Commit d4c2456a authored by Linus Torvalds's avatar Linus Torvalds

Merge branch 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc

Pull powerpc fixes from Benjamin Herrenschmidt:
 "Some more P8 related bits, a bunch of fixes for our P7+/P8 HW crypto
  drivers, some added workarounds for those radeons that don't do proper
  64-bit MSIs and a couple of other trivialities by myself."

* 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc:
  powerpc/pseries: Make 32-bit MSI quirk work on systems lacking firmware support
  powerpc/powernv: Build a zImage.epapr
  powerpc: Make radeon 32-bit MSI quirk work on powernv
  powerpc: Context switch more PMU related SPRs
  powerpc/powernv: Fix condition for when to invalidate the TCE cache
  powerpc/pci: Fix bogus message at boot about empty memory resources
  powerpc: Fix TLB cleanup at boot on POWER8
  drivers/crypto/nx: Fixes for multiple races and issues
parents eb3d3390 f1dd1531
......@@ -174,6 +174,8 @@ struct pci_dn {
/* Get the pointer to a device_node's pci_dn */
#define PCI_DN(dn) ((struct pci_dn *) (dn)->data)
extern struct pci_dn *pci_get_pdn(struct pci_dev *pdev);
extern void * update_dn_pci_info(struct device_node *dn, void *data);
static inline int pci_device_from_OF_node(struct device_node *np,
......
......@@ -284,6 +284,12 @@ struct thread_struct {
unsigned long ebbrr;
unsigned long ebbhr;
unsigned long bescr;
unsigned long siar;
unsigned long sdar;
unsigned long sier;
unsigned long mmcr0;
unsigned long mmcr2;
unsigned long mmcra;
#endif
};
......
......@@ -127,6 +127,12 @@ int main(void)
DEFINE(THREAD_BESCR, offsetof(struct thread_struct, bescr));
DEFINE(THREAD_EBBHR, offsetof(struct thread_struct, ebbhr));
DEFINE(THREAD_EBBRR, offsetof(struct thread_struct, ebbrr));
DEFINE(THREAD_SIAR, offsetof(struct thread_struct, siar));
DEFINE(THREAD_SDAR, offsetof(struct thread_struct, sdar));
DEFINE(THREAD_SIER, offsetof(struct thread_struct, sier));
DEFINE(THREAD_MMCR0, offsetof(struct thread_struct, mmcr0));
DEFINE(THREAD_MMCR2, offsetof(struct thread_struct, mmcr2));
DEFINE(THREAD_MMCRA, offsetof(struct thread_struct, mmcra));
#endif
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
DEFINE(PACATMSCRATCH, offsetof(struct paca_struct, tm_scratch));
......
......@@ -135,8 +135,12 @@ __init_HFSCR:
blr
__init_TLB:
/* Clear the TLB */
li r6,128
/*
* Clear the TLB using the "IS 3" form of tlbiel instruction
* (invalidate by congruence class). P7 has 128 CCs, P8 has 512
* so we just always do 512
*/
li r6,512
mtctr r6
li r7,0xc00 /* IS field = 0b11 */
ptesync
......
......@@ -465,6 +465,20 @@ BEGIN_FTR_SECTION
std r0, THREAD_EBBHR(r3)
mfspr r0, SPRN_EBBRR
std r0, THREAD_EBBRR(r3)
/* PMU registers made user read/(write) by EBB */
mfspr r0, SPRN_SIAR
std r0, THREAD_SIAR(r3)
mfspr r0, SPRN_SDAR
std r0, THREAD_SDAR(r3)
mfspr r0, SPRN_SIER
std r0, THREAD_SIER(r3)
mfspr r0, SPRN_MMCR0
std r0, THREAD_MMCR0(r3)
mfspr r0, SPRN_MMCR2
std r0, THREAD_MMCR2(r3)
mfspr r0, SPRN_MMCRA
std r0, THREAD_MMCRA(r3)
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
#endif
......@@ -560,6 +574,20 @@ BEGIN_FTR_SECTION
ld r0, THREAD_EBBRR(r4)
mtspr SPRN_EBBRR, r0
/* PMU registers made user read/(write) by EBB */
ld r0, THREAD_SIAR(r4)
mtspr SPRN_SIAR, r0
ld r0, THREAD_SDAR(r4)
mtspr SPRN_SDAR, r0
ld r0, THREAD_SIER(r4)
mtspr SPRN_SIER, r0
ld r0, THREAD_MMCR0(r4)
mtspr SPRN_MMCR0, r0
ld r0, THREAD_MMCR2(r4)
mtspr SPRN_MMCR2, r0
ld r0, THREAD_MMCRA(r4)
mtspr SPRN_MMCRA, r0
ld r0,THREAD_TAR(r4)
mtspr SPRN_TAR,r0
END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
......
......@@ -1520,6 +1520,7 @@ static void pcibios_setup_phb_resources(struct pci_controller *hose,
for (i = 0; i < 3; ++i) {
res = &hose->mem_resources[i];
if (!res->flags) {
if (i == 0)
printk(KERN_ERR "PCI: Memory resource 0 not set for "
"host bridge %s (domain %d)\n",
hose->dn->full_name, hose->global_number);
......
......@@ -266,3 +266,13 @@ int pcibus_to_node(struct pci_bus *bus)
}
EXPORT_SYMBOL(pcibus_to_node);
#endif
static void quirk_radeon_32bit_msi(struct pci_dev *dev)
{
struct pci_dn *pdn = pci_get_pdn(dev);
if (pdn)
pdn->force_32bit_msi = 1;
}
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x68f2, quirk_radeon_32bit_msi);
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0xaa68, quirk_radeon_32bit_msi);
......@@ -32,6 +32,14 @@
#include <asm/ppc-pci.h>
#include <asm/firmware.h>
struct pci_dn *pci_get_pdn(struct pci_dev *pdev)
{
struct device_node *dn = pci_device_to_OF_node(pdev);
if (!dn)
return NULL;
return PCI_DN(dn);
}
/*
* Traverse_func that inits the PCI fields of the device node.
* NOTE: this *must* be done before read/write config to the device.
......
......@@ -6,6 +6,7 @@ config PPC_POWERNV
select PPC_ICP_NATIVE
select PPC_P7_NAP
select PPC_PCI_CHOICE if EMBEDDED
select EPAPR_BOOT
default y
config POWERNV_MSI
......
......@@ -68,16 +68,6 @@ define_pe_printk_level(pe_err, KERN_ERR);
define_pe_printk_level(pe_warn, KERN_WARNING);
define_pe_printk_level(pe_info, KERN_INFO);
static struct pci_dn *pnv_ioda_get_pdn(struct pci_dev *dev)
{
struct device_node *np;
np = pci_device_to_OF_node(dev);
if (!np)
return NULL;
return PCI_DN(np);
}
static int pnv_ioda_alloc_pe(struct pnv_phb *phb)
{
unsigned long pe;
......@@ -110,7 +100,7 @@ static struct pnv_ioda_pe *pnv_ioda_get_pe(struct pci_dev *dev)
{
struct pci_controller *hose = pci_bus_to_host(dev->bus);
struct pnv_phb *phb = hose->private_data;
struct pci_dn *pdn = pnv_ioda_get_pdn(dev);
struct pci_dn *pdn = pci_get_pdn(dev);
if (!pdn)
return NULL;
......@@ -173,7 +163,7 @@ static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
/* Add to all parents PELT-V */
while (parent) {
struct pci_dn *pdn = pnv_ioda_get_pdn(parent);
struct pci_dn *pdn = pci_get_pdn(parent);
if (pdn && pdn->pe_number != IODA_INVALID_PE) {
rc = opal_pci_set_peltv(phb->opal_id, pdn->pe_number,
pe->pe_number, OPAL_ADD_PE_TO_DOMAIN);
......@@ -252,7 +242,7 @@ static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev)
{
struct pci_controller *hose = pci_bus_to_host(dev->bus);
struct pnv_phb *phb = hose->private_data;
struct pci_dn *pdn = pnv_ioda_get_pdn(dev);
struct pci_dn *pdn = pci_get_pdn(dev);
struct pnv_ioda_pe *pe;
int pe_num;
......@@ -323,7 +313,7 @@ static void pnv_ioda_setup_same_PE(struct pci_bus *bus, struct pnv_ioda_pe *pe)
struct pci_dev *dev;
list_for_each_entry(dev, &bus->devices, bus_list) {
struct pci_dn *pdn = pnv_ioda_get_pdn(dev);
struct pci_dn *pdn = pci_get_pdn(dev);
if (pdn == NULL) {
pr_warn("%s: No device node associated with device !\n",
......@@ -436,7 +426,7 @@ static void pnv_pci_ioda_setup_PEs(void)
static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev)
{
struct pci_dn *pdn = pnv_ioda_get_pdn(pdev);
struct pci_dn *pdn = pci_get_pdn(pdev);
struct pnv_ioda_pe *pe;
/*
......@@ -768,6 +758,7 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev,
unsigned int is_64, struct msi_msg *msg)
{
struct pnv_ioda_pe *pe = pnv_ioda_get_pe(dev);
struct pci_dn *pdn = pci_get_pdn(dev);
struct irq_data *idata;
struct irq_chip *ichip;
unsigned int xive_num = hwirq - phb->msi_base;
......@@ -783,6 +774,10 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev,
if (pe->mve_number < 0)
return -ENXIO;
/* Force 32-bit MSI on some broken devices */
if (pdn && pdn->force_32bit_msi)
is_64 = 0;
/* Assign XIVE to PE */
rc = opal_pci_set_xive_pe(phb->opal_id, pe->pe_number, xive_num);
if (rc) {
......@@ -1035,7 +1030,7 @@ static int pnv_pci_enable_device_hook(struct pci_dev *dev)
if (!phb->initialized)
return 0;
pdn = pnv_ioda_get_pdn(dev);
pdn = pci_get_pdn(dev);
if (!pdn || pdn->pe_number == IODA_INVALID_PE)
return -EINVAL;
......
......@@ -47,6 +47,10 @@ static int pnv_msi_check_device(struct pci_dev* pdev, int nvec, int type)
{
struct pci_controller *hose = pci_bus_to_host(pdev->bus);
struct pnv_phb *phb = hose->private_data;
struct pci_dn *pdn = pci_get_pdn(pdev);
if (pdn && pdn->force_32bit_msi && !phb->msi32_support)
return -ENODEV;
return (phb && phb->msi_bmp.bitmap) ? 0 : -ENODEV;
}
......@@ -367,7 +371,7 @@ static void pnv_tce_free(struct iommu_table *tbl, long index, long npages)
while (npages--)
*(tcep++) = 0;
if (tbl->it_type & TCE_PCI_SWINV_CREATE)
if (tbl->it_type & TCE_PCI_SWINV_FREE)
pnv_pci_ioda_tce_invalidate(tbl, tces, tcep - 1);
}
......
......@@ -26,26 +26,6 @@ static int query_token, change_token;
#define RTAS_CHANGE_MSIX_FN 4
#define RTAS_CHANGE_32MSI_FN 5
static struct pci_dn *get_pdn(struct pci_dev *pdev)
{
struct device_node *dn;
struct pci_dn *pdn;
dn = pci_device_to_OF_node(pdev);
if (!dn) {
dev_dbg(&pdev->dev, "rtas_msi: No OF device node\n");
return NULL;
}
pdn = PCI_DN(dn);
if (!pdn) {
dev_dbg(&pdev->dev, "rtas_msi: No PCI DN\n");
return NULL;
}
return pdn;
}
/* RTAS Helpers */
static int rtas_change_msi(struct pci_dn *pdn, u32 func, u32 num_irqs)
......@@ -91,7 +71,7 @@ static void rtas_disable_msi(struct pci_dev *pdev)
{
struct pci_dn *pdn;
pdn = get_pdn(pdev);
pdn = pci_get_pdn(pdev);
if (!pdn)
return;
......@@ -152,7 +132,7 @@ static int check_req(struct pci_dev *pdev, int nvec, char *prop_name)
struct pci_dn *pdn;
const u32 *req_msi;
pdn = get_pdn(pdev);
pdn = pci_get_pdn(pdev);
if (!pdn)
return -ENODEV;
......@@ -394,6 +374,23 @@ static int check_msix_entries(struct pci_dev *pdev)
return 0;
}
static void rtas_hack_32bit_msi_gen2(struct pci_dev *pdev)
{
u32 addr_hi, addr_lo;
/*
* We should only get in here for IODA1 configs. This is based on the
* fact that we using RTAS for MSIs, we don't have the 32 bit MSI RTAS
* support, and we are in a PCIe Gen2 slot.
*/
dev_info(&pdev->dev,
"rtas_msi: No 32 bit MSI firmware support, forcing 32 bit MSI\n");
pci_read_config_dword(pdev, pdev->msi_cap + PCI_MSI_ADDRESS_HI, &addr_hi);
addr_lo = 0xffff0000 | ((addr_hi >> (48 - 32)) << 4);
pci_write_config_dword(pdev, pdev->msi_cap + PCI_MSI_ADDRESS_LO, addr_lo);
pci_write_config_dword(pdev, pdev->msi_cap + PCI_MSI_ADDRESS_HI, 0);
}
static int rtas_setup_msi_irqs(struct pci_dev *pdev, int nvec_in, int type)
{
struct pci_dn *pdn;
......@@ -401,8 +398,9 @@ static int rtas_setup_msi_irqs(struct pci_dev *pdev, int nvec_in, int type)
struct msi_desc *entry;
struct msi_msg msg;
int nvec = nvec_in;
int use_32bit_msi_hack = 0;
pdn = get_pdn(pdev);
pdn = pci_get_pdn(pdev);
if (!pdn)
return -ENODEV;
......@@ -428,15 +426,31 @@ static int rtas_setup_msi_irqs(struct pci_dev *pdev, int nvec_in, int type)
*/
again:
if (type == PCI_CAP_ID_MSI) {
if (pdn->force_32bit_msi)
if (pdn->force_32bit_msi) {
rc = rtas_change_msi(pdn, RTAS_CHANGE_32MSI_FN, nvec);
else
if (rc < 0) {
/*
* We only want to run the 32 bit MSI hack below if
* the max bus speed is Gen2 speed
*/
if (pdev->bus->max_bus_speed != PCIE_SPEED_5_0GT)
return rc;
use_32bit_msi_hack = 1;
}
} else
rc = -1;
if (rc < 0)
rc = rtas_change_msi(pdn, RTAS_CHANGE_MSI_FN, nvec);
if (rc < 0 && !pdn->force_32bit_msi) {
if (rc < 0) {
pr_debug("rtas_msi: trying the old firmware call.\n");
rc = rtas_change_msi(pdn, RTAS_CHANGE_FN, nvec);
}
if (use_32bit_msi_hack && rc > 0)
rtas_hack_32bit_msi_gen2(pdev);
} else
rc = rtas_change_msi(pdn, RTAS_CHANGE_MSIX_FN, nvec);
......@@ -518,12 +532,3 @@ static int rtas_msi_init(void)
}
arch_initcall(rtas_msi_init);
static void quirk_radeon(struct pci_dev *dev)
{
struct pci_dn *pdn = get_pdn(dev);
if (pdn)
pdn->force_32bit_msi = 1;
}
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x68f2, quirk_radeon);
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0xaa68, quirk_radeon);
......@@ -126,6 +126,7 @@ struct crypto_alg nx_cbc_aes_alg = {
.cra_blocksize = AES_BLOCK_SIZE,
.cra_ctxsize = sizeof(struct nx_crypto_ctx),
.cra_type = &crypto_blkcipher_type,
.cra_alignmask = 0xf,
.cra_module = THIS_MODULE,
.cra_init = nx_crypto_ctx_aes_cbc_init,
.cra_exit = nx_crypto_ctx_exit,
......
......@@ -123,6 +123,7 @@ struct crypto_alg nx_ecb_aes_alg = {
.cra_priority = 300,
.cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
.cra_blocksize = AES_BLOCK_SIZE,
.cra_alignmask = 0xf,
.cra_ctxsize = sizeof(struct nx_crypto_ctx),
.cra_type = &crypto_blkcipher_type,
.cra_module = THIS_MODULE,
......
......@@ -219,7 +219,7 @@ static int gcm_aes_nx_crypt(struct aead_request *req, int enc)
if (enc)
NX_CPB_FDM(csbcpb) |= NX_FDM_ENDE_ENCRYPT;
else
nbytes -= AES_BLOCK_SIZE;
nbytes -= crypto_aead_authsize(crypto_aead_reqtfm(req));
csbcpb->cpb.aes_gcm.bit_length_data = nbytes * 8;
......
......@@ -69,7 +69,7 @@ static int nx_sha256_update(struct shash_desc *desc, const u8 *data,
* 1: <= SHA256_BLOCK_SIZE: copy into state, return 0
* 2: > SHA256_BLOCK_SIZE: process X blocks, copy in leftover
*/
if (len + sctx->count <= SHA256_BLOCK_SIZE) {
if (len + sctx->count < SHA256_BLOCK_SIZE) {
memcpy(sctx->buf + sctx->count, data, len);
sctx->count += len;
goto out;
......@@ -110,6 +110,7 @@ static int nx_sha256_update(struct shash_desc *desc, const u8 *data,
atomic_inc(&(nx_ctx->stats->sha256_ops));
/* copy the leftover back into the state struct */
if (leftover)
memcpy(sctx->buf, data + len - leftover, leftover);
sctx->count = leftover;
......@@ -130,6 +131,7 @@ static int nx_sha256_final(struct shash_desc *desc, u8 *out)
struct nx_sg *in_sg, *out_sg;
int rc;
if (NX_CPB_FDM(csbcpb) & NX_FDM_CONTINUATION) {
/* we've hit the nx chip previously, now we're finalizing,
* so copy over the partial digest */
......@@ -162,7 +164,7 @@ static int nx_sha256_final(struct shash_desc *desc, u8 *out)
atomic_inc(&(nx_ctx->stats->sha256_ops));
atomic64_add(csbcpb->cpb.sha256.message_bit_length,
atomic64_add(csbcpb->cpb.sha256.message_bit_length / 8,
&(nx_ctx->stats->sha256_bytes));
memcpy(out, csbcpb->cpb.sha256.message_digest, SHA256_DIGEST_SIZE);
out:
......
......@@ -69,7 +69,7 @@ static int nx_sha512_update(struct shash_desc *desc, const u8 *data,
* 1: <= SHA512_BLOCK_SIZE: copy into state, return 0
* 2: > SHA512_BLOCK_SIZE: process X blocks, copy in leftover
*/
if ((u64)len + sctx->count[0] <= SHA512_BLOCK_SIZE) {
if ((u64)len + sctx->count[0] < SHA512_BLOCK_SIZE) {
memcpy(sctx->buf + sctx->count[0], data, len);
sctx->count[0] += len;
goto out;
......@@ -110,6 +110,7 @@ static int nx_sha512_update(struct shash_desc *desc, const u8 *data,
atomic_inc(&(nx_ctx->stats->sha512_ops));
/* copy the leftover back into the state struct */
if (leftover)
memcpy(sctx->buf, data + len - leftover, leftover);
sctx->count[0] = leftover;
......@@ -168,7 +169,7 @@ static int nx_sha512_final(struct shash_desc *desc, u8 *out)
goto out;
atomic_inc(&(nx_ctx->stats->sha512_ops));
atomic64_add(csbcpb->cpb.sha512.message_bit_length_lo,
atomic64_add(csbcpb->cpb.sha512.message_bit_length_lo / 8,
&(nx_ctx->stats->sha512_bytes));
memcpy(out, csbcpb->cpb.sha512.message_digest, SHA512_DIGEST_SIZE);
......
......@@ -211,44 +211,20 @@ int nx_build_sg_lists(struct nx_crypto_ctx *nx_ctx,
{
struct nx_sg *nx_insg = nx_ctx->in_sg;
struct nx_sg *nx_outsg = nx_ctx->out_sg;
struct blkcipher_walk walk;
int rc;
blkcipher_walk_init(&walk, dst, src, nbytes);
rc = blkcipher_walk_virt_block(desc, &walk, AES_BLOCK_SIZE);
if (rc)
goto out;
if (iv)
memcpy(iv, walk.iv, AES_BLOCK_SIZE);
while (walk.nbytes) {
nx_insg = nx_build_sg_list(nx_insg, walk.src.virt.addr,
walk.nbytes, nx_ctx->ap->sglen);
nx_outsg = nx_build_sg_list(nx_outsg, walk.dst.virt.addr,
walk.nbytes, nx_ctx->ap->sglen);
rc = blkcipher_walk_done(desc, &walk, 0);
if (rc)
break;
}
if (walk.nbytes) {
nx_insg = nx_build_sg_list(nx_insg, walk.src.virt.addr,
walk.nbytes, nx_ctx->ap->sglen);
nx_outsg = nx_build_sg_list(nx_outsg, walk.dst.virt.addr,
walk.nbytes, nx_ctx->ap->sglen);
memcpy(iv, desc->info, AES_BLOCK_SIZE);
rc = 0;
}
nx_insg = nx_walk_and_build(nx_insg, nx_ctx->ap->sglen, src, 0, nbytes);
nx_outsg = nx_walk_and_build(nx_outsg, nx_ctx->ap->sglen, dst, 0, nbytes);
/* these lengths should be negative, which will indicate to phyp that
* the input and output parameters are scatterlists, not linear
* buffers */
nx_ctx->op.inlen = (nx_ctx->in_sg - nx_insg) * sizeof(struct nx_sg);
nx_ctx->op.outlen = (nx_ctx->out_sg - nx_outsg) * sizeof(struct nx_sg);
out:
return rc;
return 0;
}
/**
......@@ -454,6 +430,8 @@ static int nx_register_algs(void)
if (rc)
goto out;
nx_driver.of.status = NX_OKAY;
rc = crypto_register_alg(&nx_ecb_aes_alg);
if (rc)
goto out;
......@@ -498,8 +476,6 @@ static int nx_register_algs(void)
if (rc)
goto out_unreg_s512;
nx_driver.of.status = NX_OKAY;
goto out;
out_unreg_s512:
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment