From 75a048119e76540d73132cfc8e0fa0c0a8bb6c83 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Thu, 22 Jan 2009 16:17:05 -0800 Subject: x86: handle PAT more like other CPU features Impact: Cleanup When PAT was originally introduced, it was handled specially for a few reasons: - PAT bugs are hard to track down, so we wanted to maintain a whitelist of CPUs. - The i386 and x86-64 CPUID code was not yet unified. Both of these are now obsolete, so handle PAT like any other features, including ordinary feature blacklisting due to known bugs. Signed-off-by: H. Peter Anvin --- arch/x86/mm/pat.c | 31 ++++++++++++++++++++----------- 1 file changed, 20 insertions(+), 11 deletions(-) (limited to 'arch/x86/mm/pat.c') diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 8b08fb95527..430cb44dd3f 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -30,7 +30,7 @@ #ifdef CONFIG_X86_PAT int __read_mostly pat_enabled = 1; -void __cpuinit pat_disable(char *reason) +void __cpuinit pat_disable(const char *reason) { pat_enabled = 0; printk(KERN_INFO "%s\n", reason); @@ -42,6 +42,11 @@ static int __init nopat(char *str) return 0; } early_param("nopat", nopat); +#else +static inline void pat_disable(const char *reason) +{ + (void)reason; +} #endif @@ -78,16 +83,20 @@ void pat_init(void) if (!pat_enabled) return; - /* Paranoia check. */ - if (!cpu_has_pat && boot_pat_state) { - /* - * If this happens we are on a secondary CPU, but - * switched to PAT on the boot CPU. We have no way to - * undo PAT. - */ - printk(KERN_ERR "PAT enabled, " - "but not supported by secondary CPU\n"); - BUG(); + if (!cpu_has_pat) { + if (!boot_pat_state) { + pat_disable("PAT not supported by CPU."); + return; + } else { + /* + * If this happens we are on a secondary CPU, but + * switched to PAT on the boot CPU. We have no way to + * undo PAT. + */ + printk(KERN_ERR "PAT enabled, " + "but not supported by secondary CPU\n"); + BUG(); + } } /* Set PWT to Write-Combining. All other bits stay the same */ -- cgit v1.2.3 From 7880f7464546842ee14179bef16a6e14381ea638 Mon Sep 17 00:00:00 2001 From: Venkatesh Pallipadi Date: Tue, 24 Feb 2009 17:35:13 -0800 Subject: gpu/drm, x86, PAT: routine to keep identity map in sync Add a function to check and keep identity maps in sync, when changing any memory type. One of the follow on patches will also use this routine. Signed-off-by: Venkatesh Pallipadi Signed-off-by: Suresh Siddha Cc: Dave Airlie Cc: Jesse Barnes Cc: Eric Anholt Cc: Keith Packard Signed-off-by: Ingo Molnar --- arch/x86/mm/pat.c | 46 +++++++++++++++++++++++++++++----------------- 1 file changed, 29 insertions(+), 17 deletions(-) (limited to 'arch/x86/mm/pat.c') diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index aebbf67a79d..399383c6f61 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -624,6 +624,33 @@ void unmap_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot) free_memtype(addr, addr + size); } +/* + * Change the memory type for the physial address range in kernel identity + * mapping space if that range is a part of identity map. + */ +int kernel_map_sync_memtype(u64 base, unsigned long size, unsigned long flags) +{ + unsigned long id_sz; + + if (!pat_enabled || base >= __pa(high_memory)) + return 0; + + id_sz = (__pa(high_memory) < base + size) ? + __pa(high_memory) - base : + size; + + if (ioremap_change_attr((unsigned long)__va(base), id_sz, flags) < 0) { + printk(KERN_INFO + "%s:%d ioremap_change_attr failed %s " + "for %Lx-%Lx\n", + current->comm, current->pid, + cattr_name(flags), + base, (unsigned long long)(base + size)); + return -EINVAL; + } + return 0; +} + /* * Internal interface to reserve a range of physical memory with prot. * Reserved non RAM regions only and after successful reserve_memtype, @@ -633,7 +660,7 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot, int strict_prot) { int is_ram = 0; - int id_sz, ret; + int ret; unsigned long flags; unsigned long want_flags = (pgprot_val(*vma_prot) & _PAGE_CACHE_MASK); @@ -670,23 +697,8 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot, flags); } - /* Need to keep identity mapping in sync */ - if (paddr >= __pa(high_memory)) - return 0; - - id_sz = (__pa(high_memory) < paddr + size) ? - __pa(high_memory) - paddr : - size; - - if (ioremap_change_attr((unsigned long)__va(paddr), id_sz, flags) < 0) { + if (kernel_map_sync_memtype(paddr, size, flags) < 0) { free_memtype(paddr, paddr + size); - printk(KERN_ERR - "%s:%d reserve_pfn_range ioremap_change_attr failed %s " - "for %Lx-%Lx\n", - current->comm, current->pid, - cattr_name(flags), - (unsigned long long)paddr, - (unsigned long long)(paddr + size)); return -EINVAL; } return 0; -- cgit v1.2.3 From 4bb9c5c02153dfc89a6c73a6f32091413805ad7d Mon Sep 17 00:00:00 2001 From: "Pallipadi, Venkatesh" Date: Thu, 12 Mar 2009 17:45:27 -0700 Subject: VM, x86, PAT: Change is_linear_pfn_mapping to not use vm_pgoff Impact: fix false positive PAT warnings - also fix VirtalBox hang Use of vma->vm_pgoff to identify the pfnmaps that are fully mapped at mmap time is broken. vm_pgoff is set by generic mmap code even for cases where drivers are setting up the mappings at the fault time. The problem was originally reported here: http://marc.info/?l=linux-kernel&m=123383810628583&w=2 Change is_linear_pfn_mapping logic to overload VM_INSERTPAGE flag along with VM_PFNMAP to mean full PFNMAP setup at mmap time. Problem also tracked at: http://bugzilla.kernel.org/show_bug.cgi?id=12800 Reported-by: Thomas Hellstrom Tested-by: Frans Pop Signed-off-by: Venkatesh Pallipadi Signed-off-by: Suresh Siddha @intel.com> Cc: Nick Piggin Cc: "ebiederm@xmission.com" Cc: # only for 2.6.29.1, not .28 LKML-Reference: <20090313004527.GA7176@linux-os.sc.intel.com> Signed-off-by: Ingo Molnar --- arch/x86/mm/pat.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'arch/x86/mm/pat.c') diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index e0ab173b697..21bc1f787ae 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -641,10 +641,11 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot, is_ram = pat_pagerange_is_ram(paddr, paddr + size); /* - * reserve_pfn_range() doesn't support RAM pages. + * reserve_pfn_range() doesn't support RAM pages. Maintain the current + * behavior with RAM pages by returning success. */ if (is_ram != 0) - return -EINVAL; + return 0; ret = reserve_memtype(paddr, paddr + size, want_flags, &flags); if (ret) -- cgit v1.2.3 From b6ff32d9aaeeeecf98f9a852d715569183585312 Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Thu, 9 Apr 2009 14:26:51 -0700 Subject: x86, PAT: Consolidate code in pat_x_mtrr_type() and reserve_memtype() Fix pat_x_mtrr_type() to use UC_MINUS when the mtrr type return UC. This is to be consistent with ioremap() and ioremap_nocache() which uses UC_MINUS. Consolidate the code such that reserve_memtype() also uses pat_x_mtrr_type() when the caller doesn't specify any special attribute (non WB attribute). Signed-off-by: Suresh Siddha Signed-off-by: Venkatesh Pallipadi LKML-Reference: <20090409212708.939936000@intel.com> Signed-off-by: Ingo Molnar --- arch/x86/mm/pat.c | 35 +++++++++++++---------------------- 1 file changed, 13 insertions(+), 22 deletions(-) (limited to 'arch/x86/mm/pat.c') diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 640339ee4fb..8d3de958050 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -182,10 +182,10 @@ static unsigned long pat_x_mtrr_type(u64 start, u64 end, unsigned long req_type) u8 mtrr_type; mtrr_type = mtrr_type_lookup(start, end); - if (mtrr_type == MTRR_TYPE_UNCACHABLE) - return _PAGE_CACHE_UC; - if (mtrr_type == MTRR_TYPE_WRCOMB) - return _PAGE_CACHE_WC; + if (mtrr_type != MTRR_TYPE_WRBACK) + return _PAGE_CACHE_UC_MINUS; + + return _PAGE_CACHE_WB; } return req_type; @@ -352,23 +352,13 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type, return 0; } - if (req_type == -1) { - /* - * Call mtrr_lookup to get the type hint. This is an - * optimization for /dev/mem mmap'ers into WB memory (BIOS - * tools and ACPI tools). Use WB request for WB memory and use - * UC_MINUS otherwise. - */ - u8 mtrr_type = mtrr_type_lookup(start, end); - - if (mtrr_type == MTRR_TYPE_WRBACK) - actual_type = _PAGE_CACHE_WB; - else - actual_type = _PAGE_CACHE_UC_MINUS; - } else { - actual_type = pat_x_mtrr_type(start, end, - req_type & _PAGE_CACHE_MASK); - } + /* + * Call mtrr_lookup to get the type hint. This is an + * optimization for /dev/mem mmap'ers into WB memory (BIOS + * tools and ACPI tools). Use WB request for WB memory and use + * UC_MINUS otherwise. + */ + actual_type = pat_x_mtrr_type(start, end, req_type & _PAGE_CACHE_MASK); if (new_type) *new_type = actual_type; @@ -587,7 +577,8 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, if (flags != -1) { retval = reserve_memtype(offset, offset + size, flags, NULL); } else { - retval = reserve_memtype(offset, offset + size, -1, &flags); + retval = reserve_memtype(offset, offset + size, + _PAGE_CACHE_WB, &flags); } if (retval < 0) -- cgit v1.2.3 From 0c3c8a18361a636069f5a5d9d0d0f9c2124e6b94 Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Thu, 9 Apr 2009 14:26:52 -0700 Subject: x86, PAT: Remove duplicate memtype reserve in devmem mmap /dev/mem mmap code was doing memtype reserve/free for a while now. Recently we added memtype tracking in remap_pfn_range, and /dev/mem mmap uses it indirectly. So, we don't need seperate tracking in /dev/mem code any more. That means another ~100 lines of code removed :-). Signed-off-by: Suresh Siddha Signed-off-by: Venkatesh Pallipadi LKML-Reference: <20090409212709.085210000@intel.com> Signed-off-by: Ingo Molnar --- arch/x86/mm/pat.c | 60 ++----------------------------------------------------- 1 file changed, 2 insertions(+), 58 deletions(-) (limited to 'arch/x86/mm/pat.c') diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 8d3de958050..cc5e0e24e44 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -536,9 +536,7 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size) int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, unsigned long size, pgprot_t *vma_prot) { - u64 offset = ((u64) pfn) << PAGE_SHIFT; - unsigned long flags = -1; - int retval; + unsigned long flags = _PAGE_CACHE_WB; if (!range_is_allowed(pfn, size)) return 0; @@ -566,65 +564,11 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, } #endif - /* - * With O_SYNC, we can only take UC_MINUS mapping. Fail if we cannot. - * - * Without O_SYNC, we want to get - * - WB for WB-able memory and no other conflicting mappings - * - UC_MINUS for non-WB-able memory with no other conflicting mappings - * - Inherit from confliting mappings otherwise - */ - if (flags != -1) { - retval = reserve_memtype(offset, offset + size, flags, NULL); - } else { - retval = reserve_memtype(offset, offset + size, - _PAGE_CACHE_WB, &flags); - } - - if (retval < 0) - return 0; - - if (((pfn < max_low_pfn_mapped) || - (pfn >= (1UL<<(32 - PAGE_SHIFT)) && pfn < max_pfn_mapped)) && - ioremap_change_attr((unsigned long)__va(offset), size, flags) < 0) { - free_memtype(offset, offset + size); - printk(KERN_INFO - "%s:%d /dev/mem ioremap_change_attr failed %s for %Lx-%Lx\n", - current->comm, current->pid, - cattr_name(flags), - offset, (unsigned long long)(offset + size)); - return 0; - } - *vma_prot = __pgprot((pgprot_val(*vma_prot) & ~_PAGE_CACHE_MASK) | flags); return 1; } -void map_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot) -{ - unsigned long want_flags = (pgprot_val(vma_prot) & _PAGE_CACHE_MASK); - u64 addr = (u64)pfn << PAGE_SHIFT; - unsigned long flags; - - reserve_memtype(addr, addr + size, want_flags, &flags); - if (flags != want_flags) { - printk(KERN_INFO - "%s:%d /dev/mem expected mapping type %s for %Lx-%Lx, got %s\n", - current->comm, current->pid, - cattr_name(want_flags), - addr, (unsigned long long)(addr + size), - cattr_name(flags)); - } -} - -void unmap_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot) -{ - u64 addr = (u64)pfn << PAGE_SHIFT; - - free_memtype(addr, addr + size); -} - /* * Change the memory type for the physial address range in kernel identity * mapping space if that range is a part of identity map. @@ -662,8 +606,8 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot, { int is_ram = 0; int ret; - unsigned long flags; unsigned long want_flags = (pgprot_val(*vma_prot) & _PAGE_CACHE_MASK); + unsigned long flags = want_flags; is_ram = pat_pagerange_is_ram(paddr, paddr + size); -- cgit v1.2.3 From 1ee4bd92a7aa49eb66c8d5672e837090d3e7b7ff Mon Sep 17 00:00:00 2001 From: Marcin Slusarz Date: Fri, 10 Apr 2009 22:47:17 +0200 Subject: x86: fix wrong section of pat_disable & make it static pat_disable cannot be __cpuinit anymore because it's called from pat_init and the callchain looks like this: pat_disable [cpuinit] <- pat_init <- generic_set_all <- ipi_handler <- set_mtrr <- (other non init/cpuinit functions) WARNING: arch/x86/mm/built-in.o(.text+0x449e): Section mismatch in reference from the function pat_init() to the function .cpuinit.text:pat_disable() The function pat_init() references the function __cpuinit pat_disable(). This is often because pat_init lacks a __cpuinit annotation or the annotation of pat_disable is wrong. Non CONFIG_X86_PAT version of pat_disable is static inline, so this version can be static too (and there are no callers outside of this file). Signed-off-by: Marcin Slusarz Acked-by: Sam Ravnborg LKML-Reference: <49DFB055.6070405@gmail.com> Signed-off-by: Ingo Molnar --- arch/x86/mm/pat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/mm/pat.c') diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 640339ee4fb..c009a241d56 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -31,7 +31,7 @@ #ifdef CONFIG_X86_PAT int __read_mostly pat_enabled = 1; -void __cpuinit pat_disable(const char *reason) +static inline void pat_disable(const char *reason) { pat_enabled = 0; printk(KERN_INFO "%s\n", reason); -- cgit v1.2.3 From 4b065046273afa01ec8e3de7da407e8d3599251d Mon Sep 17 00:00:00 2001 From: "Pallipadi, Venkatesh" Date: Wed, 8 Apr 2009 15:37:16 -0700 Subject: x86, PAT: Remove page granularity tracking for vm_insert_pfn maps This change resolves the problem of too many single page entries in pat_memtype_list and "freeing invalid memtype" errors with i915, reported here: http://marc.info/?l=linux-kernel&m=123845244713183&w=2 Remove page level granularity track and untrack of vm_insert_pfn. memtype tracking at page granularity does not scale and cleaner approach would be for the driver to request a type for a bigger IO address range or PCI io memory range for that device, either at mmap time or driver init time and just use that type during vm_insert_pfn. This patch just removes the track/untrack of vm_insert_pfn. That means we will be in same state as 2.6.28, with respect to these APIs. Newer APIs for the drivers to request a memtype for a bigger region is coming soon. [ Impact: fix Xorg startup warnings and hangs ] Reported-by: Arkadiusz Miskiewicz Tested-by: Arkadiusz Miskiewicz Signed-off-by: Venkatesh Pallipadi Signed-off-by: Suresh Siddha Cc: Jesse Barnes LKML-Reference: <20090408223716.GC3493@linux-os.sc.intel.com> Signed-off-by: Ingo Molnar --- arch/x86/mm/pat.c | 98 +++++++++++-------------------------------------------- 1 file changed, 19 insertions(+), 79 deletions(-) (limited to 'arch/x86/mm/pat.c') diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index cc5e0e24e44..41c80571815 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -669,29 +669,28 @@ static void free_pfn_range(u64 paddr, unsigned long size) * * If the vma has a linear pfn mapping for the entire range, we get the prot * from pte and reserve the entire vma range with single reserve_pfn_range call. - * Otherwise, we reserve the entire vma range, my ging through the PTEs page - * by page to get physical address and protection. */ int track_pfn_vma_copy(struct vm_area_struct *vma) { - int retval = 0; - unsigned long i, j; resource_size_t paddr; unsigned long prot; - unsigned long vma_start = vma->vm_start; - unsigned long vma_end = vma->vm_end; - unsigned long vma_size = vma_end - vma_start; + unsigned long vma_size = vma->vm_end - vma->vm_start; pgprot_t pgprot; if (!pat_enabled) return 0; + /* + * For now, only handle remap_pfn_range() vmas where + * is_linear_pfn_mapping() == TRUE. Handling of + * vm_insert_pfn() is TBD. + */ if (is_linear_pfn_mapping(vma)) { /* * reserve the whole chunk covered by vma. We need the * starting address and protection from pte. */ - if (follow_phys(vma, vma_start, 0, &prot, &paddr)) { + if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) { WARN_ON_ONCE(1); return -EINVAL; } @@ -699,28 +698,7 @@ int track_pfn_vma_copy(struct vm_area_struct *vma) return reserve_pfn_range(paddr, vma_size, &pgprot, 1); } - /* reserve entire vma page by page, using pfn and prot from pte */ - for (i = 0; i < vma_size; i += PAGE_SIZE) { - if (follow_phys(vma, vma_start + i, 0, &prot, &paddr)) - continue; - - pgprot = __pgprot(prot); - retval = reserve_pfn_range(paddr, PAGE_SIZE, &pgprot, 1); - if (retval) - goto cleanup_ret; - } return 0; - -cleanup_ret: - /* Reserve error: Cleanup partial reservation and return error */ - for (j = 0; j < i; j += PAGE_SIZE) { - if (follow_phys(vma, vma_start + j, 0, &prot, &paddr)) - continue; - - free_pfn_range(paddr, PAGE_SIZE); - } - - return retval; } /* @@ -730,50 +708,28 @@ cleanup_ret: * prot is passed in as a parameter for the new mapping. If the vma has a * linear pfn mapping for the entire range reserve the entire vma range with * single reserve_pfn_range call. - * Otherwise, we look t the pfn and size and reserve only the specified range - * page by page. - * - * Note that this function can be called with caller trying to map only a - * subrange/page inside the vma. */ int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t *prot, unsigned long pfn, unsigned long size) { - int retval = 0; - unsigned long i, j; - resource_size_t base_paddr; resource_size_t paddr; - unsigned long vma_start = vma->vm_start; - unsigned long vma_end = vma->vm_end; - unsigned long vma_size = vma_end - vma_start; + unsigned long vma_size = vma->vm_end - vma->vm_start; if (!pat_enabled) return 0; + /* + * For now, only handle remap_pfn_range() vmas where + * is_linear_pfn_mapping() == TRUE. Handling of + * vm_insert_pfn() is TBD. + */ if (is_linear_pfn_mapping(vma)) { /* reserve the whole chunk starting from vm_pgoff */ paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT; return reserve_pfn_range(paddr, vma_size, prot, 0); } - /* reserve page by page using pfn and size */ - base_paddr = (resource_size_t)pfn << PAGE_SHIFT; - for (i = 0; i < size; i += PAGE_SIZE) { - paddr = base_paddr + i; - retval = reserve_pfn_range(paddr, PAGE_SIZE, prot, 0); - if (retval) - goto cleanup_ret; - } return 0; - -cleanup_ret: - /* Reserve error: Cleanup partial reservation and return error */ - for (j = 0; j < i; j += PAGE_SIZE) { - paddr = base_paddr + j; - free_pfn_range(paddr, PAGE_SIZE); - } - - return retval; } /* @@ -784,39 +740,23 @@ cleanup_ret: void untrack_pfn_vma(struct vm_area_struct *vma, unsigned long pfn, unsigned long size) { - unsigned long i; resource_size_t paddr; - unsigned long prot; - unsigned long vma_start = vma->vm_start; - unsigned long vma_end = vma->vm_end; - unsigned long vma_size = vma_end - vma_start; + unsigned long vma_size = vma->vm_end - vma->vm_start; if (!pat_enabled) return; + /* + * For now, only handle remap_pfn_range() vmas where + * is_linear_pfn_mapping() == TRUE. Handling of + * vm_insert_pfn() is TBD. + */ if (is_linear_pfn_mapping(vma)) { /* free the whole chunk starting from vm_pgoff */ paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT; free_pfn_range(paddr, vma_size); return; } - - if (size != 0 && size != vma_size) { - /* free page by page, using pfn and size */ - paddr = (resource_size_t)pfn << PAGE_SHIFT; - for (i = 0; i < size; i += PAGE_SIZE) { - paddr = paddr + i; - free_pfn_range(paddr, PAGE_SIZE); - } - } else { - /* free entire vma, page by page, using the pfn from pte */ - for (i = 0; i < vma_size; i += PAGE_SIZE) { - if (follow_phys(vma, vma_start + i, 0, &prot, &paddr)) - continue; - - free_pfn_range(paddr, PAGE_SIZE); - } - } } pgprot_t pgprot_writecombine(pgprot_t prot) -- cgit v1.2.3