WAIT) {
-+			spin_unlock_irq(bfqd->queue->queue_lock);
-+			new_bfqq = kmem_cache_alloc_node(bfq_pool,
-+					gfp_mask | __GFP_ZERO,
-+					bfqd->queue->node);
-+			spin_lock_irq(bfqd->queue->queue_lock);
-+			if (new_bfqq != NULL)
-+				goto retry;
-+		} else {
-+			bfqq = kmem_cache_alloc_node(bfq_pool,
-+					gfp_mask | __GFP_ZERO,
-+					bfqd->queue->node);
-+		}
-+
-+		if (bfqq != NULL) {
-+			bfq_init_bfqq(bfqd, bfqq, current->pid, is_sync);
-+			bfq_log_bfqq(bfqd, bfqq, "allocated");
-+		} else {
-+			bfqq = &bfqd->oom_bfqq;
-+			bfq_log_bfqq(bfqd, bfqq, "using oom bfqq");
-+		}
-+
-+		bfq_init_prio_data(bfqq, bic);
-+		bfq_init_entity(&bfqq->entity, bfqg);
-+	}
-+
-+	if (new_bfqq != NULL)
-+		kmem_cache_free(bfq_pool, new_bfqq);
-+
-+	return bfqq;
-+}
-+
-+static struct bfq_queue **bfq_async_queue_prio(struct bfq_data *bfqd,
-+					       struct bfq_group *bfqg,
-+					       int ioprio_class, int ioprio)
-+{
-+	switch (ioprio_class) {
-+	case IOPRIO_CLASS_RT:
-+		return &bfqg->async_bfqq[0][ioprio];
-+	case IOPRIO_CLASS_NONE:
-+		ioprio = IOPRIO_NORM;
-+		/* fall through */
-+	case IOPRIO_CLASS_BE:
-+		return &bfqg->async_bfqq[1][ioprio];
-+	case IOPRIO_CLASS_IDLE:
-+		return &bfqg->async_idle_bfqq;
-+	default:
-+		BUG();
-+	}
-+}
-+
-+static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd,
-+				       struct bfq_group *bfqg, int is_sync,
-+				       struct bfq_io_cq *bic, gfp_t gfp_mask)
-+{
-+	const int ioprio = IOPRIO_PRIO_DATA(bic->ioprio);
-+	const int ioprio_class = IOPRIO_PRIO_CLASS(bic->ioprio);
-+	struct bfq_queue **async_bfqq = NULL;
-+	struct bfq_queue *bfqq = NULL;
-+
-+	if (!is_sync) {
-+		async_bfqq = bfq_async_queue_prio(bfqd, bfqg, ioprio_class,
-+						  ioprio);
-+		bfqq = *async_bfqq;
-+	}
-+
-+	if (bfqq == NULL)
-+		bfqq = bfq_find_alloc_queue(bfqd, bfqg, is_sync, bic, gfp_mask);
-+
-+	/*
-+	 * Pin the queue now that it's allocated, scheduler exit will prune it.
-+	 */
-+	if (!is_sync && *async_bfqq == NULL) {
-+		atomic_inc(&bfqq->ref);
-+		bfq_log_bfqq(bfqd, bfqq, "get_queue, bfqq not in async: %p, %d",
-+			     bfqq, atomic_read(&bfqq->ref));
-+		*async_bfqq = bfqq;
-+	}
-+
-+	atomic_inc(&bfqq->ref);
-+	bfq_log_bfqq(bfqd, bfqq, "get_queue, at end: %p, %d", bfqq,
-+		     atomic_read(&bfqq->ref));
-+	return bfqq;
-+}
-+
-+static void bfq_update_io_thinktime(struct bfq_data *bfqd,
-+				    struct bfq_io_cq *bic)
-+{
-+	unsigned long elapsed = jiffies - bic->ttime.last_end_request;
-+	unsigned long ttime = min(elapsed, 2UL * bfqd->bfq_slice_idle);
-+
-+	bic->ttime.ttime_samples = (7*bic->ttime.ttime_samples + 256) / 8;
-+	bic->ttime.ttime_total = (7*bic->ttime.ttime_total + 256*ttime) / 8;
-+	bic->ttime.ttime_mean = (bic->ttime.ttime_total + 128) /
-+				bic->ttime.ttime_samples;
-+}
-+
-+static void bfq_update_io_seektime(struct bfq_data *bfqd,
-+				   struct bfq_queue *bfqq,
-+				   struct request *rq)
-+{
-+	sector_t sdist;
-+	u64 total;
-+
-+	if (bfqq->last_request_pos < blk_rq_pos(rq))
-+		sdist = blk_rq_pos(rq) - bfqq->last_request_pos;
-+	else
-+		sdist = bfqq->last_request_pos - blk_rq_pos(rq);
-+
-+	/*
-+	 * Don't allow the seek distance to get too large from the
-+	 * odd fragment, pagein, etc.
-+	 */
-+	if (bfqq->seek_samples == 0) /* first request, not really a seek */
-+		sdist = 0;
-+	else if (bfqq->seek_samples <= 60) /* second & third seek */
-+		sdist = min(sdist, (bfqq->seek_mean * 4) + 2*1024*1024);
-+	else
-+		sdist = min(sdist, (bfqq->seek_mean * 4) + 2*1024*64);
-+
-+	bfqq->seek_samples = (7*bfqq->seek_samples + 256) / 8;
-+	bfqq->seek_total = (7*bfqq->seek_total + (u64)256*sdist) / 8;
-+	total = bfqq->seek_total + (bfqq->seek_samples/2);
-+	do_div(total, bfqq->seek_samples);
-+	bfqq->seek_mean = (sector_t)total;
-+
-+	bfq_log_bfqq(bfqd, bfqq, "dist=%llu mean=%llu", (u64)sdist,
-+			(u64)bfqq->seek_mean);
-+}
-+
-+/*
-+ * Disable idle window if the process thinks too long or seeks so much that
-+ * it doesn't matter.
-+ */
-+static void bfq_update_idle_window(struct bfq_data *bfqd,
-+				   struct bfq_queue *bfqq,
-+				   struct bfq_io_cq *bic)
-+{
-+	int enable_idle;
-+
-+	/* Don't idle for async or idle io prio class. */
-+	if (!bfq_bfqq_sync(bfqq) || bfq_class_idle(bfqq))
-+		return;
-+
-+	enable_idle = bfq_bfqq_idle_window(bfqq);
-+
-+	if (atomic_read(&bic->icq.ioc->active_ref) == 0 ||
-+	    bfqd->bfq_slice_idle == 0 ||
-+		(bfqd->hw_tag && BFQQ_SEEKY(bfqq) &&
-+			bfqq->raising_coeff == 1))
-+		enable_idle = 0;
-+	else if (bfq_sample_valid(bic->ttime.ttime_samples)) {
-+		if (bic->ttime.ttime_mean > bfqd->bfq_slice_idle &&
-+			bfqq->raising_coeff == 1)
-+			enable_idle = 0;
-+		else
-+			enable_idle = 1;
-+	}
-+	bfq_log_bfqq(bfqd, bfqq, "update_idle_window: enable_idle %d",
-+		enable_idle);
-+
-+	if (enable_idle)
-+		bfq_mark_bfqq_idle_window(bfqq);
-+	else
-+		bfq_clear_bfqq_idle_window(bfqq);
-+}
-+
-+/*
-+ * Called when a new fs request (rq) is added to bfqq.  Check if there's
-+ * something we should do about it.
-+ */
-+static void bfq_rq_enqueued(struct bfq_data *bfqd, struct bfq_queue *bfqq,
-+			    struct request *rq)
-+{
-+	struct bfq_io_cq *bic = RQ_BIC(rq);
-+
-+	if (rq->cmd_flags & REQ_META)
-+		bfqq->meta_pending++;
-+
-+	bfq_update_io_thinktime(bfqd, bic);
-+	bfq_update_io_seektime(bfqd, bfqq, rq);
-+	if (bfqq->entity.service > bfq_max_budget(bfqd) / 8 ||
-+	    !BFQQ_SEEKY(bfqq))
-+		bfq_update_idle_window(bfqd, bfqq, bic);
-+
-+	bfq_log_bfqq(bfqd, bfqq,
-+		     "rq_enqueued: idle_window=%d (seeky %d, mean %llu)",
-+		     bfq_bfqq_idle_window(bfqq), BFQQ_SEEKY(bfqq),
-+		     (long long unsigned)bfqq->seek_mean);
-+
-+	bfqq->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq);
-+
-+	if (bfqq == bfqd->in_service_queue && bfq_bfqq_wait_request(bfqq)) {
-+		int small_req = bfqq->queued[rq_is_sync(rq)] == 1 &&
-+				blk_rq_sectors(rq) < 32;
-+		int budget_timeout = bfq_bfqq_budget_timeout(bfqq);
-+
-+		/*
-+		 * There is just this request queued: if the request
-+		 * is small and the queue is not to be expired, then
-+		 * just exit.
-+		 *
-+		 * In this way, if the disk is being idled to wait for
-+		 * a new request from the in-service queue, we avoid
-+		 * unplugging the device and committing the disk to serve
-+		 * just a small request. On the contrary, we wait for
-+		 * the block layer to decide when to unplug the device:
-+		 * hopefully, new requests will be merged to this one
-+		 * quickly, then the device will be unplugged and
-+		 * larger requests will be dispatched.
-+		 */
-+		if (small_req && !budget_timeout)
-+			return;
-+
-+		/*
-+		 * A large enough request arrived, or the queue is to
-+		 * be expired: in both cases disk idling is to be
-+		 * stopped, so clear wait_request flag and reset
-+		 * timer.
-+		 */
-+		bfq_clear_bfqq_wait_request(bfqq);
-+		del_timer(&bfqd->idle_slice_timer);
-+
-+		/*
-+		 * The queue is not empty, because a new request just
-+		 * arrived. Hence we can safely expire the queue, in
-+		 * case of budget timeout, without risking that the
-+		 * timestamps of the queue are not updated correctly.
-+		 * See [1] for more details.
-+		 */
-+		if (budget_timeout)
-+			bfq_bfqq_expire(bfqd, bfqq, 0, BFQ_BFQQ_BUDGET_TIMEOUT);
-+
-+		/*
-+		 * Let the request rip immediately, or let a new queue be
-+		 * selected if bfqq has just been expired.
-+		 */
-+		__blk_run_queue(bfqd->queue);
-+	}
-+}
-+
-+static void bfq_insert_request(struct request_queue *q, struct request *rq)
-+{
-+	struct bfq_data *bfqd = q->elevator->elevator_data;
-+	struct bfq_queue *bfqq = RQ_BFQQ(rq);
-+
-+	assert_spin_locked(bfqd->queue->queue_lock);
-+	bfq_init_prio_data(bfqq, RQ_BIC(rq));
-+
-+	bfq_add_rq_rb(rq);
-+
-+	rq_set_fifo_time(rq, jiffies + bfqd->bfq_fifo_expire[rq_is_sync(rq)]);
-+	list_add_tail(&rq->queuelist, &bfqq->fifo);
-+
-+	bfq_rq_enqueued(bfqd, bfqq, rq);
-+}
-+
-+static void bfq_update_hw_tag(struct bfq_data *bfqd)
-+{
-+	bfqd->max_rq_in_driver = max(bfqd->max_rq_in_driver,
-+				     bfqd->rq_in_driver);
-+
-+	if (bfqd->hw_tag == 1)
-+		return;
-+
-+	/*
-+	 * This sample is valid if the number of outstanding requests
-+	 * is large enough to allow a queueing behavior.  Note that the
-+	 * sum is not exact, as it's not taking into account deactivated
-+	 * requests.
-+	 */
-+	if (bfqd->rq_in_driver + bfqd->queued < BFQ_HW_QUEUE_THRESHOLD)
-+		return;
-+
-+	if (bfqd->hw_tag_samples++ < BFQ_HW_QUEUE_SAMPLES)
-+		return;
-+
-+	bfqd->hw_tag = bfqd->max_rq_in_driver > BFQ_HW_QUEUE_THRESHOLD;
-+	bfqd->max_rq_in_driver = 0;
-+	bfqd->hw_tag_samples = 0;
-+}
-+
-+static void bfq_completed_request(struct request_queue *q, struct request *rq)
-+{
-+	struct bfq_queue *bfqq = RQ_BFQQ(rq);
-+	struct bfq_data *bfqd = bfqq->bfqd;
-+	const int sync = rq_is_sync(rq);
-+
-+	bfq_log_bfqq(bfqd, bfqq, "completed %u sects req (%d)",
-+			blk_rq_sectors(rq), sync);
-+
-+	bfq_update_hw_tag(bfqd);
-+
-+	WARN_ON(!bfqd->rq_in_driver);
-+	WARN_ON(!bfqq->dispatched);
-+	bfqd->rq_in_driver--;
-+	bfqq->dispatched--;
-+
-+	if (bfq_bfqq_sync(bfqq))
-+		bfqd->sync_flight--;
-+
-+	if (sync)
-+		RQ_BIC(rq)->ttime.last_end_request = jiffies;
-+
-+	/*
-+	 * If we are waiting to discover whether the request pattern of the
-+	 * task associated with the queue is actually isochronous, and
-+	 * both requisites for this condition to hold are satisfied, then
-+	 * compute soft_rt_next_start (see the comments to the function
-+	 * bfq_bfqq_softrt_next_start()).
-+	 */
-+	if (bfq_bfqq_softrt_update(bfqq) && bfqq->dispatched == 0 &&
-+	    RB_EMPTY_ROOT(&bfqq->sort_list))
-+		bfqq->soft_rt_next_start =
-+			bfq_bfqq_softrt_next_start(bfqd, bfqq);
-+
-+	/*
-+	 * If this is the in-service queue, check if it needs to be expired,
-+	 * or if we want to idle in case it has no pending requests.
-+	 */
-+	if (bfqd->in_service_queue == bfqq) {
-+		if (bfq_bfqq_budget_new(bfqq))
-+			bfq_set_budget_timeout(bfqd);
-+
-+		if (bfq_bfqq_must_idle(bfqq)) {
-+			bfq_arm_slice_timer(bfqd);
-+			goto out;
-+		} else if (bfq_may_expire_for_budg_timeout(bfqq))
-+			bfq_bfqq_expire(bfqd, bfqq, 0, BFQ_BFQQ_BUDGET_TIMEOUT);
-+		else if (RB_EMPTY_ROOT(&bfqq->sort_list) &&
-+			 (bfqq->dispatched == 0 ||
-+			  !bfq_bfqq_must_not_expire(bfqq)))
-+			bfq_bfqq_expire(bfqd, bfqq, 0,
-+					BFQ_BFQQ_NO_MORE_REQUESTS);
-+	}
-+
-+	if (!bfqd->rq_in_driver)
-+		bfq_schedule_dispatch(bfqd);
-+
-+out:
-+	return;
-+}
-+
-+static inline int __bfq_may_queue(struct bfq_queue *bfqq)
-+{
-+	if (bfq_bfqq_wait_request(bfqq) && bfq_bfqq_must_alloc(bfqq)) {
-+		bfq_clear_bfqq_must_alloc(bfqq);
-+		return ELV_MQUEUE_MUST;
-+	}
-+
-+	return ELV_MQUEUE_MAY;
-+}
-+
-+static int bfq_may_queue(struct request_queue *q, int rw)
-+{
-+	struct bfq_data *bfqd = q->elevator->elevator_data;
-+	struct task_struct *tsk = current;
-+	struct bfq_io_cq *bic;
-+	struct bfq_queue *bfqq;
-+
-+	/*
-+	 * Don't force setup of a queue from here, as a call to may_queue
-+	 * does not necessarily imply that a request actually will be queued.
-+	 * So just lookup a possibly existing queue, or return 'may queue'
-+	 * if that fails.
-+	 */
-+	bic = bfq_bic_lookup(bfqd, tsk->io_context);
-+	if (bic == NULL)
-+		return ELV_MQUEUE_MAY;
-+
-+	bfqq = bic_to_bfqq(bic, rw_is_sync(rw));
-+	if (bfqq != NULL) {
-+		bfq_init_prio_data(bfqq, bic);
-+
-+		return __bfq_may_queue(bfqq);
-+	}
-+
-+	return ELV_MQUEUE_MAY;
-+}
-+
-+/*
-+ * Queue lock held here.
-+ */
-+static void bfq_put_request(struct request *rq)
-+{
-+	struct bfq_queue *bfqq = RQ_BFQQ(rq);
-+
-+	if (bfqq != NULL) {
-+		const int rw = rq_data_dir(rq);
-+
-+		BUG_ON(!bfqq->allocated[rw]);
-+		bfqq->allocated[rw]--;
-+
-+		rq->elv.priv[0] = NULL;
-+		rq->elv.priv[1] = NULL;
-+
-+		bfq_log_bfqq(bfqq->bfqd, bfqq, "put_request %p, %d",
-+			     bfqq, atomic_read(&bfqq->ref));
-+		bfq_put_queue(bfqq);
-+	}
-+}
-+
-+static struct bfq_queue *
-+bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
-+		struct bfq_queue *bfqq)
-+{
-+	bfq_log_bfqq(bfqd, bfqq, "merging with queue %lu",
-+		(long unsigned)bfqq->new_bfqq->pid);
-+	bic_set_bfqq(bic, bfqq->new_bfqq, 1);
-+	bfq_mark_bfqq_coop(bfqq->new_bfqq);
-+	bfq_put_queue(bfqq);
-+	return bic_to_bfqq(bic, 1);
-+}
-+
-+/*
-+ * Returns NULL if a new bfqq should be allocated, or the old bfqq if this
-+ * was the last process referring to said bfqq.
-+ */
-+static struct bfq_queue *
-+bfq_split_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq)
-+{
-+	bfq_log_bfqq(bfqq->bfqd, bfqq, "splitting queue");
-+	if (bfqq_process_refs(bfqq) == 1) {
-+		bfqq->pid = current->pid;
-+		bfq_clear_bfqq_coop(bfqq);
-+		bfq_clear_bfqq_split_coop(bfqq);
-+		return bfqq;
-+	}
-+
-+	bic_set_bfqq(bic, NULL, 1);
-+
-+	bfq_put_cooperator(bfqq);
-+
-+	bfq_put_queue(bfqq);
-+	return NULL;
-+}
-+
-+/*
-+ * Allocate bfq data structures associated with this request.
-+ */
-+static int bfq_set_request(struct request_queue *q, struct request *rq,
-+			   struct bio *bio, gfp_t gfp_mask)
-+{
-+	struct bfq_data *bfqd = q->elevator->elevator_data;
-+	struct bfq_io_cq *bic = icq_to_bic(rq->elv.icq);
-+	const int rw = rq_data_dir(rq);
-+	const int is_sync = rq_is_sync(rq);
-+	struct bfq_queue *bfqq;
-+	struct bfq_group *bfqg;
-+	unsigned long flags;
-+
-+	might_sleep_if(gfp_mask & __GFP_WAIT);
-+
-+	bfq_changed_ioprio(bic);
-+
-+	spin_lock_irqsave(q->queue_lock, flags);
-+
-+	if (bic == NULL)
-+		goto queue_fail;
-+
-+	bfqg = bfq_bic_update_cgroup(bic);
-+
-+new_queue:
-+	bfqq = bic_to_bfqq(bic, is_sync);
-+	if (bfqq == NULL || bfqq == &bfqd->oom_bfqq) {
-+		bfqq = bfq_get_queue(bfqd, bfqg, is_sync, bic, gfp_mask);
-+		bic_set_bfqq(bic, bfqq, is_sync);
-+	} else {
-+		/*
-+		 * If the queue was seeky for too long, break it apart.
-+		 */
-+		if (bfq_bfqq_coop(bfqq) && bfq_bfqq_split_coop(bfqq)) {
-+			bfq_log_bfqq(bfqd, bfqq, "breaking apart bfqq");
-+			bfqq = bfq_split_bfqq(bic, bfqq);
-+			if (!bfqq)
-+				goto new_queue;
-+		}
-+
-+		/*
-+		 * Check to see if this queue is scheduled to merge with
-+		 * another closely cooperating queue. The merging of queues
-+		 * happens here as it must be done in process context.
-+		 * The reference on new_bfqq was taken in merge_bfqqs.
-+		 */
-+		if (bfqq->new_bfqq != NULL)
-+			bfqq = bfq_merge_bfqqs(bfqd, bic, bfqq);
-+	}
-+
-+	bfqq->allocated[rw]++;
-+	atomic_inc(&bfqq->ref);
-+	bfq_log_bfqq(bfqd, bfqq, "set_request: bfqq %p, %d", bfqq,
-+		     atomic_read(&bfqq->ref));
-+
-+	rq->elv.priv[0] = bic;
-+	rq->elv.priv[1] = bfqq;
-+
-+	spin_unlock_irqrestore(q->queue_lock, flags);
-+
-+	return 0;
-+
-+queue_fail:
-+	bfq_schedule_dispatch(bfqd);
-+	spin_unlock_irqrestore(q->queue_lock, flags);
-+
-+	return 1;
-+}
-+
-+static void bfq_kick_queue(struct work_struct *work)
-+{
-+	struct bfq_data *bfqd =
-+		container_of(work, struct bfq_data, unplug_work);
-+	struct request_queue *q = bfqd->queue;
-+
-+	spin_lock_irq(q->queue_lock);
-+	__blk_run_queue(q);
-+	spin_unlock_irq(q->queue_lock);
-+}
-+
-+/*
-+ * Handler of the expiration of the timer running if the in-service queue
-+ * is idling inside its time slice.
-+ */
-+static void bfq_idle_slice_timer(unsigned long data)
-+{
-+	struct bfq_data *bfqd = (struct bfq_data *)data;
-+	struct bfq_queue *bfqq;
-+	unsigned long flags;
-+	enum bfqq_expiration reason;
-+
-+	spin_lock_irqsave(bfqd->queue->queue_lock, flags);
-+
-+	bfqq = bfqd->in_service_queue;
-+	/*
-+	 * Theoretical race here: the in-service queue can be NULL or different
-+	 * from the queue that was idling if the timer handler spins on
-+	 * the queue_lock and a new request arrives for the current
-+	 * queue and there is a full dispatch cycle that changes the
-+	 * in-service queue.  This can hardly happen, but in the worst case
-+	 * we just expire a queue too early.
-+	 */
-+	if (bfqq != NULL) {
-+		bfq_log_bfqq(bfqd, bfqq, "slice_timer expired");
-+		if (bfq_bfqq_budget_timeout(bfqq))
-+			/*
-+			 * Also here the queue can be safely expired
-+			 * for budget timeout without wasting
-+			 * guarantees
-+			 */
-+			reason = BFQ_BFQQ_BUDGET_TIMEOUT;
-+		else if (bfqq->queued[0] == 0 && bfqq->queued[1] == 0)
-+			/*
-+			 * The queue may not be empty upon timer expiration,
-+			 * because we may not disable the timer when the first
-+			 * request of the in-service queue arrives during
-+			 * disk idling
-+			 */
-+			reason = BFQ_BFQQ_TOO_IDLE;
-+		else
-+			goto schedule_dispatch;
-+
-+		bfq_bfqq_expire(bfqd, bfqq, 1, reason);
-+	}
-+
-+schedule_dispatch:
-+	bfq_schedule_dispatch(bfqd);
-+
-+	spin_unlock_irqrestore(bfqd->queue->queue_lock, flags);
-+}
-+
-+static void bfq_shutdown_timer_wq(struct bfq_data *bfqd)
-+{
-+	del_timer_sync(&bfqd->idle_slice_timer);
-+	cancel_work_sync(&bfqd->unplug_work);
-+}
-+
-+static inline void __bfq_put_async_bfqq(struct bfq_data *bfqd,
-+					struct bfq_queue **bfqq_ptr)
-+{
-+	struct bfq_group *root_group = bfqd->root_group;
-+	struct bfq_queue *bfqq = *bfqq_ptr;
-+
-+	bfq_log(bfqd, "put_async_bfqq: %p", bfqq);
-+	if (bfqq != NULL) {
-+		bfq_bfqq_move(bfqd, bfqq, &bfqq->entity, root_group);
-+		bfq_log_bfqq(bfqd, bfqq, "put_async_bfqq: putting %p, %d",
-+			     bfqq, atomic_read(&bfqq->ref));
-+		bfq_put_queue(bfqq);
-+		*bfqq_ptr = NULL;
-+	}
-+}
-+
-+/*
-+ * Release all the bfqg references to its async queues.  If we are
-+ * deallocating the group these queues may still contain requests, so
-+ * we reparent them to the root cgroup (i.e., the only one that will
-+ * exist for sure until all the requests on a device are gone).
-+ */
-+static void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg)
-+{
-+	int i, j;
-+
-+	for (i = 0; i < 2; i++)
-+		for (j = 0; j < IOPRIO_BE_NR; j++)
-+			__bfq_put_async_bfqq(bfqd, &bfqg->async_bfqq[i][j]);
-+
-+	__bfq_put_async_bfqq(bfqd, &bfqg->async_idle_bfqq);
-+}
-+
-+static void bfq_exit_queue(struct elevator_queue *e)
-+{
-+	struct bfq_data *bfqd = e->elevator_data;
-+	struct request_queue *q = bfqd->queue;
-+	struct bfq_queue *bfqq, *n;
-+
-+	bfq_shutdown_timer_wq(bfqd);
-+
-+	spin_lock_irq(q->queue_lock);
-+
-+	BUG_ON(bfqd->in_service_queue != NULL);
-+	list_for_each_entry_safe(bfqq, n, &bfqd->idle_list, bfqq_list)
-+		bfq_deactivate_bfqq(bfqd, bfqq, 0);
-+
-+	bfq_disconnect_groups(bfqd);
-+	spin_unlock_irq(q->queue_lock);
-+
-+	bfq_shutdown_timer_wq(bfqd);
-+
-+	synchronize_rcu();
-+
-+	BUG_ON(timer_pending(&bfqd->idle_slice_timer));
-+
-+	bfq_free_root_group(bfqd);
-+	kfree(bfqd);
-+}
-+
-+static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
-+{
-+	struct bfq_group *bfqg;
-+	struct bfq_data *bfqd;
-+	struct elevator_queue *eq;
-+
-+	eq = elevator_alloc(q, e);
-+	if (eq == NULL)
-+		return -ENOMEM;
-+
-+	bfqd = kzalloc_node(sizeof(*bfqd), GFP_KERNEL, q->node);
-+	if (bfqd == NULL) {
-+		kobject_put(&eq->kobj);
-+		return -ENOMEM;
-+	}
-+	eq->elevator_data = bfqd;
-+
-+	/*
-+	 * Our fallback bfqq if bfq_find_alloc_queue() runs into OOM issues.
-+	 * Grab a permanent reference to it, so that the normal code flow
-+	 * will not attempt to free it.
-+	 */
-+	bfq_init_bfqq(bfqd, &bfqd->oom_bfqq, 1, 0);
-+	atomic_inc(&bfqd->oom_bfqq.ref);
-+
-+	bfqd->queue = q;
-+
-+	spin_lock_irq(q->queue_lock);
-+	q->elevator = eq;
-+	spin_unlock_irq(q->queue_lock);
-+
-+	bfqg = bfq_alloc_root_group(bfqd, q->node);
-+	if (bfqg == NULL) {
-+		kfree(bfqd);
-+		kobject_put(&eq->kobj);
-+		return -ENOMEM;
-+	}
-+
-+	bfqd->root_group = bfqg;
-+
-+	init_timer(&bfqd->idle_slice_timer);
-+	bfqd->idle_slice_timer.function = bfq_idle_slice_timer;
-+	bfqd->idle_slice_timer.data = (unsigned long)bfqd;
-+
-+	bfqd->rq_pos_tree = RB_ROOT;
-+
-+	INIT_WORK(&bfqd->unplug_work, bfq_kick_queue);
-+
-+	INIT_LIST_HEAD(&bfqd->active_list);
-+	INIT_LIST_HEAD(&bfqd->idle_list);
-+
-+	bfqd->hw_tag = -1;
-+
-+	bfqd->bfq_max_budget = bfq_default_max_budget;
-+
-+	bfqd->bfq_quantum = bfq_quantum;
-+	bfqd->bfq_fifo_expire[0] = bfq_fifo_expire[0];
-+	bfqd->bfq_fifo_expire[1] = bfq_fifo_expire[1];
-+	bfqd->bfq_back_max = bfq_back_max;
-+	bfqd->bfq_back_penalty = bfq_back_penalty;
-+	bfqd->bfq_slice_idle = bfq_slice_idle;
-+	bfqd->bfq_class_idle_last_service = 0;
-+	bfqd->bfq_max_budget_async_rq = bfq_max_budget_async_rq;
-+	bfqd->bfq_timeout[BLK_RW_ASYNC] = bfq_timeout_async;
-+	bfqd->bfq_timeout[BLK_RW_SYNC] = bfq_timeout_sync;
-+
-+	bfqd->low_latency = true;
-+
-+	bfqd->bfq_raising_coeff = 20;
-+	bfqd->bfq_raising_rt_max_time = msecs_to_jiffies(300);
-+	bfqd->bfq_raising_max_time = 0;
-+	bfqd->bfq_raising_min_idle_time = msecs_to_jiffies(2000);
-+	bfqd->bfq_raising_min_inter_arr_async = msecs_to_jiffies(500);
-+	bfqd->bfq_raising_max_softrt_rate = 7000; /*
-+						   * Approximate rate required
-+						   * to playback or record a
-+						   * high-definition compressed
-+						   * video.
-+						   */
-+	bfqd->raised_busy_queues = 0;
-+
-+	/* Initially estimate the device's peak rate as the reference rate */
-+	if (blk_queue_nonrot(bfqd->queue)) {
-+		bfqd->RT_prod = R_nonrot * T_nonrot;
-+		bfqd->peak_rate = R_nonrot;
-+	} else {
-+		bfqd->RT_prod = R_rot * T_rot;
-+		bfqd->peak_rate = R_rot;
-+	}
-+
-+	return 0;
-+}
-+
-+static void bfq_slab_kill(void)
-+{
-+	if (bfq_pool != NULL)
-+		kmem_cache_destroy(bfq_pool);
-+}
-+
-+static int __init bfq_slab_setup(void)
-+{
-+	bfq_pool = KMEM_CACHE(bfq_queue, 0);
-+	if (bfq_pool == NULL)
-+		return -ENOMEM;
-+	return 0;
-+}
-+
-+static ssize_t bfq_var_show(unsigned int var, char *page)
-+{
-+	return sprintf(page, "%d\n", var);
-+}
-+
-+static ssize_t bfq_var_store(unsigned long *var, const char *page, size_t count)
-+{
-+	unsigned long new_val;
-+	int ret = kstrtoul(page, 10, &new_val);
-+
-+	if (ret == 0)
-+		*var = new_val;
-+
-+	return count;
-+}
-+
-+static ssize_t bfq_raising_max_time_show(struct elevator_queue *e, char *page)
-+{
-+	struct bfq_data *bfqd = e->elevator_data;
-+	return sprintf(page, "%d\n", bfqd->bfq_raising_max_time > 0 ?
-+		       jiffies_to_msecs(bfqd->bfq_raising_max_time) :
-+		       jiffies_to_msecs(bfq_wrais_duration(bfqd)));
-+}
-+
-+static ssize_t bfq_weights_show(struct elevator_queue *e, char *page)
-+{
-+	struct bfq_queue *bfqq;
-+	struct bfq_data *bfqd = e->elevator_data;
-+	ssize_t num_char = 0;
-+
-+	num_char += sprintf(page + num_char, "Tot reqs queued %d\n\n",
-+			    bfqd->queued);
-+
-+	spin_lock_irq(bfqd->queue->queue_lock);
-+
-+	num_char += sprintf(page + num_char, "Active:\n");
-+	list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list) {
-+	  num_char += sprintf(page + num_char,
-+			      "pid%d: weight %hu, nr_queued %d %d,"
-+			      " dur %d/%u\n",
-+			      bfqq->pid,
-+			      bfqq->entity.weight,
-+			      bfqq->queued[0],
-+			      bfqq->queued[1],
-+			jiffies_to_msecs(jiffies -
-+				bfqq->last_rais_start_finish),
-+			jiffies_to_msecs(bfqq->raising_cur_max_time));
-+	}
-+
-+	num_char += sprintf(page + num_char, "Idle:\n");
-+	list_for_each_entry(bfqq, &bfqd->idle_list, bfqq_list) {
-+			num_char += sprintf(page + num_char,
-+				"pid%d: weight %hu, dur %d/%u\n",
-+				bfqq->pid,
-+				bfqq->entity.weight,
-+				jiffies_to_msecs(jiffies -
-+					bfqq->last_rais_start_finish),
-+				jiffies_to_msecs(bfqq->raising_cur_max_time));
-+	}
-+
-+	spin_unlock_irq(bfqd->queue->queue_lock);
-+
-+	return num_char;
-+}
-+
-+#define SHOW_FUNCTION(__FUNC, __VAR, __CONV)				\
-+static ssize_t __FUNC(struct elevator_queue *e, char *page)		\
-+{									\
-+	struct bfq_data *bfqd = e->elevator_data;			\
-+	unsigned int __data = __VAR;					\
-+	if (__CONV)							\
-+		__data = jiffies_to_msecs(__data);			\
-+	return bfq_var_show(__data, (page));				\
-+}
-+SHOW_FUNCTION(bfq_quantum_show, bfqd->bfq_quantum, 0);
-+SHOW_FUNCTION(bfq_fifo_expire_sync_show, bfqd->bfq_fifo_expire[1], 1);
-+SHOW_FUNCTION(bfq_fifo_expire_async_show, bfqd->bfq_fifo_expire[0], 1);
-+SHOW_FUNCTION(bfq_back_seek_max_show, bfqd->bfq_back_max, 0);
-+SHOW_FUNCTION(bfq_back_seek_penalty_show, bfqd->bfq_back_penalty, 0);
-+SHOW_FUNCTION(bfq_slice_idle_show, bfqd->bfq_slice_idle, 1);
-+SHOW_FUNCTION(bfq_max_budget_show, bfqd->bfq_user_max_budget, 0);
-+SHOW_FUNCTION(bfq_max_budget_async_rq_show, bfqd->bfq_max_budget_async_rq, 0);
-+SHOW_FUNCTION(bfq_timeout_sync_show, bfqd->bfq_timeout[BLK_RW_SYNC], 1);
-+SHOW_FUNCTION(bfq_timeout_async_show, bfqd->bfq_timeout[BLK_RW_ASYNC], 1);
-+SHOW_FUNCTION(bfq_low_latency_show, bfqd->low_latency, 0);
-+SHOW_FUNCTION(bfq_raising_coeff_show, bfqd->bfq_raising_coeff, 0);
-+SHOW_FUNCTION(bfq_raising_rt_max_time_show, bfqd->bfq_raising_rt_max_time, 1);
-+SHOW_FUNCTION(bfq_raising_min_idle_time_show, bfqd->bfq_raising_min_idle_time,
-+	1);
-+SHOW_FUNCTION(bfq_raising_min_inter_arr_async_show,
-+	bfqd->bfq_raising_min_inter_arr_async,
-+	1);
-+SHOW_FUNCTION(bfq_raising_max_softrt_rate_show,
-+	bfqd->bfq_raising_max_softrt_rate, 0);
-+#undef SHOW_FUNCTION
-+
-+#define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV)			\
-+static ssize_t								\
-+__FUNC(struct elevator_queue *e, const char *page, size_t count)	\
-+{									\
-+	struct bfq_data *bfqd = e->elevator_data;			\
-+	unsigned long uninitialized_var(__data);			\
-+	int ret = bfq_var_store(&__data, (page), count);		\
-+	if (__data < (MIN))						\
-+		__data = (MIN);						\
-+	else if (__data > (MAX))					\
-+		__data = (MAX);						\
-+	if (__CONV)							\
-+		*(__PTR) = msecs_to_jiffies(__data);			\
-+	else								\
-+		*(__PTR) = __data;					\
-+	return ret;							\
-+}
-+STORE_FUNCTION(bfq_quantum_store, &bfqd->bfq_quantum, 1, INT_MAX, 0);
-+STORE_FUNCTION(bfq_fifo_expire_sync_store, &bfqd->bfq_fifo_expire[1], 1,
-+		INT_MAX, 1);
-+STORE_FUNCTION(bfq_fifo_expire_async_store, &bfqd->bfq_fifo_expire[0], 1,
-+		INT_MAX, 1);
-+STORE_FUNCTION(bfq_back_seek_max_store, &bfqd->bfq_back_max, 0, INT_MAX, 0);
-+STORE_FUNCTION(bfq_back_seek_penalty_store, &bfqd->bfq_back_penalty, 1,
-+		INT_MAX, 0);
-+STORE_FUNCTION(bfq_slice_idle_store, &bfqd->bfq_slice_idle, 0, INT_MAX, 1);
-+STORE_FUNCTION(bfq_max_budget_async_rq_store, &bfqd->bfq_max_budget_async_rq,
-+		1, INT_MAX, 0);
-+STORE_FUNCTION(bfq_timeout_async_store, &bfqd->bfq_timeout[BLK_RW_ASYNC], 0,
-+		INT_MAX, 1);
-+STORE_FUNCTION(bfq_raising_coeff_store, &bfqd->bfq_raising_coeff, 1,
-+		INT_MAX, 0);
-+STORE_FUNCTION(bfq_raising_max_time_store, &bfqd->bfq_raising_max_time, 0,
-+		INT_MAX, 1);
-+STORE_FUNCTION(bfq_raising_rt_max_time_store, &bfqd->bfq_raising_rt_max_time, 0,
-+		INT_MAX, 1);
-+STORE_FUNCTION(bfq_raising_min_idle_time_store,
-+	       &bfqd->bfq_raising_min_idle_time, 0, INT_MAX, 1);
-+STORE_FUNCTION(bfq_raising_min_inter_arr_async_store,
-+		&bfqd->bfq_raising_min_inter_arr_async, 0, INT_MAX, 1);
-+STORE_FUNCTION(bfq_raising_max_softrt_rate_store,
-+	       &bfqd->bfq_raising_max_softrt_rate, 0, INT_MAX, 0);
-+#undef STORE_FUNCTION
-+
-+/* do nothing for the moment */
-+static ssize_t bfq_weights_store(struct elevator_queue *e,
-+				    const char *page, size_t count)
-+{
-+	return count;
-+}
-+
-+static inline unsigned long bfq_estimated_max_budget(struct bfq_data *bfqd)
-+{
-+	u64 timeout = jiffies_to_msecs(bfqd->bfq_timeout[BLK_RW_SYNC]);
-+
-+	if (bfqd->peak_rate_samples >= BFQ_PEAK_RATE_SAMPLES)
-+		return bfq_calc_max_budget(bfqd->peak_rate, timeout);
-+	else
-+		return bfq_default_max_budget;
-+}
-+
-+static ssize_t bfq_max_budget_store(struct elevator_queue *e,
-+				    const char *page, size_t count)
-+{
-+	struct bfq_data *bfqd = e->elevator_data;
-+	unsigned long uninitialized_var(__data);
-+	int ret = bfq_var_store(&__data, (page), count);
-+
-+	if (__data == 0)
-+		bfqd->bfq_max_budget = bfq_estimated_max_budget(bfqd);
-+	else {
-+		if (__data > INT_MAX)
-+			__data = INT_MAX;
-+		bfqd->bfq_max_budget = __data;
-+	}
-+
-+	bfqd->bfq_user_max_budget = __data;
-+
-+	return ret;
-+}
-+
-+static ssize_t bfq_timeout_sync_store(struct elevator_queue *e,
-+				      const char *page, size_t count)
-+{
-+	struct bfq_data *bfqd = e->elevator_data;
-+	unsigned long uninitialized_var(__data);
-+	int ret = bfq_var_store(&__data, (page), count);
-+
-+	if (__data < 1)
-+		__data = 1;
-+	else if (__data > INT_MAX)
-+		__data = INT_MAX;
-+
-+	bfqd->bfq_timeout[BLK_RW_SYNC] = msecs_to_jiffies(__data);
-+	if (bfqd->bfq_user_max_budget == 0)
-+		bfqd->bfq_max_budget = bfq_estimated_max_budget(bfqd);
-+
-+	return ret;
-+}
-+
-+static ssize_t bfq_low_latency_store(struct elevator_queue *e,
-+				     const char *page, size_t count)
-+{
-+	struct bfq_data *bfqd = e->elevator_data;
-+	unsigned long uninitialized_var(__data);
-+	int ret = bfq_var_store(&__data, (page), count);
-+
-+	if (__data > 1)
-+		__data = 1;
-+	if (__data == 0 && bfqd->low_latency != 0)
-+		bfq_end_raising(bfqd);
-+	bfqd->low_latency = __data;
-+
-+	return ret;
-+}
-+
-+#define BFQ_ATTR(name) \
-+	__ATTR(name, S_IRUGO|S_IWUSR, bfq_##name##_show, bfq_##name##_store)
-+
-+static struct elv_fs_entry bfq_attrs[] = {
-+	BFQ_ATTR(quantum),
-+	BFQ_ATTR(fifo_expire_sync),
-+	BFQ_ATTR(fifo_expire_async),
-+	BFQ_ATTR(back_seek_max),
-+	BFQ_ATTR(back_seek_penalty),
-+	BFQ_ATTR(slice_idle),
-+	BFQ_ATTR(max_budget),
-+	BFQ_ATTR(max_budget_async_rq),
-+	BFQ_ATTR(timeout_sync),
-+	BFQ_ATTR(timeout_async),
-+	BFQ_ATTR(low_latency),
-+	BFQ_ATTR(raising_coeff),
-+	BFQ_ATTR(raising_max_time),
-+	BFQ_ATTR(raising_rt_max_time),
-+	BFQ_ATTR(raising_min_idle_time),
-+	BFQ_ATTR(raising_min_inter_arr_async),
-+	BFQ_ATTR(raising_max_softrt_rate),
-+	BFQ_ATTR(weights),
-+	__ATTR_NULL
-+};
-+
-+static struct elevator_type iosched_bfq = {
-+	.ops = {
-+		.elevator_merge_fn =		bfq_merge,
-+		.elevator_merged_fn =		bfq_merged_request,
-+		.elevator_merge_req_fn =	bfq_merged_requests,
-+		.elevator_allow_merge_fn =	bfq_allow_merge,
-+		.elevator_dispatch_fn =		bfq_dispatch_requests,
-+		.elevator_add_req_fn =		bfq_insert_request,
-+		.elevator_activate_req_fn =	bfq_activate_request,
-+		.elevator_deactivate_req_fn =	bfq_deactivate_request,
-+		.elevator_completed_req_fn =	bfq_completed_request,
-+		.elevator_former_req_fn =	elv_rb_former_request,
-+		.elevator_latter_req_fn =	elv_rb_latter_request,
-+		.elevator_init_icq_fn =		bfq_init_icq,
-+		.elevator_exit_icq_fn =		bfq_exit_icq,
-+		.elevator_set_req_fn =		bfq_set_request,
-+		.elevator_put_req_fn =		bfq_put_request,
-+		.elevator_may_queue_fn =	bfq_may_queue,
-+		.elevator_init_fn =		bfq_init_queue,
-+		.elevator_exit_fn =		bfq_exit_queue,
-+	},
-+	.icq_size =		sizeof(struct bfq_io_cq),
-+	.icq_align =		__alignof__(struct bfq_io_cq),
-+	.elevator_attrs =	bfq_attrs,
-+	.elevator_name =	"bfq",
-+	.elevator_owner =	THIS_MODULE,
-+};
-+
-+static int __init bfq_init(void)
-+{
-+	/*
-+	 * Can be 0 on HZ < 1000 setups.
-+	 */
-+	if (bfq_slice_idle == 0)
-+		bfq_slice_idle = 1;
-+
-+	if (bfq_timeout_async == 0)
-+		bfq_timeout_async = 1;
-+
-+	if (bfq_slab_setup())
-+		return -ENOMEM;
-+
-+	elv_register(&iosched_bfq);
-+	pr_info("BFQ I/O-scheduler version: v7r2");
-+
-+	return 0;
-+}
-+
-+static void __exit bfq_exit(void)
-+{
-+	elv_unregister(&iosched_bfq);
-+	bfq_slab_kill();
-+}
-+
-+module_init(bfq_init);
-+module_exit(bfq_exit);
-+
-+MODULE_AUTHOR("Fabio Checconi, Paolo Valente");
-diff --git a/block/bfq-sched.c b/block/bfq-sched.c
-new file mode 100644
-index 0000000..999b475
---- /dev/null
-+++ b/block/bfq-sched.c
-@@ -0,0 +1,1078 @@
-+/*
-+ * BFQ: Hierarchical B-WF2Q+ scheduler.
-+ *
-+ * Based on ideas and code from CFQ:
-+ * Copyright (C) 2003 Jens Axboe <axboe@××××××.dk>
-+ *
-+ * Copyright (C) 2008 Fabio Checconi <fabio@×××××××××××××.it>
-+ *		      Paolo Valente <paolo.valente@×××××××.it>
-+ *
-+ * Copyright (C) 2010 Paolo Valente <paolo.valente@×××××××.it>
-+ */
-+
-+#ifdef CONFIG_CGROUP_BFQIO
-+#define for_each_entity(entity)	\
-+	for (; entity != NULL; entity = entity->parent)
-+
-+#define for_each_entity_safe(entity, parent) \
-+	for (; entity && ({ parent = entity->parent; 1; }); entity = parent)
-+
-+static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd,
-+						 int extract,
-+						 struct bfq_data *bfqd);
-+
-+static inline void bfq_update_budget(struct bfq_entity *next_in_service)
-+{
-+	struct bfq_entity *bfqg_entity;
-+	struct bfq_group *bfqg;
-+	struct bfq_sched_data *group_sd;
-+
-+	BUG_ON(next_in_service == NULL);
-+
-+	group_sd = next_in_service->sched_data;
-+
-+	bfqg = container_of(group_sd, struct bfq_group, sched_data);
-+	/*
-+	 * bfq_group's my_entity field is not NULL only if the group
-+	 * is not the root group. We must not touch the root entity
-+	 * as it must never become an in-service entity.
-+	 */
-+	bfqg_entity = bfqg->my_entity;
-+	if (bfqg_entity != NULL)
-+		bfqg_entity->budget = next_in_service->budget;
-+}
-+
-+static int bfq_update_next_in_service(struct bfq_sched_data *sd)
-+{
-+	struct bfq_entity *next_in_service;
-+
-+	if (sd->in_service_entity != NULL)
-+		/* will update/requeue at the end of service */
-+		return 0;
-+
-+	/*
-+	 * NOTE: this can be improved in many ways, such as returning
-+	 * 1 (and thus propagating upwards the update) only when the
-+	 * budget changes, or caching the bfqq that will be scheduled
-+	 * next from this subtree.  By now we worry more about
-+	 * correctness than about performance...
-+	 */
-+	next_in_service = bfq_lookup_next_entity(sd, 0, NULL);
-+	sd->next_in_service = next_in_service;
-+
-+	if (next_in_service != NULL)
-+		bfq_update_budget(next_in_service);
-+
-+	return 1;
-+}
-+
-+static inline void bfq_check_next_in_service(struct bfq_sched_data *sd,
-+					     struct bfq_entity *entity)
-+{
-+	BUG_ON(sd->next_in_service != entity);
-+}
-+#else
-+#define for_each_entity(entity)	\
-+	for (; entity != NULL; entity = NULL)
-+
-+#define for_each_entity_safe(entity, parent) \
-+	for (parent = NULL; entity != NULL; entity = parent)
-+
-+static inline int bfq_update_next_in_service(struct bfq_sched_data *sd)
-+{
-+	return 0;
-+}
-+
-+static inline void bfq_check_next_in_service(struct bfq_sched_data *sd,
-+					     struct bfq_entity *entity)
-+{
-+}
-+
-+static inline void bfq_update_budget(struct bfq_entity *next_in_service)
-+{
-+}
-+#endif
-+
-+/*
-+ * Shift for timestamp calculations.  This actually limits the maximum
-+ * service allowed in one timestamp delta (small shift values increase it),
-+ * the maximum total weight that can be used for the queues in the system
-+ * (big shift values increase it), and the period of virtual time wraparounds.
-+ */
-+#define WFQ_SERVICE_SHIFT	22
-+
-+/**
-+ * bfq_gt - compare two timestamps.
-+ * @a: first ts.
-+ * @b: second ts.
-+ *
-+ * Return @a > @b, dealing with wrapping correctly.
-+ */
-+static inline int bfq_gt(u64 a, u64 b)
-+{
-+	return (s64)(a - b) > 0;
-+}
-+
-+static inline struct bfq_queue *bfq_entity_to_bfqq(struct bfq_entity *entity)
-+{
-+	struct bfq_queue *bfqq = NULL;
-+
-+	BUG_ON(entity == NULL);
-+
-+	if (entity->my_sched_data == NULL)
-+		bfqq = container_of(entity, struct bfq_queue, entity);
-+
-+	return bfqq;
-+}
-+
-+
-+/**
-+ * bfq_delta - map service into the virtual time domain.
-+ * @service: amount of service.
-+ * @weight: scale factor (weight of an entity or weight sum).
-+ */
-+static inline u64 bfq_delta(unsigned long service,
-+					unsigned long weight)
-+{
-+	u64 d = (u64)service << WFQ_SERVICE_SHIFT;
-+
-+	do_div(d, weight);
-+	return d;
-+}
-+
-+/**
-+ * bfq_calc_finish - assign the finish time to an entity.
-+ * @entity: the entity to act upon.
-+ * @service: the service to be charged to the entity.
-+ */
-+static inline void bfq_calc_finish(struct bfq_entity *entity,
-+				   unsigned long service)
-+{
-+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
-+
-+	BUG_ON(entity->weight == 0);
-+
-+	entity->finish = entity->start +
-+		bfq_delta(service, entity->weight);
-+
-+	if (bfqq != NULL) {
-+		bfq_log_bfqq(bfqq->bfqd, bfqq,
-+			"calc_finish: serv %lu, w %d",
-+			service, entity->weight);
-+		bfq_log_bfqq(bfqq->bfqd, bfqq,
-+			"calc_finish: start %llu, finish %llu, delta %llu",
-+			entity->start, entity->finish,
-+			bfq_delta(service, entity->weight));
-+	}
-+}
-+
-+/**
-+ * bfq_entity_of - get an entity from a node.
-+ * @node: the node field of the entity.
-+ *
-+ * Convert a node pointer to the relative entity.  This is used only
-+ * to simplify the logic of some functions and not as the generic
-+ * conversion mechanism because, e.g., in the tree walking functions,
-+ * the check for a %NULL value would be redundant.
-+ */
-+static inline struct bfq_entity *bfq_entity_of(struct rb_node *node)
-+{
-+	struct bfq_entity *entity = NULL;
-+
-+	if (node != NULL)
-+		entity = rb_entry(node, struct bfq_entity, rb_node);
-+
-+	return entity;
-+}
-+
-+/**
-+ * bfq_extract - remove an entity from a tree.
-+ * @root: the tree root.
-+ * @entity: the entity to remove.
-+ */
-+static inline void bfq_extract(struct rb_root *root,
-+			       struct bfq_entity *entity)
-+{
-+	BUG_ON(entity->tree != root);
-+
-+	entity->tree = NULL;
-+	rb_erase(&entity->rb_node, root);
-+}
-+
-+/**
-+ * bfq_idle_extract - extract an entity from the idle tree.
-+ * @st: the service tree of the owning @entity.
-+ * @entity: the entity being removed.
-+ */
-+static void bfq_idle_extract(struct bfq_service_tree *st,
-+			     struct bfq_entity *entity)
-+{
-+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
-+	struct rb_node *next;
-+
-+	BUG_ON(entity->tree != &st->idle);
-+
-+	if (entity == st->first_idle) {
-+		next = rb_next(&entity->rb_node);
-+		st->first_idle = bfq_entity_of(next);
-+	}
-+
-+	if (entity == st->last_idle) {
-+		next = rb_prev(&entity->rb_node);
-+		st->last_idle = bfq_entity_of(next);
-+	}
-+
-+	bfq_extract(&st->idle, entity);
-+
-+	if (bfqq != NULL)
-+		list_del(&bfqq->bfqq_list);
-+}
-+
-+/**
-+ * bfq_insert - generic tree insertion.
-+ * @root: tree root.
-+ * @entity: entity to insert.
-+ *
-+ * This is used for the idle and the active tree, since they are both
-+ * ordered by finish time.
-+ */
-+static void bfq_insert(struct rb_root *root, struct bfq_entity *entity)
-+{
-+	struct bfq_entity *entry;
-+	struct rb_node **node = &root->rb_node;
-+	struct rb_node *parent = NULL;
-+
-+	BUG_ON(entity->tree != NULL);
-+
-+	while (*node != NULL) {
-+		parent = *node;
-+		entry = rb_entry(parent, struct bfq_entity, rb_node);
-+
-+		if (bfq_gt(entry->finish, entity->finish))
-+			node = &parent->rb_left;
-+		else
-+			node = &parent->rb_right;
-+	}
-+
-+	rb_link_node(&entity->rb_node, parent, node);
-+	rb_insert_color(&entity->rb_node, root);
-+
-+	entity->tree = root;
-+}
-+
-+/**
-+ * bfq_update_min - update the min_start field of a entity.
-+ * @entity: the entity to update.
-+ * @node: one of its children.
-+ *
-+ * This function is called when @entity may store an invalid value for
-+ * min_start due to updates to the active tree.  The function  assumes
-+ * that the subtree rooted at @node (which may be its left or its right
-+ * child) has a valid min_start value.
-+ */
-+static inline void bfq_update_min(struct bfq_entity *entity,
-+				  struct rb_node *node)
-+{
-+	struct bfq_entity *child;
-+
-+	if (node != NULL) {
-+		child = rb_entry(node, struct bfq_entity, rb_node);
-+		if (bfq_gt(entity->min_start, child->min_start))
-+			entity->min_start = child->min_start;
-+	}
-+}
-+
-+/**
-+ * bfq_update_active_node - recalculate min_start.
-+ * @node: the node to update.
-+ *
-+ * @node may have changed position or one of its children may have moved,
-+ * this function updates its min_start value.  The left and right subtrees
-+ * are assumed to hold a correct min_start value.
-+ */
-+static inline void bfq_update_active_node(struct rb_node *node)
-+{
-+	struct bfq_entity *entity = rb_entry(node, struct bfq_entity, rb_node);
-+
-+	entity->min_start = entity->start;
-+	bfq_update_min(entity, node->rb_right);
-+	bfq_update_min(entity, node->rb_left);
-+}
-+
-+/**
-+ * bfq_update_active_tree - update min_start for the whole active tree.
-+ * @node: the starting node.
-+ *
-+ * @node must be the deepest modified node after an update.  This function
-+ * updates its min_start using the values held by its children, assuming
-+ * that they did not change, and then updates all the nodes that may have
-+ * changed in the path to the root.  The only nodes that may have changed
-+ * are the ones in the path or their siblings.
-+ */
-+static void bfq_update_active_tree(struct rb_node *node)
-+{
-+	struct rb_node *parent;
-+
-+up:
-+	bfq_update_active_node(node);
-+
-+	parent = rb_parent(node);
-+	if (parent == NULL)
-+		return;
-+
-+	if (node == parent->rb_left && parent->rb_right != NULL)
-+		bfq_update_active_node(parent->rb_right);
-+	else if (parent->rb_left != NULL)
-+		bfq_update_active_node(parent->rb_left);
-+
-+	node = parent;
-+	goto up;
-+}
-+
-+/**
-+ * bfq_active_insert - insert an entity in the active tree of its group/device.
-+ * @st: the service tree of the entity.
-+ * @entity: the entity being inserted.
-+ *
-+ * The active tree is ordered by finish time, but an extra key is kept
-+ * per each node, containing the minimum value for the start times of
-+ * its children (and the node itself), so it's possible to search for
-+ * the eligible node with the lowest finish time in logarithmic time.
-+ */
-+static void bfq_active_insert(struct bfq_service_tree *st,
-+			      struct bfq_entity *entity)
-+{
-+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
-+	struct rb_node *node = &entity->rb_node;
-+
-+	bfq_insert(&st->active, entity);
-+
-+	if (node->rb_left != NULL)
-+		node = node->rb_left;
-+	else if (node->rb_right != NULL)
-+		node = node->rb_right;
-+
-+	bfq_update_active_tree(node);
-+
-+	if (bfqq != NULL)
-+		list_add(&bfqq->bfqq_list, &bfqq->bfqd->active_list);
-+}
-+
-+/**
-+ * bfq_ioprio_to_weight - calc a weight from an ioprio.
-+ * @ioprio: the ioprio value to convert.
-+ */
-+static unsigned short bfq_ioprio_to_weight(int ioprio)
-+{
-+	WARN_ON(ioprio < 0 || ioprio >= IOPRIO_BE_NR);
-+	return IOPRIO_BE_NR - ioprio;
-+}
-+
-+/**
-+ * bfq_weight_to_ioprio - calc an ioprio from a weight.
-+ * @weight: the weight value to convert.
-+ *
-+ * To preserve as mush as possible the old only-ioprio user interface,
-+ * 0 is used as an escape ioprio value for weights (numerically) equal or
-+ * larger than IOPRIO_BE_NR
-+ */
-+static unsigned short bfq_weight_to_ioprio(int weight)
-+{
-+	WARN_ON(weight < BFQ_MIN_WEIGHT || weight > BFQ_MAX_WEIGHT);
-+	return IOPRIO_BE_NR - weight < 0 ? 0 : IOPRIO_BE_NR - weight;
-+}
-+
-+static inline void bfq_get_entity(struct bfq_entity *entity)
-+{
-+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
-+	struct bfq_sched_data *sd;
-+
-+	if (bfqq != NULL) {
-+		sd = entity->sched_data;
-+		atomic_inc(&bfqq->ref);
-+		bfq_log_bfqq(bfqq->bfqd, bfqq, "get_entity: %p %d",
-+			     bfqq, atomic_read(&bfqq->ref));
-+	}
-+}
-+
-+/**
-+ * bfq_find_deepest - find the deepest node that an extraction can modify.
-+ * @node: the node being removed.
-+ *
-+ * Do the first step of an extraction in an rb tree, looking for the
-+ * node that will replace @node, and returning the deepest node that
-+ * the following modifications to the tree can touch.  If @node is the
-+ * last node in the tree return %NULL.
-+ */
-+static struct rb_node *bfq_find_deepest(struct rb_node *node)
-+{
-+	struct rb_node *deepest;
-+
-+	if (node->rb_right == NULL && node->rb_left == NULL)
-+		deepest = rb_parent(node);
-+	else if (node->rb_right == NULL)
-+		deepest = node->rb_left;
-+	else if (node->rb_left == NULL)
-+		deepest = node->rb_right;
-+	else {
-+		deepest = rb_next(node);
-+		if (deepest->rb_right != NULL)
-+			deepest = deepest->rb_right;
-+		else if (rb_parent(deepest) != node)
-+			deepest = rb_parent(deepest);
-+	}
-+
-+	return deepest;
-+}
-+
-+/**
-+ * bfq_active_extract - remove an entity from the active tree.
-+ * @st: the service_tree containing the tree.
-+ * @entity: the entity being removed.
-+ */
-+static void bfq_active_extract(struct bfq_service_tree *st,
-+			       struct bfq_entity *entity)
-+{
-+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
-+	struct rb_node *node;
-+
-+	node = bfq_find_deepest(&entity->rb_node);
-+	bfq_extract(&st->active, entity);
-+
-+	if (node != NULL)
-+		bfq_update_active_tree(node);
-+
-+	if (bfqq != NULL)
-+		list_del(&bfqq->bfqq_list);
-+}
-+
-+/**
-+ * bfq_idle_insert - insert an entity into the idle tree.
-+ * @st: the service tree containing the tree.
-+ * @entity: the entity to insert.
-+ */
-+static void bfq_idle_insert(struct bfq_service_tree *st,
-+			    struct bfq_entity *entity)
-+{
-+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
-+	struct bfq_entity *first_idle = st->first_idle;
-+	struct bfq_entity *last_idle = st->last_idle;
-+
-+	if (first_idle == NULL || bfq_gt(first_idle->finish, entity->finish))
-+		st->first_idle = entity;
-+	if (last_idle == NULL || bfq_gt(entity->finish, last_idle->finish))
-+		st->last_idle = entity;
-+
-+	bfq_insert(&st->idle, entity);
-+
-+	if (bfqq != NULL)
-+		list_add(&bfqq->bfqq_list, &bfqq->bfqd->idle_list);
-+}
-+
-+/**
-+ * bfq_forget_entity - remove an entity from the wfq trees.
-+ * @st: the service tree.
-+ * @entity: the entity being removed.
-+ *
-+ * Update the device status and forget everything about @entity, putting
-+ * the device reference to it, if it is a queue.  Entities belonging to
-+ * groups are not refcounted.
-+ */
-+static void bfq_forget_entity(struct bfq_service_tree *st,
-+			      struct bfq_entity *entity)
-+{
-+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
-+	struct bfq_sched_data *sd;
-+
-+	BUG_ON(!entity->on_st);
-+
-+	entity->on_st = 0;
-+	st->wsum -= entity->weight;
-+	if (bfqq != NULL) {
-+		sd = entity->sched_data;
-+		bfq_log_bfqq(bfqq->bfqd, bfqq, "forget_entity: %p %d",
-+			     bfqq, atomic_read(&bfqq->ref));
-+		bfq_put_queue(bfqq);
-+	}
-+}
-+
-+/**
-+ * bfq_put_idle_entity - release the idle tree ref of an entity.
-+ * @st: service tree for the entity.
-+ * @entity: the entity being released.
-+ */
-+static void bfq_put_idle_entity(struct bfq_service_tree *st,
-+				struct bfq_entity *entity)
-+{
-+	bfq_idle_extract(st, entity);
-+	bfq_forget_entity(st, entity);
-+}
-+
-+/**
-+ * bfq_forget_idle - update the idle tree if necessary.
-+ * @st: the service tree to act upon.
-+ *
-+ * To preserve the global O(log N) complexity we only remove one entry here;
-+ * as the idle tree will not grow indefinitely this can be done safely.
-+ */
-+static void bfq_forget_idle(struct bfq_service_tree *st)
-+{
-+	struct bfq_entity *first_idle = st->first_idle;
-+	struct bfq_entity *last_idle = st->last_idle;
-+
-+	if (RB_EMPTY_ROOT(&st->active) && last_idle != NULL &&
-+	    !bfq_gt(last_idle->finish, st->vtime)) {
-+		/*
-+		 * Forget the whole idle tree, increasing the vtime past
-+		 * the last finish time of idle entities.
-+		 */
-+		st->vtime = last_idle->finish;
-+	}
-+
-+	if (first_idle != NULL && !bfq_gt(first_idle->finish, st->vtime))
-+		bfq_put_idle_entity(st, first_idle);
-+}
-+
-+static struct bfq_service_tree *
-+__bfq_entity_update_weight_prio(struct bfq_service_tree *old_st,
-+			 struct bfq_entity *entity)
-+{
-+	struct bfq_service_tree *new_st = old_st;
-+
-+	if (entity->ioprio_changed) {
-+		struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
-+
-+		BUG_ON(old_st->wsum < entity->weight);
-+		old_st->wsum -= entity->weight;
-+
-+		if (entity->new_weight != entity->orig_weight) {
-+			entity->orig_weight = entity->new_weight;
-+			entity->ioprio =
-+				bfq_weight_to_ioprio(entity->orig_weight);
-+		} else if (entity->new_ioprio != entity->ioprio) {
-+			entity->ioprio = entity->new_ioprio;
-+			entity->orig_weight =
-+					bfq_ioprio_to_weight(entity->ioprio);
-+		} else
-+			entity->new_weight = entity->orig_weight =
-+				bfq_ioprio_to_weight(entity->ioprio);
-+
-+		entity->ioprio_class = entity->new_ioprio_class;
-+		entity->ioprio_changed = 0;
-+
-+		/*
-+		 * NOTE: here we may be changing the weight too early,
-+		 * this will cause unfairness.  The correct approach
-+		 * would have required additional complexity to defer
-+		 * weight changes to the proper time instants (i.e.,
-+		 * when entity->finish <= old_st->vtime).
-+		 */
-+		new_st = bfq_entity_service_tree(entity);
-+		entity->weight = entity->orig_weight *
-+			(bfqq != NULL ? bfqq->raising_coeff : 1);
-+		new_st->wsum += entity->weight;
-+
-+		if (new_st != old_st)
-+			entity->start = new_st->vtime;
-+	}
-+
-+	return new_st;
-+}
-+
-+/**
-+ * bfq_bfqq_served - update the scheduler status after selection for service.
-+ * @bfqq: the queue being served.
-+ * @served: bytes to transfer.
-+ *
-+ * NOTE: this can be optimized, as the timestamps of upper level entities
-+ * are synchronized every time a new bfqq is selected for service.  By now,
-+ * we keep it to better check consistency.
-+ */
-+static void bfq_bfqq_served(struct bfq_queue *bfqq, unsigned long served)
-+{
-+	struct bfq_entity *entity = &bfqq->entity;
-+	struct bfq_service_tree *st;
-+
-+	for_each_entity(entity) {
-+		st = bfq_entity_service_tree(entity);
-+
-+		entity->service += served;
-+		BUG_ON(entity->service > entity->budget);
-+		BUG_ON(st->wsum == 0);
-+
-+		st->vtime += bfq_delta(served, st->wsum);
-+		bfq_forget_idle(st);
-+	}
-+	bfq_log_bfqq(bfqq->bfqd, bfqq, "bfqq_served %lu secs", served);
-+}
-+
-+/**
-+ * bfq_bfqq_charge_full_budget - set the service to the entity budget.
-+ * @bfqq: the queue that needs a service update.
-+ *
-+ * When it's not possible to be fair in the service domain, because
-+ * a queue is not consuming its budget fast enough (the meaning of
-+ * fast depends on the timeout parameter), we charge it a full
-+ * budget.  In this way we should obtain a sort of time-domain
-+ * fairness among all the seeky/slow queues.
-+ */
-+static inline void bfq_bfqq_charge_full_budget(struct bfq_queue *bfqq)
-+{
-+	struct bfq_entity *entity = &bfqq->entity;
-+
-+	bfq_log_bfqq(bfqq->bfqd, bfqq, "charge_full_budget");
-+
-+	bfq_bfqq_served(bfqq, entity->budget - entity->service);
-+}
-+
-+/**
-+ * __bfq_activate_entity - activate an entity.
-+ * @entity: the entity being activated.
-+ *
-+ * Called whenever an entity is activated, i.e., it is not active and one
-+ * of its children receives a new request, or has to be reactivated due to
-+ * budget exhaustion.  It uses the current budget of the entity (and the
-+ * service received if @entity is active) of the queue to calculate its
-+ * timestamps.
-+ */
-+static void __bfq_activate_entity(struct bfq_entity *entity)
-+{
-+	struct bfq_sched_data *sd = entity->sched_data;
-+	struct bfq_service_tree *st = bfq_entity_service_tree(entity);
-+
-+	if (entity == sd->in_service_entity) {
-+		BUG_ON(entity->tree != NULL);
-+		/*
-+		 * If we are requeueing the current entity we have
-+		 * to take care of not charging to it service it has
-+		 * not received.
-+		 */
-+		bfq_calc_finish(entity, entity->service);
-+		entity->start = entity->finish;
-+		sd->in_service_entity = NULL;
-+	} else if (entity->tree == &st->active) {
-+		/*
-+		 * Requeueing an entity due to a change of some
-+		 * next_in_service entity below it.  We reuse the
-+		 * old start time.
-+		 */
-+		bfq_active_extract(st, entity);
-+	} else if (entity->tree == &st->idle) {
-+		/*
-+		 * Must be on the idle tree, bfq_idle_extract() will
-+		 * check for that.
-+		 */
-+		bfq_idle_extract(st, entity);
-+		entity->start = bfq_gt(st->vtime, entity->finish) ?
-+				       st->vtime : entity->finish;
-+	} else {
-+		/*
-+		 * The finish time of the entity may be invalid, and
-+		 * it is in the past for sure, otherwise the queue
-+		 * would have been on the idle tree.
-+		 */
-+		entity->start = st->vtime;
-+		st->wsum += entity->weight;
-+		bfq_get_entity(entity);
-+
-+		BUG_ON(entity->on_st);
-+		entity->on_st = 1;
-+	}
-+
-+	st = __bfq_entity_update_weight_prio(st, entity);
-+	bfq_calc_finish(entity, entity->budget);
-+	bfq_active_insert(st, entity);
-+}
-+
-+/**
-+ * bfq_activate_entity - activate an entity and its ancestors if necessary.
-+ * @entity: the entity to activate.
-+ *
-+ * Activate @entity and all the entities on the path from it to the root.
-+ */
-+static void bfq_activate_entity(struct bfq_entity *entity)
-+{
-+	struct bfq_sched_data *sd;
-+
-+	for_each_entity(entity) {
-+		__bfq_activate_entity(entity);
-+
-+		sd = entity->sched_data;
-+		if (!bfq_update_next_in_service(sd))
-+			/*
-+			 * No need to propagate the activation to the
-+			 * upper entities, as they will be updated when
-+			 * the in-service entity is rescheduled.
-+			 */
-+			break;
-+	}
-+}
-+
-+/**
-+ * __bfq_deactivate_entity - deactivate an entity from its service tree.
-+ * @entity: the entity to deactivate.
-+ * @requeue: if false, the entity will not be put into the idle tree.
-+ *
-+ * Deactivate an entity, independently from its previous state.  If the
-+ * entity was not on a service tree just return, otherwise if it is on
-+ * any scheduler tree, extract it from that tree, and if necessary
-+ * and if the caller did not specify @requeue, put it on the idle tree.
-+ *
-+ * Return %1 if the caller should update the entity hierarchy, i.e.,
-+ * if the entity was under service or if it was the next_in_service for
-+ * its sched_data; return %0 otherwise.
-+ */
-+static int __bfq_deactivate_entity(struct bfq_entity *entity, int requeue)
-+{
-+	struct bfq_sched_data *sd = entity->sched_data;
-+	struct bfq_service_tree *st = bfq_entity_service_tree(entity);
-+	int was_in_service = entity == sd->in_service_entity;
-+	int ret = 0;
-+
-+	if (!entity->on_st)
-+		return 0;
-+
-+	BUG_ON(was_in_service && entity->tree != NULL);
-+
-+	if (was_in_service) {
-+		bfq_calc_finish(entity, entity->service);
-+		sd->in_service_entity = NULL;
-+	} else if (entity->tree == &st->active)
-+		bfq_active_extract(st, entity);
-+	else if (entity->tree == &st->idle)
-+		bfq_idle_extract(st, entity);
-+	else if (entity->tree != NULL)
-+		BUG();
-+
-+	if (was_in_service || sd->next_in_service == entity)
-+		ret = bfq_update_next_in_service(sd);
-+
-+	if (!requeue || !bfq_gt(entity->finish, st->vtime))
-+		bfq_forget_entity(st, entity);
-+	else
-+		bfq_idle_insert(st, entity);
-+
-+	BUG_ON(sd->in_service_entity == entity);
-+	BUG_ON(sd->next_in_service == entity);
-+
-+	return ret;
-+}
-+
-+/**
-+ * bfq_deactivate_entity - deactivate an entity.
-+ * @entity: the entity to deactivate.
-+ * @requeue: true if the entity can be put on the idle tree
-+ */
-+static void bfq_deactivate_entity(struct bfq_entity *entity, int requeue)
-+{
-+	struct bfq_sched_data *sd;
-+	struct bfq_entity *parent;
-+
-+	for_each_entity_safe(entity, parent) {
-+		sd = entity->sched_data;
-+
-+		if (!__bfq_deactivate_entity(entity, requeue))
-+			/*
-+			 * The parent entity is still backlogged, and
-+			 * we don't need to update it as it is still
-+			 * under service.
-+			 */
-+			break;
-+
-+		if (sd->next_in_service != NULL)
-+			/*
-+			 * The parent entity is still backlogged and
-+			 * the budgets on the path towards the root
-+			 * need to be updated.
-+			 */
-+			goto update;
-+
-+		/*
-+		 * If we reach there the parent is no more backlogged and
-+		 * we want to propagate the dequeue upwards.
-+		 */
-+		requeue = 1;
-+	}
-+
-+	return;
-+
-+update:
-+	entity = parent;
-+	for_each_entity(entity) {
-+		__bfq_activate_entity(entity);
-+
-+		sd = entity->sched_data;
-+		if (!bfq_update_next_in_service(sd))
-+			break;
-+	}
-+}
-+
-+/**
-+ * bfq_update_vtime - update vtime if necessary.
-+ * @st: the service tree to act upon.
-+ *
-+ * If necessary update the service tree vtime to have at least one
-+ * eligible entity, skipping to its start time.  Assumes that the
-+ * active tree of the device is not empty.
-+ *
-+ * NOTE: this hierarchical implementation updates vtimes quite often,
-+ * we may end up with reactivated tasks getting timestamps after a
-+ * vtime skip done because we needed a ->first_active entity on some
-+ * intermediate node.
-+ */
-+static void bfq_update_vtime(struct bfq_service_tree *st)
-+{
-+	struct bfq_entity *entry;
-+	struct rb_node *node = st->active.rb_node;
-+
-+	entry = rb_entry(node, struct bfq_entity, rb_node);
-+	if (bfq_gt(entry->min_start, st->vtime)) {
-+		st->vtime = entry->min_start;
-+		bfq_forget_idle(st);
-+	}
-+}
-+
-+/**
-+ * bfq_first_active_entity - find the eligible entity with
-+ *                           the smallest finish time
-+ * @st: the service tree to select from.
-+ *
-+ * This function searches the first schedulable entity, starting from the
-+ * root of the tree and going on the left every time on this side there is
-+ * a subtree with at least one eligible (start >= vtime) entity.  The path
-+ * on the right is followed only if a) the left subtree contains no eligible
-+ * entities and b) no eligible entity has been found yet.
-+ */
-+static struct bfq_entity *bfq_first_active_entity(struct bfq_service_tree *st)
-+{
-+	struct bfq_entity *entry, *first = NULL;
-+	struct rb_node *node = st->active.rb_node;
-+
-+	while (node != NULL) {
-+		entry = rb_entry(node, struct bfq_entity, rb_node);
-+left:
-+		if (!bfq_gt(entry->start, st->vtime))
-+			first = entry;
-+
-+		BUG_ON(bfq_gt(entry->min_start, st->vtime));
-+
-+		if (node->rb_left != NULL) {
-+			entry = rb_entry(node->rb_left,
-+					 struct bfq_entity, rb_node);
-+			if (!bfq_gt(entry->min_start, st->vtime)) {
-+				node = node->rb_left;
-+				goto left;
-+			}
-+		}
-+		if (first != NULL)
-+			break;
-+		node = node->rb_right;
-+	}
-+
-+	BUG_ON(first == NULL && !RB_EMPTY_ROOT(&st->active));
-+	return first;
-+}
-+
-+/**
-+ * __bfq_lookup_next_entity - return the first eligible entity in @st.
-+ * @st: the service tree.
-+ *
-+ * Update the virtual time in @st and return the first eligible entity
-+ * it contains.
-+ */
-+static struct bfq_entity *__bfq_lookup_next_entity(struct bfq_service_tree *st,
-+						   bool force)
-+{
-+	struct bfq_entity *entity, *new_next_in_service = NULL;
-+
-+	if (RB_EMPTY_ROOT(&st->active))
-+		return NULL;
-+
-+	bfq_update_vtime(st);
-+	entity = bfq_first_active_entity(st);
-+	BUG_ON(bfq_gt(entity->start, st->vtime));
-+
-+	/*
-+	 * If the chosen entity does not match with the sched_data's
-+	 * next_in_service and we are forcedly serving the IDLE priority
-+	 * class tree, bubble up budget update.
-+	 */
-+	if (unlikely(force && entity != entity->sched_data->next_in_service)) {
-+		new_next_in_service = entity;
-+		for_each_entity(new_next_in_service)
-+			bfq_update_budget(new_next_in_service);
-+	}
-+
-+	return entity;
-+}
-+
-+/**
-+ * bfq_lookup_next_entity - return the first eligible entity in @sd.
-+ * @sd: the sched_data.
-+ * @extract: if true the returned entity will be also extracted from @sd.
-+ *
-+ * NOTE: since we cache the next_in_service entity at each level of the
-+ * hierarchy, the complexity of the lookup can be decreased with
-+ * absolutely no effort just returning the cached next_in_service value;
-+ * we prefer to do full lookups to test the consistency of * the data
-+ * structures.
-+ */
-+static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd,
-+						 int extract,
-+						 struct bfq_data *bfqd)
-+{
-+	struct bfq_service_tree *st = sd->service_tree;
-+	struct bfq_entity *entity;
-+	int i = 0;
-+
-+	BUG_ON(sd->in_service_entity != NULL);
-+
-+	if (bfqd != NULL &&
-+	    jiffies - bfqd->bfq_class_idle_last_service > BFQ_CL_IDLE_TIMEOUT) {
-+		entity = __bfq_lookup_next_entity(st + BFQ_IOPRIO_CLASSES - 1,
-+						  true);
-+		if (entity != NULL) {
-+			i = BFQ_IOPRIO_CLASSES - 1;
-+			bfqd->bfq_class_idle_last_service = jiffies;
-+			sd->next_in_service = entity;
-+		}
-+	}
-+	for (; i < BFQ_IOPRIO_CLASSES; i++) {
-+		entity = __bfq_lookup_next_entity(st + i, false);
-+		if (entity != NULL) {
-+			if (extract) {
-+				bfq_check_next_in_service(sd, entity);
-+				bfq_active_extract(st + i, entity);
-+				sd->in_service_entity = entity;
-+				sd->next_in_service = NULL;
-+			}
-+			break;
-+		}
-+	}
-+
-+	return entity;
-+}
-+
-+/*
-+ * Get next queue for service.
-+ */
-+static struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd)
-+{
-+	struct bfq_entity *entity = NULL;
-+	struct bfq_sched_data *sd;
-+	struct bfq_queue *bfqq;
-+
-+	BUG_ON(bfqd->in_service_queue != NULL);
-+
-+	if (bfqd->busy_queues == 0)
-+		return NULL;
-+
-+	sd = &bfqd->root_group->sched_data;
-+	for (; sd != NULL; sd = entity->my_sched_data) {
-+		entity = bfq_lookup_next_entity(sd, 1, bfqd);
-+		BUG_ON(entity == NULL);
-+		entity->service = 0;
-+	}
-+
-+	bfqq = bfq_entity_to_bfqq(entity);
-+	BUG_ON(bfqq == NULL);
-+
-+	return bfqq;
-+}
-+
-+/*
-+ * Forced extraction of the given queue.
-+ */
-+static void bfq_get_next_queue_forced(struct bfq_data *bfqd,
-+				      struct bfq_queue *bfqq)
-+{
-+	struct bfq_entity *entity;
-+	struct bfq_sched_data *sd;
-+
-+	BUG_ON(bfqd->in_service_queue != NULL);
-+
-+	entity = &bfqq->entity;
-+	/*
-+	 * Bubble up extraction/update from the leaf to the root.
-+	*/
-+	for_each_entity(entity) {
-+		sd = entity->sched_data;
-+		bfq_update_budget(entity);
-+		bfq_update_vtime(bfq_entity_service_tree(entity));
-+		bfq_active_extract(bfq_entity_service_tree(entity), entity);
-+		sd->active_entity = entity;
-+		sd->next_active = NULL;
-+		entity->service = 0;
-+	}
-+
-+	return;
-+}
-+
-+static void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd)
-+{
-+	if (bfqd->in_service_bic != NULL) {
-+		put_io_context(bfqd->in_service_bic->icq.ioc);
-+		bfqd->in_service_bic = NULL;
-+	}
-+
-+	bfqd->in_service_queue = NULL;
-+	del_timer(&bfqd->idle_slice_timer);
-+}
-+
-+static void bfq_deactivate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
-+				int requeue)
-+{
-+	struct bfq_entity *entity = &bfqq->entity;
-+
-+	if (bfqq == bfqd->in_service_queue)
-+		__bfq_bfqd_reset_in_service(bfqd);
-+
-+	bfq_deactivate_entity(entity, requeue);
-+}
-+
-+static void bfq_activate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
-+{
-+	struct bfq_entity *entity = &bfqq->entity;
-+
-+	bfq_activate_entity(entity);
-+}
-+
-+/*
-+ * Called when the bfqq no longer has requests pending, remove it from
-+ * the service tree.
-+ */
-+static void bfq_del_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq,
-+			      int requeue)
-+{
-+	BUG_ON(!bfq_bfqq_busy(bfqq));
-+	BUG_ON(!RB_EMPTY_ROOT(&bfqq->sort_list));
-+
-+	bfq_log_bfqq(bfqd, bfqq, "del from busy");
-+
-+	bfq_clear_bfqq_busy(bfqq);
-+
-+	BUG_ON(bfqd->busy_queues == 0);
-+	bfqd->busy_queues--;
-+	if (bfqq->raising_coeff > 1)
-+		bfqd->raised_busy_queues--;
-+
-+	bfq_deactivate_bfqq(bfqd, bfqq, requeue);
-+}
-+
-+/*
-+ * Called when an inactive queue receives a new request.
-+ */
-+static void bfq_add_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq)
-+{
-+	BUG_ON(bfq_bfqq_busy(bfqq));
-+	BUG_ON(bfqq == bfqd->in_service_queue);
-+
-+	bfq_log_bfqq(bfqd, bfqq, "add to busy");
-+
-+	bfq_activate_bfqq(bfqd, bfqq);
-+
-+	bfq_mark_bfqq_busy(bfqq);
-+	bfqd->busy_queues++;
-+	if (bfqq->raising_coeff > 1)
-+		bfqd->raised_busy_queues++;
-+}
-diff --git a/block/bfq.h b/block/bfq.h
-new file mode 100644
-index 0000000..3ca8482
---- /dev/null
-+++ b/block/bfq.h
-@@ -0,0 +1,622 @@
-+/*
-+ * BFQ-v7r2 for 3.14.0: data structures and common functions prototypes.
-+ *
-+ * Based on ideas and code from CFQ:
-+ * Copyright (C) 2003 Jens Axboe <axboe@××××××.dk>
-+ *
-+ * Copyright (C) 2008 Fabio Checconi <fabio@×××××××××××××.it>
-+ *		      Paolo Valente <paolo.valente@×××××××.it>
-+ *
-+ * Copyright (C) 2010 Paolo Valente <paolo.valente@×××××××.it>
-+ */
-+
-+#ifndef _BFQ_H
-+#define _BFQ_H
-+
-+#include <linux/blktrace_api.h>
-+#include <linux/hrtimer.h>
-+#include <linux/ioprio.h>
-+#include <linux/rbtree.h>
-+
-+#define BFQ_IOPRIO_CLASSES	3
-+#define BFQ_CL_IDLE_TIMEOUT	(HZ/5)
-+
-+#define BFQ_MIN_WEIGHT	1
-+#define BFQ_MAX_WEIGHT	1000
-+
-+#define BFQ_DEFAULT_GRP_WEIGHT	10
-+#define BFQ_DEFAULT_GRP_IOPRIO	0
-+#define BFQ_DEFAULT_GRP_CLASS	IOPRIO_CLASS_BE
-+
-+struct bfq_entity;
-+
-+/**
-+ * struct bfq_service_tree - per ioprio_class service tree.
-+ * @active: tree for active entities (i.e., those backlogged).
-+ * @idle: tree for idle entities (i.e., those not backlogged, with V <= F_i).
-+ * @first_idle: idle entity with minimum F_i.
-+ * @last_idle: idle entity with maximum F_i.
-+ * @vtime: scheduler virtual time.
-+ * @wsum: scheduler weight sum; active and idle entities contribute to it.
-+ *
-+ * Each service tree represents a B-WF2Q+ scheduler on its own.  Each
-+ * ioprio_class has its own independent scheduler, and so its own
-+ * bfq_service_tree.  All the fields are protected by the queue lock
-+ * of the containing bfqd.
-+ */
-+struct bfq_service_tree {
-+	struct rb_root active;
-+	struct rb_root idle;
-+
-+	struct bfq_entity *first_idle;
-+	struct bfq_entity *last_idle;
-+
-+	u64 vtime;
-+	unsigned long wsum;
-+};
-+
-+/**
-+ * struct bfq_sched_data - multi-class scheduler.
-+ * @in_service_entity: entity under service.
-+ * @next_in_service: head-of-the-line entity in the scheduler.
-+ * @service_tree: array of service trees, one per ioprio_class.
-+ *
-+ * bfq_sched_data is the basic scheduler queue.  It supports three
-+ * ioprio_classes, and can be used either as a toplevel queue or as
-+ * an intermediate queue on a hierarchical setup.
-+ * @next_in_service points to the active entity of the sched_data
-+ * service trees that will be scheduled next.
-+ *
-+ * The supported ioprio_classes are the same as in CFQ, in descending
-+ * priority order, IOPRIO_CLASS_RT, IOPRIO_CLASS_BE, IOPRIO_CLASS_IDLE.
-+ * Requests from higher priority queues are served before all the
-+ * requests from lower priority queues; among requests of the same
-+ * queue requests are served according to B-WF2Q+.
-+ * All the fields are protected by the queue lock of the containing bfqd.
-+ */
-+struct bfq_sched_data {
-+	struct bfq_entity *in_service_entity;
-+	struct bfq_entity *next_in_service;
-+	struct bfq_service_tree service_tree[BFQ_IOPRIO_CLASSES];
-+};
-+
-+/**
-+ * struct bfq_entity - schedulable entity.
-+ * @rb_node: service_tree member.
-+ * @on_st: flag, true if the entity is on a tree (either the active or
-+ *         the idle one of its service_tree).
-+ * @finish: B-WF2Q+ finish timestamp (aka F_i).
-+ * @start: B-WF2Q+ start timestamp (aka S_i).
-+ * @tree: tree the entity is enqueued into; %NULL if not on a tree.
-+ * @min_start: minimum start time of the (active) subtree rooted at
-+ *             this entity; used for O(log N) lookups into active trees.
-+ * @service: service received during the last round of service.
-+ * @budget: budget used to calculate F_i; F_i = S_i + @budget / @weight.
-+ * @weight: weight of the queue
-+ * @parent: parent entity, for hierarchical scheduling.
-+ * @my_sched_data: for non-leaf nodes in the cgroup hierarchy, the
-+ *                 associated scheduler queue, %NULL on leaf nodes.
-+ * @sched_data: the scheduler queue this entity belongs to.
-+ * @ioprio: the ioprio in use.
-+ * @new_weight: when a weight change is requested, the new weight value.
-+ * @orig_weight: original weight, used to implement weight boosting
-+ * @new_ioprio: when an ioprio change is requested, the new ioprio value.
-+ * @ioprio_class: the ioprio_class in use.
-+ * @new_ioprio_class: when an ioprio_class change is requested, the new
-+ *                    ioprio_class value.
-+ * @ioprio_changed: flag, true when the user requested a weight, ioprio or
-+ *                  ioprio_class change.
-+ *
-+ * A bfq_entity is used to represent either a bfq_queue (leaf node in the
-+ * cgroup hierarchy) or a bfq_group into the upper level scheduler.  Each
-+ * entity belongs to the sched_data of the parent group in the cgroup
-+ * hierarchy.  Non-leaf entities have also their own sched_data, stored
-+ * in @my_sched_data.
-+ *
-+ * Each entity stores independently its priority values; this would
-+ * allow different weights on different devices, but this
-+ * functionality is not exported to userspace by now.  Priorities and
-+ * weights are updated lazily, first storing the new values into the
-+ * new_* fields, then setting the @ioprio_changed flag.  As soon as
-+ * there is a transition in the entity state that allows the priority
-+ * update to take place the effective and the requested priority
-+ * values are synchronized.
-+ *
-+ * Unless cgroups are used, the weight value is calculated from the
-+ * ioprio to export the same interface as CFQ.  When dealing with
-+ * ``well-behaved'' queues (i.e., queues that do not spend too much
-+ * time to consume their budget and have true sequential behavior, and
-+ * when there are no external factors breaking anticipation) the
-+ * relative weights at each level of the cgroups hierarchy should be
-+ * guaranteed.  All the fields are protected by the queue lock of the
-+ * containing bfqd.
-+ */
-+struct bfq_entity {
-+	struct rb_node rb_node;
-+
-+	int on_st;
-+
-+	u64 finish;
-+	u64 start;
-+
-+	struct rb_root *tree;
-+
-+	u64 min_start;
-+
-+	unsigned long service, budget;
-+	unsigned short weight, new_weight;
-+	unsigned short orig_weight;
-+
-+	struct bfq_entity *parent;
-+
-+	struct bfq_sched_data *my_sched_data;
-+	struct bfq_sched_data *sched_data;
-+
-+	unsigned short ioprio, new_ioprio;
-+	unsigned short ioprio_class, new_ioprio_class;
-+
-+	int ioprio_changed;
-+};
-+
-+struct bfq_group;
-+
-+/**
-+ * struct bfq_queue - leaf schedulable entity.
-+ * @ref: reference counter.
-+ * @bfqd: parent bfq_data.
-+ * @new_bfqq: shared bfq_queue if queue is cooperating with
-+ *           one or more other queues.
-+ * @pos_node: request-position tree member (see bfq_data's @rq_pos_tree).
-+ * @pos_root: request-position tree root (see bfq_data's @rq_pos_tree).
-+ * @sort_list: sorted list of pending requests.
-+ * @next_rq: if fifo isn't expired, next request to serve.
-+ * @queued: nr of requests queued in @sort_list.
-+ * @allocated: currently allocated requests.
-+ * @meta_pending: pending metadata requests.
-+ * @fifo: fifo list of requests in sort_list.
-+ * @entity: entity representing this queue in the scheduler.
-+ * @max_budget: maximum budget allowed from the feedback mechanism.
-+ * @budget_timeout: budget expiration (in jiffies).
-+ * @dispatched: number of requests on the dispatch list or inside driver.
-+ * @org_ioprio: saved ioprio during boosted periods.
-+ * @flags: status flags.
-+ * @bfqq_list: node for active/idle bfqq list inside our bfqd.
-+ * @seek_samples: number of seeks sampled
-+ * @seek_total: sum of the distances of the seeks sampled
-+ * @seek_mean: mean seek distance
-+ * @last_request_pos: position of the last request enqueued
-+ * @pid: pid of the process owning the queue, used for logging purposes.
-+ * @last_rais_start_finish: start time of the current weight-raising period if
-+ *                          the @bfq-queue is being weight-raised, otherwise
-+ *                          finish time of the last weight-raising period
-+ * @raising_cur_max_time: current max raising time for this queue
-+ * @soft_rt_next_start: minimum time instant such that, only if a new request
-+ *                      is enqueued after this time instant in an idle
-+ *                      @bfq_queue with no outstanding requests, then the
-+ *                      task associated with the queue it is deemed as soft
-+ *                      real-time (see the comments to the function
-+ *                      bfq_bfqq_softrt_next_start())
-+ * @last_idle_bklogged: time of the last transition of the @bfq_queue from
-+ *                      idle to backlogged
-+ * @service_from_backlogged: cumulative service received from the @bfq_queue
-+ *                           since the last transition from idle to backlogged
-+ *
-+ * A bfq_queue is a leaf request queue; it can be associated with an io_context
-+ * or more, if it is async or shared between cooperating processes. @cgroup
-+ * holds a reference to the cgroup, to be sure that it does not disappear while
-+ * a bfqq still references it (mostly to avoid races between request issuing and
-+ * task migration followed by cgroup destruction).
-+ * All the fields are protected by the queue lock of the containing bfqd.
-+ */
-+struct bfq_queue {
-+	atomic_t ref;
-+	struct bfq_data *bfqd;
-+
-+	/* fields for cooperating queues handling */
-+	struct bfq_queue *new_bfqq;
-+	struct rb_node pos_node;
-+	struct rb_root *pos_root;
-+
-+	struct rb_root sort_list;
-+	struct request *next_rq;
-+	int queued[2];
-+	int allocated[2];
-+	int meta_pending;
-+	struct list_head fifo;
-+
-+	struct bfq_entity entity;
-+
-+	unsigned long max_budget;
-+	unsigned long budget_timeout;
-+
-+	int dispatched;
-+
-+	unsigned short org_ioprio;
-+
-+	unsigned int flags;
-+
-+	struct list_head bfqq_list;
-+
-+	unsigned int seek_samples;
-+	u64 seek_total;
-+	sector_t seek_mean;
-+	sector_t last_request_pos;
-+
-+	pid_t pid;
-+
-+	/* weight-raising fields */
-+	unsigned long raising_cur_max_time;
-+	unsigned long soft_rt_next_start;
-+	unsigned long last_rais_start_finish;
-+	unsigned int raising_coeff;
-+	unsigned long last_idle_bklogged;
-+	unsigned long service_from_backlogged;
-+};
-+
-+/**
-+ * struct bfq_ttime - per process thinktime stats.
-+ * @ttime_total: total process thinktime
-+ * @ttime_samples: number of thinktime samples
-+ * @ttime_mean: average process thinktime
-+ */
-+struct bfq_ttime {
-+	unsigned long last_end_request;
-+
-+	unsigned long ttime_total;
-+	unsigned long ttime_samples;
-+	unsigned long ttime_mean;
-+};
-+
-+/**
-+ * struct bfq_io_cq - per (request_queue, io_context) structure.
-+ * @icq: associated io_cq structure
-+ * @bfqq: array of two process queues, the sync and the async
-+ * @ttime: associated @bfq_ttime struct
-+ */
-+struct bfq_io_cq {
-+	struct io_cq icq; /* must be the first member */
-+	struct bfq_queue *bfqq[2];
-+	struct bfq_ttime ttime;
-+	int ioprio;
-+};
-+
-+/**
-+ * struct bfq_data - per device data structure.
-+ * @queue: request queue for the managed device.
-+ * @root_group: root bfq_group for the device.
-+ * @rq_pos_tree: rbtree sorted by next_request position,
-+ *		used when determining if two or more queues
-+ *		have interleaving requests (see bfq_close_cooperator).
-+ * @busy_queues: number of bfq_queues containing requests (including the
-+ *		 queue under service, even if it is idling).
-+ * @raised_busy_queues: number of weight-raised busy bfq_queues.
-+ * @queued: number of queued requests.
-+ * @rq_in_driver: number of requests dispatched and waiting for completion.
-+ * @sync_flight: number of sync requests in the driver.
-+ * @max_rq_in_driver: max number of reqs in driver in the last @hw_tag_samples
-+ *		      completed requests .
-+ * @hw_tag_samples: nr of samples used to calculate hw_tag.
-+ * @hw_tag: flag set to one if the driver is showing a queueing behavior.
-+ * @budgets_assigned: number of budgets assigned.
-+ * @idle_slice_timer: timer set when idling for the next sequential request
-+ *                    from the queue under service.
-+ * @unplug_work: delayed work to restart dispatching on the request queue.
-+ * @in_service_queue: bfq_queue under service.
-+ * @in_service_bic: bfq_io_cq (bic) associated with the @in_service_queue.
-+ * @last_position: on-disk position of the last served request.
-+ * @last_budget_start: beginning of the last budget.
-+ * @last_idling_start: beginning of the last idle slice.
-+ * @peak_rate: peak transfer rate observed for a budget.
-+ * @peak_rate_samples: number of samples used to calculate @peak_rate.
-+ * @bfq_max_budget: maximum budget allotted to a bfq_queue before rescheduling.
-+ * @group_list: list of all the bfq_groups active on the device.
-+ * @active_list: list of all the bfq_queues active on the device.
-+ * @idle_list: list of all the bfq_queues idle on the device.
-+ * @bfq_quantum: max number of requests dispatched per dispatch round.
-+ * @bfq_fifo_expire: timeout for async/sync requests; when it expires
-+ *                   requests are served in fifo order.
-+ * @bfq_back_penalty: weight of backward seeks wrt forward ones.
-+ * @bfq_back_max: maximum allowed backward seek.
-+ * @bfq_slice_idle: maximum idling time.
-+ * @bfq_user_max_budget: user-configured max budget value (0 for auto-tuning).
-+ * @bfq_max_budget_async_rq: maximum budget (in nr of requests) allotted to
-+ *                           async queues.
-+ * @bfq_timeout: timeout for bfq_queues to consume their budget; used to
-+ *               to prevent seeky queues to impose long latencies to well
-+ *               behaved ones (this also implies that seeky queues cannot
-+ *               receive guarantees in the service domain; after a timeout
-+ *               they are charged for the whole allocated budget, to try
-+ *               to preserve a behavior reasonably fair among them, but
-+ *               without service-domain guarantees).
-+ * @bfq_raising_coeff: Maximum factor by which the weight of a boosted
-+ *                            queue is multiplied
-+ * @bfq_raising_max_time: maximum duration of a weight-raising period (jiffies)
-+ * @bfq_raising_rt_max_time: maximum duration for soft real-time processes
-+ * @bfq_raising_min_idle_time: minimum idle period after which weight-raising
-+ *			       may be reactivated for a queue (in jiffies)
-+ * @bfq_raising_min_inter_arr_async: minimum period between request arrivals
-+ *				     after which weight-raising may be
-+ *				     reactivated for an already busy queue
-+ *				     (in jiffies)
-+ * @bfq_raising_max_softrt_rate: max service-rate for a soft real-time queue,
-+ *			         sectors per seconds
-+ * @RT_prod: cached value of the product R*T used for computing the maximum
-+ *	     duration of the weight raising automatically
-+ * @oom_bfqq: fallback dummy bfqq for extreme OOM conditions
-+ *
-+ * All the fields are protected by the @queue lock.
-+ */
-+struct bfq_data {
-+	struct request_queue *queue;
-+
-+	struct bfq_group *root_group;
-+
-+	struct rb_root rq_pos_tree;
-+
-+	int busy_queues;
-+	int raised_busy_queues;
-+	int queued;
-+	int rq_in_driver;
-+	int sync_flight;
-+
-+	int max_rq_in_driver;
-+	int hw_tag_samples;
-+	int hw_tag;
-+
-+	int budgets_assigned;
-+
-+	struct timer_list idle_slice_timer;
-+	struct work_struct unplug_work;
-+
-+	struct bfq_queue *in_service_queue;
-+	struct bfq_io_cq *in_service_bic;
-+
-+	sector_t last_position;
-+
-+	ktime_t last_budget_start;
-+	ktime_t last_idling_start;
-+	int peak_rate_samples;
-+	u64 peak_rate;
-+	unsigned long bfq_max_budget;
-+
-+	struct hlist_head group_list;
-+	struct list_head active_list;
-+	struct list_head idle_list;
-+
-+	unsigned int bfq_quantum;
-+	unsigned int bfq_fifo_expire[2];
-+	unsigned int bfq_back_penalty;
-+	unsigned int bfq_back_max;
-+	unsigned int bfq_slice_idle;
-+	u64 bfq_class_idle_last_service;
-+
-+	unsigned int bfq_user_max_budget;
-+	unsigned int bfq_max_budget_async_rq;
-+	unsigned int bfq_timeout[2];
-+
-+	bool low_latency;
-+
-+	/* parameters of the low_latency heuristics */
-+	unsigned int bfq_raising_coeff;
-+	unsigned int bfq_raising_max_time;
-+	unsigned int bfq_raising_rt_max_time;
-+	unsigned int bfq_raising_min_idle_time;
-+	unsigned long bfq_raising_min_inter_arr_async;
-+	unsigned int bfq_raising_max_softrt_rate;
-+	u64 RT_prod;
-+
-+	struct bfq_queue oom_bfqq;
-+};
-+
-+enum bfqq_state_flags {
-+	BFQ_BFQQ_FLAG_busy = 0,		/* has requests or is under service */
-+	BFQ_BFQQ_FLAG_wait_request,	/* waiting for a request */
-+	BFQ_BFQQ_FLAG_must_alloc,	/* must be allowed rq alloc */
-+	BFQ_BFQQ_FLAG_fifo_expire,	/* FIFO checked in this slice */
-+	BFQ_BFQQ_FLAG_idle_window,	/* slice idling enabled */
-+	BFQ_BFQQ_FLAG_prio_changed,	/* task priority has changed */
-+	BFQ_BFQQ_FLAG_sync,		/* synchronous queue */
-+	BFQ_BFQQ_FLAG_budget_new,	/* no completion with this budget */
-+	BFQ_BFQQ_FLAG_coop,		/* bfqq is shared */
-+	BFQ_BFQQ_FLAG_split_coop,	/* shared bfqq will be splitted */
-+	BFQ_BFQQ_FLAG_softrt_update,	/* needs softrt-next-start update */
-+};
-+
-+#define BFQ_BFQQ_FNS(name)						\
-+static inline void bfq_mark_bfqq_##name(struct bfq_queue *bfqq)		\
-+{									\
-+	(bfqq)->flags |= (1 << BFQ_BFQQ_FLAG_##name);			\
-+}									\
-+static inline void bfq_clear_bfqq_##name(struct bfq_queue *bfqq)	\
-+{									\
-+	(bfqq)->flags &= ~(1 << BFQ_BFQQ_FLAG_##name);			\
-+}									\
-+static inline int bfq_bfqq_##name(const struct bfq_queue *bfqq)		\
-+{									\
-+	return ((bfqq)->flags & (1 << BFQ_BFQQ_FLAG_##name)) != 0;	\
-+}
-+
-+BFQ_BFQQ_FNS(busy);
-+BFQ_BFQQ_FNS(wait_request);
-+BFQ_BFQQ_FNS(must_alloc);
-+BFQ_BFQQ_FNS(fifo_expire);
-+BFQ_BFQQ_FNS(idle_window);
-+BFQ_BFQQ_FNS(prio_changed);
-+BFQ_BFQQ_FNS(sync);
-+BFQ_BFQQ_FNS(budget_new);
-+BFQ_BFQQ_FNS(coop);
-+BFQ_BFQQ_FNS(split_coop);
-+BFQ_BFQQ_FNS(softrt_update);
-+#undef BFQ_BFQQ_FNS
-+
-+/* Logging facilities. */
-+#define bfq_log_bfqq(bfqd, bfqq, fmt, args...) \
-+	blk_add_trace_msg((bfqd)->queue, "bfq%d " fmt, (bfqq)->pid, ##args)
-+
-+#define bfq_log(bfqd, fmt, args...) \
-+	blk_add_trace_msg((bfqd)->queue, "bfq " fmt, ##args)
-+
-+/* Expiration reasons. */
-+enum bfqq_expiration {
-+	BFQ_BFQQ_TOO_IDLE = 0,		/* queue has been idling for too long */
-+	BFQ_BFQQ_BUDGET_TIMEOUT,	/* budget took too long to be used */
-+	BFQ_BFQQ_BUDGET_EXHAUSTED,	/* budget consumed */
-+	BFQ_BFQQ_NO_MORE_REQUESTS,	/* the queue has no more requests */
-+};
-+
-+#ifdef CONFIG_CGROUP_BFQIO
-+/**
-+ * struct bfq_group - per (device, cgroup) data structure.
-+ * @entity: schedulable entity to insert into the parent group sched_data.
-+ * @sched_data: own sched_data, to contain child entities (they may be
-+ *              both bfq_queues and bfq_groups).
-+ * @group_node: node to be inserted into the bfqio_cgroup->group_data
-+ *              list of the containing cgroup's bfqio_cgroup.
-+ * @bfqd_node: node to be inserted into the @bfqd->group_list list
-+ *             of the groups active on the same device; used for cleanup.
-+ * @bfqd: the bfq_data for the device this group acts upon.
-+ * @async_bfqq: array of async queues for all the tasks belonging to
-+ *              the group, one queue per ioprio value per ioprio_class,
-+ *              except for the idle class that has only one queue.
-+ * @async_idle_bfqq: async queue for the idle class (ioprio is ignored).
-+ * @my_entity: pointer to @entity, %NULL for the toplevel group; used
-+ *             to avoid too many special cases during group creation/migration.
-+ *
-+ * Each (device, cgroup) pair has its own bfq_group, i.e., for each cgroup
-+ * there is a set of bfq_groups, each one collecting the lower-level
-+ * entities belonging to the group that are acting on the same device.
-+ *
-+ * Locking works as follows:
-+ *    o @group_node is protected by the bfqio_cgroup lock, and is accessed
-+ *      via RCU from its readers.
-+ *    o @bfqd is protected by the queue lock, RCU is used to access it
-+ *      from the readers.
-+ *    o All the other fields are protected by the @bfqd queue lock.
-+ */
-+struct bfq_group {
-+	struct bfq_entity entity;
-+	struct bfq_sched_data sched_data;
-+
-+	struct hlist_node group_node;
-+	struct hlist_node bfqd_node;
-+
-+	void *bfqd;
-+
-+	struct bfq_queue *async_bfqq[2][IOPRIO_BE_NR];
-+	struct bfq_queue *async_idle_bfqq;
-+
-+	struct bfq_entity *my_entity;
-+};
-+
-+/**
-+ * struct bfqio_cgroup - bfq cgroup data structure.
-+ * @css: subsystem state for bfq in the containing cgroup.
-+ * @online: flag marked when the subsystem is inserted.
-+ * @weight: cgroup weight.
-+ * @ioprio: cgroup ioprio.
-+ * @ioprio_class: cgroup ioprio_class.
-+ * @lock: spinlock that protects @ioprio, @ioprio_class and @group_data.
-+ * @group_data: list containing the bfq_group belonging to this cgroup.
-+ *
-+ * @group_data is accessed using RCU, with @lock protecting the updates,
-+ * @ioprio and @ioprio_class are protected by @lock.
-+ */
-+struct bfqio_cgroup {
-+	struct cgroup_subsys_state css;
-+	bool online;
-+
-+	unsigned short weight, ioprio, ioprio_class;
-+
-+	spinlock_t lock;
-+	struct hlist_head group_data;
-+};
-+#else
-+struct bfq_group {
-+	struct bfq_sched_data sched_data;
-+
-+	struct bfq_queue *async_bfqq[2][IOPRIO_BE_NR];
-+	struct bfq_queue *async_idle_bfqq;
-+};
-+#endif
-+
-+static inline struct bfq_service_tree *
-+bfq_entity_service_tree(struct bfq_entity *entity)
-+{
-+	struct bfq_sched_data *sched_data = entity->sched_data;
-+	unsigned int idx = entity->ioprio_class - 1;
-+
-+	BUG_ON(idx >= BFQ_IOPRIO_CLASSES);
-+	BUG_ON(sched_data == NULL);
-+
-+	return sched_data->service_tree + idx;
-+}
-+
-+static inline struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic,
-+					    int is_sync)
-+{
-+	return bic->bfqq[!!is_sync];
-+}
-+
-+static inline void bic_set_bfqq(struct bfq_io_cq *bic,
-+				struct bfq_queue *bfqq, int is_sync)
-+{
-+	bic->bfqq[!!is_sync] = bfqq;
-+}
-+
-+static inline struct bfq_data *bic_to_bfqd(struct bfq_io_cq *bic)
-+{
-+	return bic->icq.q->elevator->elevator_data;
-+}
-+
-+/**
-+ * bfq_get_bfqd_locked - get a lock to a bfqd using a RCU protected pointer.
-+ * @ptr: a pointer to a bfqd.
-+ * @flags: storage for the flags to be saved.
-+ *
-+ * This function allows bfqg->bfqd to be protected by the
-+ * queue lock of the bfqd they reference; the pointer is dereferenced
-+ * under RCU, so the storage for bfqd is assured to be safe as long
-+ * as the RCU read side critical section does not end.  After the
-+ * bfqd->queue->queue_lock is taken the pointer is rechecked, to be
-+ * sure that no other writer accessed it.  If we raced with a writer,
-+ * the function returns NULL, with the queue unlocked, otherwise it
-+ * returns the dereferenced pointer, with the queue locked.
-+ */
-+static inline struct bfq_data *bfq_get_bfqd_locked(void **ptr,
-+						   unsigned long *flags)
-+{
-+	struct bfq_data *bfqd;
-+
-+	rcu_read_lock();
-+	bfqd = rcu_dereference(*(struct bfq_data **)ptr);
-+
-+	if (bfqd != NULL) {
-+		spin_lock_irqsave(bfqd->queue->queue_lock, *flags);
-+		if (*ptr == bfqd)
-+			goto out;
-+		spin_unlock_irqrestore(bfqd->queue->queue_lock, *flags);
-+	}
-+
-+	bfqd = NULL;
-+out:
-+	rcu_read_unlock();
-+	return bfqd;
-+}
-+
-+static inline void bfq_put_bfqd_unlock(struct bfq_data *bfqd,
-+				       unsigned long *flags)
-+{
-+	spin_unlock_irqrestore(bfqd->queue->queue_lock, *flags);
-+}
-+
-+static void bfq_changed_ioprio(struct bfq_io_cq *bic);
-+static void bfq_put_queue(struct bfq_queue *bfqq);
-+static void bfq_dispatch_insert(struct request_queue *q, struct request *rq);
-+static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd,
-+				       struct bfq_group *bfqg, int is_sync,
-+				       struct bfq_io_cq *bic, gfp_t gfp_mask);
-+static void bfq_end_raising_async_queues(struct bfq_data *bfqd,
-+					 struct bfq_group *bfqg);
-+static void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg);
-+static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq);
-+#endif
--- 
-1.9.0
-

Deleted: genpatches-2.6/trunk/3.15/5003_BFQ-3-block-bfq-add-Early-Queue-Merge-EQM-to-BFQ-v7r2-for-3.14.0.patch
===================================================================
--- genpatches-2.6/trunk/3.15/5003_BFQ-3-block-bfq-add-Early-Queue-Merge-EQM-to-BFQ-v7r2-for-3.14.0.patch	2014-05-05 14:22:27 UTC (rev 2771)
+++ genpatches-2.6/trunk/3.15/5003_BFQ-3-block-bfq-add-Early-Queue-Merge-EQM-to-BFQ-v7r2-for-3.14.0.patch	2014-05-05 14:28:48 UTC (rev 2772)
@@ -1,1038 +0,0 @@
-From 4fbeda28a90d7fccd05d28a89d9fc409b2344e0a Mon Sep 17 00:00:00 2001
-From: Mauro Andreolini <mauro.andreolini@×××××××.it>
-Date: Fri, 14 Feb 2014 12:52:49 +0100
-Subject: [PATCH 3/3] block, bfq: add Early Queue Merge (EQM) to BFQ-v7r2 for
- 3.14.0
-
-A set of processes may happen  to  perform interleaved reads, i.e., requests
-whose union would give rise to a  sequential read  pattern.  There are two
-typical  cases: in the first  case,   processes  read  fixed-size chunks of
-data at a fixed distance from each other, while in the second case processes
-may read variable-size chunks at  variable distances. The latter case occurs
-for  example with  KVM, which  splits the  I/O generated  by the  guest into
-multiple chunks,  and lets these chunks  be served by a  pool of cooperating
-processes,  iteratively  assigning  the  next  chunk of  I/O  to  the first
-available  process. CFQ  uses actual  queue merging  for the  first type of
-rocesses, whereas it  uses preemption to get a sequential  read pattern out
-of the read requests  performed by the second type of  processes. In the end
-it uses  two different  mechanisms to  achieve the  same goal: boosting the
-throughput with interleaved I/O.
-
-This patch introduces  Early Queue Merge (EQM), a unified mechanism to get a
-sequential  read pattern  with both  types of  processes. The  main idea is
-checking newly arrived requests against the next request of the active queue
-both in case of actual request insert and in case of request merge. By doing
-so, both the types of processes can be handled by just merging their queues.
-EQM is  then simpler and  more compact than the  pair of mechanisms used in
-CFQ.
-
-Finally, EQM  also preserves the  typical low-latency properties of BFQ, by
-properly restoring the weight-raising state of  a queue when it gets back to
-a non-merged state.
-
-Signed-off-by: Mauro Andreolini <mauro.andreolini@×××××××.it>
-Signed-off-by: Arianna Avanzini <avanzini.arianna@×××××.com>
-Reviewed-by: Paolo Valente <paolo.valente@×××××××.it>
----
- block/bfq-iosched.c | 657 ++++++++++++++++++++++++++++++++++++----------------
- block/bfq-sched.c   |  28 ---
- block/bfq.h         |  20 +-
- 3 files changed, 476 insertions(+), 229 deletions(-)
-
-diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
-index f5f71e4..0d3503d 100644
---- a/block/bfq-iosched.c
-+++ b/block/bfq-iosched.c
-@@ -445,6 +445,46 @@ static inline unsigned int bfq_wrais_duration(struct bfq_data *bfqd)
- 	return dur;
- }
- 
-+static inline void
-+bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_io_cq *bic)
-+{
-+	if (bic->saved_idle_window)
-+		bfq_mark_bfqq_idle_window(bfqq);
-+	else
-+		bfq_clear_bfqq_idle_window(bfqq);
-+	if (bic->raising_time_left && bfqq->bfqd->low_latency) {
-+		/*
-+		 * Start a weight raising period with the duration given by
-+		 * the raising_time_left snapshot.
-+		 */
-+		if (bfq_bfqq_busy(bfqq))
-+			bfqq->bfqd->raised_busy_queues++;
-+		bfqq->raising_coeff = bfqq->bfqd->bfq_raising_coeff;
-+		bfqq->raising_cur_max_time = bic->raising_time_left;
-+		bfqq->last_rais_start_finish = jiffies;
-+		bfqq->entity.ioprio_changed = 1;
-+	}
-+	/*
-+	 * Clear raising_time_left to prevent bfq_bfqq_save_state() from
-+	 * getting confused about the queue's need of a weight-raising
-+	 * period.
-+	 */
-+	bic->raising_time_left = 0;
-+}
-+
-+/*
-+ * Must be called with the queue_lock held.
-+ */
-+static int bfqq_process_refs(struct bfq_queue *bfqq)
-+{
-+	int process_refs, io_refs;
-+
-+	io_refs = bfqq->allocated[READ] + bfqq->allocated[WRITE];
-+	process_refs = atomic_read(&bfqq->ref) - io_refs - bfqq->entity.on_st;
-+	BUG_ON(process_refs < 0);
-+	return process_refs;
-+}
-+
- static void bfq_add_rq_rb(struct request *rq)
- {
- 	struct bfq_queue *bfqq = RQ_BFQQ(rq);
-@@ -486,12 +526,20 @@ static void bfq_add_rq_rb(struct request *rq)
- 		if (!bfqd->low_latency)
- 			goto add_bfqq_busy;
- 
-+		if (bfq_bfqq_just_split(bfqq))
-+			goto set_ioprio_changed;
-+
- 		/*
--		 * If the queue is not being boosted and has been idle
--		 * for enough time, start a weight-raising period
-+		 * If the queue:
-+		 * - is not being boosted,
-+		 * - has been idle for enough time,
-+		 * - is not a sync queue or is linked to a bfq_io_cq (it is
-+		 *   shared "for its nature" or it is not shared and its
-+		 *   requests have not been redirected to a shared queue)
-+		 * start a weight-raising period.
- 		 */
--		if (old_raising_coeff == 1 &&
--		    (idle_for_long_time || soft_rt)) {
-+		if (old_raising_coeff == 1 && (idle_for_long_time || soft_rt) &&
-+		    (!bfq_bfqq_sync(bfqq) || bfqq->bic != NULL)) {
- 			bfqq->raising_coeff = bfqd->bfq_raising_coeff;
- 			if (idle_for_long_time)
- 				bfqq->raising_cur_max_time =
-@@ -574,6 +622,7 @@ static void bfq_add_rq_rb(struct request *rq)
- 					bfqd->bfq_raising_rt_max_time;
- 			}
- 		}
-+set_ioprio_changed:
- 		if (old_raising_coeff != bfqq->raising_coeff)
- 			entity->ioprio_changed = 1;
- add_bfqq_busy:
-@@ -756,90 +805,35 @@ static void bfq_end_raising(struct bfq_data *bfqd)
- 	spin_unlock_irq(bfqd->queue->queue_lock);
- }
- 
--static int bfq_allow_merge(struct request_queue *q, struct request *rq,
--			   struct bio *bio)
--{
--	struct bfq_data *bfqd = q->elevator->elevator_data;
--	struct bfq_io_cq *bic;
--	struct bfq_queue *bfqq;
--
--	/*
--	 * Disallow merge of a sync bio into an async request.
--	 */
--	if (bfq_bio_sync(bio) && !rq_is_sync(rq))
--		return 0;
--
--	/*
--	 * Lookup the bfqq that this bio will be queued with. Allow
--	 * merge only if rq is queued there.
--	 * Queue lock is held here.
--	 */
--	bic = bfq_bic_lookup(bfqd, current->io_context);
--	if (bic == NULL)
--		return 0;
--
--	bfqq = bic_to_bfqq(bic, bfq_bio_sync(bio));
--	return bfqq == RQ_BFQQ(rq);
--}
--
--static void __bfq_set_in_service_queue(struct bfq_data *bfqd,
--				       struct bfq_queue *bfqq)
--{
--	if (bfqq != NULL) {
--		bfq_mark_bfqq_must_alloc(bfqq);
--		bfq_mark_bfqq_budget_new(bfqq);
--		bfq_clear_bfqq_fifo_expire(bfqq);
--
--		bfqd->budgets_assigned = (bfqd->budgets_assigned*7 + 256) / 8;
--
--		bfq_log_bfqq(bfqd, bfqq,
--			     "set_in_service_queue, cur-budget = %lu",
--			     bfqq->entity.budget);
--	}
--
--	bfqd->in_service_queue = bfqq;
--}
--
--/*
-- * Get and set a new queue for service.
-- */
--static struct bfq_queue *bfq_set_in_service_queue(struct bfq_data *bfqd,
--						  struct bfq_queue *bfqq)
-+static inline sector_t bfq_io_struct_pos(void *io_struct, bool request)
- {
--	if (!bfqq)
--		bfqq = bfq_get_next_queue(bfqd);
-+	if (request)
-+		return blk_rq_pos(io_struct);
- 	else
--		bfq_get_next_queue_forced(bfqd, bfqq);
--
--	__bfq_set_in_service_queue(bfqd, bfqq);
--	return bfqq;
-+		return ((struct bio *)io_struct)->bi_iter.bi_sector;
- }
- 
--static inline sector_t bfq_dist_from_last(struct bfq_data *bfqd,
--					  struct request *rq)
-+static inline sector_t bfq_dist_from(sector_t pos1,
-+				     sector_t pos2)
- {
--	if (blk_rq_pos(rq) >= bfqd->last_position)
--		return blk_rq_pos(rq) - bfqd->last_position;
-+	if (pos1 >= pos2)
-+		return pos1 - pos2;
- 	else
--		return bfqd->last_position - blk_rq_pos(rq);
-+		return pos2 - pos1;
- }
- 
--/*
-- * Return true if bfqq has no request pending and rq is close enough to
-- * bfqd->last_position, or if rq is closer to bfqd->last_position than
-- * bfqq->next_rq
-- */
--static inline int bfq_rq_close(struct bfq_data *bfqd, struct request *rq)
-+static inline int bfq_rq_close_to_sector(void *io_struct, bool request,
-+					 sector_t sector)
- {
--	return bfq_dist_from_last(bfqd, rq) <= BFQQ_SEEK_THR;
-+	return bfq_dist_from(bfq_io_struct_pos(io_struct, request), sector) <=
-+	       BFQQ_SEEK_THR;
- }
- 
--static struct bfq_queue *bfqq_close(struct bfq_data *bfqd)
-+static struct bfq_queue *bfqq_close(struct bfq_data *bfqd, sector_t sector)
- {
- 	struct rb_root *root = &bfqd->rq_pos_tree;
- 	struct rb_node *parent, *node;
- 	struct bfq_queue *__bfqq;
--	sector_t sector = bfqd->last_position;
- 
- 	if (RB_EMPTY_ROOT(root))
- 		return NULL;
-@@ -858,7 +852,7 @@ static struct bfq_queue *bfqq_close(struct bfq_data *bfqd)
- 	 * position).
- 	 */
- 	__bfqq = rb_entry(parent, struct bfq_queue, pos_node);
--	if (bfq_rq_close(bfqd, __bfqq->next_rq))
-+	if (bfq_rq_close_to_sector(__bfqq->next_rq, true, sector))
- 		return __bfqq;
- 
- 	if (blk_rq_pos(__bfqq->next_rq) < sector)
-@@ -869,7 +863,7 @@ static struct bfq_queue *bfqq_close(struct bfq_data *bfqd)
- 		return NULL;
- 
- 	__bfqq = rb_entry(node, struct bfq_queue, pos_node);
--	if (bfq_rq_close(bfqd, __bfqq->next_rq))
-+	if (bfq_rq_close_to_sector(__bfqq->next_rq, true, sector))
- 		return __bfqq;
- 
- 	return NULL;
-@@ -878,14 +872,12 @@ static struct bfq_queue *bfqq_close(struct bfq_data *bfqd)
- /*
-  * bfqd - obvious
-  * cur_bfqq - passed in so that we don't decide that the current queue
-- *            is closely cooperating with itself.
-- *
-- * We are assuming that cur_bfqq has dispatched at least one request,
-- * and that bfqd->last_position reflects a position on the disk associated
-- * with the I/O issued by cur_bfqq.
-+ *            is closely cooperating with itself
-+ * sector - used as a reference point to search for a close queue
-  */
- static struct bfq_queue *bfq_close_cooperator(struct bfq_data *bfqd,
--					      struct bfq_queue *cur_bfqq)
-+					      struct bfq_queue *cur_bfqq,
-+					      sector_t sector)
- {
- 	struct bfq_queue *bfqq;
- 
-@@ -905,7 +897,7 @@ static struct bfq_queue *bfq_close_cooperator(struct bfq_data *bfqd,
- 	 * working closely on the same area of the disk. In that case,
- 	 * we can group them together and don't waste time idling.
- 	 */
--	bfqq = bfqq_close(bfqd);
-+	bfqq = bfqq_close(bfqd, sector);
- 	if (bfqq == NULL || bfqq == cur_bfqq)
- 		return NULL;
- 
-@@ -932,6 +924,282 @@ static struct bfq_queue *bfq_close_cooperator(struct bfq_data *bfqd,
- 	return bfqq;
- }
- 
-+static struct bfq_queue *
-+bfq_setup_merge(struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
-+{
-+	int process_refs, new_process_refs;
-+	struct bfq_queue *__bfqq;
-+
-+	/*
-+	 * If there are no process references on the new_bfqq, then it is
-+	 * unsafe to follow the ->new_bfqq chain as other bfqq's in the chain
-+	 * may have dropped their last reference (not just their last process
-+	 * reference).
-+	 */
-+	if (!bfqq_process_refs(new_bfqq))
-+		return NULL;
-+
-+	/* Avoid a circular list and skip interim queue merges. */
-+	while ((__bfqq = new_bfqq->new_bfqq)) {
-+		if (__bfqq == bfqq)
-+			return NULL;
-+		new_bfqq = __bfqq;
-+	}
-+
-+	process_refs = bfqq_process_refs(bfqq);
-+	new_process_refs = bfqq_process_refs(new_bfqq);
-+	/*
-+	 * If the process for the bfqq has gone away, there is no
-+	 * sense in merging the queues.
-+	 */
-+	if (process_refs == 0 || new_process_refs == 0)
-+		return NULL;
-+
-+	bfq_log_bfqq(bfqq->bfqd, bfqq, "scheduling merge with queue %d",
-+		new_bfqq->pid);
-+
-+	/*
-+	 * Merging is just a redirection: the requests of the process owning
-+	 * one of the two queues are redirected to the other queue. The latter
-+	 * queue, in its turn, is set as shared if this is the first time that
-+	 * the requests of some process are redirected to it.
-+	 *
-+	 * We redirect bfqq to new_bfqq and not the opposite, because we
-+	 * are in the context of the process owning bfqq, hence we have the
-+	 * io_cq of this process. So we can immediately configure this io_cq
-+	 * to redirect the requests of the process to new_bfqq.
-+	 *
-+	 * NOTE, even if new_bfqq coincides with the in-service queue, the
-+	 * io_cq of new_bfqq is not available, because, if the in-service queue
-+	 * is shared, bfqd->in_service_bic may not point to the io_cq of the
-+	 * in-service queue.
-+	 * Redirecting the requests of the process owning bfqq to the currently
-+	 * in-service queue is in any case the best option, as we feed the
-+	 * in-service queue with new requests close to the last request served
-+	 * and, by doing so, hopefully increase the throughput.
-+	 */
-+	bfqq->new_bfqq = new_bfqq;
-+	atomic_add(process_refs, &new_bfqq->ref);
-+	return new_bfqq;
-+}
-+
-+/*
-+ * Attempt to schedule a merge of bfqq with the currently in-service queue or
-+ * with a close queue among the scheduled queues.
-+ * Return NULL if no merge was scheduled, a pointer to the shared bfq_queue
-+ * structure otherwise.
-+ */
-+static struct bfq_queue *
-+bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq,
-+		     void *io_struct, bool request)
-+{
-+	struct bfq_queue *in_service_bfqq, *new_bfqq;
-+
-+	if (bfqq->new_bfqq)
-+		return bfqq->new_bfqq;
-+
-+	if (!io_struct)
-+		return NULL;
-+
-+	in_service_bfqq = bfqd->in_service_queue;
-+
-+	if (in_service_bfqq == NULL || in_service_bfqq == bfqq ||
-+	    !bfqd->in_service_bic)
-+		goto check_scheduled;
-+
-+	if (bfq_class_idle(in_service_bfqq) || bfq_class_idle(bfqq))
-+		goto check_scheduled;
-+
-+	if (bfq_class_rt(in_service_bfqq) != bfq_class_rt(bfqq))
-+		goto check_scheduled;
-+
-+	if (in_service_bfqq->entity.parent != bfqq->entity.parent)
-+		goto check_scheduled;
-+
-+	if (bfq_rq_close_to_sector(io_struct, request, bfqd->last_position) &&
-+	    bfq_bfqq_sync(in_service_bfqq) && bfq_bfqq_sync(bfqq)) {
-+		new_bfqq = bfq_setup_merge(bfqq, in_service_bfqq);
-+		if (new_bfqq != NULL)
-+			return new_bfqq; /* Merge with the in-service queue */
-+	}
-+
-+	/*
-+	 * Check whether there is a cooperator among currently scheduled
-+	 * queues. The only thing we need is that the bio/request is not
-+	 * NULL, as we need it to establish whether a cooperator exists.
-+	 */
-+check_scheduled:
-+	new_bfqq = bfq_close_cooperator(bfqd, bfqq,
-+					bfq_io_struct_pos(io_struct, request));
-+	if (new_bfqq)
-+		return bfq_setup_merge(bfqq, new_bfqq);
-+
-+	return NULL;
-+}
-+
-+static inline void
-+bfq_bfqq_save_state(struct bfq_queue *bfqq)
-+{
-+	/*
-+	 * If bfqq->bic == NULL, the queue is already shared or its requests
-+	 * have already been redirected to a shared queue; both idle window
-+	 * and weight raising state have already been saved. Do nothing.
-+	 */
-+	if (bfqq->bic == NULL)
-+		return;
-+	if (bfqq->bic->raising_time_left)
-+		/*
-+		 * This is the queue of a just-started process, and would
-+		 * deserve weight raising: we set raising_time_left to the full
-+		 * weight-raising duration to trigger weight-raising when and
-+		 * if the queue is split and the first request of the queue
-+		 * is enqueued.
-+		 */
-+		bfqq->bic->raising_time_left = bfq_wrais_duration(bfqq->bfqd);
-+	else if (bfqq->raising_coeff > 1) {
-+		unsigned long wrais_duration =
-+			jiffies - bfqq->last_rais_start_finish;
-+		/*
-+		 * It may happen that a queue's weight raising period lasts
-+		 * longer than its raising_cur_max_time, as weight raising is
-+		 * handled only when a request is enqueued or dispatched (it
-+		 * does not use any timer). If the weight raising period is
-+		 * about to end, don't save it.
-+		 */
-+		if (bfqq->raising_cur_max_time <= wrais_duration)
-+			bfqq->bic->raising_time_left = 0;
-+		else
-+			bfqq->bic->raising_time_left =
-+				bfqq->raising_cur_max_time - wrais_duration;
-+		/*
-+		 * The bfq_queue is becoming shared or the requests of the
-+		 * process owning the queue are being redirected to a shared
-+		 * queue. Stop the weight raising period of the queue, as in
-+		 * both cases it should not be owned by an interactive or soft
-+		 * real-time application.
-+		 */
-+		bfq_bfqq_end_raising(bfqq);
-+	} else
-+		bfqq->bic->raising_time_left = 0;
-+	bfqq->bic->saved_idle_window = bfq_bfqq_idle_window(bfqq);
-+}
-+
-+static inline void
-+bfq_get_bic_reference(struct bfq_queue *bfqq)
-+{
-+	/*
-+	 * If bfqq->bic has a non-NULL value, the bic to which it belongs
-+	 * is about to begin using a shared bfq_queue.
-+	 */
-+	if (bfqq->bic)
-+		atomic_long_inc(&bfqq->bic->icq.ioc->refcount);
-+}
-+
-+static void
-+bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
-+		struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
-+{
-+	bfq_log_bfqq(bfqd, bfqq, "merging with queue %lu",
-+		(long unsigned)new_bfqq->pid);
-+	/* Save weight raising and idle window of the merged queues */
-+	bfq_bfqq_save_state(bfqq);
-+	bfq_bfqq_save_state(new_bfqq);
-+	/*
-+	 * Grab a reference to the bic, to prevent it from being destroyed
-+	 * before being possibly touched by a bfq_split_bfqq().
-+	 */
-+	bfq_get_bic_reference(bfqq);
-+	bfq_get_bic_reference(new_bfqq);
-+	/* Merge queues (that is, let bic redirect its requests to new_bfqq) */
-+	bic_set_bfqq(bic, new_bfqq, 1);
-+	bfq_mark_bfqq_coop(new_bfqq);
-+	/*
-+	 * new_bfqq now belongs to at least two bics (it is a shared queue): set
-+	 * new_bfqq->bic to NULL. bfqq either:
-+	 * - does not belong to any bic any more, and hence bfqq->bic must
-+	 *   be set to NULL, or
-+	 * - is a queue whose owning bics have already been redirected to a
-+	 *   different queue, hence the queue is destined to not belong to any
-+	 *   bic soon and bfqq->bic is already NULL (therefore the next
-+	 *   assignment causes no harm).
-+	 */
-+	new_bfqq->bic = NULL;
-+	bfqq->bic = NULL;
-+	bfq_put_queue(bfqq);
-+}
-+
-+static int bfq_allow_merge(struct request_queue *q, struct request *rq,
-+			   struct bio *bio)
-+{
-+	struct bfq_data *bfqd = q->elevator->elevator_data;
-+	struct bfq_io_cq *bic;
-+	struct bfq_queue *bfqq, *new_bfqq;
-+
-+	/*
-+	 * Disallow merge of a sync bio into an async request.
-+	 */
-+	if (bfq_bio_sync(bio) && !rq_is_sync(rq))
-+		return 0;
-+
-+	/*
-+	 * Lookup the bfqq that this bio will be queued with. Allow
-+	 * merge only if rq is queued there.
-+	 * Queue lock is held here.
-+	 */
-+	bic = bfq_bic_lookup(bfqd, current->io_context);
-+	if (bic == NULL)
-+		return 0;
-+
-+	bfqq = bic_to_bfqq(bic, bfq_bio_sync(bio));
-+	/*
-+	 * We take advantage of this function to perform an early merge
-+	 * of the queues of possible cooperating processes.
-+	 */
-+	if (bfqq != NULL) {
-+		new_bfqq = bfq_setup_cooperator(bfqd, bfqq, bio, false);
-+		if (new_bfqq != NULL) {
-+			bfq_merge_bfqqs(bfqd, bic, bfqq, new_bfqq);
-+			/*
-+			 * If we get here, the bio will be queued in the shared
-+			 * queue, i.e., new_bfqq, so use new_bfqq to decide
-+			 * whether bio and rq can be merged.
-+			 */
-+			bfqq = new_bfqq;
-+		}
-+	}
-+
-+	return bfqq == RQ_BFQQ(rq);
-+}
-+
-+static void __bfq_set_in_service_queue(struct bfq_data *bfqd,
-+				       struct bfq_queue *bfqq)
-+{
-+	if (bfqq != NULL) {
-+		bfq_mark_bfqq_must_alloc(bfqq);
-+		bfq_mark_bfqq_budget_new(bfqq);
-+		bfq_clear_bfqq_fifo_expire(bfqq);
-+
-+		bfqd->budgets_assigned = (bfqd->budgets_assigned*7 + 256) / 8;
-+
-+		bfq_log_bfqq(bfqd, bfqq,
-+			     "set_in_service_queue, cur-budget = %lu",
-+			     bfqq->entity.budget);
-+	}
-+
-+	bfqd->in_service_queue = bfqq;
-+}
-+
-+/*
-+ * Get and set a new queue for service.
-+ */
-+static struct bfq_queue *bfq_set_in_service_queue(struct bfq_data *bfqd)
-+{
-+	struct bfq_queue *bfqq = bfq_get_next_queue(bfqd);
-+
-+	__bfq_set_in_service_queue(bfqd, bfqq);
-+	return bfqq;
-+}
-+
- /*
-  * If enough samples have been computed, return the current max budget
-  * stored in bfqd, which is dynamically updated according to the
-@@ -1079,63 +1347,6 @@ static struct request *bfq_check_fifo(struct bfq_queue *bfqq)
- 	return rq;
- }
- 
--/*
-- * Must be called with the queue_lock held.
-- */
--static int bfqq_process_refs(struct bfq_queue *bfqq)
--{
--	int process_refs, io_refs;
--
--	io_refs = bfqq->allocated[READ] + bfqq->allocated[WRITE];
--	process_refs = atomic_read(&bfqq->ref) - io_refs - bfqq->entity.on_st;
--	BUG_ON(process_refs < 0);
--	return process_refs;
--}
--
--static void bfq_setup_merge(struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
--{
--	int process_refs, new_process_refs;
--	struct bfq_queue *__bfqq;
--
--	/*
--	 * If there are no process references on the new_bfqq, then it is
--	 * unsafe to follow the ->new_bfqq chain as other bfqq's in the chain
--	 * may have dropped their last reference (not just their last process
--	 * reference).
--	 */
--	if (!bfqq_process_refs(new_bfqq))
--		return;
--
--	/* Avoid a circular list and skip interim queue merges. */
--	while ((__bfqq = new_bfqq->new_bfqq)) {
--		if (__bfqq == bfqq)
--			return;
--		new_bfqq = __bfqq;
--	}
--
--	process_refs = bfqq_process_refs(bfqq);
--	new_process_refs = bfqq_process_refs(new_bfqq);
--	/*
--	 * If the process for the bfqq has gone away, there is no
--	 * sense in merging the queues.
--	 */
--	if (process_refs == 0 || new_process_refs == 0)
--		return;
--
--	/*
--	 * Merge in the direction of the lesser amount of work.
--	 */
--	if (new_process_refs >= process_refs) {
--		bfqq->new_bfqq = new_bfqq;
--		atomic_add(process_refs, &new_bfqq->ref);
--	} else {
--		new_bfqq->new_bfqq = bfqq;
--		atomic_add(new_process_refs, &bfqq->ref);
--	}
--	bfq_log_bfqq(bfqq->bfqd, bfqq, "scheduling merge with queue %d",
--		new_bfqq->pid);
--}
--
- static inline unsigned long bfq_bfqq_budget_left(struct bfq_queue *bfqq)
- {
- 	struct bfq_entity *entity = &bfqq->entity;
-@@ -1729,7 +1940,7 @@ static inline bool bfq_bfqq_must_idle(struct bfq_queue *bfqq)
-  */
- static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd)
- {
--	struct bfq_queue *bfqq, *new_bfqq = NULL;
-+	struct bfq_queue *bfqq;
- 	struct request *next_rq;
- 	enum bfqq_expiration reason = BFQ_BFQQ_BUDGET_TIMEOUT;
- 
-@@ -1739,17 +1950,6 @@ static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd)
- 
- 	bfq_log_bfqq(bfqd, bfqq, "select_queue: already in-service queue");
- 
--	/*
--         * If another queue has a request waiting within our mean seek
--         * distance, let it run. The expire code will check for close
--         * cooperators and put the close queue at the front of the
--         * service tree. If possible, merge the expiring queue with the
--         * new bfqq.
--         */
--        new_bfqq = bfq_close_cooperator(bfqd, bfqq);
--        if (new_bfqq != NULL && bfqq->new_bfqq == NULL)
--                bfq_setup_merge(bfqq, new_bfqq);
--
- 	if (bfq_may_expire_for_budg_timeout(bfqq) &&
- 	    !timer_pending(&bfqd->idle_slice_timer) &&
- 	    !bfq_bfqq_must_idle(bfqq))
-@@ -1786,36 +1986,26 @@ static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd)
- 				bfq_clear_bfqq_wait_request(bfqq);
- 				del_timer(&bfqd->idle_slice_timer);
- 			}
--			if (new_bfqq == NULL)
--				goto keep_queue;
--			else
--				goto expire;
-+			goto keep_queue;
- 		}
- 	}
- 
- 	/*
--	 * No requests pending.  If the in-service queue has no cooperator and
--	 * still has requests in flight (possibly waiting for a completion)
--	 * or is idling for a new request, then keep it.
-+	 * No requests pending.  If the in-service queue still has requests in
-+	 * flight (possibly waiting for a completion) or is idling for a new
-+	 * request, then keep it.
- 	 */
--	if (new_bfqq == NULL && (timer_pending(&bfqd->idle_slice_timer) ||
--	    (bfqq->dispatched != 0 && bfq_bfqq_must_not_expire(bfqq)))) {
-+	if (timer_pending(&bfqd->idle_slice_timer) ||
-+	    (bfqq->dispatched != 0 && bfq_bfqq_must_not_expire(bfqq))) {
- 		bfqq = NULL;
- 		goto keep_queue;
--	} else if (new_bfqq != NULL && timer_pending(&bfqd->idle_slice_timer)) {
--		/*
--		 * Expiring the queue because there is a close cooperator,
--		 * cancel timer.
--		 */
--		bfq_clear_bfqq_wait_request(bfqq);
--		del_timer(&bfqd->idle_slice_timer);
- 	}
- 
- 	reason = BFQ_BFQQ_NO_MORE_REQUESTS;
- expire:
- 	bfq_bfqq_expire(bfqd, bfqq, 0, reason);
- new_queue:
--	bfqq = bfq_set_in_service_queue(bfqd, new_bfqq);
-+	bfqq = bfq_set_in_service_queue(bfqd);
- 	bfq_log(bfqd, "select_queue: new queue %d returned",
- 		bfqq != NULL ? bfqq->pid : 0);
- keep_queue:
-@@ -1825,9 +2015,8 @@ keep_queue:
- static void bfq_update_raising_data(struct bfq_data *bfqd,
- 				    struct bfq_queue *bfqq)
- {
-+	struct bfq_entity *entity = &bfqq->entity;
- 	if (bfqq->raising_coeff > 1) { /* queue is being boosted */
--		struct bfq_entity *entity = &bfqq->entity;
--
- 		bfq_log_bfqq(bfqd, bfqq,
- 			"raising period dur %u/%u msec, "
- 			"old raising coeff %u, w %d(%d)",
-@@ -1844,7 +2033,7 @@ static void bfq_update_raising_data(struct bfq_data *bfqd,
- 			"WARN: pending prio change");
- 		/*
- 		 * If too much time has elapsed from the beginning
--		 * of this weight-raising, stop it.
-+		 * of this weight-raising period, stop it.
- 		 */
- 		if (time_is_before_jiffies(bfqq->last_rais_start_finish +
- 					   bfqq->raising_cur_max_time)) {
-@@ -1856,11 +2045,13 @@ static void bfq_update_raising_data(struct bfq_data *bfqd,
- 				     jiffies_to_msecs(bfqq->
- 					raising_cur_max_time));
- 			bfq_bfqq_end_raising(bfqq);
--			__bfq_entity_update_weight_prio(
--				bfq_entity_service_tree(entity),
--				entity);
- 		}
- 	}
-+	/* Update weight both if it must be raised and if it must be lowered */
-+	if ((entity->weight > entity->orig_weight) != (bfqq->raising_coeff > 1))
-+		__bfq_entity_update_weight_prio(
-+			bfq_entity_service_tree(entity),
-+			entity);
- }
- 
- /*
-@@ -2101,6 +2292,25 @@ static void bfq_init_icq(struct io_cq *icq)
- 	struct bfq_io_cq *bic = icq_to_bic(icq);
- 
- 	bic->ttime.last_end_request = jiffies;
-+	/*
-+	 * A newly created bic indicates that the process has just
-+	 * started doing I/O, and is probably mapping into memory its
-+	 * executable and libraries: it definitely needs weight raising.
-+	 * There is however the possibility that the process performs,
-+	 * for a while, I/O close to some other process. EQM intercepts
-+	 * this behavior and may merge the queue corresponding to the
-+	 * process  with some other queue, BEFORE the weight of the queue
-+	 * is raised. Merged queues are not weight-raised (they are assumed
-+	 * to belong to processes that benefit only from high throughput).
-+	 * If the merge is basically the consequence of an accident, then
-+	 * the queue will be split soon and will get back its old weight.
-+	 * It is then important to write down somewhere that this queue
-+	 * does need weight raising, even if it did not make it to get its
-+	 * weight raised before being merged. To this purpose, we overload
-+	 * the field raising_time_left and assign 1 to it, to mark the queue
-+	 * as needing weight raising.
-+	 */
-+	bic->raising_time_left = 1;
- }
- 
- static void bfq_exit_icq(struct io_cq *icq)
-@@ -2114,6 +2324,13 @@ static void bfq_exit_icq(struct io_cq *icq)
- 	}
- 
- 	if (bic->bfqq[BLK_RW_SYNC]) {
-+		/*
-+		 * If the bic is using a shared queue, put the reference
-+		 * taken on the io_context when the bic started using a
-+		 * shared bfq_queue.
-+		 */
-+		if (bfq_bfqq_coop(bic->bfqq[BLK_RW_SYNC]))
-+			put_io_context(icq->ioc);
- 		bfq_exit_bfqq(bfqd, bic->bfqq[BLK_RW_SYNC]);
- 		bic->bfqq[BLK_RW_SYNC] = NULL;
- 	}
-@@ -2405,6 +2622,10 @@ static void bfq_update_idle_window(struct bfq_data *bfqd,
- 	if (!bfq_bfqq_sync(bfqq) || bfq_class_idle(bfqq))
- 		return;
- 
-+	/* Idle window just restored, statistics are meaningless. */
-+	if (bfq_bfqq_just_split(bfqq))
-+		return;
-+
- 	enable_idle = bfq_bfqq_idle_window(bfqq);
- 
- 	if (atomic_read(&bic->icq.ioc->active_ref) == 0 ||
-@@ -2445,6 +2666,7 @@ static void bfq_rq_enqueued(struct bfq_data *bfqd, struct bfq_queue *bfqq,
- 	if (bfqq->entity.service > bfq_max_budget(bfqd) / 8 ||
- 	    !BFQQ_SEEKY(bfqq))
- 		bfq_update_idle_window(bfqd, bfqq, bic);
-+	bfq_clear_bfqq_just_split(bfqq);
- 
- 	bfq_log_bfqq(bfqd, bfqq,
- 		     "rq_enqueued: idle_window=%d (seeky %d, mean %llu)",
-@@ -2505,13 +2727,48 @@ static void bfq_rq_enqueued(struct bfq_data *bfqd, struct bfq_queue *bfqq,
- static void bfq_insert_request(struct request_queue *q, struct request *rq)
- {
- 	struct bfq_data *bfqd = q->elevator->elevator_data;
--	struct bfq_queue *bfqq = RQ_BFQQ(rq);
-+	struct bfq_queue *bfqq = RQ_BFQQ(rq), *new_bfqq;
- 
- 	assert_spin_locked(bfqd->queue->queue_lock);
-+
-+	/*
-+	 * An unplug may trigger a requeue of a request from the device
-+	 * driver: make sure we are in process context while trying to
-+	 * merge two bfq_queues.
-+	 */
-+	if (!in_interrupt()) {
-+		new_bfqq = bfq_setup_cooperator(bfqd, bfqq, rq, true);
-+		if (new_bfqq != NULL) {
-+			if (bic_to_bfqq(RQ_BIC(rq), 1) != bfqq)
-+				new_bfqq = bic_to_bfqq(RQ_BIC(rq), 1);
-+			/*
-+			 * Release the request's reference to the old bfqq
-+			 * and make sure one is taken to the shared queue.
-+			 */
-+			new_bfqq->allocated[rq_data_dir(rq)]++;
-+			bfqq->allocated[rq_data_dir(rq)]--;
-+			atomic_inc(&new_bfqq->ref);
-+			bfq_put_queue(bfqq);
-+			if (bic_to_bfqq(RQ_BIC(rq), 1) == bfqq)
-+				bfq_merge_bfqqs(bfqd, RQ_BIC(rq),
-+						bfqq, new_bfqq);
-+			rq->elv.priv[1] = new_bfqq;
-+			bfqq = new_bfqq;
-+		}
-+	}
-+
- 	bfq_init_prio_data(bfqq, RQ_BIC(rq));
- 
- 	bfq_add_rq_rb(rq);
- 
-+	/*
-+	 * Here a newly-created bfq_queue has already started a weight-raising
-+	 * period: clear raising_time_left to prevent bfq_bfqq_save_state()
-+	 * from assigning it a full weight-raising period. See the detailed
-+	 * comments about this field in bfq_init_icq().
-+	 */
-+	if (bfqq->bic != NULL)
-+		bfqq->bic->raising_time_left = 0;
- 	rq_set_fifo_time(rq, jiffies + bfqd->bfq_fifo_expire[rq_is_sync(rq)]);
- 	list_add_tail(&rq->queuelist, &bfqq->fifo);
- 
-@@ -2663,18 +2920,6 @@ static void bfq_put_request(struct request *rq)
- 	}
- }
- 
--static struct bfq_queue *
--bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
--		struct bfq_queue *bfqq)
--{
--	bfq_log_bfqq(bfqd, bfqq, "merging with queue %lu",
--		(long unsigned)bfqq->new_bfqq->pid);
--	bic_set_bfqq(bic, bfqq->new_bfqq, 1);
--	bfq_mark_bfqq_coop(bfqq->new_bfqq);
--	bfq_put_queue(bfqq);
--	return bic_to_bfqq(bic, 1);
--}
--
- /*
-  * Returns NULL if a new bfqq should be allocated, or the old bfqq if this
-  * was the last process referring to said bfqq.
-@@ -2683,6 +2928,9 @@ static struct bfq_queue *
- bfq_split_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq)
- {
- 	bfq_log_bfqq(bfqq->bfqd, bfqq, "splitting queue");
-+
-+	put_io_context(bic->icq.ioc);
-+
- 	if (bfqq_process_refs(bfqq) == 1) {
- 		bfqq->pid = current->pid;
- 		bfq_clear_bfqq_coop(bfqq);
-@@ -2711,6 +2959,7 @@ static int bfq_set_request(struct request_queue *q, struct request *rq,
- 	struct bfq_queue *bfqq;
- 	struct bfq_group *bfqg;
- 	unsigned long flags;
-+	bool split = false;
- 
- 	might_sleep_if(gfp_mask & __GFP_WAIT);
- 
-@@ -2729,24 +2978,14 @@ new_queue:
- 		bfqq = bfq_get_queue(bfqd, bfqg, is_sync, bic, gfp_mask);
- 		bic_set_bfqq(bic, bfqq, is_sync);
- 	} else {
--		/*
--		 * If the queue was seeky for too long, break it apart.
--		 */
-+		/* If the queue was seeky for too long, break it apart. */
- 		if (bfq_bfqq_coop(bfqq) && bfq_bfqq_split_coop(bfqq)) {
- 			bfq_log_bfqq(bfqd, bfqq, "breaking apart bfqq");
- 			bfqq = bfq_split_bfqq(bic, bfqq);
-+			split = true;
- 			if (!bfqq)
- 				goto new_queue;
- 		}
--
--		/*
--		 * Check to see if this queue is scheduled to merge with
--		 * another closely cooperating queue. The merging of queues
--		 * happens here as it must be done in process context.
--		 * The reference on new_bfqq was taken in merge_bfqqs.
--		 */
--		if (bfqq->new_bfqq != NULL)
--			bfqq = bfq_merge_bfqqs(bfqd, bic, bfqq);
- 	}
- 
- 	bfqq->allocated[rw]++;
-@@ -2757,6 +2996,26 @@ new_queue:
- 	rq->elv.priv[0] = bic;
- 	rq->elv.priv[1] = bfqq;
- 
-+	/*
-+	 * If a bfq_queue has only one process reference, it is owned
-+	 * by only one bfq_io_cq: we can set the bic field of the
-+	 * bfq_queue to the address of that structure. Also, if the
-+	 * queue has just been split, mark a flag so that the
-+	 * information is available to the other scheduler hooks.
-+	 */
-+	if (bfqq_process_refs(bfqq) == 1) {
-+		bfqq->bic = bic;
-+		if (split) {
-+			bfq_mark_bfqq_just_split(bfqq);
-+			/*
-+			 * If the queue has just been split from a shared queue,
-+			 * restore the idle window and the possible weight
-+			 * raising period.
-+			 */
-+			bfq_bfqq_resume_state(bfqq, bic);
-+		}
-+	}
-+
- 	spin_unlock_irqrestore(q->queue_lock, flags);
- 
- 	return 0;
-diff --git a/block/bfq-sched.c b/block/bfq-sched.c
-index 999b475..e54ea33 100644
---- a/block/bfq-sched.c
-+++ b/block/bfq-sched.c
-@@ -980,34 +980,6 @@ static struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd)
- 	return bfqq;
- }
- 
--/*
-- * Forced extraction of the given queue.
-- */
--static void bfq_get_next_queue_forced(struct bfq_data *bfqd,
--				      struct bfq_queue *bfqq)
--{
--	struct bfq_entity *entity;
--	struct bfq_sched_data *sd;
--
--	BUG_ON(bfqd->in_service_queue != NULL);
--
--	entity = &bfqq->entity;
--	/*
--	 * Bubble up extraction/update from the leaf to the root.
--	*/
--	for_each_entity(entity) {
--		sd = entity->sched_data;
--		bfq_update_budget(entity);
--		bfq_update_vtime(bfq_entity_service_tree(entity));
--		bfq_active_extract(bfq_entity_service_tree(entity), entity);
--		sd->active_entity = entity;
--		sd->next_active = NULL;
--		entity->service = 0;
--	}
--
--	return;
--}
--
- static void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd)
- {
- 	if (bfqd->in_service_bic != NULL) {
-diff --git a/block/bfq.h b/block/bfq.h
-index 3ca8482..c278796 100644
---- a/block/bfq.h
-+++ b/block/bfq.h
-@@ -200,6 +200,8 @@ struct bfq_group;
-  *                      idle to backlogged
-  * @service_from_backlogged: cumulative service received from the @bfq_queue
-  *                           since the last transition from idle to backlogged
-+ * @bic: pointer to the bfq_io_cq owning the bfq_queue, set to %NULL if the
-+ *	 queue is shared
-  *
-  * A bfq_queue is a leaf request queue; it can be associated with an io_context
-  * or more, if it is async or shared between cooperating processes. @cgroup
-@@ -243,6 +245,7 @@ struct bfq_queue {
- 	sector_t last_request_pos;
- 
- 	pid_t pid;
-+	struct bfq_io_cq *bic;
- 
- 	/* weight-raising fields */
- 	unsigned long raising_cur_max_time;
-@@ -272,12 +275,23 @@ struct bfq_ttime {
-  * @icq: associated io_cq structure
-  * @bfqq: array of two process queues, the sync and the async
-  * @ttime: associated @bfq_ttime struct
-+ * @raising_time_left: snapshot of the time left before weight raising ends
-+ *		       for the sync queue associated to this process; this
-+ *		       snapshot is taken to remember this value while the weight
-+ *		       raising is suspended because the queue is merged with a
-+ *		       shared queue, and is used to set @raising_cur_max_time
-+ *		       when the queue is split from the shared queue and its
-+ *		       weight is raised again
-+ * @saved_idle_window: same purpose as the previous field for the idle window
-  */
- struct bfq_io_cq {
- 	struct io_cq icq; /* must be the first member */
- 	struct bfq_queue *bfqq[2];
- 	struct bfq_ttime ttime;
- 	int ioprio;
-+
-+	unsigned int raising_time_left;
-+	unsigned int saved_idle_window;
- };
- 
- /**
-@@ -418,8 +432,9 @@ enum bfqq_state_flags {
- 	BFQ_BFQQ_FLAG_sync,		/* synchronous queue */
- 	BFQ_BFQQ_FLAG_budget_new,	/* no completion with this budget */
- 	BFQ_BFQQ_FLAG_coop,		/* bfqq is shared */
--	BFQ_BFQQ_FLAG_split_coop,	/* shared bfqq will be splitted */
--	BFQ_BFQQ_FLAG_softrt_update,	/* needs softrt-next-start update */
-+	BFQ_BFQQ_FLAG_split_coop,	/* shared bfqq will be split */
-+	BFQ_BFQQ_FLAG_just_split,	/* queue has just been split */
-+	BFQ_BFQQ_FLAG_softrt_update,	/* may need softrt-next-start update */
- };
- 
- #define BFQ_BFQQ_FNS(name)						\
-@@ -446,6 +461,7 @@ BFQ_BFQQ_FNS(sync);
- BFQ_BFQQ_FNS(budget_new);
- BFQ_BFQQ_FNS(coop);
- BFQ_BFQQ_FNS(split_coop);
-+BFQ_BFQQ_FNS(just_split);
- BFQ_BFQQ_FNS(softrt_update);
- #undef BFQ_BFQQ_FNS
- 
--- 
-1.9.0
-