cregit-Linux how code gets into the kernel

Release 4.14 arch/x86/mm/pat.c

Directory: arch/x86/mm
/*
 * Handle caching attributes in page tables (PAT)
 *
 * Authors: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
 *          Suresh B Siddha <suresh.b.siddha@intel.com>
 *
 * Loosely based on earlier PAT patchset from Eric Biederman and Andi Kleen.
 */

#include <linux/seq_file.h>
#include <linux/bootmem.h>
#include <linux/debugfs.h>
#include <linux/ioport.h>
#include <linux/kernel.h>
#include <linux/pfn_t.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/fs.h>
#include <linux/rbtree.h>

#include <asm/cacheflush.h>
#include <asm/processor.h>
#include <asm/tlbflush.h>
#include <asm/x86_init.h>
#include <asm/pgtable.h>
#include <asm/fcntl.h>
#include <asm/e820/api.h>
#include <asm/mtrr.h>
#include <asm/page.h>
#include <asm/msr.h>
#include <asm/pat.h>
#include <asm/io.h>

#include "pat_internal.h"
#include "mm_internal.h"


#undef pr_fmt

#define pr_fmt(fmt) "" fmt


static bool __read_mostly boot_cpu_done;

static bool __read_mostly pat_disabled = !IS_ENABLED(CONFIG_X86_PAT);

static bool __read_mostly pat_initialized;

static bool __read_mostly init_cm_done;




void pat_disable(const char *reason)
{
	if (pat_disabled)
		return;

	if (boot_cpu_done) {
		WARN_ONCE(1, "x86/PAT: PAT cannot be disabled after initialization\n");
		return;
	}

	pat_disabled = true;
	pr_info("x86/PAT: %s\n", reason);
}


Contributors
PersonTokensPropCommitsCommitProp
Toshi Kani1845.00%116.67%


Venkatesh Pallipadi1127.50%116.67%


Thomas Gleixner512.50%116.67%


Mikulas Patocka37.50%116.67%


Luis R. Rodriguez25.00%116.67%


H. Peter Anvin12.50%116.67%


Total40100.00%6100.00%






static int __init nopat(char *str)
{
	pat_disable("PAT support disabled.");
	return 0;
}

Contributors
PersonTokensPropCommitsCommitProp
Venkatesh Pallipadi1263.16%133.33%


Thomas Gleixner631.58%133.33%


Andrew Morton15.26%133.33%


Total19100.00%3100.00%



early_param("nopat", nopat);




bool pat_enabled(void)
{
	return pat_initialized;
}

Contributors
PersonTokensPropCommitsCommitProp
Luis R. Rodriguez550.00%133.33%


H. Peter Anvin440.00%133.33%


Mikulas Patocka110.00%133.33%


Total10100.00%3100.00%




EXPORT_SYMBOL_GPL(pat_enabled);


int pat_debug_enable;




static int __init pat_debug_setup(char *str)
{
	pat_debug_enable = 1;
	return 0;
}

Contributors
PersonTokensPropCommitsCommitProp
Venkatesh Pallipadi18100.00%2100.00%


Total18100.00%2100.00%



__setup("debugpat", pat_debug_setup);

#ifdef CONFIG_X86_PAT
/*
 * X86 PAT uses page flags arch_1 and uncached together to keep track of
 * memory type of pages that have backing page struct.
 *
 * X86 PAT supports 4 different memory types:
 *  - _PAGE_CACHE_MODE_WB
 *  - _PAGE_CACHE_MODE_WC
 *  - _PAGE_CACHE_MODE_UC_MINUS
 *  - _PAGE_CACHE_MODE_WT
 *
 * _PAGE_CACHE_MODE_WB is the default type.
 */


#define _PGMT_WB		0

#define _PGMT_WC		(1UL << PG_arch_1)

#define _PGMT_UC_MINUS		(1UL << PG_uncached)

#define _PGMT_WT		(1UL << PG_uncached | 1UL << PG_arch_1)

#define _PGMT_MASK		(1UL << PG_uncached | 1UL << PG_arch_1)

#define _PGMT_CLEAR_MASK	(~_PGMT_MASK)




static inline enum page_cache_mode get_page_memtype(struct page *pg)
{
	unsigned long pg_flags = pg->flags & _PGMT_MASK;

	if (pg_flags == _PGMT_WB)
		return _PAGE_CACHE_MODE_WB;
	else if (pg_flags == _PGMT_WC)
		return _PAGE_CACHE_MODE_WC;
	else if (pg_flags == _PGMT_UC_MINUS)
		return _PAGE_CACHE_MODE_UC_MINUS;
	else
		return _PAGE_CACHE_MODE_WT;
}


Contributors
PersonTokensPropCommitsCommitProp
Thomas Gleixner5394.64%150.00%


Toshi Kani35.36%150.00%


Total56100.00%2100.00%






static inline void set_page_memtype(struct page *pg,
				    enum page_cache_mode memtype)
{
	unsigned long memtype_flags;
	unsigned long old_flags;
	unsigned long new_flags;

	switch (memtype) {
	case _PAGE_CACHE_MODE_WC:
		memtype_flags = _PGMT_WC;
		break;
	case _PAGE_CACHE_MODE_UC_MINUS:
		memtype_flags = _PGMT_UC_MINUS;
		break;
	case _PAGE_CACHE_MODE_WT:
		memtype_flags = _PGMT_WT;
		break;
	case _PAGE_CACHE_MODE_WB:
	default:
		memtype_flags = _PGMT_WB;
		break;
	}

	do {
		old_flags = pg->flags;
		new_flags = (old_flags & _PGMT_CLEAR_MASK) | memtype_flags;
	} while (cmpxchg(&pg->flags, old_flags, new_flags) != old_flags);
}

Contributors
PersonTokensPropCommitsCommitProp
Thomas Gleixner9794.17%150.00%


Toshi Kani65.83%150.00%


Total103100.00%2100.00%



#else



static inline enum page_cache_mode get_page_memtype(struct page *pg)
{
	return -1;
}

Contributors
PersonTokensPropCommitsCommitProp
Thomas Gleixner17100.00%1100.00%


Total17100.00%1100.00%






static inline void set_page_memtype(struct page *pg,
				    enum page_cache_mode memtype)
{
}

Contributors
PersonTokensPropCommitsCommitProp
Thomas Gleixner15100.00%1100.00%


Total15100.00%1100.00%



#endif

enum {
	
PAT_UC = 0,		/* uncached */
	
PAT_WC = 1,		/* Write combining */
	
PAT_WT = 4,		/* Write Through */
	
PAT_WP = 5,		/* Write Protected */
	
PAT_WB = 6,		/* Write Back (default) */
	
PAT_UC_MINUS = 7,	/* UC, but can be overridden by MTRR */
};


#define CM(c) (_PAGE_CACHE_MODE_ ## c)




static enum page_cache_mode pat_get_cache_mode(unsigned pat_val, char *msg)
{
	enum page_cache_mode cache;
	char *cache_mode;

	switch (pat_val) {
	case PAT_UC:       cache = CM(UC);       cache_mode = "UC  "; break;
	case PAT_WC:       cache = CM(WC);       cache_mode = "WC  "; break;
	case PAT_WT:       cache = CM(WT);       cache_mode = "WT  "; break;
	case PAT_WP:       cache = CM(WP);       cache_mode = "WP  "; break;
	case PAT_WB:       cache = CM(WB);       cache_mode = "WB  "; break;
	case PAT_UC_MINUS: cache = CM(UC_MINUS); cache_mode = "UC- "; break;
	default:           cache = CM(WB);       cache_mode = "WB  "; break;
	}

	memcpy(msg, cache_mode, 4);

	return cache;
}


Contributors
PersonTokensPropCommitsCommitProp
Juergen Gross143100.00%1100.00%


Total143100.00%1100.00%




#undef CM

/*
 * Update the cache mode to pgprot translation tables according to PAT
 * configuration.
 * Using lower indices is preferred, so we start with highest index.
 */



static void __init_cache_modes(u64 pat)
{
	enum page_cache_mode cache;
	char pat_msg[33];
	int i;

	pat_msg[32] = 0;
	for (i = 7; i >= 0; i--) {
		cache = pat_get_cache_mode((pat >> (i * 8)) & 7,
					   pat_msg + 4 * i);
		update_cache_mode_entry(i, cache);
	}
	pr_info("x86/PAT: Configuration [0-7]: %s\n", pat_msg);

	init_cm_done = true;
}


Contributors
PersonTokensPropCommitsCommitProp
Juergen Gross7487.06%116.67%


Mikulas Patocka44.71%116.67%


Borislav Petkov44.71%116.67%


Toshi Kani22.35%233.33%


Luis R. Rodriguez11.18%116.67%


Total85100.00%6100.00%




#define PAT(x, y)	((u64)PAT_ ## y << ((x)*8))




static void pat_bsp_init(u64 pat)
{
	u64 tmp_pat;

	if (!boot_cpu_has(X86_FEATURE_PAT)) {
		pat_disable("PAT not supported by CPU.");
		return;
	}

	rdmsrl(MSR_IA32_CR_PAT, tmp_pat);
	if (!tmp_pat) {
		pat_disable("PAT MSR is 0, disabled.");
		return;
	}

	wrmsrl(MSR_IA32_CR_PAT, pat);
	pat_initialized = true;

	__init_cache_modes(pat);
}


Contributors
PersonTokensPropCommitsCommitProp
Borislav Petkov3046.88%225.00%


H. Peter Anvin1117.19%112.50%


Venkatesh Pallipadi812.50%112.50%


Thomas Gleixner69.38%112.50%


Toshi Kani57.81%225.00%


Mikulas Patocka46.25%112.50%


Total64100.00%8100.00%






static void pat_ap_init(u64 pat)
{
	if (!boot_cpu_has(X86_FEATURE_PAT)) {
		/*
                 * If this happens we are on a secondary CPU, but switched to
                 * PAT on the boot CPU. We have no way to undo PAT.
                 */
		panic("x86/PAT: PAT enabled, but not supported by secondary CPU\n");
	}

	wrmsrl(MSR_IA32_CR_PAT, pat);
}


Contributors
PersonTokensPropCommitsCommitProp
Borislav Petkov2784.38%125.00%


Toshi Kani39.38%125.00%


H. Peter Anvin13.12%125.00%


Ingo Molnar13.12%125.00%


Total32100.00%4100.00%






void init_cache_modes(void)
{
	u64 pat = 0;

	if (init_cm_done)
		return;

	if (boot_cpu_has(X86_FEATURE_PAT)) {
		/*
                 * CPU supports PAT. Set PAT table to be consistent with
                 * PAT MSR. This case supports "nopat" boot option, and
                 * virtual machine environments which support PAT without
                 * MTRRs. In specific, Xen has unique setup to PAT MSR.
                 *
                 * If PAT MSR returns 0, it is considered invalid and emulates
                 * as No PAT.
                 */
		rdmsrl(MSR_IA32_CR_PAT, pat);
	}

	if (!pat) {
		/*
                 * No PAT. Emulate the PAT table that corresponds to the two
                 * cache bits, PWT (Write Through) and PCD (Cache Disable).
                 * This setup is also the same as the BIOS default setup.
                 *
                 * PTE encoding:
                 *
                 *       PCD
                 *       |PWT  PAT
                 *       ||    slot
                 *       00    0    WB : _PAGE_CACHE_MODE_WB
                 *       01    1    WT : _PAGE_CACHE_MODE_WT
                 *       10    2    UC-: _PAGE_CACHE_MODE_UC_MINUS
                 *       11    3    UC : _PAGE_CACHE_MODE_UC
                 *
                 * NOTE: When WC or WP is used, it is redirected to UC- per
                 * the default setup in __cachemode2pte_tbl[].
                 */
		pat = PAT(0, WB) | PAT(1, WT) | PAT(2, UC_MINUS) | PAT(3, UC) |
		      PAT(4, WB) | PAT(5, WT) | PAT(6, UC_MINUS) | PAT(7, UC);
	}

	__init_cache_modes(pat);
}


Contributors
PersonTokensPropCommitsCommitProp
Borislav Petkov7167.62%250.00%


Toshi Kani3432.38%250.00%


Total105100.00%4100.00%



/**
 * pat_init - Initialize PAT MSR and PAT table
 *
 * This function initializes PAT MSR and PAT table with an OS-defined value
 * to enable additional cache attributes, WC, WT and WP.
 *
 * This function must be called on all CPUs using the specific sequence of
 * operations defined in Intel SDM. mtrr_rendezvous_handler() provides this
 * procedure for PAT.
 */



void pat_init(void)
{
	u64 pat;
	struct cpuinfo_x86 *c = &boot_cpu_data;

	if (pat_disabled)
		return;

	if ((c->x86_vendor == X86_VENDOR_INTEL) &&
	    (((c->x86 == 0x6) && (c->x86_model <= 0xd)) ||
	     ((c->x86 == 0xf) && (c->x86_model <= 0x6)))) {
		/*
                 * PAT support with the lower four entries. Intel Pentium 2,
                 * 3, M, and 4 are affected by PAT errata, which makes the
                 * upper four entries unusable. To be on the safe side, we don't
                 * use those.
                 *
                 *  PTE encoding:
                 *      PAT
                 *      |PCD
                 *      ||PWT  PAT
                 *      |||    slot
                 *      000    0    WB : _PAGE_CACHE_MODE_WB
                 *      001    1    WC : _PAGE_CACHE_MODE_WC
                 *      010    2    UC-: _PAGE_CACHE_MODE_UC_MINUS
                 *      011    3    UC : _PAGE_CACHE_MODE_UC
                 * PAT bit unused
                 *
                 * NOTE: When WT or WP is used, it is redirected to UC- per
                 * the default setup in __cachemode2pte_tbl[].
                 */
		pat = PAT(0, WB) | PAT(1, WC) | PAT(2, UC_MINUS) | PAT(3, UC) |
		      PAT(4, WB) | PAT(5, WC) | PAT(6, UC_MINUS) | PAT(7, UC);
	} else {
		/*
                 * Full PAT support.  We put WT in slot 7 to improve
                 * robustness in the presence of errata that might cause
                 * the high PAT bit to be ignored.  This way, a buggy slot 7
                 * access will hit slot 3, and slot 3 is UC, so at worst
                 * we lose performance without causing a correctness issue.
                 * Pentium 4 erratum N46 is an example for such an erratum,
                 * although we try not to use PAT at all on affected CPUs.
                 *
                 *  PTE encoding:
                 *      PAT
                 *      |PCD
                 *      ||PWT  PAT
                 *      |||    slot
                 *      000    0    WB : _PAGE_CACHE_MODE_WB
                 *      001    1    WC : _PAGE_CACHE_MODE_WC
                 *      010    2    UC-: _PAGE_CACHE_MODE_UC_MINUS
                 *      011    3    UC : _PAGE_CACHE_MODE_UC
                 *      100    4    WB : Reserved
                 *      101    5    WP : _PAGE_CACHE_MODE_WP
                 *      110    6    UC-: Reserved
                 *      111    7    WT : _PAGE_CACHE_MODE_WT
                 *
                 * The reserved slots are unused, but mapped to their
                 * corresponding types in the presence of PAT errata.
                 */
		pat = PAT(0, WB) | PAT(1, WC) | PAT(2, UC_MINUS) | PAT(3, UC) |
		      PAT(4, WB) | PAT(5, WP) | PAT(6, UC_MINUS) | PAT(7, WT);
	}

	if (!boot_cpu_done) {
		pat_bsp_init(pat);
		boot_cpu_done = true;
	} else {
		pat_ap_init(pat);
	}
}


Contributors
PersonTokensPropCommitsCommitProp
Toshi Kani13059.63%225.00%


Venkatesh Pallipadi7032.11%112.50%


Borislav Petkov125.50%225.00%


Juergen Gross31.38%112.50%


Tom Lendacky20.92%112.50%


Mikulas Patocka10.46%112.50%


Total218100.00%8100.00%




#undef PAT

static DEFINE_SPINLOCK(memtype_lock);	/* protects memtype accesses */

/*
 * Does intersection of PAT memory type and MTRR memory type and returns
 * the resulting memory type as PAT understands it.
 * (Type in pat and mtrr will not have same value)
 * The intersection is based on "Effective Memory Type" tables in IA-32
 * SDM vol 3a
 */



static unsigned long pat_x_mtrr_type(u64 start, u64 end,
				     enum page_cache_mode req_type)
{
	/*
         * Look for MTRR hint to get the effective type in case where PAT
         * request is for WB.
         */
	if (req_type == _PAGE_CACHE_MODE_WB) {
		u8 mtrr_type, uniform;

		mtrr_type = mtrr_type_lookup(start, end, &uniform);
		if (mtrr_type != MTRR_TYPE_WRBACK)
			return _PAGE_CACHE_MODE_UC_MINUS;

		return _PAGE_CACHE_MODE_WB;
	}

	return req_type;
}


Contributors
PersonTokensPropCommitsCommitProp
Andreas Herrmann2644.83%228.57%


Venkatesh Pallipadi1831.03%228.57%


Toshi Kani58.62%114.29%


Juergen Gross58.62%114.29%


Hugh Dickins46.90%114.29%


Total58100.00%7100.00%




struct pagerange_state {
	
unsigned long		cur_pfn;
	
int			ram;
	
int			not_ram;
};



static int

pagerange_is_ram_callback(unsigned long initial_pfn, unsigned long total_nr_pages, void *arg)
{
	struct pagerange_state *state = arg;

	state->not_ram	|= initial_pfn > state->cur_pfn;
	state->ram	|= total_nr_pages > 0;
	state->cur_pfn	 = initial_pfn + total_nr_pages;

	return state->ram && state->not_ram;
}


Contributors
PersonTokensPropCommitsCommitProp
John Dykstra60100.00%1100.00%


Total60100.00%1100.00%






static int pat_pagerange_is_ram(resource_size_t start, resource_size_t end)
{
	int ret = 0;
	unsigned long start_pfn = start >> PAGE_SHIFT;
	unsigned long end_pfn = (end + PAGE_SIZE - 1) >> PAGE_SHIFT;
	struct pagerange_state state = {start_pfn, 0, 0};

	/*
         * For legacy reasons, physical address range in the legacy ISA
         * region is tracked as non-RAM. This will allow users of
         * /dev/mem to map portions of legacy ISA region, even when
         * some of those portions are listed(or not even listed) with
         * different e820 types(RAM/reserved/..)
         */
	if (start_pfn < ISA_END_ADDRESS >> PAGE_SHIFT)
		start_pfn = ISA_END_ADDRESS >> PAGE_SHIFT;

	if (start_pfn < end_pfn) {
		ret = walk_system_ram_range(start_pfn, end_pfn - start_pfn,
				&state, pagerange_is_ram_callback);
	}

	return (ret > 0) ? -1 : (state.ram ? 1 : 0);
}


Contributors
PersonTokensPropCommitsCommitProp
John Dykstra6962.73%133.33%


Suresh B. Siddha3935.45%133.33%


Yasuaki Ishimatsu21.82%133.33%


Total110100.00%3100.00%



/*
 * For RAM pages, we use page flags to mark the pages with appropriate type.
 * The page flags are limited to four types, WB (default), WC, WT and UC-.
 * WP request fails with -EINVAL, and UC gets redirected to UC-.  Setting
 * a new memory type is only allowed for a page mapped with the default WB
 * type.
 *
 * Here we do two passes:
 * - Find the memtype of all the pages in the range, look for any conflicts.
 * - In case of no conflicts, set the new memtype for pages in the range.
 */



static int reserve_ram_pages_type(u64 start, u64 end,
				  enum page_cache_mode req_type,
				  enum page_cache_mode *new_type)
{
	struct page *page;
	u64 pfn;

	if (req_type == _PAGE_CACHE_MODE_WP) {
		if (new_type)
			*new_type = _PAGE_CACHE_MODE_UC_MINUS;
		return -EINVAL;
	}

	if (req_type == _PAGE_CACHE_MODE_UC) {
		/* We do not support strong UC */
		WARN_ON_ONCE(1);
		req_type = _PAGE_CACHE_MODE_UC_MINUS;
	}

	for (pfn = (start >> PAGE_SHIFT); pfn < (end >> PAGE_SHIFT); ++pfn) {
		enum page_cache_mode type;

		page = pfn_to_page(pfn);
		type = get_page_memtype(page);
		if (type != _PAGE_CACHE_MODE_WB) {
			pr_info("x86/PAT: reserve_ram_pages_type failed [mem %#010Lx-%#010Lx], track 0x%x, req 0x%x\n",
				start, end - 1, type, req_type);
			if (new_type)
				*new_type = type;

			return -EBUSY;
		}
	}

	if (new_type)
		*new_type = req_type;

	for (pfn = (start >> PAGE_SHIFT); pfn < (end >> PAGE_SHIFT); ++pfn) {
		page = pfn_to_page(pfn);
		set_page_memtype(page, req_type);
	}
	return 0;
}


Contributors
PersonTokensPropCommitsCommitProp
Suresh B. Siddha9750.00%114.29%


Venkatesh Pallipadi6332.47%114.29%


Toshi Kani2211.34%228.57%


Juergen Gross94.64%114.29%


Björn Helgaas21.03%114.29%


Luis R. Rodriguez10.52%114.29%


Total194100.00%7100.00%






static int free_ram_pages_type(u64 start, u64 end)
{
	struct page *page;
	u64 pfn;

	for (pfn = (start >> PAGE_SHIFT); pfn < (end >> PAGE_SHIFT); ++pfn) {
		page = pfn_to_page(pfn);
		set_page_memtype(page, _PAGE_CACHE_MODE_WB);
	}
	return 0;
}


Contributors
PersonTokensPropCommitsCommitProp
Suresh B. Siddha5795.00%133.33%


Venkatesh Pallipadi23.33%133.33%


Toshi Kani11.67%133.33%


Total60100.00%3100.00%



/*
 * req_type typically has one of the:
 * - _PAGE_CACHE_MODE_WB
 * - _PAGE_CACHE_MODE_WC
 * - _PAGE_CACHE_MODE_UC_MINUS
 * - _PAGE_CACHE_MODE_UC
 * - _PAGE_CACHE_MODE_WT
 *
 * If new_type is NULL, function will return an error if it cannot reserve the
 * region with req_type. If new_type is non-NULL, function will return
 * available type in new_type in case of no error. In case of any error
 * it will return a negative return value.
 */



int reserve_memtype(u64 start, u64 end, enum page_cache_mode req_type,
		    enum page_cache_mode *new_type)
{
	struct memtype *new;
	enum page_cache_mode actual_type;
	int is_range_ram;
	int err = 0;

	BUG_ON(start >= end); /* end is exclusive */

	if (!pat_enabled()) {
		/* This is identical to page table setting without PAT */
		if (new_type)
			*new_type = req_type;
		return 0;
	}

	/* Low ISA region is always mapped WB in page table. No need to track */
	if (x86_platform.is_untracked_pat_range(start, end)) {
		if (new_type)
			*new_type = _PAGE_CACHE_MODE_WB;
		return 0;
	}

	/*
         * 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);

	if (new_type)
		*new_type = actual_type;

	is_range_ram = pat_pagerange_is_ram(start, end);
	if (is_range_ram == 1) {

		err = reserve_ram_pages_type(start, end, req_type, new_type);

		return err;
	} else if (is_range_ram < 0) {
		return -EINVAL;
	}

	new  = kzalloc(sizeof(struct memtype), GFP_KERNEL);
	if (!new)
		return -ENOMEM;

	new->start	= start;
	new->end	= end;
	new->type	= actual_type;

	spin_lock(&memtype_lock);

	err = rbt_memtype_check_insert(new, new_type);
	if (err) {
		pr_info("x86/PAT: reserve_memtype failed [mem %#010Lx-%#010Lx], track %s, req %s\n",
			start, end - 1,
			cattr_name(new->type), cattr_name(req_type));
		kfree(new);
		spin_unlock(&memtype_lock);

		return err;
	}

	spin_unlock(&memtype_lock);

	dprintk("reserve_memtype added [mem %#010Lx-%#010Lx], track %s, req %s, ret %s\n",
		start, end - 1, cattr_name(new->type), cattr_name(req_type),
		new_type ? cattr_name(*new_type) : "-");

	return err;
}


Contributors
PersonTokensPropCommitsCommitProp
Venkatesh Pallipadi19063.55%934.62%


Suresh B. Siddha4715.72%415.38%


Andreas Herrmann4013.38%623.08%


Juergen Gross72.34%13.85%


Björn Helgaas51.67%13.85%


Jack Steiner31.00%13.85%


Ingo Molnar31.00%13.85%


Luis R. Rodriguez31.00%27.69%


Hugh Dickins10.33%13.85%


Total299100.00%26100.00%






int free_memtype(u64 start, u64 end)
{
	int err = -EINVAL;
	int is_range_ram;
	struct memtype *entry;

	if (!pat_enabled())
		return 0;

	/* Low ISA region is always mapped WB. No need to track */
	if (x86_platform.is_untracked_pat_range(start, end))
		return 0;

	is_range_ram = pat_pagerange_is_ram(start, end);
	if (is_range_ram == 1) {

		err = free_ram_pages_type(start, end);

		return err;
	} else if (is_range_ram < 0) {
		return -EINVAL;
	}

	spin_lock(&memtype_lock);
	entry = rbt_memtype_erase(start, end);
	spin_unlock(&memtype_lock);

	if (IS_ERR(entry)) {
		pr_info("x86/PAT: %s:%d freeing invalid memtype [mem %#010Lx-%#010Lx]\n",
			current->comm, current->pid, start, end - 1);
		return -EINVAL;
	}

	kfree(entry);

	dprintk("free_memtype request [mem %#010Lx-%#010Lx]\n", start, end - 1);

	return 0;
}



Contributors
PersonTokensPropCommitsCommitProp
Venkatesh Pallipadi9256.44%741.18%


Suresh B. Siddha3622.09%211.76%


Xiaotian Feng1710.43%15.88%


Björn Helgaas53.07%15.88%


Andreas Herrmann42.45%211.76%


Luis R. Rodriguez31.84%211.76%


Toshi Kani31.84%15.88%


Jack Steiner31.84%15.88%


Total163100.00%17100.00%



/**
 * lookup_memtype - Looksup the memory type for a physical address
 * @paddr: physical address of which memory type needs to be looked up
 *
 * Only to be called when PAT is enabled
 *
 * Returns _PAGE_CACHE_MODE_WB, _PAGE_CACHE_MODE_WC, _PAGE_CACHE_MODE_UC_MINUS
 * or _PAGE_CACHE_MODE_WT.
 */



static enum page_cache_mode lookup_memtype(u64 paddr)
{
	enum page_cache_mode rettype = _PAGE_CACHE_MODE_WB;
	struct memtype *entry;

	if (x86_platform.is_untracked_pat_range(paddr, paddr + PAGE_SIZE))
		return rettype;

	if (pat_pagerange_is_ram(paddr, paddr + PAGE_SIZE)) {
		struct page *page;

		page = pfn_to_page(paddr >> PAGE_SHIFT);
		return get_page_memtype(page);
	}

	spin_lock(&memtype_lock);

	entry = rbt_memtype_lookup(paddr);
	if (entry != NULL)
		rettype = entry->type;
	else
		rettype = _PAGE_CACHE_MODE_UC_MINUS;

	spin_unlock(&memtype_lock);
	return rettype;
}


Contributors
PersonTokensPropCommitsCommitProp
Venkatesh Pallipadi9990.83%240.00%


Juergen Gross65.50%120.00%


Jack Steiner32.75%120.00%


Toshi Kani10.92%120.00%


Total109100.00%5100.00%



/**
 * io_reserve_memtype - Request a memory type mapping for a region of memory
 * @start: start (physical address) of the region
 * @end: end (physical address) of the region
 * @type: A pointer to memtype, with requested type. On success, requested
 * or any other compatible type that was available for the region is returned
 *
 * On success, returns 0
 * On failure, returns non-zero
 */



int io_reserve_memtype(resource_size_t start, resource_size_t end,
			enum page_cache_mode *type)
{
	resource_size_t size = end - start;
	enum page_cache_mode req_type = *type;
	enum page_cache_mode new_type;
	int ret;

	WARN_ON_ONCE(iomem_map_sanity_check(start, size));

	ret = reserve_memtype(start, end, req_type, &new_type);
	if (ret)
		goto out_err;

	if (!is_new_memtype_allowed(start, size, req_type, new_type))
		goto out_free;

	if (kernel_map_sync_memtype(start, size, new_type) < 0)
		goto out_free;

	*type = new_type;
	return 0;

out_free:
	free_memtype(start, end);
	ret = -EBUSY;
out_err:
	return ret;
}


Contributors
PersonTokensPropCommitsCommitProp
Venkatesh Pallipadi11186.72%360.00%


H. Peter Anvin118.59%120.00%


Juergen Gross64.69%120.00%


Total128100.00%5100.00%



/**
 * io_free_memtype - Release a memory type mapping for a region of memory
 * @start: start (physical address) of the region
 * @end: end (physical address) of the region
 */



void io_free_memtype(resource_size_t start, resource_size_t end)
{
	free_memtype(start, end);
}


Contributors
PersonTokensPropCommitsCommitProp
Venkatesh Pallipadi18100.00%1100.00%


Total18100.00%1100.00%






int arch_io_reserve_memtype_wc(resource_size_t start, resource_size_t size)
{
	enum page_cache_mode type = _PAGE_CACHE_MODE_WC;

	return io_reserve_memtype(start, start + size, &type);
}

Contributors
PersonTokensPropCommitsCommitProp
Dave Airlie30100.00%1100.00%


Total30100.00%1100.00%




EXPORT_SYMBOL(arch_io_reserve_memtype_wc);




void arch_io_free_memtype_wc(resource_size_t start, resource_size_t size)
{
	io_free_memtype(start, start + size);
}

Contributors
PersonTokensPropCommitsCommitProp
Dave Airlie20100.00%1100.00%


Total20100.00%1100.00%




EXPORT_SYMBOL(arch_io_free_memtype_wc);




pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
				unsigned long size, pgprot_t vma_prot)
{
	if (!phys_mem_access_encrypted(pfn << PAGE_SHIFT, size))
		vma_prot = pgprot_decrypted(vma_prot);

	return vma_prot;
}


Contributors
PersonTokensPropCommitsCommitProp
Venkatesh Pallipadi2455.81%150.00%


Tom Lendacky1944.19%150.00%


Total43100.00%2100.00%



#ifdef CONFIG_STRICT_DEVMEM
/* This check is done in drivers/char/mem.c in case of STRICT_DEVMEM */



static inline int range_is_allowed(unsigned long pfn, unsigned long size)
{
	return 1;
}

Contributors
PersonTokensPropCommitsCommitProp
Venkatesh Pallipadi18100.00%1100.00%


Total18100.00%1100.00%



#else
/* This check is needed to avoid cache aliasing when PAT is enabled */



static inline int range_is_allowed(unsigned long pfn, unsigned long size)
{
	u64 from = ((u64)pfn) << PAGE_SHIFT;
	u64 to = from + size;
	u64 cursor = from;

	if (!pat_enabled())
		return 1;

	while (cursor < to) {
		if (!devmem_is_allowed(pfn))
			return 0;
		cursor += PAGE_SIZE;
		pfn++;
	}
	return 1;
}

Contributors
PersonTokensPropCommitsCommitProp
Venkatesh Pallipadi6888.31%133.33%


Ravikiran G. Thirumalai810.39%133.33%


Luis R. Rodriguez11.30%133.33%


Total77100.00%3100.00%



#endif /* CONFIG_STRICT_DEVMEM */




int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
				unsigned long size, pgprot_t *vma_prot)
{
	enum page_cache_mode pcm = _PAGE_CACHE_MODE_WB;

	if (!range_is_allowed(pfn, size))
		return 0;

	if (file->f_flags & O_DSYNC)
		pcm = _PAGE_CACHE_MODE_UC_MINUS;

	*vma_prot = __pgprot((pgprot_val(*vma_prot) & ~_PAGE_CACHE_MASK) |
			     cachemode2protval(pcm));
	return 1;
}


Contributors
PersonTokensPropCommitsCommitProp
Venkatesh Pallipadi6785.90%360.00%


Juergen Gross1012.82%120.00%


Christoph Hellwig11.28%120.00%


Total78100.00%5100.00%



/*
 * 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,
			    enum page_cache_mode pcm)
{
	unsigned long id_sz;

	if (base > __pa(high_memory-1))
		return 0;

	/*
         * some areas in the middle of the kernel identity range
         * are not mapped, like the PCI space.
         */
	if (!page_is_ram(base >> PAGE_SHIFT))
		return 0;

	id_sz = (__pa(high_memory-1) <= base + size) ?
				__pa(high_memory) - base :
				size;

	if (ioremap_change_attr((unsigned long)__va(base), id_sz, pcm) < 0) {
		pr_info("x86/PAT: %s:%d ioremap_change_attr failed %s for [mem %#010Lx-%#010Lx]\n",
			current->comm, current->pid,
			cattr_name(pcm),
			base, (unsigned long long)(base + size-1));
		return -EINVAL;
	}
	return 0;
}


Contributors
PersonTokensPropCommitsCommitProp
Venkatesh Pallipadi8563.43%330.00%


Dave Hansen2014.93%220.00%


Linus Torvalds139.70%110.00%


Pranith Kumar75.22%110.00%


Juergen Gross53.73%110.00%


Luis R. Rodriguez21.49%110.00%


Björn Helgaas21.49%110.00%


Total134100.00%10100.00%



/*
 * Internal interface to reserve a range of physical memory with prot.
 * Reserved non RAM regions only and after successful reserve_memtype,
 * this func also keeps identity mapping (if any) in sync with this new prot.
 */



static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
				int strict_prot)
{
	int is_ram = 0;
	int ret;
	enum page_cache_mode want_pcm = pgprot2cachemode(*vma_prot);
	enum page_cache_mode pcm = want_pcm;

	is_ram = pat_pagerange_is_ram(paddr, paddr + size);

	/*
         * reserve_pfn_range() for RAM pages. We do not refcount to keep
         * track of number of mappings of RAM pages. We can assert that
         * the type requested matches the type of first page in the range.
         */
	if (is_ram) {
		if (!pat_enabled())
			return 0;

		pcm = lookup_memtype(paddr);
		if (want_pcm != pcm) {
			pr_warn("x86/PAT: %s:%d map pfn RAM range req %s for [mem %#010Lx-%#010Lx], got %s\n",
				current->comm, current->pid,
				cattr_name(want_pcm),
				(unsigned long long)paddr,
				(unsigned long long)(paddr + size - 1),
				cattr_name(pcm));
			*vma_prot = __pgprot((pgprot_val(*vma_prot) &
					     (~_PAGE_CACHE_MASK)) |
					     cachemode2protval(pcm));
		}
		return 0;
	}

	ret = reserve_memtype(paddr, paddr + size, want_pcm, &pcm);
	if (ret)
		return ret;

	if (pcm != want_pcm) {
		if (strict_prot ||
		    !is_new_memtype_allowed(paddr, size, want_pcm, pcm)) {
			free_memtype(paddr, paddr + size);
			pr_err("x86/PAT: %s:%d map pfn expected mapping type %s for [mem %#010Lx-%#010Lx], got %s\n",
			       current->comm, current->pid,
			       cattr_name(want_pcm),
			       (unsigned long long)paddr,
			       (unsigned long long)(paddr + size - 1),
			       cattr_name(pcm));
			return -EINVAL;
		}
		/*
                 * We allow returning different type than the one requested in
                 * non strict case.
                 */
		*vma_prot = __pgprot((pgprot_val(*vma_prot) &
				      (~_PAGE_CACHE_MASK)) |
				     cachemode2protval(pcm));
	}

	if (kernel_map_sync_memtype(paddr, size, pcm) < 0) {
		free_memtype(paddr, paddr + size);
		return -EINVAL;
	}
	return 0;
}


Contributors
PersonTokensPropCommitsCommitProp
Venkatesh Pallipadi26282.65%642.86%


Juergen Gross309.46%17.14%


Linus Torvalds61.89%17.14%


Ingo Molnar51.58%17.14%


Luis R. Rodriguez51.58%214.29%


Suresh B. Siddha51.58%214.29%


Björn Helgaas41.26%17.14%


Total317100.00%14100.00%



/*
 * Internal interface to free a range of physical memory.
 * Frees non RAM regions only.
 */



static void free_pfn_range(u64 paddr, unsigned long size)
{
	int is_ram;

	is_ram = pat_pagerange_is_ram(paddr, paddr + size);
	if (is_ram == 0)
		free_memtype(paddr, paddr + size);
}


Contributors
PersonTokensPropCommitsCommitProp
Venkatesh Pallipadi4197.62%150.00%


Suresh B. Siddha12.38%150.00%


Total42100.00%2100.00%



/*
 * track_pfn_copy is called when vma that is covering the pfnmap gets
 * copied through copy_page_range().
 *
 * 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.
 */



int track_pfn_copy(struct vm_area_struct *vma)
{
	resource_size_t paddr;
	unsigned long prot;
	unsigned long vma_size = vma->vm_end - vma->vm_start;
	pgprot_t pgprot;

	if (vma->vm_flags & VM_PAT) {
		/*
                 * reserve the whole chunk covered by vma. We need the
                 * starting address and protection from pte.
                 */
		if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) {
			WARN_ON_ONCE(1);
			return -EINVAL;
		}
		pgprot = __pgprot(prot);
		return reserve_pfn_range(paddr, vma_size, &pgprot, 1);
	}

	return 0;
}


Contributors
PersonTokensPropCommitsCommitProp
Venkatesh Pallipadi9093.75%457.14%


Konstantin Khlebnikov44.17%114.29%


Suresh B. Siddha11.04%114.29%


H. Peter Anvin11.04%114.29%


Total96100.00%7100.00%



/*
 * prot is passed in as a parameter for the new mapping. If the vma has
 * a linear pfn mapping for the entire range, or no vma is provided,
 * reserve the entire pfn + size range with single reserve_pfn_range
 * call.
 */



int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
		    unsigned long pfn, unsigned long addr, unsigned long size)
{
	resource_size_t paddr = (resource_size_t)pfn << PAGE_SHIFT;
	enum page_cache_mode pcm;

	/* reserve the whole chunk starting from paddr */
	if (!vma || (addr == vma->vm_start
				&& size == (vma->vm_end - vma->vm_start))) {
		int ret;

		ret = reserve_pfn_range(paddr, size, prot, 0);
		if (ret == 0 && vma)
			vma->vm_flags |= VM_PAT;
		return ret;
	}

	if (!pat_enabled())
		return 0;

	/*
         * For anything smaller than the vma size we set prot based on the
         * lookup.
         */
	pcm = lookup_memtype(paddr);

	/* Check memtype for the remaining pages */
	while (size > PAGE_SIZE) {
		size -= PAGE_SIZE;
		paddr += PAGE_SIZE;
		if (pcm != lookup_memtype(paddr))
			return -EINVAL;
	}

	*prot = __pgprot((pgprot_val(*prot) & (~_PAGE_CACHE_MASK)) |
			 cachemode2protval(pcm));

	return 0;
}


Contributors
PersonTokensPropCommitsCommitProp
Suresh B. Siddha6336.00%216.67%


Venkatesh Pallipadi5028.57%433.33%


Konstantin Khlebnikov4022.86%18.33%


Dan J Williams95.14%18.33%


Juergen Gross95.14%18.33%


Matthew Wilcox21.14%18.33%


H. Peter Anvin10.57%18.33%


Luis R. Rodriguez10.57%18.33%


Total175100.00%12100.00%






void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, pfn_t pfn)
{
	enum page_cache_mode pcm;

	if (!pat_enabled())
		return;

	/* Set prot based on lookup */
	pcm = lookup_memtype(pfn_t_to_phys(pfn));
	*prot = __pgprot((pgprot_val(*prot) & (~_PAGE_CACHE_MASK)) |
			 cachemode2protval(pcm));
}


Contributors
PersonTokensPropCommitsCommitProp
Suresh B. Siddha2742.86%112.50%


Venkatesh Pallipadi1930.16%225.00%


Juergen Gross812.70%112.50%


Dan J Williams46.35%112.50%


Borislav Petkov23.17%112.50%


Matthew Wilcox23.17%112.50%


Luis R. Rodriguez11.59%112.50%


Total63100.00%8100.00%



/*
 * untrack_pfn is called while unmapping a pfnmap for a region.
 * untrack can be called for a specific region indicated by pfn and size or
 * can be for the entire vma (in which case pfn, size are zero).
 */



void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
		 unsigned long size)
{
	resource_size_t paddr;
	unsigned long prot;

	if (vma && !(vma->vm_flags & VM_PAT))
		return;

	/* free the chunk starting from pfn or the whole chunk */
	paddr = (resource_size_t)pfn << PAGE_SHIFT;
	if (!paddr && !size) {
		if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) {
			WARN_ON_ONCE(1);
			return;
		}

		size = vma->vm_end - vma->vm_start;
	}
	free_pfn_range(paddr, size);
	if (vma)
		vma->vm_flags &= ~VM_PAT;
}


Contributors
PersonTokensPropCommitsCommitProp
Suresh B. Siddha5447.37%233.33%


Venkatesh Pallipadi3934.21%116.67%


Konstantin Khlebnikov1311.40%116.67%


Dan J Williams65.26%116.67%


H. Peter Anvin21.75%116.67%


Total114100.00%6100.00%



/*
 * untrack_pfn_moved is called, while mremapping a pfnmap for a new region,
 * with the old vma after its pfnmap page table has been removed.  The new
 * vma has a new pfnmap to the same pfn & cache type with VM_PAT set.
 */



void untrack_pfn_moved(struct vm_area_struct *vma)
{
	vma->vm_flags &= ~VM_PAT;
}


Contributors
PersonTokensPropCommitsCommitProp
Toshi Kani17100.00%1100.00%


Total17100.00%1100.00%






pgprot_t pgprot_writecombine(pgprot_t prot)
{
	return __pgprot(pgprot_val(prot) |
				cachemode2protval(_PAGE_CACHE_MODE_WC));
}

Contributors
PersonTokensPropCommitsCommitProp
Venkatesh Pallipadi1881.82%150.00%


Juergen Gross418.18%150.00%


Total22100.00%2100.00%




EXPORT_SYMBOL_GPL(pgprot_writecombine);




pgprot_t pgprot_writethrough(pgprot_t prot)
{
	return __pgprot(pgprot_val(prot) |
				cachemode2protval(_PAGE_CACHE_MODE_WT));
}

Contributors
PersonTokensPropCommitsCommitProp
Toshi Kani22100.00%1100.00%


Total22100.00%1100.00%




EXPORT_SYMBOL_GPL(pgprot_writethrough);

#if defined(CONFIG_DEBUG_FS) && defined(CONFIG_X86_PAT)




static struct memtype *memtype_get_idx(loff_t pos)
{
	struct memtype *print_entry;
	int ret;

	print_entry  = kzalloc(sizeof(struct memtype), GFP_KERNEL);
	if (!print_entry)
		return NULL;

	spin_lock(&memtype_lock);
	ret = rbt_memtype_copy_nth_element(print_entry, pos);
	spin_unlock(&memtype_lock);

	if (!ret) {
		return print_entry;
	} else {
		kfree(print_entry);
		return NULL;
	}
}


Contributors
PersonTokensPropCommitsCommitProp
Venkatesh Pallipadi82100.00%3100.00%


Total82100.00%3100.00%






static void *memtype_seq_start(struct seq_file *seq, loff_t *pos)
{
	if (*pos == 0) {
		++*pos;
		seq_puts(seq, "PAT memtype list:\n");
	}

	return memtype_get_idx(*pos);
}


Contributors
PersonTokensPropCommitsCommitProp
Venkatesh Pallipadi4297.67%150.00%


Rasmus Villemoes12.33%150.00%


Total43100.00%2100.00%






static void *memtype_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	++*pos;
	return memtype_get_idx(*pos);
}


Contributors
PersonTokensPropCommitsCommitProp
Venkatesh Pallipadi31100.00%1100.00%


Total31100.00%1100.00%






static void memtype_seq_stop(struct seq_file *seq, void *v)
{
}


Contributors
PersonTokensPropCommitsCommitProp
Venkatesh Pallipadi14100.00%1100.00%


Total14100.00%1100.00%






static int memtype_seq_show(struct seq_file *seq, void *v)
{
	struct memtype *print_entry = (struct memtype *)v;

	seq_printf(seq, "%s @ 0x%Lx-0x%Lx\n", cattr_name(print_entry->type),
			print_entry->start, print_entry->end);
	kfree(print_entry);

	return 0;
}


Contributors
PersonTokensPropCommitsCommitProp
Venkatesh Pallipadi57100.00%1100.00%


Total57100.00%1100.00%




static const struct seq_operations memtype_seq_ops = {
	.start = memtype_seq_start,
	.next  = memtype_seq_next,
	.stop  = memtype_seq_stop,
	.show  = memtype_seq_show,
};




static int memtype_seq_open(struct inode *inode, struct file *file)
{
	return seq_open(file, &memtype_seq_ops);
}


Contributors
PersonTokensPropCommitsCommitProp
Venkatesh Pallipadi25100.00%1100.00%


Total25100.00%1100.00%




static const struct file_operations memtype_fops = {
	.open    = memtype_seq_open,
	.read    = seq_read,
	.llseek  = seq_lseek,
	.release = seq_release,
};




static int __init pat_memtype_list_init(void)
{
	if (pat_enabled()) {
		debugfs_create_file("pat_memtype_list", S_IRUSR,
				    arch_debugfs_dir, NULL, &memtype_fops);
	}
	return 0;
}


Contributors
PersonTokensPropCommitsCommitProp
Venkatesh Pallipadi2678.79%133.33%


Xiaotian Feng618.18%133.33%


Luis R. Rodriguez13.03%133.33%


Total33100.00%3100.00%




late_initcall(pat_memtype_list_init);

#endif /* CONFIG_DEBUG_FS && CONFIG_X86_PAT */

Overall Contributors
PersonTokensPropCommitsCommitProp
Venkatesh Pallipadi195648.44%2524.51%


Suresh B. Siddha42910.62%76.86%


Juergen Gross3338.25%65.88%


Toshi Kani2857.06%1110.78%


Thomas Gleixner2365.84%21.96%


Borislav Petkov1503.71%32.94%


John Dykstra1443.57%10.98%


Andreas Herrmann761.88%98.82%


Dave Airlie601.49%10.98%


Konstantin Khlebnikov571.41%10.98%


Luis R. Rodriguez461.14%32.94%


Ingo Molnar370.92%65.88%


H. Peter Anvin320.79%32.94%


Mikulas Patocka260.64%10.98%


Dan J Williams230.57%21.96%


Xiaotian Feng230.57%21.96%


Tom Lendacky220.54%21.96%


Dave Hansen200.50%21.96%


Linus Torvalds190.47%10.98%


Björn Helgaas180.45%10.98%


Jack Steiner120.30%10.98%


Ravikiran G. Thirumalai90.22%10.98%


Pranith Kumar70.17%10.98%


Hugh Dickins50.12%10.98%


Matthew Wilcox40.10%10.98%


Yasuaki Ishimatsu20.05%10.98%


Tejun Heo10.02%10.98%


Adam Buchbinder10.02%10.98%


Christoph Hellwig10.02%10.98%


Tobias Klauser10.02%10.98%


Rasmus Villemoes10.02%10.98%


Andrew Morton10.02%10.98%


Pavel Machek10.02%10.98%


Total4038100.00%102100.00%


Directory: arch/x86/mm



Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.
Created with cregit.