Merge branch 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 mm updates from Ingo Molnar:
 "The dominant change in this cycle was the continued work to isolate
  kernel drivers from MTRR legacies: this tree gets rid of all kernel
  internal driver interfaces to MTRRs (mostly by rewriting it to proper
  PAT interfaces), the only access left is the /proc/mtrr ABI.

  This work was done by Luis R Rodriguez.

  There's also some related PCI interface additions for which I've
  Cc:-ed Bjorn"

* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (21 commits)
  x86/mm/mtrr: Remove kernel internal MTRR interfaces: unexport mtrr_add() and mtrr_del()
  s390/io: Add pci_iomap_wc() and pci_iomap_wc_range()
  drivers/dma/iop-adma: Use dma_alloc_writecombine() kernel-style
  drivers/video/fbdev/vt8623fb: Use arch_phys_wc_add() and pci_iomap_wc()
  drivers/video/fbdev/s3fb: Use arch_phys_wc_add() and pci_iomap_wc()
  drivers/video/fbdev/arkfb.c: Use arch_phys_wc_add() and pci_iomap_wc()
  PCI: Add pci_iomap_wc() variants
  drivers/video/fbdev/gxt4500: Use pci_ioremap_wc_bar() to map framebuffer
  drivers/video/fbdev/kyrofb: Use arch_phys_wc_add() and pci_ioremap_wc_bar()
  drivers/video/fbdev/i740fb: Use arch_phys_wc_add() and pci_ioremap_wc_bar()
  PCI: Add pci_ioremap_wc_bar()
  x86/mm: Make kernel/check.c explicitly non-modular
  x86/mm/pat: Make mm/pageattr[-test].c explicitly non-modular
  x86/mm/pat: Add comments to cachemode translation tables
  arch/*/io.h: Add ioremap_uc() to all architectures
  drivers/video/fbdev/atyfb: Use arch_phys_wc_add() and ioremap_wc()
  drivers/video/fbdev/atyfb: Replace MTRR UC hole with strong UC
  drivers/video/fbdev/atyfb: Clarify ioremap() base and length used
  drivers/video/fbdev/atyfb: Carve out framebuffer length fudging into a helper
  x86/mm, asm-generic: Add IOMMU ioremap_uc() variant default
  ...

Documentation/x86/mtrr.txt

@@ -6,10 +6,22 @@ Luis R. Rodriguez <mcgrof@do-not-panic.com> - April 9, 2015
 ===============================================================================
 Phasing out MTRR use
 
-MTRR use is replaced on modern x86 hardware with PAT. Over time the only type
-of effective MTRR that is expected to be supported will be for write-combining.
-As MTRR use is phased out device drivers should use arch_phys_wc_add() to make
-MTRR effective on non-PAT systems while a no-op on PAT enabled systems.
+MTRR use is replaced on modern x86 hardware with PAT. Direct MTRR use by
+drivers on Linux is now completely phased out, device drivers should use
+arch_phys_wc_add() in combination with ioremap_wc() to make MTRR effective on
+non-PAT systems while a no-op but equally effective on PAT enabled systems.
+
+Even if Linux does not use MTRRs directly, some x86 platform firmware may still
+set up MTRRs early before booting the OS. They do this as some platform
+firmware may still have implemented access to MTRRs which would be controlled
+and handled by the platform firmware directly. An example of platform use of
+MTRRs is through the use of SMI handlers, one case could be for fan control,
+the platform code would need uncachable access to some of its fan control
+registers. Such platform access does not need any Operating System MTRR code in
+place other than mtrr_type_lookup() to ensure any OS specific mapping requests
+are aligned with platform MTRR setup. If MTRRs are only set up by the platform
+firmware code though and the OS does not make any specific MTRR mapping
+requests mtrr_type_lookup() should always return MTRR_TYPE_INVALID.
 
 For details refer to Documentation/x86/pat.txt.
 

arch/avr32/include/asm/io.h

@@ -297,6 +297,7 @@ extern void __iounmap(void __iomem *addr);
 
 #define ioremap_wc ioremap_nocache
 #define ioremap_wt ioremap_nocache
+#define ioremap_uc ioremap_nocache
 
 #define cached(addr) P1SEGADDR(addr)
 #define uncached(addr) P2SEGADDR(addr)

arch/frv/include/asm/io.h

@@ -278,6 +278,7 @@ static inline void __iomem *ioremap_fullcache(unsigned long physaddr, unsigned l
 }
 
 #define ioremap_wc ioremap_nocache
+#define ioremap_uc ioremap_nocache
 
 extern void iounmap(void volatile __iomem *addr);
 

arch/m32r/include/asm/io.h

@@ -69,6 +69,7 @@ extern void iounmap(volatile void __iomem *addr);
 #define ioremap_nocache(off,size) ioremap(off,size)
 #define ioremap_wc ioremap_nocache
 #define ioremap_wt ioremap_nocache
+#define ioremap_uc ioremap_nocache
 
 /*
  * IO bus memory addresses are also 1:1 with the physical address

arch/m68k/include/asm/io_mm.h

@@ -468,6 +468,7 @@ static inline void __iomem *ioremap_nocache(unsigned long physaddr, unsigned lon
 {
 	return __ioremap(physaddr, size, IOMAP_NOCACHE_SER);
 }
+#define ioremap_uc ioremap_nocache
 static inline void __iomem *ioremap_wt(unsigned long physaddr,
 					 unsigned long size)
 {

arch/mn10300/include/asm/io.h

@@ -283,6 +283,7 @@ static inline void __iomem *ioremap_nocache(unsigned long offset, unsigned long
 
 #define ioremap_wc ioremap_nocache
 #define ioremap_wt ioremap_nocache
+#define ioremap_uc ioremap_nocache
 
 static inline void iounmap(void __iomem *addr)
 {

arch/powerpc/include/asm/io.h

@@ -721,6 +721,7 @@ extern void __iomem *ioremap_prot(phys_addr_t address, unsigned long size,
 				  unsigned long flags);
 extern void __iomem *ioremap_wc(phys_addr_t address, unsigned long size);
 #define ioremap_nocache(addr, size)	ioremap((addr), (size))
+#define ioremap_uc(addr, size)		ioremap((addr), (size))
 
 extern void iounmap(volatile void __iomem *addr);
 

arch/s390/include/asm/io.h

@@ -57,6 +57,8 @@ static inline void ioport_unmap(void __iomem *p)
  */
 #define pci_iomap pci_iomap
 #define pci_iounmap pci_iounmap
+#define pci_iomap_wc pci_iomap
+#define pci_iomap_wc_range pci_iomap_range
 
 #define memcpy_fromio(dst, src, count)	zpci_memcpy_fromio(dst, src, count)
 #define memcpy_toio(dst, src, count)	zpci_memcpy_toio(dst, src, count)

arch/sh/include/asm/io.h

@@ -368,6 +368,7 @@ static inline int iounmap_fixed(void __iomem *addr) { return -EINVAL; }
 #endif
 
 #define ioremap_nocache	ioremap
+#define ioremap_uc	ioremap
 #define iounmap		__iounmap
 
 /*

arch/tile/include/asm/io.h

@@ -55,6 +55,7 @@ extern void iounmap(volatile void __iomem *addr);
 #define ioremap_nocache(physaddr, size)		ioremap(physaddr, size)
 #define ioremap_wc(physaddr, size)		ioremap(physaddr, size)
 #define ioremap_wt(physaddr, size)		ioremap(physaddr, size)
+#define ioremap_uc(physaddr, size)		ioremap(physaddr, size)
 #define ioremap_fullcache(physaddr, size)	ioremap(physaddr, size)
 
 #define mmiowb()

arch/x86/include/asm/io.h

@@ -180,6 +180,8 @@ static inline unsigned int isa_virt_to_bus(volatile void *address)
  */
 extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size);
 extern void __iomem *ioremap_uc(resource_size_t offset, unsigned long size);
+#define ioremap_uc ioremap_uc
+
 extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size);
 extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size,
 				unsigned long prot_val);

arch/x86/kernel/check.c

-#include <linux/module.h>
+#include <linux/init.h>
 #include <linux/sched.h>
 #include <linux/kthread.h>
 #include <linux/workqueue.h>
@@ -163,6 +163,5 @@ static int start_periodic_check_for_corruption(void)
 	schedule_delayed_work(&bios_check_work, 0);
 	return 0;
 }
-
-module_init(start_periodic_check_for_corruption);
+device_initcall(start_periodic_check_for_corruption);
 

arch/x86/kernel/cpu/mtrr/main.c

@@ -448,7 +448,6 @@ int mtrr_add(unsigned long base, unsigned long size, unsigned int type,
 	return mtrr_add_page(base >> PAGE_SHIFT, size >> PAGE_SHIFT, type,
 			     increment);
 }
-EXPORT_SYMBOL(mtrr_add);
 
 /**
  * mtrr_del_page - delete a memory type region
@@ -537,7 +536,6 @@ int mtrr_del(int reg, unsigned long base, unsigned long size)
 		return -EINVAL;
 	return mtrr_del_page(reg, base >> PAGE_SHIFT, size >> PAGE_SHIFT);
 }
-EXPORT_SYMBOL(mtrr_del);
 
 /**
  * arch_phys_wc_add - add a WC MTRR and handle errors if PAT is unavailable

arch/x86/mm/init.c

@@ -30,8 +30,11 @@
 /*
  * Tables translating between page_cache_type_t and pte encoding.
  *
- * Minimal supported modes are defined statically, they are modified
- * during bootup if more supported cache modes are available.
+ * The default values are defined statically as minimal supported mode;
+ * WC and WT fall back to UC-.  pat_init() updates these values to support
+ * more cache modes, WC and WT, when it is safe to do so.  See pat_init()
+ * for the details.  Note, __early_ioremap() used during early boot-time
+ * takes pgprot_t (pte encoding) and does not use these tables.
  *
  *   Index into __cachemode2pte_tbl[] is the cachemode.
  *

arch/x86/mm/init_32.c

@@ -137,6 +137,7 @@ page_table_range_init_count(unsigned long start, unsigned long end)
 
 	vaddr = start;
 	pgd_idx = pgd_index(vaddr);
+	pmd_idx = pmd_index(vaddr);
 
 	for ( ; (pgd_idx < PTRS_PER_PGD) && (vaddr != end); pgd_idx++) {
 		for (; (pmd_idx < PTRS_PER_PMD) && (vaddr != end);

arch/x86/mm/pageattr-test.c

@@ -8,6 +8,7 @@
 #include <linux/kthread.h>
 #include <linux/random.h>
 #include <linux/kernel.h>
+#include <linux/init.h>
 #include <linux/mm.h>
 #include <linux/vmalloc.h>
 
@@ -256,5 +257,4 @@ static int start_pageattr_test(void)
 
 	return 0;
 }
-
-module_init(start_pageattr_test);
+device_initcall(start_pageattr_test);

arch/x86/mm/pageattr.c

@@ -4,7 +4,6 @@
  */
 #include <linux/highmem.h>
 #include <linux/bootmem.h>
-#include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>

drivers/dma/iop-adma.c

@@ -1300,10 +1300,11 @@ static int iop_adma_probe(struct platform_device *pdev)
 	 * note: writecombine gives slightly better performance, but
 	 * requires that we explicitly flush the writes
 	 */
-	if ((adev->dma_desc_pool_virt = dma_alloc_writecombine(&pdev->dev,
-					plat_data->pool_size,
-					&adev->dma_desc_pool,
-					GFP_KERNEL)) == NULL) {
+	adev->dma_desc_pool_virt = dma_alloc_writecombine(&pdev->dev,
+							  plat_data->pool_size,
+							  &adev->dma_desc_pool,
+							  GFP_KERNEL);
+	if (!adev->dma_desc_pool_virt) {
 		ret = -ENOMEM;
 		goto err_free_adev;
 	}

drivers/pci/pci.c

@@ -138,6 +138,20 @@ void __iomem *pci_ioremap_bar(struct pci_dev *pdev, int bar)
 	return ioremap_nocache(res->start, resource_size(res));
 }
 EXPORT_SYMBOL_GPL(pci_ioremap_bar);
+
+void __iomem *pci_ioremap_wc_bar(struct pci_dev *pdev, int bar)
+{
+	/*
+	 * Make sure the BAR is actually a memory resource, not an IO resource
+	 */
+	if (!(pci_resource_flags(pdev, bar) & IORESOURCE_MEM)) {
+		WARN_ON(1);
+		return NULL;
+	}
+	return ioremap_wc(pci_resource_start(pdev, bar),
+			  pci_resource_len(pdev, bar));
+}
+EXPORT_SYMBOL_GPL(pci_ioremap_wc_bar);
 #endif
 
 

drivers/video/fbdev/arkfb.c

@@ -26,13 +26,9 @@
 #include <linux/console.h> /* Why should fb driver call console functions? because console_lock() */
 #include <video/vga.h>
 
-#ifdef CONFIG_MTRR
-#include <asm/mtrr.h>
-#endif
-
 struct arkfb_info {
 	int mclk_freq;
-	int mtrr_reg;
+	int wc_cookie;
 
 	struct dac_info *dac;
 	struct vgastate state;
@@ -102,10 +98,6 @@ static const struct svga_timing_regs ark_timing_regs     = {
 
 static char *mode_option = "640x480-8@60";
 
-#ifdef CONFIG_MTRR
-static int mtrr = 1;
-#endif
-
 MODULE_AUTHOR("(c) 2007 Ondrej Zajicek <santiago@crfreenet.org>");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("fbdev driver for ARK 2000PV");
@@ -115,11 +107,6 @@ MODULE_PARM_DESC(mode_option, "Default video mode ('640x480-8@60', etc)");
 module_param_named(mode, mode_option, charp, 0444);
 MODULE_PARM_DESC(mode, "Default video mode ('640x480-8@60', etc) (deprecated)");
 
-#ifdef CONFIG_MTRR
-module_param(mtrr, int, 0444);
-MODULE_PARM_DESC(mtrr, "Enable write-combining with MTRR (1=enable, 0=disable, default=1)");
-#endif
-
 static int threshold = 4;
 
 module_param(threshold, int, 0644);
@@ -1002,7 +989,7 @@ static int ark_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	info->fix.smem_len = pci_resource_len(dev, 0);
 
 	/* Map physical IO memory address into kernel space */
-	info->screen_base = pci_iomap(dev, 0, 0);
+	info->screen_base = pci_iomap_wc(dev, 0, 0);
 	if (! info->screen_base) {
 		rc = -ENOMEM;
 		dev_err(info->device, "iomap for framebuffer failed\n");
@@ -1057,14 +1044,8 @@ static int ark_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 
 	/* Record a reference to the driver data */
 	pci_set_drvdata(dev, info);
-
-#ifdef CONFIG_MTRR
-	if (mtrr) {
-		par->mtrr_reg = -1;
-		par->mtrr_reg = mtrr_add(info->fix.smem_start, info->fix.smem_len, MTRR_TYPE_WRCOMB, 1);
-	}
-#endif
-
+	par->wc_cookie = arch_phys_wc_add(info->fix.smem_start,
+					  info->fix.smem_len);
 	return 0;
 
 	/* Error handling */
@@ -1092,14 +1073,7 @@ static void ark_pci_remove(struct pci_dev *dev)
 
 	if (info) {
 		struct arkfb_info *par = info->par;
-
-#ifdef CONFIG_MTRR
-		if (par->mtrr_reg >= 0) {
-			mtrr_del(par->mtrr_reg, 0, 0);
-			par->mtrr_reg = -1;
-		}
-#endif
-
+		arch_phys_wc_del(par->wc_cookie);
 		dac_release(par->dac);
 		unregister_framebuffer(info);
 		fb_dealloc_cmap(&info->cmap);

drivers/video/fbdev/aty/atyfb.h

@@ -182,10 +182,7 @@ struct atyfb_par {
 	unsigned long irq_flags;
 	unsigned int irq;
 	spinlock_t int_lock;
-#ifdef CONFIG_MTRR
-	int mtrr_aper;
-	int mtrr_reg;
-#endif
+	int wc_cookie;
 	u32 mem_cntl;
 	struct crtc saved_crtc;
 	union aty_pll saved_pll;

drivers/video/fbdev/aty/atyfb_base.c

@@ -98,9 +98,6 @@
 #ifdef CONFIG_PMAC_BACKLIGHT
 #include <asm/backlight.h>
 #endif
-#ifdef CONFIG_MTRR
-#include <asm/mtrr.h>
-#endif
 
 /*
  * Debug flags.
@@ -303,9 +300,7 @@ static struct fb_ops atyfb_ops = {
 };
 
 static bool noaccel;
-#ifdef CONFIG_MTRR
 static bool nomtrr;
-#endif
 static int vram;
 static int pll;
 static int mclk;
@@ -427,6 +422,20 @@ static struct {
 #endif /* CONFIG_FB_ATY_CT */
 };
 
+/*
+ * Last page of 8 MB (4 MB on ISA) aperture is MMIO,
+ * unless the auxiliary register aperture is used.
+ */
+static void aty_fudge_framebuffer_len(struct fb_info *info)
+{
+	struct atyfb_par *par = (struct atyfb_par *) info->par;
+
+	if (!par->aux_start &&
+	    (info->fix.smem_len == 0x800000 ||
+	     (par->bus_type == ISA && info->fix.smem_len == 0x400000)))
+		info->fix.smem_len -= GUI_RESERVE;
+}
+
 static int correct_chipset(struct atyfb_par *par)
 {
 	u8 rev;
@@ -2603,14 +2612,7 @@ static int aty_init(struct fb_info *info)
 	if (par->pll_ops->resume_pll)
 		par->pll_ops->resume_pll(info, &par->pll);
 
-	/*
-	 * Last page of 8 MB (4 MB on ISA) aperture is MMIO,
-	 * unless the auxiliary register aperture is used.
-	 */
-	if (!par->aux_start &&
-	    (info->fix.smem_len == 0x800000 ||
-	     (par->bus_type == ISA && info->fix.smem_len == 0x400000)))
-		info->fix.smem_len -= GUI_RESERVE;
+	aty_fudge_framebuffer_len(info);
 
 	/*
 	 * Disable register access through the linear aperture
@@ -2621,25 +2623,13 @@ static int aty_init(struct fb_info *info)
 		aty_st_le32(BUS_CNTL, aty_ld_le32(BUS_CNTL, par) |
 			    BUS_APER_REG_DIS, par);
 
-#ifdef CONFIG_MTRR
-	par->mtrr_aper = -1;
-	par->mtrr_reg = -1;
-	if (!nomtrr) {
-		/* Cover the whole resource. */
-		par->mtrr_aper = mtrr_add(par->res_start, par->res_size,
-					  MTRR_TYPE_WRCOMB, 1);
-		if (par->mtrr_aper >= 0 && !par->aux_start) {
-			/* Make a hole for mmio. */
-			par->mtrr_reg = mtrr_add(par->res_start + 0x800000 -
-						 GUI_RESERVE, GUI_RESERVE,
-						 MTRR_TYPE_UNCACHABLE, 1);
-			if (par->mtrr_reg < 0) {
-				mtrr_del(par->mtrr_aper, 0, 0);
-				par->mtrr_aper = -1;
-			}
-		}
-	}
-#endif
+	if (!nomtrr)
+		/*
+		 * Only the ioremap_wc()'d area will get WC here
+		 * since ioremap_uc() was used on the entire PCI BAR.
+		 */
+		par->wc_cookie = arch_phys_wc_add(par->res_start,
+						  par->res_size);
 
 	info->fbops = &atyfb_ops;
 	info->pseudo_palette = par->pseudo_palette;
@@ -2767,17 +2757,8 @@ static int aty_init(struct fb_info *info)
 	/* restore video mode */
 	aty_set_crtc(par, &par->saved_crtc);
 	par->pll_ops->set_pll(info, &par->saved_pll);
+	arch_phys_wc_del(par->wc_cookie);
 
-#ifdef CONFIG_MTRR
-	if (par->mtrr_reg >= 0) {
-		mtrr_del(par->mtrr_reg, 0, 0);
-		par->mtrr_reg = -1;
-	}
-	if (par->mtrr_aper >= 0) {
-		mtrr_del(par->mtrr_aper, 0, 0);
-		par->mtrr_aper = -1;
-	}
-#endif
 	return ret;
 }
 
@@ -3459,7 +3440,11 @@ static int atyfb_setup_generic(struct pci_dev *pdev, struct fb_info *info,
 	}
 
 	info->fix.mmio_start = raddr;
-	par->ati_regbase = ioremap(info->fix.mmio_start, 0x1000);
+	/*
+	 * By using strong UC we force the MTRR to never have an
+	 * effect on the MMIO region on both non-PAT and PAT systems.
+	 */
+	par->ati_regbase = ioremap_uc(info->fix.mmio_start, 0x1000);
 	if (par->ati_regbase == NULL)
 		return -ENOMEM;
 
@@ -3482,7 +3467,24 @@ static int atyfb_setup_generic(struct pci_dev *pdev, struct fb_info *info,
 
 	/* Map in frame buffer */
 	info->fix.smem_start = addr;
-	info->screen_base = ioremap(addr, 0x800000);
+
+	/*
+	 * The framebuffer is not always 8 MiB, that's just the size of the
+	 * PCI BAR. We temporarily abuse smem_len here to store the size
+	 * of the BAR. aty_init() will later correct it to match the actual
+	 * framebuffer size.
+	 *
+	 * On devices that don't have the auxiliary register aperture, the
+	 * registers are housed at the top end of the framebuffer PCI BAR.
+	 * aty_fudge_framebuffer_len() is used to reduce smem_len to not
+	 * overlap with the registers.
+	 */
+	info->fix.smem_len = 0x800000;
+
+	aty_fudge_framebuffer_len(info);
+
+	info->screen_base = ioremap_wc(info->fix.smem_start,
+				       info->fix.smem_len);
 	if (info->screen_base == NULL) {
 		ret = -ENOMEM;
 		goto atyfb_setup_generic_fail;
@@ -3554,6 +3556,7 @@ static int atyfb_pci_probe(struct pci_dev *pdev,
 		return -ENOMEM;
 	}
 	par = info->par;
+	par->bus_type = PCI;
 	info->fix = atyfb_fix;
 	info->device = &pdev->dev;
 	par->pci_id = pdev->device;
@@ -3655,7 +3658,8 @@ static int __init atyfb_atari_probe(void)
 		 * Map the video memory (physical address given)
 		 * to somewhere in the kernel address space.
 		 */
-		info->screen_base = ioremap(phys_vmembase[m64_num], phys_size[m64_num]);
+		info->screen_base = ioremap_wc(phys_vmembase[m64_num],
+					       phys_size[m64_num]);
 		info->fix.smem_start = (unsigned long)info->screen_base; /* Fake! */
 		par->ati_regbase = ioremap(phys_guiregbase[m64_num], 0x10000) +
 						0xFC00ul;
@@ -3721,17 +3725,8 @@ static void atyfb_remove(struct fb_info *info)
 	if (M64_HAS(MOBIL_BUS))
 		aty_bl_exit(info->bl_dev);
 #endif
+	arch_phys_wc_del(par->wc_cookie);
 
-#ifdef CONFIG_MTRR
-	if (par->mtrr_reg >= 0) {
-		mtrr_del(par->mtrr_reg, 0, 0);
-		par->mtrr_reg = -1;
-	}
-	if (par->mtrr_aper >= 0) {
-		mtrr_del(par->mtrr_aper, 0, 0);
-		par->mtrr_aper = -1;
-	}
-#endif
 #ifndef __sparc__
 	if (par->ati_regbase)
 		iounmap(par->ati_regbase);
@@ -3847,10 +3842,8 @@ static int __init atyfb_setup(char *options)
 	while ((this_opt = strsep(&options, ",")) != NULL) {
 		if (!strncmp(this_opt, "noaccel", 7)) {
 			noaccel = 1;
-#ifdef CONFIG_MTRR
 		} else if (!strncmp(this_opt, "nomtrr", 6)) {
 			nomtrr = 1;
-#endif
 		} else if (!strncmp(this_opt, "vram:", 5))
 			vram = simple_strtoul(this_opt + 5, NULL, 0);
 		else if (!strncmp(this_opt, "pll:", 4))
@@ -4020,7 +4013,5 @@ module_param(comp_sync, int, 0);
 MODULE_PARM_DESC(comp_sync, "Set composite sync signal to low (0) or high (1)");
 module_param(mode, charp, 0);
 MODULE_PARM_DESC(mode, "Specify resolution as \"<xres>x<yres>[-<bpp>][@<refresh>]\" ");
-#ifdef CONFIG_MTRR
 module_param(nomtrr, bool, 0);
 MODULE_PARM_DESC(nomtrr, "bool: disable use of MTRR registers");
-#endif

drivers/video/fbdev/gxt4500.c

@@ -662,7 +662,7 @@ static int gxt4500_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	info->fix.smem_start = fb_phys;
 	info->fix.smem_len = pci_resource_len(pdev, 1);
-	info->screen_base = pci_ioremap_bar(pdev, 1);
+	info->screen_base = pci_ioremap_wc_bar(pdev, 1);
 	if (!info->screen_base) {
 		dev_err(&pdev->dev, "gxt4500: cannot map framebuffer\n");
 		goto err_unmap_regs;

drivers/video/fbdev/i740fb.c

@@ -27,24 +27,15 @@
 #include <linux/console.h>
 #include <video/vga.h>
 
-#ifdef CONFIG_MTRR
-#include <asm/mtrr.h>
-#endif
-
 #include "i740_reg.h"
 
 static char *mode_option;
-
-#ifdef CONFIG_MTRR
 static int mtrr = 1;
-#endif
 
 struct i740fb_par {
 	unsigned char __iomem *regs;
 	bool has_sgram;
-#ifdef CONFIG_MTRR
-	int mtrr_reg;
-#endif
+	int wc_cookie;
 	bool ddc_registered;
 	struct i2c_adapter ddc_adapter;
 	struct i2c_algo_bit_data ddc_algo;
@@ -1040,7 +1031,7 @@ static int i740fb_probe(struct pci_dev *dev, const struct pci_device_id *ent)
 		goto err_request_regions;
 	}
 
-	info->screen_base = pci_ioremap_bar(dev, 0);
+	info->screen_base = pci_ioremap_wc_bar(dev, 0);
 	if (!info->screen_base) {
 		dev_err(info->device, "error remapping base\n");
 		ret = -ENOMEM;
@@ -1144,13 +1135,9 @@ static int i740fb_probe(struct pci_dev *dev, const struct pci_device_id *ent)
 
 	fb_info(info, "%s frame buffer device\n", info->fix.id);
 	pci_set_drvdata(dev, info);
-#ifdef CONFIG_MTRR
-	if (mtrr) {
-		par->mtrr_reg = -1;
-		par->mtrr_reg = mtrr_add(info->fix.smem_start,
-				info->fix.smem_len, MTRR_TYPE_WRCOMB, 1);
-	}
-#endif
+	if (mtrr)
+		par->wc_cookie = arch_phys_wc_add(info->fix.smem_start,
+						  info->fix.smem_len);
 	return 0;
 
 err_reg_framebuffer:
@@ -1177,13 +1164,7 @@ static void i740fb_remove(struct pci_dev *dev)
 
 	if (info) {
 		struct i740fb_par *par = info->par;
-
-#ifdef CONFIG_MTRR
-		if (par->mtrr_reg >= 0) {
-			mtrr_del(par->mtrr_reg, 0, 0);
-			par->mtrr_reg = -1;
-		}
-#endif
+		arch_phys_wc_del(par->wc_cookie);
 		unregister_framebuffer(info);
 		fb_dealloc_cmap(&info->cmap);
 		if (par->ddc_registered)
@@ -1287,10 +1268,8 @@ static int  __init i740fb_setup(char *options)
 	while ((opt = strsep(&options, ",")) != NULL) {
 		if (!*opt)
 			continue;
-#ifdef CONFIG_MTRR
 		else if (!strncmp(opt, "mtrr:", 5))
 			mtrr = simple_strtoul(opt + 5, NULL, 0);
-#endif
 		else
 			mode_option = opt;
 	}
@@ -1327,7 +1306,5 @@ MODULE_DESCRIPTION("fbdev driver for Intel740");
 module_param(mode_option, charp, 0444);
 MODULE_PARM_DESC(mode_option, "Default video mode ('640x480-8@60', etc)");
 
-#ifdef CONFIG_MTRR
 module_param(mtrr, int, 0444);
 MODULE_PARM_DESC(mtrr, "Enable write-combining with MTRR (1=enable, 0=disable, default=1)");
-#endif

drivers/video/fbdev/kyro/fbdev.c

@@ -22,9 +22,6 @@
 #include <linux/pci.h>
 #include <asm/io.h>
 #include <linux/uaccess.h>
-#ifdef CONFIG_MTRR
-#include <asm/mtrr.h>
-#endif
 
 #include <video/kyro.h>
 
@@ -84,9 +81,7 @@ static device_info_t deviceInfo;
 static char *mode_option = NULL;
 static int nopan = 0;
 static int nowrap = 1;
-#ifdef CONFIG_MTRR
 static int nomtrr = 0;
-#endif
 
 /* PCI driver prototypes */
 static int kyrofb_probe(struct pci_dev *pdev, const struct pci_device_id *ent);
@@ -570,10 +565,8 @@ static int __init kyrofb_setup(char *options)
 			nopan = 1;
 		} else if (strcmp(this_opt, "nowrap") == 0) {
 			nowrap = 1;
-#ifdef CONFIG_MTRR
 		} else if (strcmp(this_opt, "nomtrr") == 0) {
 			nomtrr = 1;
-#endif
 		} else {
 			mode_option = this_opt;
 		}
@@ -691,17 +684,16 @@ static int kyrofb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	currentpar->regbase = deviceInfo.pSTGReg =
 		ioremap_nocache(kyro_fix.mmio_start, kyro_fix.mmio_len);
+	if (!currentpar->regbase)
+		goto out_free_fb;
 
-	info->screen_base = ioremap_nocache(kyro_fix.smem_start,
-					    kyro_fix.smem_len);
+	info->screen_base = pci_ioremap_wc_bar(pdev, 0);
+	if (!info->screen_base)
+		goto out_unmap_regs;
 
-#ifdef CONFIG_MTRR
 	if (!nomtrr)
-		currentpar->mtrr_handle =
-			mtrr_add(kyro_fix.smem_start,
-				 kyro_fix.smem_len,
-				 MTRR_TYPE_WRCOMB, 1);
-#endif
+		currentpar->wc_cookie = arch_phys_wc_add(kyro_fix.smem_start,
+							 kyro_fix.smem_len);
 
 	kyro_fix.ypanstep	= nopan ? 0 : 1;
 	kyro_fix.ywrapstep	= nowrap ? 0 : 1;
@@ -745,8 +737,10 @@ static int kyrofb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	return 0;
 
 out_unmap:
-	iounmap(currentpar->regbase);
 	iounmap(info->screen_base);
+out_unmap_regs:
+	iounmap(currentpar->regbase);
+out_free_fb:
 	framebuffer_release(info);
 
 	return -EINVAL;
@@ -770,12 +764,7 @@ static void kyrofb_remove(struct pci_dev *pdev)
 	iounmap(info->screen_base);
 	iounmap(par->regbase);
 
-#ifdef CONFIG_MTRR
-	if (par->mtrr_handle)
-		mtrr_del(par->mtrr_handle,
-			 info->fix.smem_start,
-			 info->fix.smem_len);
-#endif
+	arch_phys_wc_del(par->wc_cookie);
 
 	unregister_framebuffer(info);
 	framebuffer_release(info);

drivers/video/fbdev/s3fb.c

@@ -28,13 +28,9 @@
 #include <linux/i2c.h>
 #include <linux/i2c-algo-bit.h>
 
-#ifdef CONFIG_MTRR
-#include <asm/mtrr.h>
-#endif
-
 struct s3fb_info {
 	int chip, rev, mclk_freq;
-	int mtrr_reg;
+	int wc_cookie;
 	struct vgastate state;
 	struct mutex open_lock;
 	unsigned int ref_count;
@@ -154,11 +150,7 @@ static const struct svga_timing_regs s3_timing_regs     = {
 
 
 static char *mode_option;
-
-#ifdef CONFIG_MTRR
 static int mtrr = 1;
-#endif
-
 static int fasttext = 1;
 
 
@@ -170,11 +162,8 @@ module_param(mode_option, charp, 0444);
 MODULE_PARM_DESC(mode_option, "Default video mode ('640x480-8@60', etc)");
 module_param_named(mode, mode_option, charp, 0444);
 MODULE_PARM_DESC(mode, "Default video mode ('640x480-8@60', etc) (deprecated)");
-
-#ifdef CONFIG_MTRR
 module_param(mtrr, int, 0444);
 MODULE_PARM_DESC(mtrr, "Enable write-combining with MTRR (1=enable, 0=disable, default=1)");
-#endif
 
 module_param(fasttext, int, 0644);
 MODULE_PARM_DESC(fasttext, "Enable S3 fast text mode (1=enable, 0=disable, default=1)");
@@ -1168,7 +1157,7 @@ static int s3_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	info->fix.smem_len = pci_resource_len(dev, 0);
 
 	/* Map physical IO memory address into kernel space */
-	info->screen_base = pci_iomap(dev, 0, 0);
+	info->screen_base = pci_iomap_wc(dev, 0, 0);
 	if (! info->screen_base) {
 		rc = -ENOMEM;
 		dev_err(info->device, "iomap for framebuffer failed\n");
@@ -1365,12 +1354,9 @@ static int s3_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	/* Record a reference to the driver data */
 	pci_set_drvdata(dev, info);
 
-#ifdef CONFIG_MTRR
-	if (mtrr) {
-		par->mtrr_reg = -1;
-		par->mtrr_reg = mtrr_add(info->fix.smem_start, info->fix.smem_len, MTRR_TYPE_WRCOMB, 1);
-	}
-#endif
+	if (mtrr)
+		par->wc_cookie = arch_phys_wc_add(info->fix.smem_start,
+						  info->fix.smem_len);
 
 	return 0;
 
@@ -1405,14 +1391,7 @@ static void s3_pci_remove(struct pci_dev *dev)
 
 	if (info) {
 		par = info->par;
-
-#ifdef CONFIG_MTRR
-		if (par->mtrr_reg >= 0) {
-			mtrr_del(par->mtrr_reg, 0, 0);
-			par->mtrr_reg = -1;
-		}
-#endif
-
+		arch_phys_wc_del(par->wc_cookie);
 		unregister_framebuffer(info);
 		fb_dealloc_cmap(&info->cmap);
 
@@ -1551,10 +1530,8 @@ static int  __init s3fb_setup(char *options)
 
 		if (!*opt)
 			continue;
-#ifdef CONFIG_MTRR
 		else if (!strncmp(opt, "mtrr:", 5))
 			mtrr = simple_strtoul(opt + 5, NULL, 0);
-#endif
 		else if (!strncmp(opt, "fasttext:", 9))
 			fasttext = simple_strtoul(opt + 9, NULL, 0);
 		else

drivers/video/fbdev/vt8623fb.c

@@ -26,13 +26,9 @@
 #include <linux/console.h> /* Why should fb driver call console functions? because console_lock() */
 #include <video/vga.h>
 
-#ifdef CONFIG_MTRR
-#include <asm/mtrr.h>
-#endif
-
 struct vt8623fb_info {
 	char __iomem *mmio_base;
-	int mtrr_reg;
+	int wc_cookie;
 	struct vgastate state;
 	struct mutex open_lock;
 	unsigned int ref_count;
@@ -99,10 +95,7 @@ static struct svga_timing_regs vt8623_timing_regs     = {
 /* Module parameters */
 
 static char *mode_option = "640x480-8@60";
-
-#ifdef CONFIG_MTRR
 static int mtrr = 1;
-#endif
 
 MODULE_AUTHOR("(c) 2006 Ondrej Zajicek <santiago@crfreenet.org>");
 MODULE_LICENSE("GPL");
@@ -112,11 +105,8 @@ module_param(mode_option, charp, 0644);
 MODULE_PARM_DESC(mode_option, "Default video mode ('640x480-8@60', etc)");
 module_param_named(mode, mode_option, charp, 0);
 MODULE_PARM_DESC(mode, "Default video mode e.g. '648x480-8@60' (deprecated)");
-
-#ifdef CONFIG_MTRR
 module_param(mtrr, int, 0444);
 MODULE_PARM_DESC(mtrr, "Enable write-combining with MTRR (1=enable, 0=disable, default=1)");
-#endif
 
 
 /* ------------------------------------------------------------------------- */
@@ -710,7 +700,7 @@ static int vt8623_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	info->fix.mmio_len = pci_resource_len(dev, 1);
 
 	/* Map physical IO memory address into kernel space */
-	info->screen_base = pci_iomap(dev, 0, 0);
+	info->screen_base = pci_iomap_wc(dev, 0, 0);
 	if (! info->screen_base) {
 		rc = -ENOMEM;
 		dev_err(info->device, "iomap for framebuffer failed\n");
@@ -781,12 +771,9 @@ static int vt8623_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	/* Record a reference to the driver data */
 	pci_set_drvdata(dev, info);
 
-#ifdef CONFIG_MTRR
-	if (mtrr) {
-		par->mtrr_reg = -1;
-		par->mtrr_reg = mtrr_add(info->fix.smem_start, info->fix.smem_len, MTRR_TYPE_WRCOMB, 1);
-	}
-#endif
+	if (mtrr)
+		par->wc_cookie = arch_phys_wc_add(info->fix.smem_start,
+						  info->fix.smem_len);
 
 	return 0;
 
@@ -816,13 +803,7 @@ static void vt8623_pci_remove(struct pci_dev *dev)
 	if (info) {
 		struct vt8623fb_info *par = info->par;
 
-#ifdef CONFIG_MTRR
-		if (par->mtrr_reg >= 0) {
-			mtrr_del(par->mtrr_reg, 0, 0);
-			par->mtrr_reg = -1;
-		}
-#endif
-
+		arch_phys_wc_del(par->wc_cookie);
 		unregister_framebuffer(info);
 		fb_dealloc_cmap(&info->cmap);
 

include/asm-generic/io.h

@@ -736,6 +736,35 @@ static inline void *phys_to_virt(unsigned long address)
 }
 #endif
 
+/**
+ * DOC: ioremap() and ioremap_*() variants
+ *
+ * If you have an IOMMU your architecture is expected to have both ioremap()
+ * and iounmap() implemented otherwise the asm-generic helpers will provide a
+ * direct mapping.
+ *
+ * There are ioremap_*() call variants, if you have no IOMMU we naturally will
+ * default to direct mapping for all of them, you can override these defaults.
+ * If you have an IOMMU you are highly encouraged to provide your own
+ * ioremap variant implementation as there currently is no safe architecture
+ * agnostic default. To avoid possible improper behaviour default asm-generic
+ * ioremap_*() variants all return NULL when an IOMMU is available. If you've
+ * defined your own ioremap_*() variant you must then declare your own
+ * ioremap_*() variant as defined to itself to avoid the default NULL return.
+ */
+
+#ifdef CONFIG_MMU
+
+#ifndef ioremap_uc
+#define ioremap_uc ioremap_uc
+static inline void __iomem *ioremap_uc(phys_addr_t offset, size_t size)
+{
+	return NULL;
+}
+#endif
+
+#else /* !CONFIG_MMU */
+
 /*
  * Change "struct page" to physical address.
  *
@@ -743,7 +772,6 @@ static inline void *phys_to_virt(unsigned long address)
  * you'll need to provide your own definitions.
  */
 
-#ifndef CONFIG_MMU
 #ifndef ioremap
 #define ioremap ioremap
 static inline void __iomem *ioremap(phys_addr_t offset, size_t size)

include/asm-generic/pci_iomap.h

@@ -15,9 +15,13 @@ struct pci_dev;
 #ifdef CONFIG_PCI
 /* Create a virtual mapping cookie for a PCI BAR (memory or IO) */
 extern void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max);
+extern void __iomem *pci_iomap_wc(struct pci_dev *dev, int bar, unsigned long max);
 extern void __iomem *pci_iomap_range(struct pci_dev *dev, int bar,
 				     unsigned long offset,
 				     unsigned long maxlen);
+extern void __iomem *pci_iomap_wc_range(struct pci_dev *dev, int bar,
+					unsigned long offset,
+					unsigned long maxlen);
 /* Create a virtual mapping cookie for a port on a given PCI device.
  * Do not call this directly, it exists to make it easier for architectures
  * to override */
@@ -34,12 +38,22 @@ static inline void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned lon
 	return NULL;
 }
 
+static inline void __iomem *pci_iomap_wc(struct pci_dev *dev, int bar, unsigned long max)
+{
+	return NULL;
+}
 static inline void __iomem *pci_iomap_range(struct pci_dev *dev, int bar,
 					    unsigned long offset,
 					    unsigned long maxlen)
 {
 	return NULL;
 }
+static inline void __iomem *pci_iomap_wc_range(struct pci_dev *dev, int bar,
+					       unsigned long offset,
+					       unsigned long maxlen)
+{
+	return NULL;
+}
 #endif
 
 #endif /* __ASM_GENERIC_IO_H */

include/linux/pci.h

@@ -1710,6 +1710,7 @@ static inline void pci_mmcfg_late_init(void) { }
 int pci_ext_cfg_avail(void);
 
 void __iomem *pci_ioremap_bar(struct pci_dev *pdev, int bar);
+void __iomem *pci_ioremap_wc_bar(struct pci_dev *pdev, int bar);
 
 #ifdef CONFIG_PCI_IOV
 int pci_iov_virtfn_bus(struct pci_dev *dev, int id);

include/video/kyro.h

@@ -35,9 +35,7 @@ struct kyrofb_info {
 	/* Useful to hold depth here for Linux */
 	u8 PIXDEPTH;
 
-#ifdef CONFIG_MTRR
-	int mtrr_handle;
-#endif
+	int wc_cookie;
 };
 
 extern int kyro_dev_init(void);

lib/pci_iomap.c

@@ -51,6 +51,51 @@ void __iomem *pci_iomap_range(struct pci_dev *dev,
 }
 EXPORT_SYMBOL(pci_iomap_range);
 
+/**
+ * pci_iomap_wc_range - create a virtual WC mapping cookie for a PCI BAR
+ * @dev: PCI device that owns the BAR
+ * @bar: BAR number
+ * @offset: map memory at the given offset in BAR
+ * @maxlen: max length of the memory to map
+ *
+ * Using this function you will get a __iomem address to your device BAR.
+ * You can access it using ioread*() and iowrite*(). These functions hide
+ * the details if this is a MMIO or PIO address space and will just do what
+ * you expect from them in the correct way. When possible write combining
+ * is used.
+ *
+ * @maxlen specifies the maximum length to map. If you want to get access to
+ * the complete BAR from offset to the end, pass %0 here.
+ * */
+void __iomem *pci_iomap_wc_range(struct pci_dev *dev,
+				 int bar,
+				 unsigned long offset,
+				 unsigned long maxlen)
+{
+	resource_size_t start = pci_resource_start(dev, bar);
+	resource_size_t len = pci_resource_len(dev, bar);
+	unsigned long flags = pci_resource_flags(dev, bar);
+
+
+	if (flags & IORESOURCE_IO)
+		return NULL;
+
+	if (len <= offset || !start)
+		return NULL;
+
+	len -= offset;
+	start += offset;
+	if (maxlen && len > maxlen)
+		len = maxlen;
+
+	if (flags & IORESOURCE_MEM)
+		return ioremap_wc(start, len);
+
+	/* What? */
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(pci_iomap_wc_range);
+
 /**
  * pci_iomap - create a virtual mapping cookie for a PCI BAR
  * @dev: PCI device that owns the BAR
@@ -70,4 +115,25 @@ void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
 	return pci_iomap_range(dev, bar, 0, maxlen);
 }
 EXPORT_SYMBOL(pci_iomap);
+
+/**
+ * pci_iomap_wc - create a virtual WC mapping cookie for a PCI BAR
+ * @dev: PCI device that owns the BAR
+ * @bar: BAR number
+ * @maxlen: length of the memory to map
+ *
+ * Using this function you will get a __iomem address to your device BAR.
+ * You can access it using ioread*() and iowrite*(). These functions hide
+ * the details if this is a MMIO or PIO address space and will just do what
+ * you expect from them in the correct way. When possible write combining
+ * is used.
+ *
+ * @maxlen specifies the maximum length to map. If you want to get access to
+ * the complete BAR without checking for its length first, pass %0 here.
+ * */
+void __iomem *pci_iomap_wc(struct pci_dev *dev, int bar, unsigned long maxlen)
+{
+	return pci_iomap_wc_range(dev, bar, 0, maxlen);
+}
+EXPORT_SYMBOL_GPL(pci_iomap_wc);
 #endif /* CONFIG_PCI */