aboutsummaryrefslogtreecommitdiff
path: root/arch/powerpc/platforms/pseries/lpar.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/powerpc/platforms/pseries/lpar.c')
-rw-r--r--arch/powerpc/platforms/pseries/lpar.c582
1 files changed, 316 insertions, 266 deletions
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index f129040d974..b02af9ef3ff 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -25,12 +25,12 @@
#include <linux/kernel.h>
#include <linux/dma-mapping.h>
#include <linux/console.h>
+#include <linux/export.h>
#include <asm/processor.h>
#include <asm/mmu.h>
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/machdep.h>
-#include <asm/abs_addr.h>
#include <asm/mmu_context.h>
#include <asm/iommu.h>
#include <asm/tlbflush.h>
@@ -40,10 +40,18 @@
#include <asm/udbg.h>
#include <asm/smp.h>
#include <asm/trace.h>
+#include <asm/firmware.h>
+#include <asm/plpar_wrappers.h>
-#include "plpar_wrappers.h"
#include "pseries.h"
+/* Flag bits for H_BULK_REMOVE */
+#define HBR_REQUEST 0x4000000000000000UL
+#define HBR_RESPONSE 0x8000000000000000UL
+#define HBR_END 0xc000000000000000UL
+#define HBR_AVPN 0x0200000000000000UL
+#define HBR_ANDCOND 0x0100000000000000UL
+
/* in hvCall.S */
EXPORT_SYMBOL(plpar_hcall);
@@ -52,197 +60,6 @@ EXPORT_SYMBOL(plpar_hcall_norets);
extern void pSeries_find_serial_port(void);
-
-static int vtermno; /* virtual terminal# for udbg */
-
-#define __ALIGNED__ __attribute__((__aligned__(sizeof(long))))
-static void udbg_hvsi_putc(char c)
-{
- /* packet's seqno isn't used anyways */
- uint8_t packet[] __ALIGNED__ = { 0xff, 5, 0, 0, c };
- int rc;
-
- if (c == '\n')
- udbg_hvsi_putc('\r');
-
- do {
- rc = plpar_put_term_char(vtermno, sizeof(packet), packet);
- } while (rc == H_BUSY);
-}
-
-static long hvsi_udbg_buf_len;
-static uint8_t hvsi_udbg_buf[256];
-
-static int udbg_hvsi_getc_poll(void)
-{
- unsigned char ch;
- int rc, i;
-
- if (hvsi_udbg_buf_len == 0) {
- rc = plpar_get_term_char(vtermno, &hvsi_udbg_buf_len, hvsi_udbg_buf);
- if (rc != H_SUCCESS || hvsi_udbg_buf[0] != 0xff) {
- /* bad read or non-data packet */
- hvsi_udbg_buf_len = 0;
- } else {
- /* remove the packet header */
- for (i = 4; i < hvsi_udbg_buf_len; i++)
- hvsi_udbg_buf[i-4] = hvsi_udbg_buf[i];
- hvsi_udbg_buf_len -= 4;
- }
- }
-
- if (hvsi_udbg_buf_len <= 0 || hvsi_udbg_buf_len > 256) {
- /* no data ready */
- hvsi_udbg_buf_len = 0;
- return -1;
- }
-
- ch = hvsi_udbg_buf[0];
- /* shift remaining data down */
- for (i = 1; i < hvsi_udbg_buf_len; i++) {
- hvsi_udbg_buf[i-1] = hvsi_udbg_buf[i];
- }
- hvsi_udbg_buf_len--;
-
- return ch;
-}
-
-static int udbg_hvsi_getc(void)
-{
- int ch;
- for (;;) {
- ch = udbg_hvsi_getc_poll();
- if (ch == -1) {
- /* This shouldn't be needed...but... */
- volatile unsigned long delay;
- for (delay=0; delay < 2000000; delay++)
- ;
- } else {
- return ch;
- }
- }
-}
-
-static void udbg_putcLP(char c)
-{
- char buf[16];
- unsigned long rc;
-
- if (c == '\n')
- udbg_putcLP('\r');
-
- buf[0] = c;
- do {
- rc = plpar_put_term_char(vtermno, 1, buf);
- } while(rc == H_BUSY);
-}
-
-/* Buffered chars getc */
-static long inbuflen;
-static long inbuf[2]; /* must be 2 longs */
-
-static int udbg_getc_pollLP(void)
-{
- /* The interface is tricky because it may return up to 16 chars.
- * We save them statically for future calls to udbg_getc().
- */
- char ch, *buf = (char *)inbuf;
- int i;
- long rc;
- if (inbuflen == 0) {
- /* get some more chars. */
- inbuflen = 0;
- rc = plpar_get_term_char(vtermno, &inbuflen, buf);
- if (rc != H_SUCCESS)
- inbuflen = 0; /* otherwise inbuflen is garbage */
- }
- if (inbuflen <= 0 || inbuflen > 16) {
- /* Catch error case as well as other oddities (corruption) */
- inbuflen = 0;
- return -1;
- }
- ch = buf[0];
- for (i = 1; i < inbuflen; i++) /* shuffle them down. */
- buf[i-1] = buf[i];
- inbuflen--;
- return ch;
-}
-
-static int udbg_getcLP(void)
-{
- int ch;
- for (;;) {
- ch = udbg_getc_pollLP();
- if (ch == -1) {
- /* This shouldn't be needed...but... */
- volatile unsigned long delay;
- for (delay=0; delay < 2000000; delay++)
- ;
- } else {
- return ch;
- }
- }
-}
-
-/* call this from early_init() for a working debug console on
- * vterm capable LPAR machines
- */
-void __init udbg_init_debug_lpar(void)
-{
- vtermno = 0;
- udbg_putc = udbg_putcLP;
- udbg_getc = udbg_getcLP;
- udbg_getc_poll = udbg_getc_pollLP;
-
- register_early_udbg_console();
-}
-
-/* returns 0 if couldn't find or use /chosen/stdout as console */
-void __init find_udbg_vterm(void)
-{
- struct device_node *stdout_node;
- const u32 *termno;
- const char *name;
-
- /* find the boot console from /chosen/stdout */
- if (!of_chosen)
- return;
- name = of_get_property(of_chosen, "linux,stdout-path", NULL);
- if (name == NULL)
- return;
- stdout_node = of_find_node_by_path(name);
- if (!stdout_node)
- return;
- name = of_get_property(stdout_node, "name", NULL);
- if (!name) {
- printk(KERN_WARNING "stdout node missing 'name' property!\n");
- goto out;
- }
-
- /* Check if it's a virtual terminal */
- if (strncmp(name, "vty", 3) != 0)
- goto out;
- termno = of_get_property(stdout_node, "reg", NULL);
- if (termno == NULL)
- goto out;
- vtermno = termno[0];
-
- if (of_device_is_compatible(stdout_node, "hvterm1")) {
- udbg_putc = udbg_putcLP;
- udbg_getc = udbg_getcLP;
- udbg_getc_poll = udbg_getc_pollLP;
- add_preferred_console("hvc", termno[0] & 0xff, NULL);
- } else if (of_device_is_compatible(stdout_node, "hvterm-protocol")) {
- vtermno = termno[0];
- udbg_putc = udbg_hvsi_putc;
- udbg_getc = udbg_hvsi_getc;
- udbg_getc_poll = udbg_hvsi_getc_poll;
- add_preferred_console("hvsi", termno[0] & 0xff, NULL);
- }
-out:
- of_node_put(stdout_node);
-}
-
void vpa_init(int cpu)
{
int hwcpu = get_hard_smp_processor_id(cpu);
@@ -251,30 +68,37 @@ void vpa_init(int cpu)
struct paca_struct *pp;
struct dtl_entry *dtl;
+ /*
+ * The spec says it "may be problematic" if CPU x registers the VPA of
+ * CPU y. We should never do that, but wail if we ever do.
+ */
+ WARN_ON(cpu != smp_processor_id());
+
if (cpu_has_feature(CPU_FTR_ALTIVEC))
lppaca_of(cpu).vmxregs_in_use = 1;
+ if (cpu_has_feature(CPU_FTR_ARCH_207S))
+ lppaca_of(cpu).ebb_regs_in_use = 1;
+
addr = __pa(&lppaca_of(cpu));
ret = register_vpa(hwcpu, addr);
if (ret) {
- printk(KERN_ERR "WARNING: vpa_init: VPA registration for "
- "cpu %d (hw %d) of area %lx returns %ld\n",
- cpu, hwcpu, addr, ret);
+ pr_err("WARNING: VPA registration for cpu %d (hw %d) of area "
+ "%lx failed with %ld\n", cpu, hwcpu, addr, ret);
return;
}
/*
* PAPR says this feature is SLB-Buffer but firmware never
* reports that. All SPLPAR support SLB shadow buffer.
*/
- addr = __pa(&slb_shadow[cpu]);
+ addr = __pa(paca[cpu].slb_shadow_ptr);
if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
ret = register_slb_shadow(hwcpu, addr);
if (ret)
- printk(KERN_ERR
- "WARNING: vpa_init: SLB shadow buffer "
- "registration for cpu %d (hw %d) of area %lx "
- "returns %ld\n", cpu, hwcpu, addr, ret);
+ pr_err("WARNING: SLB shadow buffer registration for "
+ "cpu %d (hw %d) of area %lx failed with %ld\n",
+ cpu, hwcpu, addr, ret);
}
/*
@@ -288,19 +112,20 @@ void vpa_init(int cpu)
lppaca_of(cpu).dtl_idx = 0;
/* hypervisor reads buffer length from this field */
- dtl->enqueue_to_dispatch_time = DISPATCH_LOG_BYTES;
+ dtl->enqueue_to_dispatch_time = cpu_to_be32(DISPATCH_LOG_BYTES);
ret = register_dtl(hwcpu, __pa(dtl));
if (ret)
- pr_warn("DTL registration failed for cpu %d (%ld)\n",
- cpu, ret);
+ pr_err("WARNING: DTL registration of cpu %d (hw %d) "
+ "failed with %ld\n", smp_processor_id(),
+ hwcpu, ret);
lppaca_of(cpu).dtl_enable_mask = 2;
}
}
static long pSeries_lpar_hpte_insert(unsigned long hpte_group,
- unsigned long va, unsigned long pa,
- unsigned long rflags, unsigned long vflags,
- int psize, int ssize)
+ unsigned long vpn, unsigned long pa,
+ unsigned long rflags, unsigned long vflags,
+ int psize, int apsize, int ssize)
{
unsigned long lpar_rc;
unsigned long flags;
@@ -308,12 +133,12 @@ static long pSeries_lpar_hpte_insert(unsigned long hpte_group,
unsigned long hpte_v, hpte_r;
if (!(vflags & HPTE_V_BOLTED))
- pr_devel("hpte_insert(group=%lx, va=%016lx, pa=%016lx, "
- "rflags=%lx, vflags=%lx, psize=%d)\n",
- hpte_group, va, pa, rflags, vflags, psize);
+ pr_devel("hpte_insert(group=%lx, vpn=%016lx, "
+ "pa=%016lx, rflags=%lx, vflags=%lx, psize=%d)\n",
+ hpte_group, vpn, pa, rflags, vflags, psize);
- hpte_v = hpte_encode_v(va, psize, ssize) | vflags | HPTE_V_VALID;
- hpte_r = hpte_encode_r(pa, psize) | rflags;
+ hpte_v = hpte_encode_v(vpn, psize, apsize, ssize) | vflags | HPTE_V_VALID;
+ hpte_r = hpte_encode_r(pa, psize, apsize) | rflags;
if (!(vflags & HPTE_V_BOLTED))
pr_devel(" hpte_v=%016lx, hpte_r=%016lx\n", hpte_v, hpte_r);
@@ -327,8 +152,11 @@ static long pSeries_lpar_hpte_insert(unsigned long hpte_group,
flags = 0;
/* Make pHyp happy */
- if ((rflags & _PAGE_NO_CACHE) & !(rflags & _PAGE_WRITETHRU))
- hpte_r &= ~_PAGE_COHERENT;
+ if ((rflags & _PAGE_NO_CACHE) && !(rflags & _PAGE_WRITETHRU))
+ hpte_r &= ~HPTE_R_M;
+
+ if (firmware_has_feature(FW_FEATURE_XCMO) && !(hpte_r & HPTE_R_N))
+ flags |= H_COALESCE_CAND;
lpar_rc = plpar_pte_enter(flags, hpte_group, hpte_v, hpte_r, &slot);
if (unlikely(lpar_rc == H_PTEG_FULL)) {
@@ -344,7 +172,7 @@ static long pSeries_lpar_hpte_insert(unsigned long hpte_group,
*/
if (unlikely(lpar_rc != H_SUCCESS)) {
if (!(vflags & HPTE_V_BOLTED))
- pr_devel(" lpar err %lu\n", lpar_rc);
+ pr_devel(" lpar err %ld\n", lpar_rc);
return -2;
}
if (!(vflags & HPTE_V_BOLTED))
@@ -375,7 +203,13 @@ static long pSeries_lpar_hpte_remove(unsigned long hpte_group)
(0x1UL << 4), &dummy1, &dummy2);
if (lpar_rc == H_SUCCESS)
return i;
- BUG_ON(lpar_rc != H_NOT_FOUND);
+
+ /*
+ * The test for adjunct partition is performed before the
+ * ANDCOND test. H_RESOURCE may be returned, so we need to
+ * check for that as well.
+ */
+ BUG_ON(lpar_rc != H_NOT_FOUND && lpar_rc != H_RESOURCE);
slot_offset++;
slot_offset &= 0x7;
@@ -393,7 +227,7 @@ static void pSeries_lpar_hptab_clear(void)
unsigned long ptel;
} ptes[4];
long lpar_rc;
- int i, j;
+ unsigned long i, j;
/* Read in batches of 4,
* invalidate only valid entries not in the VRMA
@@ -412,22 +246,23 @@ static void pSeries_lpar_hptab_clear(void)
&(ptes[j].pteh), &(ptes[j].ptel));
}
}
-}
-
-/*
- * This computes the AVPN and B fields of the first dword of a HPTE,
- * for use when we want to match an existing PTE. The bottom 7 bits
- * of the returned value are zero.
- */
-static inline unsigned long hpte_encode_avpn(unsigned long va, int psize,
- int ssize)
-{
- unsigned long v;
- v = (va >> 23) & ~(mmu_psize_defs[psize].avpnm);
- v <<= HPTE_V_AVPN_SHIFT;
- v |= ((unsigned long) ssize) << HPTE_V_SSIZE_SHIFT;
- return v;
+#ifdef __LITTLE_ENDIAN__
+ /* Reset exceptions to big endian */
+ if (firmware_has_feature(FW_FEATURE_SET_MODE)) {
+ long rc;
+
+ rc = pseries_big_endian_exceptions();
+ /*
+ * At this point it is unlikely panic() will get anything
+ * out to the user, but at least this will stop us from
+ * continuing on further and creating an even more
+ * difficult to debug situation.
+ */
+ if (rc)
+ panic("Could not enable big endian exceptions");
+ }
+#endif
}
/*
@@ -438,14 +273,15 @@ static inline unsigned long hpte_encode_avpn(unsigned long va, int psize,
*/
static long pSeries_lpar_hpte_updatepp(unsigned long slot,
unsigned long newpp,
- unsigned long va,
- int psize, int ssize, int local)
+ unsigned long vpn,
+ int psize, int apsize,
+ int ssize, int local)
{
unsigned long lpar_rc;
unsigned long flags = (newpp & 7) | H_AVPN;
unsigned long want_v;
- want_v = hpte_encode_avpn(va, psize, ssize);
+ want_v = hpte_encode_avpn(vpn, psize, ssize);
pr_devel(" update: avpnv=%016lx, hash=%016lx, f=%lx, psize: %d ...",
want_v, slot, flags, psize);
@@ -483,15 +319,15 @@ static unsigned long pSeries_lpar_hpte_getword0(unsigned long slot)
return dword0;
}
-static long pSeries_lpar_hpte_find(unsigned long va, int psize, int ssize)
+static long pSeries_lpar_hpte_find(unsigned long vpn, int psize, int ssize)
{
unsigned long hash;
unsigned long i;
long slot;
unsigned long want_v, hpte_v;
- hash = hpt_hash(va, mmu_psize_defs[psize].shift, ssize);
- want_v = hpte_encode_avpn(va, psize, ssize);
+ hash = hpt_hash(vpn, mmu_psize_defs[psize].shift, ssize);
+ want_v = hpte_encode_avpn(vpn, psize, ssize);
/* Bolted entries are always in the primary group */
slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
@@ -511,12 +347,13 @@ static void pSeries_lpar_hpte_updateboltedpp(unsigned long newpp,
unsigned long ea,
int psize, int ssize)
{
- unsigned long lpar_rc, slot, vsid, va, flags;
+ unsigned long vpn;
+ unsigned long lpar_rc, slot, vsid, flags;
vsid = get_kernel_vsid(ea, ssize);
- va = hpt_va(ea, vsid, ssize);
+ vpn = hpt_vpn(ea, vsid, ssize);
- slot = pSeries_lpar_hpte_find(va, psize, ssize);
+ slot = pSeries_lpar_hpte_find(vpn, psize, ssize);
BUG_ON(slot == -1);
flags = newpp & 7;
@@ -525,17 +362,18 @@ static void pSeries_lpar_hpte_updateboltedpp(unsigned long newpp,
BUG_ON(lpar_rc != H_SUCCESS);
}
-static void pSeries_lpar_hpte_invalidate(unsigned long slot, unsigned long va,
- int psize, int ssize, int local)
+static void pSeries_lpar_hpte_invalidate(unsigned long slot, unsigned long vpn,
+ int psize, int apsize,
+ int ssize, int local)
{
unsigned long want_v;
unsigned long lpar_rc;
unsigned long dummy1, dummy2;
- pr_devel(" inval : slot=%lx, va=%016lx, psize: %d, local: %d\n",
- slot, va, psize, local);
+ pr_devel(" inval : slot=%lx, vpn=%016lx, psize: %d, local: %d\n",
+ slot, vpn, psize, local);
- want_v = hpte_encode_avpn(va, psize, ssize);
+ want_v = hpte_encode_avpn(vpn, psize, ssize);
lpar_rc = plpar_pte_remove(H_AVPN, slot, want_v, &dummy1, &dummy2);
if (lpar_rc == H_NOT_FOUND)
return;
@@ -543,39 +381,142 @@ static void pSeries_lpar_hpte_invalidate(unsigned long slot, unsigned long va,
BUG_ON(lpar_rc != H_SUCCESS);
}
+/*
+ * Limit iterations holding pSeries_lpar_tlbie_lock to 3. We also need
+ * to make sure that we avoid bouncing the hypervisor tlbie lock.
+ */
+#define PPC64_HUGE_HPTE_BATCH 12
+
+static void __pSeries_lpar_hugepage_invalidate(unsigned long *slot,
+ unsigned long *vpn, int count,
+ int psize, int ssize)
+{
+ unsigned long param[8];
+ int i = 0, pix = 0, rc;
+ unsigned long flags = 0;
+ int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
+
+ if (lock_tlbie)
+ spin_lock_irqsave(&pSeries_lpar_tlbie_lock, flags);
+
+ for (i = 0; i < count; i++) {
+
+ if (!firmware_has_feature(FW_FEATURE_BULK_REMOVE)) {
+ pSeries_lpar_hpte_invalidate(slot[i], vpn[i], psize, 0,
+ ssize, 0);
+ } else {
+ param[pix] = HBR_REQUEST | HBR_AVPN | slot[i];
+ param[pix+1] = hpte_encode_avpn(vpn[i], psize, ssize);
+ pix += 2;
+ if (pix == 8) {
+ rc = plpar_hcall9(H_BULK_REMOVE, param,
+ param[0], param[1], param[2],
+ param[3], param[4], param[5],
+ param[6], param[7]);
+ BUG_ON(rc != H_SUCCESS);
+ pix = 0;
+ }
+ }
+ }
+ if (pix) {
+ param[pix] = HBR_END;
+ rc = plpar_hcall9(H_BULK_REMOVE, param, param[0], param[1],
+ param[2], param[3], param[4], param[5],
+ param[6], param[7]);
+ BUG_ON(rc != H_SUCCESS);
+ }
+
+ if (lock_tlbie)
+ spin_unlock_irqrestore(&pSeries_lpar_tlbie_lock, flags);
+}
+
+static void pSeries_lpar_hugepage_invalidate(struct mm_struct *mm,
+ unsigned char *hpte_slot_array,
+ unsigned long addr, int psize)
+{
+ int ssize = 0, i, index = 0;
+ unsigned long s_addr = addr;
+ unsigned int max_hpte_count, valid;
+ unsigned long vpn_array[PPC64_HUGE_HPTE_BATCH];
+ unsigned long slot_array[PPC64_HUGE_HPTE_BATCH];
+ unsigned long shift, hidx, vpn = 0, vsid, hash, slot;
+
+ shift = mmu_psize_defs[psize].shift;
+ max_hpte_count = 1U << (PMD_SHIFT - shift);
+
+ for (i = 0; i < max_hpte_count; i++) {
+ valid = hpte_valid(hpte_slot_array, i);
+ if (!valid)
+ continue;
+ hidx = hpte_hash_index(hpte_slot_array, i);
+
+ /* get the vpn */
+ addr = s_addr + (i * (1ul << shift));
+ if (!is_kernel_addr(addr)) {
+ ssize = user_segment_size(addr);
+ vsid = get_vsid(mm->context.id, addr, ssize);
+ WARN_ON(vsid == 0);
+ } else {
+ vsid = get_kernel_vsid(addr, mmu_kernel_ssize);
+ ssize = mmu_kernel_ssize;
+ }
+
+ vpn = hpt_vpn(addr, vsid, ssize);
+ hash = hpt_hash(vpn, shift, ssize);
+ if (hidx & _PTEIDX_SECONDARY)
+ hash = ~hash;
+
+ slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
+ slot += hidx & _PTEIDX_GROUP_IX;
+
+ slot_array[index] = slot;
+ vpn_array[index] = vpn;
+ if (index == PPC64_HUGE_HPTE_BATCH - 1) {
+ /*
+ * Now do a bluk invalidate
+ */
+ __pSeries_lpar_hugepage_invalidate(slot_array,
+ vpn_array,
+ PPC64_HUGE_HPTE_BATCH,
+ psize, ssize);
+ index = 0;
+ } else
+ index++;
+ }
+ if (index)
+ __pSeries_lpar_hugepage_invalidate(slot_array, vpn_array,
+ index, psize, ssize);
+}
+
static void pSeries_lpar_hpte_removebolted(unsigned long ea,
int psize, int ssize)
{
- unsigned long slot, vsid, va;
+ unsigned long vpn;
+ unsigned long slot, vsid;
vsid = get_kernel_vsid(ea, ssize);
- va = hpt_va(ea, vsid, ssize);
+ vpn = hpt_vpn(ea, vsid, ssize);
- slot = pSeries_lpar_hpte_find(va, psize, ssize);
+ slot = pSeries_lpar_hpte_find(vpn, psize, ssize);
BUG_ON(slot == -1);
-
- pSeries_lpar_hpte_invalidate(slot, va, psize, ssize, 0);
+ /*
+ * lpar doesn't use the passed actual page size
+ */
+ pSeries_lpar_hpte_invalidate(slot, vpn, psize, 0, ssize, 0);
}
-/* Flag bits for H_BULK_REMOVE */
-#define HBR_REQUEST 0x4000000000000000UL
-#define HBR_RESPONSE 0x8000000000000000UL
-#define HBR_END 0xc000000000000000UL
-#define HBR_AVPN 0x0200000000000000UL
-#define HBR_ANDCOND 0x0100000000000000UL
-
/*
* Take a spinlock around flushes to avoid bouncing the hypervisor tlbie
* lock.
*/
static void pSeries_lpar_flush_hash_range(unsigned long number, int local)
{
+ unsigned long vpn;
unsigned long i, pix, rc;
unsigned long flags = 0;
struct ppc64_tlb_batch *batch = &__get_cpu_var(ppc64_tlb_batch);
- int lock_tlbie = !cpu_has_feature(CPU_FTR_LOCKLESS_TLBIE);
+ int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
unsigned long param[9];
- unsigned long va;
unsigned long hash, index, shift, hidx, slot;
real_pte_t pte;
int psize, ssize;
@@ -587,21 +528,24 @@ static void pSeries_lpar_flush_hash_range(unsigned long number, int local)
ssize = batch->ssize;
pix = 0;
for (i = 0; i < number; i++) {
- va = batch->vaddr[i];
+ vpn = batch->vpn[i];
pte = batch->pte[i];
- pte_iterate_hashed_subpages(pte, psize, va, index, shift) {
- hash = hpt_hash(va, shift, ssize);
+ pte_iterate_hashed_subpages(pte, psize, vpn, index, shift) {
+ hash = hpt_hash(vpn, shift, ssize);
hidx = __rpte_to_hidx(pte, index);
if (hidx & _PTEIDX_SECONDARY)
hash = ~hash;
slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
slot += hidx & _PTEIDX_GROUP_IX;
if (!firmware_has_feature(FW_FEATURE_BULK_REMOVE)) {
- pSeries_lpar_hpte_invalidate(slot, va, psize,
- ssize, local);
+ /*
+ * lpar doesn't use the passed actual page size
+ */
+ pSeries_lpar_hpte_invalidate(slot, vpn, psize,
+ 0, ssize, local);
} else {
param[pix] = HBR_REQUEST | HBR_AVPN | slot;
- param[pix+1] = hpte_encode_avpn(va, psize,
+ param[pix+1] = hpte_encode_avpn(vpn, psize,
ssize);
pix += 2;
if (pix == 8) {
@@ -627,6 +571,18 @@ static void pSeries_lpar_flush_hash_range(unsigned long number, int local)
spin_unlock_irqrestore(&pSeries_lpar_tlbie_lock, flags);
}
+static int __init disable_bulk_remove(char *str)
+{
+ if (strcmp(str, "off") == 0 &&
+ firmware_has_feature(FW_FEATURE_BULK_REMOVE)) {
+ printk(KERN_INFO "Disabling BULK_REMOVE firmware feature");
+ powerpc_firmware_features &= ~FW_FEATURE_BULK_REMOVE;
+ }
+ return 1;
+}
+
+__setup("bulk_remove=", disable_bulk_remove);
+
void __init hpte_init_lpar(void)
{
ppc_md.hpte_invalidate = pSeries_lpar_hpte_invalidate;
@@ -637,6 +593,7 @@ void __init hpte_init_lpar(void)
ppc_md.hpte_removebolted = pSeries_lpar_hpte_removebolted;
ppc_md.flush_hash_range = pSeries_lpar_flush_hash_range;
ppc_md.hpte_clear_all = pSeries_lpar_hptab_clear;
+ ppc_md.hugepage_invalidate = pSeries_lpar_hugepage_invalidate;
}
#ifdef CONFIG_PPC_SMLPAR
@@ -701,6 +658,13 @@ EXPORT_SYMBOL(arch_free_page);
/* NB: reg/unreg are called while guarded with the tracepoints_mutex */
extern long hcall_tracepoint_refcount;
+/*
+ * Since the tracing code might execute hcalls we need to guard against
+ * recursion. One example of this are spinlocks calling H_YIELD on
+ * shared processor partitions.
+ */
+static DEFINE_PER_CPU(unsigned int, hcall_trace_depth);
+
void hcall_tracepoint_regfunc(void)
{
hcall_tracepoint_refcount++;
@@ -713,12 +677,98 @@ void hcall_tracepoint_unregfunc(void)
void __trace_hcall_entry(unsigned long opcode, unsigned long *args)
{
+ unsigned long flags;
+ unsigned int *depth;
+
+ /*
+ * We cannot call tracepoints inside RCU idle regions which
+ * means we must not trace H_CEDE.
+ */
+ if (opcode == H_CEDE)
+ return;
+
+ local_irq_save(flags);
+
+ depth = &__get_cpu_var(hcall_trace_depth);
+
+ if (*depth)
+ goto out;
+
+ (*depth)++;
+ preempt_disable();
trace_hcall_entry(opcode, args);
+ (*depth)--;
+
+out:
+ local_irq_restore(flags);
}
void __trace_hcall_exit(long opcode, unsigned long retval,
unsigned long *retbuf)
{
+ unsigned long flags;
+ unsigned int *depth;
+
+ if (opcode == H_CEDE)
+ return;
+
+ local_irq_save(flags);
+
+ depth = &__get_cpu_var(hcall_trace_depth);
+
+ if (*depth)
+ goto out;
+
+ (*depth)++;
trace_hcall_exit(opcode, retval, retbuf);
+ preempt_enable();
+ (*depth)--;
+
+out:
+ local_irq_restore(flags);
}
#endif
+
+/**
+ * h_get_mpp
+ * H_GET_MPP hcall returns info in 7 parms
+ */
+int h_get_mpp(struct hvcall_mpp_data *mpp_data)
+{
+ int rc;
+ unsigned long retbuf[PLPAR_HCALL9_BUFSIZE];
+
+ rc = plpar_hcall9(H_GET_MPP, retbuf);
+
+ mpp_data->entitled_mem = retbuf[0];
+ mpp_data->mapped_mem = retbuf[1];
+
+ mpp_data->group_num = (retbuf[2] >> 2 * 8) & 0xffff;
+ mpp_data->pool_num = retbuf[2] & 0xffff;
+
+ mpp_data->mem_weight = (retbuf[3] >> 7 * 8) & 0xff;
+ mpp_data->unallocated_mem_weight = (retbuf[3] >> 6 * 8) & 0xff;
+ mpp_data->unallocated_entitlement = retbuf[3] & 0xffffffffffffUL;
+
+ mpp_data->pool_size = retbuf[4];
+ mpp_data->loan_request = retbuf[5];
+ mpp_data->backing_mem = retbuf[6];
+
+ return rc;
+}
+EXPORT_SYMBOL(h_get_mpp);
+
+int h_get_mpp_x(struct hvcall_mpp_x_data *mpp_x_data)
+{
+ int rc;
+ unsigned long retbuf[PLPAR_HCALL9_BUFSIZE] = { 0 };
+
+ rc = plpar_hcall9(H_GET_MPP_X, retbuf);
+
+ mpp_x_data->coalesced_bytes = retbuf[0];
+ mpp_x_data->pool_coalesced_bytes = retbuf[1];
+ mpp_x_data->pool_purr_cycles = retbuf[2];
+ mpp_x_data->pool_spurr_cycles = retbuf[3];
+
+ return rc;
+}